ON THE IMPROVEMENT OF NO-REFERENCE MEAN OPINION SCORE ESTIMATION ACCURACY BY FOLLOWING A FRAME-LEVEL REGRESSION APPROACH

Size: px
Start display at page:

Download "ON THE IMPROVEMENT OF NO-REFERENCE MEAN OPINION SCORE ESTIMATION ACCURACY BY FOLLOWING A FRAME-LEVEL REGRESSION APPROACH"

Transcription

1 ON THE IMPROVEMENT OF NO-REFERENCE MEAN OPINION SCORE ESTIMATION ACCURACY BY FOLLOWING A FRAME-LEVEL REGRESSION APPROACH Katerina Pandremmenou, M. Shahid, Lisimachos P. Kondi Department of Computer Science and Engineering, University of Ioannina, GR-, Ioannina, Greece Blekinge Institute of Technology, Karlskrona, Sweden. ABSTRACT In order to estimate subjective video quality, it usually happens to deal with a large number of features and a small sample set. Applying regression on complex datasets may lead to imprecise solutions due to possible irrelevant or noisy features as well as the effect of overfitting. In an effort to establish a robust regression model that generalizes well to unknown data and increase Mean Opinion Score (MOS) estimation accuracy, we propose a frame-level MOS estimation approach, where average MOS for each sequence are obtained. Since it is impractical to obtain the per-frame MOS ground truth through subjective experiments, we propose an objective metric able to do this task, providing an intuition about the relative quality of each individual frame as well. Experiments on both sequence- and frame-level domains reveal that regression on frame level offers better results in terms of all examined measures of performance either feature selection is performed or not. Index Terms Estimation accuracy, frame-level, MOS, objective metric, overfitting, sequence-level.. INTRODUCTION The continuous technological advancements have enabled the proliferation of streaming video services and consequently, the matter of Video Quality Assessment (VQA) has become very popular. Since the goal of each video communication product is to satisfy user s experience, subjective quality assessment is the most reliable way for evaluating its quality. Nonetheless, the conduction of subjective tests faces many challenges. For example, a large number of viewers is required, and the viewers are not always available or willing to rate a large variety of differently distorted video sequences. In addition, through subjective experiments we are unable to get instantaneous measurements of video quality due to many practical limitations. Thus, a single quality value for the whole video does not provide any information about the individual quality of the video frames, being unable to know which parts of the video have the greatest influence in forming the viewer s judgement. An alternative approach to subjective VQA is to automatically get video quality scores, through the use of objective metrics [, ], where an ideal objective metric is able to provide quality scores that highly correlate with human ratings. In the literature, many works construct objective metrics through the use of various machine learning techniques such as Partial Least Squares Regression (PLSR) [], Neural Networks (NN) [], Support Vector Machines (SVM) [] and Support Vector Regression (SVR) [6]. A number of qualityrelevant features that account for different types of distortion are given as input in each considered regression model and significantly influence the accuracy of MOS estimations [7]. Theoretically, the larger the number of features the better the estimation power of the regression model. However, a large number of features along with a possibly small number of observations (sample set) involves the risk of fitting the model to the noise of the training data, being unable to generalize well to unseen data (testing data). For this reason, a feature selection procedure often takes place before video quality estimation [8, 9]. In this work, we propose a novel approach for estimating perceptual video quality separately for each frame, and in the following we average these values in order to obtain a Mean Opinion Score (MOS) estimate for each sequence. The objective of this paper is two-fold: i) to improve the persequence MOS estimation accuracy through the development of a model which is robust and has a good generalization capability, ii) to provide a reliable indicator for the quality of each frame, offering an intuition about their individual contribution to the overall video quality score. Driven by the work presented in [], we develop a metric that provides the ground truth of the frame MOS, which plays the role of the target variable in the regression procedure. The works presented in [, ] elaborated on a similar concept of considering frame quality measurements and measurements over small units of video sequences that guide the overall video quality rating. However, the goal of both [, ] is different from the one of the current paper. In [] a NR objective metric that provides video quality scores per second so as to align with the subjective results of a Single Stimulus Continuous Quality Evaluation (SSCQE) method [] was introduced, and in [] the authors applied a fusion mecha-

2 nism in order to integrate the scores from some video integrals into a final one, increasing in this way the correlation with the MOS. The rest of the article is organized as follows: Section presents the proposed Full Reference (FR) metric that offers the ground truth of frame video quality. Our approach for estimating MOS in frame-level is analyzed in Section along with experimental results and discussion that highlight its efficiency. Last, in Section conclusions are drawn.. PROPOSED VIDEO QUALITY METRIC In order to estimate MOS in frame level, EMOS fr, for Common Intermediate Format (CIF) resolution sequences, it is necessary to obtain the actual MOS for each frame, MOS fr, so as to be able to verify the model s performance. Due to practical limitations involved in collecting human votes for thousands of video frames, we develop an FR objective metric, which produces automatically quality scores for each frame. It is worth mentioning that since we intend to employ these results as the target values that need to be predicted in the regression model we describe later, it is important for the average values of per-frame MOS, MOS fr, in sequence-level to highly correlate with the actual MOS for each sequence, MOS s. The research conducted in [] proved that an exponential function can map Peak Signal to Noise Ratio (PSNR) to MOS with high accuracy, considering the temporal and spatial activity levels of the video sequence in question. However, the metric developed in [] is not universal since it was only tested on CIF resolution sequences with a frame rate of frames per second (fps), scourged mainly by channel distortion. Therefore, in this paper we extend the research of [] and examine if the exponential function given by: MOS = exp ( PSNR a b ) () fits also well to the case of CIF resolution sequences. The parameters a and b represent the vertical shift and the steepness of the curve, and the PSNR s corresponds to the PSNR of each sequence. For our experiments, we employ the database of [] for CIF resolution sequences (7x76 pixels). Our test material comprises of the Ice, Harbour, Soccer, CrowdRun, DucksTakeOff and ParkJoy sequences of 8, 98, 98,, and frames, respectively; the former three sequences are at fps and the latter three at fps. The Group Of Pictures (GOP) structure is IBBP with a GOP size of 6 frames. The sources are encoded using the JM. version of H.6/AVC reference software using the High profile, where a full row of MacroBlocks (MBs) is coded as a separate slice and each of the sequences is corrupted with a Packet Loss Rate (PLR) of.%,.%, %, %, % and %, for two channel realizations. Thus, our dataset consists of 7 distorted versions of the 6 original video sequences (6 original sequences x 6 PLRs x channel realizations). In addition, in [] subjective results from the Ecole Polytechnique Fédérale de Lausanne (EPFL) and Politecnico di Milano (PoliMi) are also included. For each of the 7 video sequences, we calculated the PSNR values and using the MOS values of [] from both EPFL and PoliMi, we plotted these values, fit the Eq. () and examined the coefficient of determination R, which is an indicator of how well the observed outcomes (our data points) are replicated by the model (Eq. ()). Figure presents indicative fitting results for the DucksTakeOff and ParkJoy video sequences, while similar fitting performance was also observed for the rest CIF sequences. However, for the sake of saving space we omit the presentation of their fitting curves from this paper. It is to be noted that the value of R was for all sequences above.9 and the Root Mean Squared Error (RMSE) less than.. MOS MOS DucksTakeOff PSNR ParkJoy 6 8 PSNR Fig. : MOS-PSNR fitting curves. Based on these results, it is clear that the exponential shape of Eq. () accurately describes the MOS-PSNR relationship for the CIF sequences as well. Having reached to this useful conclusion, we applied Ordinary Least-Squares (OLS) optimization in order to solve parameters α and β of Eq. (), using the pair values of (MOS s, P SNR s ) for each CIF sequence. Afterwards, we calculated the PSNR values for each frame of all considered CIF sequences, P SNR fr, and next we computed the MOS fr. In order to validate the quality of the obtained values, we go averaged the per-frame MOS values to obtain a representative value for each separate sequence, MOS fr, and checked for correlation with the corresponding measured values, MOS s. The estimated a and b parameters as well as the Pearson Correlation Coefficient (PCC) [] for each examined sequence are depicted in Table. PCC = indicates a perfect linear relationship between measured and estimated data (MOS in our case). As we can see from this table, if we ap-

3 ply to Eq. () the parameters resulting either from EPFL or PoliMi dataset, the subjective results can be estimated nearly perfectly. Table : Estimated a and b values. %. The horizontal line represents the actual MOS of the sequence (.777), while as we observe, there is a high discrepancy among the MOS values of each separate frame of the sequence, although their average value (.77) is virtually identical to the measured MOS. EPFL MOS CrowdRun DucksTakeOff Harbour Ice ParkJoy Soccer a b PCC PoliMi MOS a b PCC Moreover, Fig. is the scatter plot of MOS fr and MOS s, when both EPFL (on the left) and PoliMi (on the right) results are employed. MOS fr 6 Ice with PLR=%. data points linear fit EPFL Results. data points fit line PoliMi Results Frame M OSfr.. o line M OSfr.. o line Fig. : Per-frame MOS... MOS s Fig. : Correlation results... MOS s More light about the efficiency of the proposed FR metric is shed by the results presented on Table. A comparison of the proposed metric using results from both EPFL and PoliMi with the state-of-the-art Perceptual Evaluation of Video Quality (PEVQ) [6] and Video Quality Metric (VQM) [7] reveals that although all of these metrics correlate well with MOS, the metric proposed in this article is even more efficient in terms of PCC [], Spearman Rank Order Correlation Coefficient (SROCC) [8] and RMSE []. It presents a nearly perfect linear correlation with the measured MOS s values. Moreover, we signify that the performance of our proposed metric using either the EPFL or the PoliMi MOS results is equivalent. Hence, since accurate per-frame MOS were obtained, we recommend their use as ground truth in per-frame MOS estimation problems. Table : FR Objective Metrics Comparison Proposed (EPFL) Proposed (Polimi) PEVQ VQM PCC SROCC RMSE Continuing, an additional feature of our proposed metric is that it offers an intuition about the relative quality of each frame, and how much it contributes to the overall score of the sequence. Figure presents the MOS values for each frame of the Ice video sequence, when PLR is equal to Nonetheless, from Fig. it seems that some MOS fr are slightly above the upper bound of the -point rating scale []. It is expected as these results come from simulations and cannot mimic the weakness of subjective data, which are usually compressed at the ends of the rating scale. Therefore, it is reasonable that when we average these values in sequence-level, the obtained per-sequence MOS fall also outside the rating scale. In order to circumvent with this issue, we applied a non-linear mapping on the averaged per-frame MOS before computing any of the performance metrics. Specifically, we used the cubic polynomial function given by []: MOS fr = a MOS fr +a MOS fr +a MOS s +a () which is found to perform well empirically. The weights a, a, a and the constant a are calculated by fitting the function to the data (MOS fr, MOS s ) with the goal of maximizing their correlation.. MOS ESTIMATION IN FRAME-LEVEL After the collection of the per-frame MOS values we construct a regression model that can automatically generate perframe MOS estimates, which will be next averaged to provide an overall MOS value for each sequence. Our sequencelevel dataset consists of 7 video sequences and perceptual quality-related features, proposed in our previous work [7], and our frame-level dataset includes 98 frame observations and features. To be noted that for the rest of our experiments we adopted the PoliMi MOS. Before applying regression, we split the dataset into separate training and test sets such that each impaired sequence set

4 of each original video to be used for testing, and next we apply ridge regression [9, ] on both the sequence- and framelevel domains. Ridge is an extension of the OLS regression method and is able to improve the OLS estimates by allowing a little bias in order to reduce the variance of the estimated values. It solves the problem: min w ( ) n (y i w φ(x i )) + λ w i= where y includes the measured quality values for all n observations (n = 7 for the sequence domain and n = 98 for the frame-domain) and x i includes the values for all features. The parameter λ is a regularization parameter, which shrinks regression coefficient values towards zero. For λ = no regression is performed and the solution of the OLS is obtained, while for larger λ values, the closer to zero the regression coefficient estimates. In our experiments we set λ = in the regression models of both domains. Therefore, ridge tradeoffs the Sum of Squared Errors (SSE) (first term of Eq. ()) and the penalty (second term of Eq. ()). Table presents the performance statistics when regression is applied on both the sequence- and frame-level domains. At this point we should mention that since the goal of this work is not to deepen in the regression procedure, we omit the presentation of the regression coefficient estimates from this work. For the sequence-level case the actual MOS values are compared with the MOS values obtained from ridge. For the frame-level case the MOS estimates for each frame obtained from ridge are averaged to obtain a MOS value for each video sequence and next we compare these results with the actual sequence-level MOS values. Furthermore, in the same table we present the RMSE not only in the testing set but also in the training set. This is an interesting approach since the sequence-level dataset is fairly complex, that is it includes a large number of features as compared to the number of observations, posing the risk of overfitting. Table : Regression results on raw datasets. Sequence-level Frame-level PCC SROCC.8.96 RMSE (training)..9 RMSE (testing).8. From the results of Table it is clear that regression on the frame-level dataset guarantees better performance statistics as compared to the regression on the sequence-level dataset. After a thorough investigation of the training and testing errors in each dataset sub-partition of both the sequence- and framelevel cases, we confirmed that for the frame level case a similar amount of error in both the training and testing sets is observed. On the other hand, in the sequence-level case there is a great discrepancy between training and testing errors. This difference is more evident before applying Eq. () to account () for the quality rating compression at the extremes of the test range. Nonetheless, even after applying Eq. (), the overall testing error is three times greater than the corresponding error in the training set. This implies that our model may fit to the irregularities of the training set (a noteworthy low RMSE is observed in this case) and cannot effectively estimate the response variable when it deals with unknown data. In an effort to enhance the strength of the sequence-level regression model in making precise estimations when it is provided with new data, we applied stepwise regression [] to the sequence-level dataset so as to perform feature selection by iteratively adding features or their interactions (products of features in pairs) or trimming features from a linear model, based on their statistical significance in the regression process. The method begins with an initial dataset and then compares the explanatory power of incrementally larger and smaller datasets. In addition, stepwise regression was also performed on the frame-level dataset. After this operation, we ended up with a sequence-level set of dimension 7x6 and a frame-level set of dimension 98x9. For the sake of saving space, we do not mention in this paper the features as well as their interactions that have been selected by stepwise regression for each case. Based on our processed sequence-level and frame-level datasets, we applied again ridge regression to obtain new MOS estimates. The results presented on Table reinforce our claim that a more stable model is achieved when regression is applied on frame-level, which offers more precise MOS estimations compared to the model built in sequencelevel. For the frame-level model similar performance is achieved either the dataset is raw or free of useless features, or slightly improved in the latter case. Regarding the sequence-level case, the correlation measures are considerably improved and the difference between training and testing error is minor in this case. Table : Regression on processed datasets. Sequence-level Frame-level PCC SROCC RMSE (training).9.8 RMSE (testing)..8 Additional information about the improvement achieved on the sequence-level dataset after applying feature selection is provided on Table. From R value on the raw dataset we Table : Goodness-of-fit statistics. R Adjusted-R SSE Raw dataset Processed dataset can say that 96% of the total variance is explained by the regression model. While this value seems promising (the more variance accounted for by the regression model, the closer the

5 data points fall to the fitted regression line), this value may be misleadingly high because many features are included in the model. For this purpose, we also computed the Adjusted- R measure, which penalizes the R statistic when extra variables are added. Also, we assessed SSE to determine whether the coefficient estimates and predictions are biased. From the results of Table we confirm that all statistics are improved when stepwise regression is applied. Therefore, it is reasonable that we get better prediction results in this case as depicted in Table.. CONCLUSIONS In this work, we propose an alternative approach for estimating MOS in frame level, and then average the per-frame MOS estimations in order to obtain the overall MOS for each sequence, instead of performing regression directly in sequence-level. In order to obtain the per-frame ground truth of quality, we develop a FR metric, which is able to map per-frame PSNR to MOS. The accuracy of the results produced by this metric with regard to the actual MOS values highly recommends their use for model s verification. Ridge regression conducted on both the sequence- and frame-level domains verified the ability of higher-dimension datasets to estimate MOS more precisely overcoming the issue of overfitting. In addition, in both datasets we applied stepwise regression so as to keep the features and their interactions that are statistically significant. In this case, the performance of the sequence-level dataset was improved. However, the advantage of the frame-level dataset is clear since it not only gathers better performance statistics but also is more stable and robust, tackling the problem of MOS estimation with efficiency either feature selection is performed or not. Thus, the benefit of our proposed method of exploiting a large number of training data as a means of reducing the variance captured in the model is more important compared to feature selection or addition of extra (feature interactions) than can be favourable towards the same purpose.

6 . REFERENCES [] S. Chikkerur, V. Sundaram, M. Reisslein, and L. J. Karam, Objective video quality assessment methods: A classification, review, and performance comparison, IEEE Transactions on Broadcasting, vol. 7, no., pp. 6 8, Jun.. [] Zhou Wang, Hamid R. Sheikh, and Alan C. Bovik, Objective video quality assessment, in IN THE HAND- BOOK OF VIDEO DATABASES: DESIGN AND AP- PLICATIONS., pp. 78, CRC Press. [] C. Keimel, J. Habigt, M. Klimpke, and K. Diepold, Design of no-reference video quality metrics with multiway partial least squares regression, in Third International Workshop on Quality of Multimedia Experience (QoMEX), Sept., pp. 9. [] Jihwan Choe, Jonghwa Lee, and Chulhee Lee, Noreference video quality measurement using neural networks, in 6th International Conference on Digital Signal Processing, Jul. 9, pp.. [] Beibei Wang, Dekun Zou, and Ran Ding, Support vector regression based video quality prediction, in IEEE International Symposium on Multimedia (ISM), Dec., pp [6] M. Narwaria and Weisi Lin, SVD-based quality metric for image and video using machine learning, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, vol., no., pp. 7 6, Apr.. [7] Katerina Pandremmenou, Muhammad Shahid, Lisimachos P. Kondi, and Benny Lövström, A no-reference bitstream-based perceptual model for video quality estimation of videos affected by coding artifacts and packet losses, in Proc. of IS&T/SPIE Electronic Imaging. Feb., SPIE, to appear. [8] Caihong Wang, Ting-Lan Lin, and P. C. Cosman, Network-based model for video packet importance considering both compression artifacts and packet losses, in IEEE Global Telecommunications Conference (GLOBECOM), Dec., pp.. [9] D. Culibrk, M. Mirkovic, V. Zlokolica, M. Pokric, V. Crnojevic, and D. Kukolj, Salient motion features for video quality assessment, IEEE Transactions on Image Processing, vol., no., pp , Apr.. [] Y. Kawayokeita and Y. Horita, NR objective continuous video quality assessment model based on frame quality measure, in th IEEE International Conference on Image Processing (ICIP), Oct. 8, pp [] Tsung-Jung Liu, Weisi Lin, and C. C. J. Kuo, A fusion approach to video quality assessment based on temporal decomposition, in Signal Information Processing Association Annual Summit and Conference (APSIPA ASC), Dec., pp.. [] Alpert Th. and Evain J-. P., Subjective quality evaluation the SSCQE and DSCQE methodologies, 997, EBU Technical Review. [] Francesca De Simone, Matteo Naccari, Marco Tagliasacchi, Frdric Dufaux, Stefano Tubaro, and Touradj Ebrahimi, Subjective quality assessment of H.6/AVC video streaming with packet losses, Eurasip Journal on Image and Video Processing, vol. Article ID 9,. [] Video Quality Experts Group, VQEG report on validation of video quality models for high definition video content,. [6] ITU-T Rec. J.7, Objective perceptual multimedia video quality measurement in the presence of a full reference, 8. [7],. [8] D. E. Hinkle, W. Wiersma, and S. G. Jurs, Applied statistics for the behavioral sciences., Boston, Mass: Houghton Mifflin,. [9] Ridge regression in practice, The American Statistician, vol. 9, no., pp., 97. [] A. E. Hoerl and R. W. Kennard, Ridge regression: Biased estimation for nonorthogonal problems, Technometrics, vol., pp. 67, 97. [] Norman Richard Draper and Harry Smith, Applied regression analysis, A Wiley-Interscience publication. Wiley, New York, NY [u.a.],. ed. edition, 998. [] J. Korhonen and J. You, Improving objective video quality assessment with content analysis, in Fifth International Workshop on Video Processing and Quality Metrics for Consumer Electronics (VPQM ), Scottsdale, AZ, USA, Jan..

LENGTH-INDEPENDENT REFINEMENT OF VIDEO QUALITY METRICS BASED ON MULTIWAY DATA ANALYSIS

LENGTH-INDEPENDENT REFINEMENT OF VIDEO QUALITY METRICS BASED ON MULTIWAY DATA ANALYSIS LEGTH-IDEPEDET REFIEMET OF VIDEO QUALITY METRICS BASED O MULTIWAY DATA AALYSIS Clemens Horch, Christian Keimel, Julian Habigt and Klaus Diepold Technische Universität München, Institute for Data Processing,

More information

Copyright IEEE. Citation for the published paper:

Copyright IEEE. Citation for the published paper: Copyright IEEE. Citation for the published paper: This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of BTH's products

More information

No-reference perceptual quality metric for H.264/AVC encoded video. Maria Paula Queluz

No-reference perceptual quality metric for H.264/AVC encoded video. Maria Paula Queluz No-reference perceptual quality metric for H.264/AVC encoded video Tomás Brandão Maria Paula Queluz IT ISCTE IT IST VPQM 2010, Scottsdale, USA, January 2010 Outline 1. Motivation and proposed work 2. Technical

More information

HYBRID NO-REFERENCE VIDEO QUALITY METRIC BASED ON MULTIWAY PLSR. Christian Keimel, Julian Habigt and Klaus Diepold

HYBRID NO-REFERENCE VIDEO QUALITY METRIC BASED ON MULTIWAY PLSR. Christian Keimel, Julian Habigt and Klaus Diepold 20th European Signal Processing Conference (EUSIPCO 2012) Bucharest, Romania, August 27-31, 2012 HYBRID NO-REFERENCE VIDEO QUALITY METRIC BASED ON MULTIWAY PLSR Christian Keimel, Julian Habigt and Klaus

More information

Open Access Research on No-reference Video Quality Assessment Based on H.264/AVC Bitstream

Open Access Research on No-reference Video Quality Assessment Based on H.264/AVC Bitstream Send Orders for Reprints to reprints@benthamscience.ae 444 The Open Automation and Control Systems Journal, 204, 6, 444-450 Open Access Research on No-reference Video Quality Assessment Based on H.264/AVC

More information

OBJECTIVE IMAGE QUALITY ASSESSMENT WITH SINGULAR VALUE DECOMPOSITION. Manish Narwaria and Weisi Lin

OBJECTIVE IMAGE QUALITY ASSESSMENT WITH SINGULAR VALUE DECOMPOSITION. Manish Narwaria and Weisi Lin OBJECTIVE IMAGE UALITY ASSESSMENT WITH SINGULAR VALUE DECOMPOSITION Manish Narwaria and Weisi Lin School of Computer Engineering, Nanyang Technological University, Singapore, 639798 Email: {mani008, wslin}@ntu.edu.sg

More information

Image and Video Quality Assessment Using Neural Network and SVM

Image and Video Quality Assessment Using Neural Network and SVM TSINGHUA SCIENCE AND TECHNOLOGY ISSN 1007-0214 18/19 pp112-116 Volume 13, Number 1, February 2008 Image and Video Quality Assessment Using Neural Network and SVM DING Wenrui (), TONG Yubing (), ZHANG Qishan

More information

Image Quality Assessment based on Improved Structural SIMilarity

Image Quality Assessment based on Improved Structural SIMilarity Image Quality Assessment based on Improved Structural SIMilarity Jinjian Wu 1, Fei Qi 2, and Guangming Shi 3 School of Electronic Engineering, Xidian University, Xi an, Shaanxi, 710071, P.R. China 1 jinjian.wu@mail.xidian.edu.cn

More information

Optimizing the Deblocking Algorithm for. H.264 Decoder Implementation

Optimizing the Deblocking Algorithm for. H.264 Decoder Implementation Optimizing the Deblocking Algorithm for H.264 Decoder Implementation Ken Kin-Hung Lam Abstract In the emerging H.264 video coding standard, a deblocking/loop filter is required for improving the visual

More information

Video Quality Evaluation in IP Networks

Video Quality Evaluation in IP Networks Video Quality Evaluation in IP Networks Miguel Chin Instituto Superior Técnico Technical University of Lisbon Lisbon, Portugal Abstract In this paper, no-reference objective quality metrics for encoded

More information

Low-Complexity No-Reference PSNR Estimation for H.264/AVC Encoded Video

Low-Complexity No-Reference PSNR Estimation for H.264/AVC Encoded Video Low-Complexity No-Reference PSNR Estimation for H.264/AVC Encoded Video Damien Schroeder, Ali El Essaili, Eckehard Steinbach Institute for Media Technology Technische Universität München Munich, Germany

More information

DCT-BASED IMAGE QUALITY ASSESSMENT FOR MOBILE SYSTEM. Jeoong Sung Park and Tokunbo Ogunfunmi

DCT-BASED IMAGE QUALITY ASSESSMENT FOR MOBILE SYSTEM. Jeoong Sung Park and Tokunbo Ogunfunmi DCT-BASED IMAGE QUALITY ASSESSMENT FOR MOBILE SYSTEM Jeoong Sung Park and Tokunbo Ogunfunmi Department of Electrical Engineering Santa Clara University Santa Clara, CA 9553, USA Email: jeoongsung@gmail.com

More information

Blind Prediction of Natural Video Quality and H.264 Applications

Blind Prediction of Natural Video Quality and H.264 Applications Proceedings of Seventh International Workshop on Video Processing and Quality Metrics for Consumer Electronics January 30-February 1, 2013, Scottsdale, Arizona 1 Blind Prediction of Natural Video Quality

More information

Quality versus Intelligibility: Evaluating the Coding Trade-offs for American Sign Language Video

Quality versus Intelligibility: Evaluating the Coding Trade-offs for American Sign Language Video Quality versus Intelligibility: Evaluating the Coding Trade-offs for American Sign Language Video Frank Ciaramello, Jung Ko, Sheila Hemami School of Electrical and Computer Engineering Cornell University,

More information

Network-based model for video packet importance considering both compression artifacts and packet losses

Network-based model for video packet importance considering both compression artifacts and packet losses Network-based model for video packet importance considering both compression artifacts and packet losses Yuxia Wang Communication University of China Beijing, China, 124 Email: yuxiaw@cuc.edu.cn Ting-Lan

More information

MULTI-SCALE STRUCTURAL SIMILARITY FOR IMAGE QUALITY ASSESSMENT. (Invited Paper)

MULTI-SCALE STRUCTURAL SIMILARITY FOR IMAGE QUALITY ASSESSMENT. (Invited Paper) MULTI-SCALE STRUCTURAL SIMILARITY FOR IMAGE QUALITY ASSESSMENT Zhou Wang 1, Eero P. Simoncelli 1 and Alan C. Bovik 2 (Invited Paper) 1 Center for Neural Sci. and Courant Inst. of Math. Sci., New York Univ.,

More information

A NO-REFERENCE AUDIO-VISUAL VIDEO QUALITY METRIC

A NO-REFERENCE AUDIO-VISUAL VIDEO QUALITY METRIC A NO-REFERENCE AUDIO-VISUAL VIDEO QUALITY METRIC Helard Becerra Martinez and Mylène C. Q. Farias Department of Electrical Engineering Department of Computer Science University of Brasília, Brasília - DF,

More information

A Comparison of Still-Image Compression Standards Using Different Image Quality Metrics and Proposed Methods for Improving Lossy Image Quality

A Comparison of Still-Image Compression Standards Using Different Image Quality Metrics and Proposed Methods for Improving Lossy Image Quality A Comparison of Still-Image Compression Standards Using Different Image Quality Metrics and Proposed Methods for Improving Lossy Image Quality Multidimensional DSP Literature Survey Eric Heinen 3/21/08

More information

Fast Decision of Block size, Prediction Mode and Intra Block for H.264 Intra Prediction EE Gaurav Hansda

Fast Decision of Block size, Prediction Mode and Intra Block for H.264 Intra Prediction EE Gaurav Hansda Fast Decision of Block size, Prediction Mode and Intra Block for H.264 Intra Prediction EE 5359 Gaurav Hansda 1000721849 gaurav.hansda@mavs.uta.edu Outline Introduction to H.264 Current algorithms for

More information

Freely Available Large-scale Video Quality Assessment Database in Full-HD Resolution with H.264 Coding

Freely Available Large-scale Video Quality Assessment Database in Full-HD Resolution with H.264 Coding Freely Available Large-scale Video Quality Assessment Database in Full-HD Resolution with H.264 Coding Mikolaj Leszczuk, Lucjan Janowski, Marcus Barkowsky To cite this version: Mikolaj Leszczuk, Lucjan

More information

A Linear Regression Framework For Assessing Time-Varying Subjective Quality in HTTP Streaming. Nagabhushan Eswara IIT Hyderabad November 14, 2017

A Linear Regression Framework For Assessing Time-Varying Subjective Quality in HTTP Streaming. Nagabhushan Eswara IIT Hyderabad November 14, 2017 A Linear Regression Framework For Assessing Time-Varying Subjective Quality in HTTP Streaming Nagabhushan Eswara IIT Hyderabad November 14, 2017 1 Introduction Increased mobile data traffic 1 : Data traffic

More information

A COMPARATIVE STUDY OF QUALITY AND CONTENT-BASED SPATIAL POOLING STRATEGIES IN IMAGE QUALITY ASSESSMENT. Dogancan Temel and Ghassan AlRegib

A COMPARATIVE STUDY OF QUALITY AND CONTENT-BASED SPATIAL POOLING STRATEGIES IN IMAGE QUALITY ASSESSMENT. Dogancan Temel and Ghassan AlRegib A COMPARATIVE STUDY OF QUALITY AND CONTENT-BASED SPATIAL POOLING STRATEGIES IN IMAGE QUALITY ASSESSMENT Dogancan Temel and Ghassan AlRegib Center for Signal and Information Processing (CSIP) School of

More information

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging 1 CS 9 Final Project Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging Feiyu Chen Department of Electrical Engineering ABSTRACT Subject motion is a significant

More information

Efficient Color Image Quality Assessment Using Gradient Magnitude Similarity Deviation

Efficient Color Image Quality Assessment Using Gradient Magnitude Similarity Deviation IJECT Vo l. 8, Is s u e 3, Ju l y - Se p t 2017 ISSN : 2230-7109 (Online) ISSN : 2230-9543 (Print) Efficient Color Image Quality Assessment Using Gradient Magnitude Similarity Deviation 1 Preeti Rani,

More information

BLIND QUALITY ASSESSMENT OF JPEG2000 COMPRESSED IMAGES USING NATURAL SCENE STATISTICS. Hamid R. Sheikh, Alan C. Bovik and Lawrence Cormack

BLIND QUALITY ASSESSMENT OF JPEG2000 COMPRESSED IMAGES USING NATURAL SCENE STATISTICS. Hamid R. Sheikh, Alan C. Bovik and Lawrence Cormack BLIND QUALITY ASSESSMENT OF JPEG2 COMPRESSED IMAGES USING NATURAL SCENE STATISTICS Hamid R. Sheikh, Alan C. Bovik and Lawrence Cormack Laboratory for Image and Video Engineering, Department of Electrical

More information

Storage Efficient NL-Means Burst Denoising for Programmable Cameras

Storage Efficient NL-Means Burst Denoising for Programmable Cameras Storage Efficient NL-Means Burst Denoising for Programmable Cameras Brendan Duncan Stanford University brendand@stanford.edu Miroslav Kukla Stanford University mkukla@stanford.edu Abstract An effective

More information

Lecture on Modeling Tools for Clustering & Regression

Lecture on Modeling Tools for Clustering & Regression Lecture on Modeling Tools for Clustering & Regression CS 590.21 Analysis and Modeling of Brain Networks Department of Computer Science University of Crete Data Clustering Overview Organizing data into

More information

Image Quality Assessment Techniques: An Overview

Image Quality Assessment Techniques: An Overview Image Quality Assessment Techniques: An Overview Shruti Sonawane A. M. Deshpande Department of E&TC Department of E&TC TSSM s BSCOER, Pune, TSSM s BSCOER, Pune, Pune University, Maharashtra, India Pune

More information

SUBJECTIVE ANALYSIS OF VIDEO QUALITY ON MOBILE DEVICES. Anush K. Moorthy, Lark K. Choi, Gustavo de Veciana and Alan C. Bovik

SUBJECTIVE ANALYSIS OF VIDEO QUALITY ON MOBILE DEVICES. Anush K. Moorthy, Lark K. Choi, Gustavo de Veciana and Alan C. Bovik SUBJECTIVE ANALYSIS OF VIDEO QUALITY ON MOBILE DEVICES Anush K. Moorthy, Lark K. Choi, Gustavo de Veciana and Alan C. Bovik Department of Electrical and Computer Engineering, The University of Texas at

More information

SINGLE PASS DEPENDENT BIT ALLOCATION FOR SPATIAL SCALABILITY CODING OF H.264/SVC

SINGLE PASS DEPENDENT BIT ALLOCATION FOR SPATIAL SCALABILITY CODING OF H.264/SVC SINGLE PASS DEPENDENT BIT ALLOCATION FOR SPATIAL SCALABILITY CODING OF H.264/SVC Randa Atta, Rehab F. Abdel-Kader, and Amera Abd-AlRahem Electrical Engineering Department, Faculty of Engineering, Port

More information

Complexity Reduced Mode Selection of H.264/AVC Intra Coding

Complexity Reduced Mode Selection of H.264/AVC Intra Coding Complexity Reduced Mode Selection of H.264/AVC Intra Coding Mohammed Golam Sarwer 1,2, Lai-Man Po 1, Jonathan Wu 2 1 Department of Electronic Engineering City University of Hong Kong Kowloon, Hong Kong

More information

A REDUCED REFERENCE VIDEO QUALITY METRIC FOR AVC/H.264

A REDUCED REFERENCE VIDEO QUALITY METRIC FOR AVC/H.264 A REDUCED REFERENCE VIDEO QUALITY METRIC FOR AVC/H.264 Tobias Oelbaum, Klaus Diepold Institute for Data Processing Technische Universität München Munich, Germany oelbaum@tum.de, kldi@tum.de. ABSTRACT A

More information

SURVEILLANCE VIDEO FOR MOBILE DEVICES

SURVEILLANCE VIDEO FOR MOBILE DEVICES SURVEILLANCE VIDEO FOR MOBILE DEVICES Olivier Steiger, Touradj Ebrahimi Signal Processing Institute Ecole Polytechnique Fédérale de Lausanne (EPFL) CH-1015 Lausanne, Switzerland {olivier.steiger,touradj.ebrahimi}@epfl.ch

More information

How Many Humans Does it Take to Judge Video Quality?

How Many Humans Does it Take to Judge Video Quality? How Many Humans Does it Take to Judge Video Quality? Bill Reckwerdt, CTO Video Clarity, Inc. Version 1.0 A Video Clarity Case Study page 1 of 5 Abstract for Subjective Video Quality Assessment In order

More information

QUANTIZER DESIGN FOR EXPLOITING COMMON INFORMATION IN LAYERED CODING. Mehdi Salehifar, Tejaswi Nanjundaswamy, and Kenneth Rose

QUANTIZER DESIGN FOR EXPLOITING COMMON INFORMATION IN LAYERED CODING. Mehdi Salehifar, Tejaswi Nanjundaswamy, and Kenneth Rose QUANTIZER DESIGN FOR EXPLOITING COMMON INFORMATION IN LAYERED CODING Mehdi Salehifar, Tejaswi Nanjundaswamy, and Kenneth Rose Department of Electrical and Computer Engineering University of California,

More information

A Novel Deblocking Filter Algorithm In H.264 for Real Time Implementation

A Novel Deblocking Filter Algorithm In H.264 for Real Time Implementation 2009 Third International Conference on Multimedia and Ubiquitous Engineering A Novel Deblocking Filter Algorithm In H.264 for Real Time Implementation Yuan Li, Ning Han, Chen Chen Department of Automation,

More information

Image retrieval based on bag of images

Image retrieval based on bag of images University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2009 Image retrieval based on bag of images Jun Zhang University of Wollongong

More information

Attention modeling for video quality assessment balancing global quality and local quality

Attention modeling for video quality assessment balancing global quality and local quality Downloaded from orbit.dtu.dk on: Jul 02, 2018 Attention modeling for video quality assessment balancing global quality and local quality You, Junyong; Korhonen, Jari; Perkis, Andrew Published in: proceedings

More information

ADAPTIVE VIDEO STREAMING FOR BANDWIDTH VARIATION WITH OPTIMUM QUALITY

ADAPTIVE VIDEO STREAMING FOR BANDWIDTH VARIATION WITH OPTIMUM QUALITY ADAPTIVE VIDEO STREAMING FOR BANDWIDTH VARIATION WITH OPTIMUM QUALITY Joseph Michael Wijayantha Medagama (08/8015) Thesis Submitted in Partial Fulfillment of the Requirements for the Degree Master of Science

More information

OVERVIEW OF IEEE 1857 VIDEO CODING STANDARD

OVERVIEW OF IEEE 1857 VIDEO CODING STANDARD OVERVIEW OF IEEE 1857 VIDEO CODING STANDARD Siwei Ma, Shiqi Wang, Wen Gao {swma,sqwang, wgao}@pku.edu.cn Institute of Digital Media, Peking University ABSTRACT IEEE 1857 is a multi-part standard for multimedia

More information

Context based optimal shape coding

Context based optimal shape coding IEEE Signal Processing Society 1999 Workshop on Multimedia Signal Processing September 13-15, 1999, Copenhagen, Denmark Electronic Proceedings 1999 IEEE Context based optimal shape coding Gerry Melnikov,

More information

A Matlab-Based Tool for Video Quality Evaluation without Reference

A Matlab-Based Tool for Video Quality Evaluation without Reference RADIOENGINEERING, VOL. 23, NO. 1, APRIL 2014 405 A Matlab-Based Tool for Video Quality Evaluation without Reference Ondřej ZACH, Martin SLANINA Dept. of Radio Electronics, Brno University of Technology,

More information

Fast Mode Decision for H.264/AVC Using Mode Prediction

Fast Mode Decision for H.264/AVC Using Mode Prediction Fast Mode Decision for H.264/AVC Using Mode Prediction Song-Hak Ri and Joern Ostermann Institut fuer Informationsverarbeitung, Appelstr 9A, D-30167 Hannover, Germany ri@tnt.uni-hannover.de ostermann@tnt.uni-hannover.de

More information

Video Quality Analysis for H.264 Based on Human Visual System

Video Quality Analysis for H.264 Based on Human Visual System IOSR Journal of Engineering (IOSRJEN) ISSN (e): 2250-3021 ISSN (p): 2278-8719 Vol. 04 Issue 08 (August. 2014) V4 PP 01-07 www.iosrjen.org Subrahmanyam.Ch 1 Dr.D.Venkata Rao 2 Dr.N.Usha Rani 3 1 (Research

More information

Optimized Strategies for Real-Time Multimedia Communications from Mobile Devices

Optimized Strategies for Real-Time Multimedia Communications from Mobile Devices Optimized Strategies for Real-Time Multimedia Communications from Mobile Devices Enrico Masala Dept. of Control and Computer Engineering, Politecnico di Torino, Torino, Italy ( Part of this work has been

More information

Summer Internship at STMicroelectronics, Greater Noida, India

Summer Internship at STMicroelectronics, Greater Noida, India Summer Internship at STMicroelectronics, Greater Noida, India Thibault Lefeuvre, Ecole Polytechnique, France August 2015 Techniques of frame compression in ultra low power encoder Introduction At first,

More information

ISSN: An Efficient Fully Exploiting Spatial Correlation of Compress Compound Images in Advanced Video Coding

ISSN: An Efficient Fully Exploiting Spatial Correlation of Compress Compound Images in Advanced Video Coding An Efficient Fully Exploiting Spatial Correlation of Compress Compound Images in Advanced Video Coding Ali Mohsin Kaittan*1 President of the Association of scientific research and development in Iraq Abstract

More information

An Efficient Saliency Based Lossless Video Compression Based On Block-By-Block Basis Method

An Efficient Saliency Based Lossless Video Compression Based On Block-By-Block Basis Method An Efficient Saliency Based Lossless Video Compression Based On Block-By-Block Basis Method Ms. P.MUTHUSELVI, M.E(CSE), V.P.M.M Engineering College for Women, Krishnankoil, Virudhungar(dt),Tamil Nadu Sukirthanagarajan@gmail.com

More information

Technical Recommendation S. 10/07: Source Encoding of High Definition Mobile TV Services

Technical Recommendation S. 10/07: Source Encoding of High Definition Mobile TV Services Technical Recommendation S. 10/07: Source Encoding of High Definition Mobile TV Services Version: 0.4 Date: November 29, 2007 Authors: M. Ries, M. Rupp Status: Final Page 1 / 7 Technical Recommendation

More information

RATE-DISTORTION EVALUATION FOR TWO-LAYER CODING SYSTEMS. Philippe Hanhart and Touradj Ebrahimi

RATE-DISTORTION EVALUATION FOR TWO-LAYER CODING SYSTEMS. Philippe Hanhart and Touradj Ebrahimi RATE-DISTORTION EVALUATION FOR TWO-LAYER CODING SYSTEMS Philippe Hanhart and Touradj Ebrahimi Multimedia Signal Processing Group, EPFL, Lausanne, Switzerland ABSTRACT The Bjøntegaard model is widely used

More information

QoS to QoE Mapping Model for Wired/Wireless Video Communication

QoS to QoE Mapping Model for Wired/Wireless Video Communication QoS to QoE Mapping Model for Wired/Wireless Video Communication Federica Battisti, Marco Carli, Pradip Paudyal University of Roma, TRE Rome, Italy name.lastname@uniroma.it Abstract Multimedia service providers

More information

No-Refrence Image Quality Assessment Using Blind Image Quality Indices

No-Refrence Image Quality Assessment Using Blind Image Quality Indices No-Refrence Image Quality Assessment Using Blind Image Quality Indices Parul Satsangi, Sagar Tandon, Prashant Kr. Yadav & Priyal Diwakar Electronics and Communication Department, M.I.T,Moradabad E-mail

More information

2 Video Quality Assessment framework for ROI-based Mobile Video Adaptation

2 Video Quality Assessment framework for ROI-based Mobile Video Adaptation 3rd International Conference on Multimedia Technology(ICMT 2013) A Noel Scheme of Video Quality Estimation for the ROI Transcoding Video Ting Yao 1. Abstract. Because of the limitation of bandwidth and

More information

Mapping of Hierarchical Activation in the Visual Cortex Suman Chakravartula, Denise Jones, Guillaume Leseur CS229 Final Project Report. Autumn 2008.

Mapping of Hierarchical Activation in the Visual Cortex Suman Chakravartula, Denise Jones, Guillaume Leseur CS229 Final Project Report. Autumn 2008. Mapping of Hierarchical Activation in the Visual Cortex Suman Chakravartula, Denise Jones, Guillaume Leseur CS229 Final Project Report. Autumn 2008. Introduction There is much that is unknown regarding

More information

Sketchable Histograms of Oriented Gradients for Object Detection

Sketchable Histograms of Oriented Gradients for Object Detection Sketchable Histograms of Oriented Gradients for Object Detection No Author Given No Institute Given Abstract. In this paper we investigate a new representation approach for visual object recognition. The

More information

Robust Ring Detection In Phase Correlation Surfaces

Robust Ring Detection In Phase Correlation Surfaces Griffith Research Online https://research-repository.griffith.edu.au Robust Ring Detection In Phase Correlation Surfaces Author Gonzalez, Ruben Published 2013 Conference Title 2013 International Conference

More information

An ICA based Approach for Complex Color Scene Text Binarization

An ICA based Approach for Complex Color Scene Text Binarization An ICA based Approach for Complex Color Scene Text Binarization Siddharth Kherada IIIT-Hyderabad, India siddharth.kherada@research.iiit.ac.in Anoop M. Namboodiri IIIT-Hyderabad, India anoop@iiit.ac.in

More information

JPEG 2000 vs. JPEG in MPEG Encoding

JPEG 2000 vs. JPEG in MPEG Encoding JPEG 2000 vs. JPEG in MPEG Encoding V.G. Ruiz, M.F. López, I. García and E.M.T. Hendrix Dept. Computer Architecture and Electronics University of Almería. 04120 Almería. Spain. E-mail: vruiz@ual.es, mflopez@ace.ual.es,

More information

Compression of VQM Features for Low Bit-Rate Video Quality Monitoring

Compression of VQM Features for Low Bit-Rate Video Quality Monitoring Compression of VQM Features for Low Bit-Rate Video Quality Monitoring Mina Makar, Yao-Chung Lin, Andre F. de Araujo and Bernd Girod Information Systems Laboratory, Stanford University, Stanford, CA 9435

More information

Reduction of Blocking artifacts in Compressed Medical Images

Reduction of Blocking artifacts in Compressed Medical Images ISSN 1746-7659, England, UK Journal of Information and Computing Science Vol. 8, No. 2, 2013, pp. 096-102 Reduction of Blocking artifacts in Compressed Medical Images Jagroop Singh 1, Sukhwinder Singh

More information

A NO-REFERENCE VIDEO QUALITY PREDICTOR FOR COMPRESSION AND SCALING ARTIFACTS

A NO-REFERENCE VIDEO QUALITY PREDICTOR FOR COMPRESSION AND SCALING ARTIFACTS A NO-REFERENCE VIDEO QUALITY PREDICTOR FOR COMPRESSION AND SCALING ARTIFACTS Deepti Ghadiyaram The University of Texas at Austin Chao Chen, Sasi Inguva, and Anil Kokaram Google Inc. ABSTRACT No-Reference

More information

ADAPTIVE PICTURE SLICING FOR DISTORTION-BASED CLASSIFICATION OF VIDEO PACKETS

ADAPTIVE PICTURE SLICING FOR DISTORTION-BASED CLASSIFICATION OF VIDEO PACKETS ADAPTIVE PICTURE SLICING FOR DISTORTION-BASED CLASSIFICATION OF VIDEO PACKETS E. Masala, D. Quaglia, J.C. De Martin Λ Dipartimento di Automatica e Informatica/ Λ IRITI-CNR Politecnico di Torino, Italy

More information

Deblocking Filter Algorithm with Low Complexity for H.264 Video Coding

Deblocking Filter Algorithm with Low Complexity for H.264 Video Coding Deblocking Filter Algorithm with Low Complexity for H.264 Video Coding Jung-Ah Choi and Yo-Sung Ho Gwangju Institute of Science and Technology (GIST) 261 Cheomdan-gwagiro, Buk-gu, Gwangju, 500-712, Korea

More information

Structural Similarity Based Image Quality Assessment Using Full Reference Method

Structural Similarity Based Image Quality Assessment Using Full Reference Method From the SelectedWorks of Innovative Research Publications IRP India Spring April 1, 2015 Structural Similarity Based Image Quality Assessment Using Full Reference Method Innovative Research Publications,

More information

Rate Distortion Optimization in Video Compression

Rate Distortion Optimization in Video Compression Rate Distortion Optimization in Video Compression Xue Tu Dept. of Electrical and Computer Engineering State University of New York at Stony Brook 1. Introduction From Shannon s classic rate distortion

More information

Effect of Principle Component Analysis and Support Vector Machine in Software Fault Prediction

Effect of Principle Component Analysis and Support Vector Machine in Software Fault Prediction International Journal of Computer Trends and Technology (IJCTT) volume 7 number 3 Jan 2014 Effect of Principle Component Analysis and Support Vector Machine in Software Fault Prediction A. Shanthini 1,

More information

A COST-EFFICIENT RESIDUAL PREDICTION VLSI ARCHITECTURE FOR H.264/AVC SCALABLE EXTENSION

A COST-EFFICIENT RESIDUAL PREDICTION VLSI ARCHITECTURE FOR H.264/AVC SCALABLE EXTENSION A COST-EFFICIENT RESIDUAL PREDICTION VLSI ARCHITECTURE FOR H.264/AVC SCALABLE EXTENSION Yi-Hau Chen, Tzu-Der Chuang, Chuan-Yung Tsai, Yu-Jen Chen, and Liang-Gee Chen DSP/IC Design Lab., Graduate Institute

More information

ESTIMATION OF THE UTILITIES OF THE NAL UNITS IN H.264/AVC SCALABLE VIDEO BITSTREAMS. Bin Zhang, Mathias Wien and Jens-Rainer Ohm

ESTIMATION OF THE UTILITIES OF THE NAL UNITS IN H.264/AVC SCALABLE VIDEO BITSTREAMS. Bin Zhang, Mathias Wien and Jens-Rainer Ohm 19th European Signal Processing Conference (EUSIPCO 2011) Barcelona, Spain, August 29 - September 2, 2011 ESTIMATION OF THE UTILITIES OF THE NAL UNITS IN H.264/AVC SCALABLE VIDEO BITSTREAMS Bin Zhang,

More information

Image Quality Assessment Method Based On Statistics of Pixel Value Difference And Local Variance Similarity

Image Quality Assessment Method Based On Statistics of Pixel Value Difference And Local Variance Similarity 212 International Conference on Computer Technology and Science (ICCTS 212) IPCSIT vol. 47 (212) (212) IACSIT Press, Singapore DOI: 1.7763/IPCSIT.212.V47.28 Image Quality Assessment Method Based On Statistics

More information

EE Low Complexity H.264 encoder for mobile applications

EE Low Complexity H.264 encoder for mobile applications EE 5359 Low Complexity H.264 encoder for mobile applications Thejaswini Purushotham Student I.D.: 1000-616 811 Date: February 18,2010 Objective The objective of the project is to implement a low-complexity

More information

Model-based Enhancement of Lighting Conditions in Image Sequences

Model-based Enhancement of Lighting Conditions in Image Sequences Model-based Enhancement of Lighting Conditions in Image Sequences Peter Eisert and Bernd Girod Information Systems Laboratory Stanford University {eisert,bgirod}@stanford.edu http://www.stanford.edu/ eisert

More information

BLIND IMAGE QUALITY ASSESSMENT WITH LOCAL CONTRAST FEATURES

BLIND IMAGE QUALITY ASSESSMENT WITH LOCAL CONTRAST FEATURES BLIND IMAGE QUALITY ASSESSMENT WITH LOCAL CONTRAST FEATURES Ganta Kasi Vaibhav, PG Scholar, Department of Electronics and Communication Engineering, University College of Engineering Vizianagaram,JNTUK.

More information

A hybrid video quality metric for analyzing quality degradation due to frame drop

A hybrid video quality metric for analyzing quality degradation due to frame drop A hybrid video quality metric for analyzing quality degradation due to frame drop Manish K Thakur, Vikas Saxena 2 and J P Gupta 3 Department of CSE/IT, Jaypee Institute of Information Technology Noida,

More information

2 Framework of The Proposed Voice Quality Assessment System

2 Framework of The Proposed Voice Quality Assessment System 3rd International Conference on Multimedia Technology(ICMT 2013) A Packet-layer Quality Assessment System for VoIP Liangliang Jiang 1 and Fuzheng Yang 2 Abstract. A packet-layer quality assessment system

More information

A Multi-purpose Objective Quality Metric for Image Watermarking

A Multi-purpose Objective Quality Metric for Image Watermarking A Multi-purpose Objective Quality Metric for Image Watermarking Vinod Pankajakshan, Florent Autrusseau To cite this version: Vinod Pankajakshan, Florent Autrusseau. A Multi-purpose Objective Quality Metric

More information

This is the published version of a paper presented at IS&T international symposium Electronic Imaging 2016.

This is the published version of a paper presented at IS&T international symposium Electronic Imaging 2016. http://www.diva-portal.org This is the published version of a paper presented at IS&T international symposium Electronic Imaging 206. Citation for the original published paper: Søgaard, J., Krasula, L.,

More information

Texture Image Segmentation using FCM

Texture Image Segmentation using FCM Proceedings of 2012 4th International Conference on Machine Learning and Computing IPCSIT vol. 25 (2012) (2012) IACSIT Press, Singapore Texture Image Segmentation using FCM Kanchan S. Deshmukh + M.G.M

More information

STUDY AND IMPLEMENTATION OF VIDEO COMPRESSION STANDARDS (H.264/AVC, DIRAC)

STUDY AND IMPLEMENTATION OF VIDEO COMPRESSION STANDARDS (H.264/AVC, DIRAC) STUDY AND IMPLEMENTATION OF VIDEO COMPRESSION STANDARDS (H.264/AVC, DIRAC) EE 5359-Multimedia Processing Spring 2012 Dr. K.R Rao By: Sumedha Phatak(1000731131) OBJECTIVE A study, implementation and comparison

More information

Calculation of average coding efficiency based on subjective quality scores

Calculation of average coding efficiency based on subjective quality scores Calculation of average coding efficiency based on subjective quality scores Philippe Hanhart, Touradj Ebrahimi Multimedia Signal Processing Group, EPFL, Lausanne, Switzerland Abstract The Bjøntegaard model

More information

A Subjective Study to Evaluate Video Quality Assessment Algorithms

A Subjective Study to Evaluate Video Quality Assessment Algorithms A Subjective Study to Evaluate Video Quality Assessment Algorithms Kalpana Seshadrinathan a, Rajiv Soundararajan b, Alan C. Bovik b and Lawrence K. Cormack b a Intel Corporation, Chandler, AZ - USA. b

More information

JPEG compression of monochrome 2D-barcode images using DCT coefficient distributions

JPEG compression of monochrome 2D-barcode images using DCT coefficient distributions Edith Cowan University Research Online ECU Publications Pre. JPEG compression of monochrome D-barcode images using DCT coefficient distributions Keng Teong Tan Hong Kong Baptist University Douglas Chai

More information

Nelder-Mead Enhanced Extreme Learning Machine

Nelder-Mead Enhanced Extreme Learning Machine Philip Reiner, Bogdan M. Wilamowski, "Nelder-Mead Enhanced Extreme Learning Machine", 7-th IEEE Intelligent Engineering Systems Conference, INES 23, Costa Rica, June 9-2., 29, pp. 225-23 Nelder-Mead Enhanced

More information

A STUDY ON THE EFFECTS OF QUALITY OF SERVICE PARAMETERS ON PERCEIVED VIDEO QUALITY. P. Paudyal, F. Battisti and M. Carli

A STUDY ON THE EFFECTS OF QUALITY OF SERVICE PARAMETERS ON PERCEIVED VIDEO QUALITY. P. Paudyal, F. Battisti and M. Carli A STUDY ON THE EFFECTS OF QUALITY OF SERVICE PARAMETERS ON PERCEIVED VIDEO QUALITY P. Paudyal, F. Battisti and M. Carli COMLAB - Telecommunication Lab Universitá degli Studi Roma TRE Via Vito Volterra

More information

VIDEO streaming applications over the Internet are gaining. Brief Papers

VIDEO streaming applications over the Internet are gaining. Brief Papers 412 IEEE TRANSACTIONS ON BROADCASTING, VOL. 54, NO. 3, SEPTEMBER 2008 Brief Papers Redundancy Reduction Technique for Dual-Bitstream MPEG Video Streaming With VCR Functionalities Tak-Piu Ip, Yui-Lam Chan,

More information

CS 260: Seminar in Computer Science: Multimedia Networking

CS 260: Seminar in Computer Science: Multimedia Networking CS 260: Seminar in Computer Science: Multimedia Networking Jiasi Chen Lectures: MWF 4:10-5pm in CHASS http://www.cs.ucr.edu/~jiasi/teaching/cs260_spring17/ Multimedia is User perception Content creation

More information

I How does the formulation (5) serve the purpose of the composite parameterization

I How does the formulation (5) serve the purpose of the composite parameterization Supplemental Material to Identifying Alzheimer s Disease-Related Brain Regions from Multi-Modality Neuroimaging Data using Sparse Composite Linear Discrimination Analysis I How does the formulation (5)

More information

BLOCK MATCHING-BASED MOTION COMPENSATION WITH ARBITRARY ACCURACY USING ADAPTIVE INTERPOLATION FILTERS

BLOCK MATCHING-BASED MOTION COMPENSATION WITH ARBITRARY ACCURACY USING ADAPTIVE INTERPOLATION FILTERS 4th European Signal Processing Conference (EUSIPCO ), Florence, Italy, September 4-8,, copyright by EURASIP BLOCK MATCHING-BASED MOTION COMPENSATION WITH ARBITRARY ACCURACY USING ADAPTIVE INTERPOLATION

More information

Quality Estimation of Video Transmitted over an Additive WGN Channel based on Digital Watermarking and Wavelet Transform

Quality Estimation of Video Transmitted over an Additive WGN Channel based on Digital Watermarking and Wavelet Transform Quality Estimation of Video Transmitted over an Additive WGN Channel based on Digital Watermarking and Wavelet Transform Mohamed S. El-Mahallawy, Attalah Hashad, Hazem Hassan Ali, and Heba Sami Zaky Abstract

More information

PERCEPTUAL ALIASING FACTORS AND THE IMPACT OF FRAME RATE ON VIDEO QUALITY. Rasoul Mohammadi Nasiri and Zhou Wang

PERCEPTUAL ALIASING FACTORS AND THE IMPACT OF FRAME RATE ON VIDEO QUALITY. Rasoul Mohammadi Nasiri and Zhou Wang PERCEPTUAL ALIASING FACTORS AND THE IMPACT OF FRAME RATE ON VIDEO QUALITY Rasoul Mohammadi Nasiri and Zhou Wang Dept. of Electrical and Computer Engineering, University of Waterloo Emails: {r26moham, zhou.wang}@uwaterloo.ca

More information

Equation to LaTeX. Abhinav Rastogi, Sevy Harris. I. Introduction. Segmentation.

Equation to LaTeX. Abhinav Rastogi, Sevy Harris. I. Introduction. Segmentation. Equation to LaTeX Abhinav Rastogi, Sevy Harris {arastogi,sharris5}@stanford.edu I. Introduction Copying equations from a pdf file to a LaTeX document can be time consuming because there is no easy way

More information

Frequency Band Coding Mode Selection for Key Frames of Wyner-Ziv Video Coding

Frequency Band Coding Mode Selection for Key Frames of Wyner-Ziv Video Coding 2009 11th IEEE International Symposium on Multimedia Frequency Band Coding Mode Selection for Key Frames of Wyner-Ziv Video Coding Ghazaleh R. Esmaili and Pamela C. Cosman Department of Electrical and

More information

Offset Trace-Based Video Quality Evaluation after Network Transport

Offset Trace-Based Video Quality Evaluation after Network Transport JOURNAL OF MULTIMEDIA, VOL. 1, NO. 2, MAY 06 1 Offset Trace-Based Video Quality Evaluation after Network Transport Patrick Seeling and Martin Reisslein Dept. of Electrical Engineering Arizona State University

More information

FAST MOTION ESTIMATION WITH DUAL SEARCH WINDOW FOR STEREO 3D VIDEO ENCODING

FAST MOTION ESTIMATION WITH DUAL SEARCH WINDOW FOR STEREO 3D VIDEO ENCODING FAST MOTION ESTIMATION WITH DUAL SEARCH WINDOW FOR STEREO 3D VIDEO ENCODING 1 Michal Joachimiak, 2 Kemal Ugur 1 Dept. of Signal Processing, Tampere University of Technology, Tampere, Finland 2 Jani Lainema,

More information

VISUAL QUALITY ASSESSMENT CHALLENGES FOR ARCHITECTURE DESIGN EXPLORATIONS. Wen-Fu Kao and Durgaprasad Bilagi. Intel Corporation Folsom, CA 95630

VISUAL QUALITY ASSESSMENT CHALLENGES FOR ARCHITECTURE DESIGN EXPLORATIONS. Wen-Fu Kao and Durgaprasad Bilagi. Intel Corporation Folsom, CA 95630 Proceedings of Seventh International Workshop on Video Processing and Quality Metrics for Consumer Electronics January 30-February 1, 2013, Scottsdale, Arizona VISUAL QUALITY ASSESSMENT CHALLENGES FOR

More information

ERROR-ROBUST INTER/INTRA MACROBLOCK MODE SELECTION USING ISOLATED REGIONS

ERROR-ROBUST INTER/INTRA MACROBLOCK MODE SELECTION USING ISOLATED REGIONS ERROR-ROBUST INTER/INTRA MACROBLOCK MODE SELECTION USING ISOLATED REGIONS Ye-Kui Wang 1, Miska M. Hannuksela 2 and Moncef Gabbouj 3 1 Tampere International Center for Signal Processing (TICSP), Tampere,

More information

Research Article No-Reference Video Quality Assessment Model for Distortion Caused by Packet Loss in the Real-Time Mobile Video Services

Research Article No-Reference Video Quality Assessment Model for Distortion Caused by Packet Loss in the Real-Time Mobile Video Services Advances in Multimedia Volume 214, Article ID 66493, 15 pages http://dx.doi.org/1.1155/214/66493 Research Article No-Reference Video Quality Assessment Model for Distortion Caused by Packet Loss in the

More information

Implementation of the Highly Secured H.264/AVC Bit-Streams Using Correlated Motion (Cm) Estimation for High Video Quality of Service (Qos)

Implementation of the Highly Secured H.264/AVC Bit-Streams Using Correlated Motion (Cm) Estimation for High Video Quality of Service (Qos) Implementation of the Highly Secured H.264/AVC Bit-Streams Using Correlated Motion (Cm) Estimation for High Video Quality of Service (Qos) DHIVYA G, RAJESWARI A Graduate student, M.E Applied Electronics,

More information

Compressive Sensing for Multimedia. Communications in Wireless Sensor Networks

Compressive Sensing for Multimedia. Communications in Wireless Sensor Networks Compressive Sensing for Multimedia 1 Communications in Wireless Sensor Networks Wael Barakat & Rabih Saliba MDDSP Project Final Report Prof. Brian L. Evans May 9, 2008 Abstract Compressive Sensing is an

More information

A NOVEL SECURED BOOLEAN BASED SECRET IMAGE SHARING SCHEME

A NOVEL SECURED BOOLEAN BASED SECRET IMAGE SHARING SCHEME VOL 13, NO 13, JULY 2018 ISSN 1819-6608 2006-2018 Asian Research Publishing Network (ARPN) All rights reserved wwwarpnjournalscom A NOVEL SECURED BOOLEAN BASED SECRET IMAGE SHARING SCHEME Javvaji V K Ratnam

More information

International Journal of Emerging Technology and Advanced Engineering Website: (ISSN , Volume 2, Issue 4, April 2012)

International Journal of Emerging Technology and Advanced Engineering Website:   (ISSN , Volume 2, Issue 4, April 2012) A Technical Analysis Towards Digital Video Compression Rutika Joshi 1, Rajesh Rai 2, Rajesh Nema 3 1 Student, Electronics and Communication Department, NIIST College, Bhopal, 2,3 Prof., Electronics and

More information