VISUAL ATTENTION FOR CONTENT BASED IMAGE RETRIEVAL. Alex Papushoy and Adrian G. Bors

Size: px
Start display at page:

Download "VISUAL ATTENTION FOR CONTENT BASED IMAGE RETRIEVAL. Alex Papushoy and Adrian G. Bors"

Transcription

1 VISUAL ATTENTION FOR CONTENT BASED IMAGE RETRIEVAL Alex Papushoy and Adrian G. Bors Department of Computer Science, University of York, York YO10 5GH, UK ABSTRACT A new image retrieval method, based on human visual attention models, called query by saliency content retrieval (QSCR) is presented in this paper. Each image is segmented and a set of characteristic features is evaluated for each region. The saliency for each image region, as it would be perceived by a human observer, is estimated for each region and then used for image retrieval. Images displaying similar features and characterized by similar saliency are then retrieved from the database. Both local and global saliency are considered in the retrieval process. The proposed method ranks the similarity between the query and the a set of given images using the Earth Mover Distance algorithm. Index Terms Content based image retrieval, human visual attention model, saliency, salient edges. 1. INTRODUCTION Content-based image retrieval (CBIR) considers a user-provided image as a query, whose visual information is processed and used in a content-based search [1, 2]. CBIR is based on the notion that visual similarity implies semantic similarity, which is not always the case, but is a valid assumption. The main challenge in CBIR systems is the ambiguity in the high-level (semantic) concepts extracted from the low-level (pixels) features of the image [3, 4, 5]. The second obstacle is the sensory gap which can be interpreted as the incompleteness of the object information captured by an imaging device. Generally, it is difficult for CBIR systems to search for broad semantic concepts because it is hard to limit the feature space without broadening the semantic gap. There are four categories of CBIR methods, [2]: bottom-up, top-down, relevance feedback and based on image classification. Those that rely purely on the information contained in the image are bottom-up approaches such as [6], while top-down approaches consider the prior knowledge. In image classification approaches, the system is presented with training data from which it learns a query [7]. Systems involving the user in the retrieval process via relevance feedback mechanisms are a mixture of bottom-up and top-down approaches [8]. Blobworld [5] is a region-based image retrieval system (RBIR) that segments the image into regions using the Expectation- Maximization (EM) algorithm and then prompts the user to specify the query regions of interest (ROI) and their importance. Certain top-down approaches employ machine learning techniques for the relevance feedback such as support vector machine (SVM) [9] or multiple instance learning (MIL) [10]. In our paper we propose a new query by similarity content retrieval (QSCR) method which is based on human visual attention models [11, 12]. During the first processing stage, the image is segmented into regions and feature vectors characterizing color, contrast, texture, region centroid, and the contrast with respect to the neighborhood are extracted for each region. Saliency is considered at too levels: localized, for defining the saliency of each segmented region, and global for the entire image, estimated based on the statistics of salient edges [13]. An optimization procedure called the Earth Mover s Distance (EMD) [14] is used together with the energy of salient edges for evaluating the similarity between the query image and a given retrieved image. The proposed QSCR methodology and the visual attention model is described in Section 2 while the similarity-based ranking procedure is detailed in Section 3. Experimental results are provided in Section 4 and the conclusions of this research study are outlined in Section QUERY BY SIMILARITY CONTENT RETRIEVAL BASED ON VISUAL ATTENTION MODELS Local saliency is represented as a weight for a distances in the feature space between salient regions, while globally is determined by the statistics of salient edges. The proposed methodology consists of three main processing stages as shown in the diagram from Fig. 1. Image segmentation is performed using the mean-shift algorithm [15]. For each segmented region we calculate a characteristic feature vector with entries corresponding to: color, contrast, texture information, the region neighbourhood information and region centroid. These features are then used into a inter-region distance measure between two images weighted according to their similarity. The human visual system is attracted to specific image regions coinciding with the fixation points chosen by saccades (random eye movements) at the pre-attentive stage for foveation (conscious acquisition of detail). Such image regions are characterized by local discontinuities and relevant features that make them stand out from the rest of the image. There are two ways to identify salient regions in images: bottom-up and top-down attention. Bottom-up attention is instinctive and involuntary corresponding to a human reflex. It is entirely driven by the image, usually by the colors, regions size, orientation, position, and motion. Top-down attention on the other hand, is driven by memory and prior experiences. The Itti-Koch saliency model [11, 16] is a well-known biologically plausible method designed for fast bottom-up scene analysis which employs the model of neurological processes occurring in primates brains. Graph-Based Visual Saliency (GBVS) [12] is the graph-based normalization of the Itti-Koch model. Other approaches, loosely based on the visual attention model of Itti-Koch, are the Saliency Using Natural statistics (SUN) [17] and the Frequency-Tuned Saliency (FTS) [18]. In [18] orientation features are obtained from filtering the image with a bank of Gabor filters at different orientations. SUN is a hybrid biologically-plausible and computational attention model based on the Bayesian framework using the a priori information from natural images collected off-line [17]. GBVS [12] was chosen in this study for calculating the saliency map in images due to its ability to clearly identify the most salient objects and image regions. Generally, saliency maps are created in three steps: feature vectors are extracted for every pixel to create feature maps, then activation maps are computed, and finally the activation maps are normalized and combined. GBVS employs dyadic /15/$ IEEE 971 ICIP 2015

2 Fig. 1: The system used for query by similarity content retrieval (QSCR). Gaussian pyramids for the image scales of 2:1, 3:1 and 4:1. These are applied for each channel of the physiologically derived D*K*L* color space. Orientation maps are created after applying Gabor filters at {0,45,90,135} degrees at every scale of each color channel. Unlike the Itti-Koch model that computes activation maps by centre-surround differences of image features [11], GBVS applies a graph-based approach [12]. The adjacency matrix is constructed by connecting each pixel of the map to all the other pixels, excluding itself, by using the following similarity function w(m x,m y) between feature vectors corresponding to the pixels located at x and y: [ ] Mx w 1(M x,m y) = log exp x y 2 (1) 2σ 2 M y where σ is the scale, in the range of [0.1,0,2] from the given map width. A Markov chain is defined over this adjacency matrix, where the weights of outbound edges are normalized to 1, by assuming that graph nodes are states, and edges are transition probabilities. By computing the equilibrium distribution yields an activation map A, where large values are concentrated in areas of high activation and thus are salient. The resulting activation map is smoothed and normalized. A new graph is constructed on the activation map, with each node connected to all the others including itself and which has the edge weights given by : ] w 2(M x,m y) = A(y)exp [ x y 2 (2) 2σ 2 where A(y) corresponds to the activation at location y. The normalization of the activation maps leads to emphasizing the areas of true dissimilarity, while suppressing non-salient regions. The resulting saliency map for the entire image is denoted as S are represents the sum of the normalized activation maps for each color and local orientation channel as provided by the Gabor filters. The salient regions are decided, following extensive experimentation, as those that have more than 20 % salient pixels in their segmented areas. For evaluating the global saliency we consider the edges extracted by the Canny edge detector [19]. Edge saliency is determined by the edge length and the saliency in the edge surrounding area as given by : S e = λ LL e +λ NN e (3) where S e represents the saliency of edge e, L e represents the length of the edge,n e is the saliency in the edge neighbourhood, and where λ L = 0.3 and λ N = 0.7 are weighting factors. The saliency in the neighbourhood of the edge is calculated by averaging over a small neighbourhood. Salient edges are those that have their saliency above as 25% from the maximum saliency, which was assessed following empirical evaluation. The statistics of the edges are grouped in edge histogram descriptors (EHD) as in the representation of the edge information by the MPEG-7 image compression standard [20]. Salient edges are counted for each orientation from the entire image, resulting in a vector EHD(θ,I), where θ = {0,π/2,π,3π/4,nondir}, where non-dir stands for non-directional. 3. SIMILARITY-BASED IMAGE RANKING The procedure of segmentation, feature extraction and saliency extraction described in the previous section is applied to all the retrieval candidate images as well as to the query image. Given a query image, we rank all the available candidate images according to their similarity with the query image. Let us consider that both the query imageqand a given imagei from the database are segmented into several regions Q i, i = 1,...,M and I j, j = 1,...,N, respectively. The similarity ranking becomes a many-to-many region matching problem which takes into account the salient edges as well. Examples of many-to-many region matching distances are the Integrated Region Matching (IRM) algorithm [4] and the Earth Mover s Distances (EMD) metric [14]. The similarity-based image ranking procedure proposed in this paper is outlined in the lower part of the diagram from Fig. 1. We propose a similarity measure between the query imageqand a given image I, represented as the weighted sum of the EMD matching cost function and the global image saliency measure as given by its salient edges : S(Q,I) = 0.7 EMD(Q,I) θ +0.3 EHD(θ,Q) EHD(θ,I) α EMD 5 α E (4) where EMD(Q,I) is the EMD metric between images Q and I, EHD(θ, Q) represents the average salient edge energy in the direction of θ = {0,π/2,π,3π/4,non-dir} for the image Q. α EMD and α E represent the robustness factors which are set as the 95th percentile of the cumulative distribution function of the EMD and the EHD measures, respectively, calculated using a statistically significant image sample set. The robustness factors are used for normalizing whilst eliminating outliers. EMD represents a measure of similarity in the local salient regions between the images Q and I, while EHD represents the similarity in the salient edge distributions and is extracted as described in the previous section. A inter-region distance measure D(Q i,i j) is calculated between each region i = 1,...,M from the query image Q and each region j = 1,...,N from the candidate retrieval image I as: D(Q i,i j) = ψ(s i,s j)(0.45d 2 cl +2.34d 2 te +0.45d 2 co +0.04d 2 nn +0.04d 2 cd) 1/2 (5) where ψ(s i,s j) denotes the joint saliency weight for Q i and I j, d cl, d te and d co are the Euclidean distances between the primary features of color, texture and contrast vectors, whiled nn andd cd are the Euclidean distances between the secondary features characterizing the colors of the nearest neighboring regions and the centroids of the regions Q i and I j. Each distance component is normalized to the interval[0,1] and is weighted according to its significance for 972

3 retrieval with an empirically estimated weight. The color distance d cl is calculated as the average distance of the normalized E2000 distance, which conforms to the minimal perceptual color difference according to CIE. This distance is calculated as the sum of the differences between the median L*a*b* color coordinates of the regions Q i and I j and the normalized distances between their corresponding standard deviations. The texture distance d te corresponds to the Euclidean distance between the average of the horizontal, vertical and oblique absolute value of the Discrete Wavelet Transform coefficients for the regions Q i and I j divided by their corresponding standard deviations calculated across the entire image database. The contrast difference d co is represented by the normalized Euclidean difference of the contrast features corresponding to the two regions. The neighbourhood characteristic differenced nn is calculated as the average of the resulting twelve color space distances to the four nearest neighboring regions from above, below, left and right. The centroid distance d cd is the Euclidean distance between the coordinates of the regions centers. These inter-region distances from (5) are weighted by the following weight corresponding to the joint saliency of the image regions Q i and I j : ψ(s i,s j) = max ( 1 Si +Sj,0.1 2 where S i is the saliency of the query image region Q i and S j is the saliency of a candidate image region I j, where the region saliency is given by the ratio of salient pixels, calculated as described in the previous section. It can be observed that the distance D(Q i,i j) is smaller when the two regions Q i and I j are both salient. The resulting inter-region matrix D acts as the ground matrix for the EMD algorithm. EMD algorithm [14] is an optimization algorithm with constraints, representing the normalized cost of transforming the query image signature into the signature of the candidate retrieval image. The corresponding weights only add up to unity when all image regions are used. We are filtering out non-salient regions and consequently the weights will add up to a value less than one. Such signatures enable partial matching which is essential in image retrieval where there is a high likelihood of occlusion in the salient regions. 4. EXPERIMENTAL RESULTS We have applied the proposed query by saliency content retrieval (QSCR) methodology to various databases such as Corel 1000, SIVAL and Flickr. Corel 1000 is well known for its medium-to-high image complexity. This database consists of 10 semantic categories of natural scenes, each containing 100 images showing distinct objects. Flickr database consists of 20 categories with 100 highly diverse images in each, while another 2000 images do not have any specific concept. Images are ranked based on their similarity to the query, thus producing an ordered set of results. The rank-weighted average precision (WPR) is given by, [4]: WPR = 1 N N k=1 ) (6) n k k, (7) where N is the total number of retrieved images and n k is the number of matches in the first k retrieved images. Receiver Operating Characteristic (ROC) plots the true positive rate versus false positive rate (false alarm). For assessing the retrieval performance we consider the area under the ROC curve (AUC), which corresponds to the Wilcoxon-Mann-Whitney statistics [6]. Quantitative tests are performed by evaluating the average performance of the QSCR system across the whole of each database considering 300 queries for COREL 1000, 600 queries for Flickr. Fig. 2: Comparison of saliency maps. Original images are in the first row, Itti-Koch saliency maps are in the second row, GBVS maps are in the third row, SUN maps are in the fourth row, and FTS maps are in the fifth row. Saliency maps, pseudo-colored from red to blue depending on the visual attention intensity, are overlaid. In Fig. 2 we provide a comparison of saliency maps produced by four saliency algorithms: Itti-Koch (IK) [11], graph-based visual saliency (GBVS) [12], saliency using natural statistics (SUN) [17], and frequency-tuned saliency (FTS), [18]. From these results it can be seen that IK produces small highly focused peaks in saliency that tend to concentrate on small areas of the object which are insufficient for representing the semantic concept of the image. The large amount of false positives, bias, and lack of precision makes SUN an unsuitable choice for retrieval in the broad image domain, but perhaps it could prove itself useful in specialized applications. FTS algorithm works well when there is a salient color object in the image. GBVS produces the most useful maps for the purposes of image retrieval as it can be observed from Fig. 2. Fig. 3: Retrieving a translucent bowl image from SIVAL database. The query image is the first right-top image on each row followed by the retrieved images without and with modelling the visual attention. In Fig. 3 we present an example of retrieving the translucent bowl (TB) image in SIVAL database without visual attention models and with visual attention models. As it can be observed in this figure when using visual attention models, all first six retrieved images and eight out of the total of nine correspond to the TB category, while when not using the visual attention models only the seventh image is from the correct category but none of the other eight images. Salient edges are extracted and used in the final image ranking evaluation measure from (4). Unlike in [21], the method proposed in this paper decouples the edge histogram from its spatial domain 973

4 Fig. 4: Retrieval by salient edges on COREL 1000 database subset using AUC measure. µ indicates the average area under ROC curve. by considering the edge energy, corresponding to a specific image feature orientation, calculated from the entire image. In Fig. 4 we compare the proposed salient edge retrieval approach when using only the global image saliency as provided by edges and not the local saliency, with SEHD image retrieval method [21]. The mean AUC value for SEHD is while for the proposed method, the mean is Thus, performing a two-tailed Students t-test at the highly significant 1% level with 598 degrees of freedom yields ap-value of which shows that the difference is statistically significant. In Fig.?? we provide the results for segmentation, saliency map extraction, salient edges and the salient region selection for three images from three distinct image categories of COREL 1000 database. Fig. 6: Retrieval of 30 images from the architecture category from COREL database. The first line shows the original image, its saliency, selected salient regions and salient edge images while the subsequent lines displays the ordered retrieved images. The semantic gap is most evident in Flickr database, because its images and ground truths were obtained by performing keyword search. However, retrieval system features, such as edges, that perform well on the Corel database, have a reduced performance in the Flickr database. Fig. 5: Extracting query information from images. The image columns indicate from left to right: original image, segmented regions, the GBVS saliency map, salient edges and the salient regions. Images are ranked according to the similarity measure S(Q, I) from (4), between the query image Q and a candidate retrieval image I. In Fig. 6 we provide the first 30 images retrieved for a query image from the Architecture (ARC) category of Corel The selected region is a false positive in this case because the true object occupies most of the image and the most dissimilar area is a patch of sky in the middle. Nevertheless, the retrieval succeeds because the salient region selection method considers some of the surrounding areas as well. In Fig. 7a we provide the results for the average rank the proposed QSCR algorithm when compared with with SIMPLIcity from [4] on the entire COREL 1000 database, using the average rank or retrieval. QSCR unlike SIMPLIcity provides rather uniform results for all image categories. In Fig. 7b we compare the results of QSCR, with the two retrieval methods proposed in [6], on Flickr database when using AUC. The results of QSCR and ACCIO are broadly similar while outperforming the ACCIO segmentation with neighbors method from [6]. Moreover, ACCIO involves feedback from human intervention, while the proposed approach is completely automatic. The salient edge information provides better performance when the category has limited variation among its salient objects. (a) Fig. 7: Comparison results with: (a) SIMPLIcity on COREL database; (b) ACCIO on Flickr database. 5. CONCLUSION In this paper we present a novel image query by saliency content retrieval using visual attention models. The proposed method is bottom-up and unsupervised and we consider the saliency both locally and global for the entire image. After segmenting each image, we calculate the feature vectors for each region characterizing color, contrast, texture, the region centroid, and the contrast with respect to the neighbourhood. Those regions from the image which attract the human attention are defined as salient by using the graph-based visual saliency algorithm. The global image saliency is assessed using the statistics of salient edges. The final ranking is performed by means of the Earth Mover s Distance (EMD), between image regions, used together with a distance measure in the global saliency. Image query by saliency content retrieval has several applications including image database search, image classification based on content and image characterization. (b) 974

5 6. REFERENCES [1] A. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain, Content-based image retrieval at the end of the early years, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 12, pp , [2] R. Datta, D. Joshi, J. Li, and J. Z. Wan, Image retrieval: Ideas, influences, and trends of the new age, ACM Computing Surveys, vol. 40, no. 2, pp. 5:1 5:60, [3] J. Z. Wang, G. Wiederhold, O. Firschein, and X. W. Sha, content-based image indexing and searching using daubechies wavelets, International Journal on Digital Libraries, vol. 1, no. 4, pp , [4] J. Wang, J. Li, and G. Wiederhold, Simplicity: Semanticssensitive integrated matching for picture libraries, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 23, no. 9, pp , [5] C. Carson, S. Belongie, H. Greenspan, and J. Malik, Blobworld: Image segmentation using expectation-maximization and its application to image querying, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, no. 8, pp , [6] R. Rahmani, S. A. Goldman, H. Zhang, S. R. Cholleti, and J. E. Fritts, Localized content-based image retrieval, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 11, pp , [7] Y. Chen and Wang, Image categorization by learning and reasoning with images, J. of Machine Learning Research, pp , [8] Y. Rui, T. Huang, M. Ortega, and S. Mehrotra, Relevance feedback: A power tool in interactive content-based image retrieval, IEEE Trans. on Circuits and Systems for Video Technology, vol. 8, no. 5, pp , [9] J. Bi, Y. Chen, and J. Wang, A sparse support vector machine approach to region-based image categorization, in Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition, vol. 19, 2005, pp [10] R. Rahmani, S. A. Goldman, H. Zhang, S. R. Cholleti, and J. E. Fritts, Localized content-based image retrieval, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 30, no. 11, pp , [11] L. Itti, C. Koch, and E. Niebur, A model of saliency-based visual attention for rapid scene analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp , [12] J. Harel, C. Koch, and P. Perona, Graph-based visual saliency, in Proc. Advances in Neural Information Processing Systems (NIPS), vol. 19, 2007, pp [13] A. Papushoy and A. G. Bors, Image retrieval based on query by saliency content, Digital Signal Processing, vol. 36, pp , [14] Y. Rubner, C. Tomasi, and L. J. Guibas, The earth mover distance as a metric for image retrieval, Int. Journal of Computer Vision, vol. 40, no. 2, pp , [15] D. Comaniciu and P. Meer, Mean shift: a robust approach toward feature space analysis, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp , [16] L. Itti and S. Ullman, Shifts in selective visual attention: Towards the underlying neural circuitry, Human Neurobiology, vol. 4, no. 4, pp , [17] L. Zhang, M. H. Tong, T. K. Marks, H. Shan, and G. W. Cottrell, SUN: A Bayesian framework for saliency using natural statistics, Jour. of Vision, vol. 8, no. 7, pp , [18] R. Achanta, S. Hemami, F. Estrada, and S. Susstrunk, Frequency-tuned salient region detection, in Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition, 2009, pp [19] J. Canny, A computational approach to edge detection, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp , [20] G. Stamou and S. Kollias, Multimedia Content and the Semantic Web: Standards, Methods and Tools. Wiley & Sons, [21] S. Feng, D. Xu, and X. Yang, Attention-driven salient edge(s) and region(s) extraction with application to CBIR, Signal Processing, vol. 90, no. 1, pp. 1 15,

Saliency Detection for Videos Using 3D FFT Local Spectra

Saliency Detection for Videos Using 3D FFT Local Spectra Saliency Detection for Videos Using 3D FFT Local Spectra Zhiling Long and Ghassan AlRegib School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA ABSTRACT

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

IMAGE SALIENCY DETECTION VIA MULTI-SCALE STATISTICAL NON-REDUNDANCY MODELING. Christian Scharfenberger, Aanchal Jain, Alexander Wong, and Paul Fieguth

IMAGE SALIENCY DETECTION VIA MULTI-SCALE STATISTICAL NON-REDUNDANCY MODELING. Christian Scharfenberger, Aanchal Jain, Alexander Wong, and Paul Fieguth IMAGE SALIENCY DETECTION VIA MULTI-SCALE STATISTICAL NON-REDUNDANCY MODELING Christian Scharfenberger, Aanchal Jain, Alexander Wong, and Paul Fieguth Department of Systems Design Engineering, University

More information

Image Compression and Resizing Using Improved Seam Carving for Retinal Images

Image Compression and Resizing Using Improved Seam Carving for Retinal Images Image Compression and Resizing Using Improved Seam Carving for Retinal Images Prabhu Nayak 1, Rajendra Chincholi 2, Dr.Kalpana Vanjerkhede 3 1 PG Student, Department of Electronics and Instrumentation

More information

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009 Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer

More information

Small Object Segmentation Based on Visual Saliency in Natural Images

Small Object Segmentation Based on Visual Saliency in Natural Images J Inf Process Syst, Vol.9, No.4, pp.592-601, December 2013 http://dx.doi.org/10.3745/jips.2013.9.4.592 pissn 1976-913X eissn 2092-805X Small Object Segmentation Based on Visual Saliency in Natural Images

More information

Texture. Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image.

Texture. Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Texture Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Structural approach: a set of texels in some regular or repeated pattern

More information

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S Radha Krishna Rambola, Associate Professor, NMIMS University, India Akash Agrawal, Student at NMIMS University, India ABSTRACT Due to the

More information

Journal of Asian Scientific Research FEATURES COMPOSITION FOR PROFICIENT AND REAL TIME RETRIEVAL IN CBIR SYSTEM. Tohid Sedghi

Journal of Asian Scientific Research FEATURES COMPOSITION FOR PROFICIENT AND REAL TIME RETRIEVAL IN CBIR SYSTEM. Tohid Sedghi Journal of Asian Scientific Research, 013, 3(1):68-74 Journal of Asian Scientific Research journal homepage: http://aessweb.com/journal-detail.php?id=5003 FEATURES COMPOSTON FOR PROFCENT AND REAL TME RETREVAL

More information

Learning video saliency from human gaze using candidate selection

Learning video saliency from human gaze using candidate selection Learning video saliency from human gaze using candidate selection Rudoy, Goldman, Shechtman, Zelnik-Manor CVPR 2013 Paper presentation by Ashish Bora Outline What is saliency? Image vs video Candidates

More information

Detecting Salient Contours Using Orientation Energy Distribution. Part I: Thresholding Based on. Response Distribution

Detecting Salient Contours Using Orientation Energy Distribution. Part I: Thresholding Based on. Response Distribution Detecting Salient Contours Using Orientation Energy Distribution The Problem: How Does the Visual System Detect Salient Contours? CPSC 636 Slide12, Spring 212 Yoonsuck Choe Co-work with S. Sarma and H.-C.

More information

DETECTION OF IMAGE PAIRS USING CO-SALIENCY MODEL

DETECTION OF IMAGE PAIRS USING CO-SALIENCY MODEL DETECTION OF IMAGE PAIRS USING CO-SALIENCY MODEL N S Sandhya Rani 1, Dr. S. Bhargavi 2 4th sem MTech, Signal Processing, S. J. C. Institute of Technology, Chickballapur, Karnataka, India 1 Professor, Dept

More information

Query-Sensitive Similarity Measure for Content-Based Image Retrieval

Query-Sensitive Similarity Measure for Content-Based Image Retrieval Query-Sensitive Similarity Measure for Content-Based Image Retrieval Zhi-Hua Zhou Hong-Bin Dai National Laboratory for Novel Software Technology Nanjing University, Nanjing 2193, China {zhouzh, daihb}@lamda.nju.edu.cn

More information

Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition

Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition Sikha O K 1, Sachin Kumar S 2, K P Soman 2 1 Department of Computer Science 2 Centre for Computational Engineering and

More information

Robust Frequency-tuned Salient Region Detection

Robust Frequency-tuned Salient Region Detection Robust Frequency-tuned Salient Region Detection 1 Yong Zhang, 2 Yihua Lan, 3 Haozheng Ren, 4 Ming Li 1 School of Computer Engineering, Huaihai Institute of Technology, Lianyungang, China, zhyhglyg@126.com

More information

Color Image Segmentation

Color Image Segmentation Color Image Segmentation Yining Deng, B. S. Manjunath and Hyundoo Shin* Department of Electrical and Computer Engineering University of California, Santa Barbara, CA 93106-9560 *Samsung Electronics Inc.

More information

Texture Segmentation by Windowed Projection

Texture Segmentation by Windowed Projection Texture Segmentation by Windowed Projection 1, 2 Fan-Chen Tseng, 2 Ching-Chi Hsu, 2 Chiou-Shann Fuh 1 Department of Electronic Engineering National I-Lan Institute of Technology e-mail : fctseng@ccmail.ilantech.edu.tw

More information

2.1 Optimized Importance Map

2.1 Optimized Importance Map 3rd International Conference on Multimedia Technology(ICMT 2013) Improved Image Resizing using Seam Carving and scaling Yan Zhang 1, Jonathan Z. Sun, Jingliang Peng Abstract. Seam Carving, the popular

More information

Saliency based Person Re-Identification in Video using Colour Features

Saliency based Person Re-Identification in Video using Colour Features GRD Journals- Global Research and Development Journal for Engineering Volume 1 Issue 10 September 2016 ISSN: 2455-5703 Saliency based Person Re-Identification in Video using Colour Features Srujy Krishna

More information

An Introduction to Content Based Image Retrieval

An Introduction to Content Based Image Retrieval CHAPTER -1 An Introduction to Content Based Image Retrieval 1.1 Introduction With the advancement in internet and multimedia technologies, a huge amount of multimedia data in the form of audio, video and

More information

ADAPTIVE TEXTURE IMAGE RETRIEVAL IN TRANSFORM DOMAIN

ADAPTIVE TEXTURE IMAGE RETRIEVAL IN TRANSFORM DOMAIN THE SEVENTH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV 2002), DEC. 2-5, 2002, SINGAPORE. ADAPTIVE TEXTURE IMAGE RETRIEVAL IN TRANSFORM DOMAIN Bin Zhang, Catalin I Tomai,

More information

Quasi-thematic Features Detection & Tracking. Future Rover Long-Distance Autonomous Navigation

Quasi-thematic Features Detection & Tracking. Future Rover Long-Distance Autonomous Navigation Quasi-thematic Feature Detection And Tracking For Future Rover Long-Distance Autonomous Navigation Authors: Affan Shaukat, Conrad Spiteri, Yang Gao, Said Al-Milli, and Abhinav Bajpai Surrey Space Centre,

More information

IJREAT International Journal of Research in Engineering & Advanced Technology, Volume 1, Issue 5, Oct-Nov, 2013 ISSN:

IJREAT International Journal of Research in Engineering & Advanced Technology, Volume 1, Issue 5, Oct-Nov, 2013 ISSN: Semi Automatic Annotation Exploitation Similarity of Pics in i Personal Photo Albums P. Subashree Kasi Thangam 1 and R. Rosy Angel 2 1 Assistant Professor, Department of Computer Science Engineering College,

More information

Salient Region Detection using Weighted Feature Maps based on the Human Visual Attention Model

Salient Region Detection using Weighted Feature Maps based on the Human Visual Attention Model Salient Region Detection using Weighted Feature Maps based on the Human Visual Attention Model Yiqun Hu 2, Xing Xie 1, Wei-Ying Ma 1, Liang-Tien Chia 2 and Deepu Rajan 2 1 Microsoft Research Asia 5/F Sigma

More information

Contour-Based Large Scale Image Retrieval

Contour-Based Large Scale Image Retrieval Contour-Based Large Scale Image Retrieval Rong Zhou, and Liqing Zhang MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Department of Computer Science and Engineering, Shanghai

More information

International Journal of Mechatronics, Electrical and Computer Technology

International Journal of Mechatronics, Electrical and Computer Technology An Efficient Importance Map for Content Aware Image Resizing Abstract Ahmad Absetan 1* and Mahdi Nooshyar 2 1 Faculty of Engineering, University of MohagheghArdabili, Ardabil, Iran 2 Faculty of Engineering,

More information

A New Feature Local Binary Patterns (FLBP) Method

A New Feature Local Binary Patterns (FLBP) Method A New Feature Local Binary Patterns (FLBP) Method Jiayu Gu and Chengjun Liu The Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102, USA Abstract - This paper presents

More information

Video saliency detection by spatio-temporal sampling and sparse matrix decomposition

Video saliency detection by spatio-temporal sampling and sparse matrix decomposition Video saliency detection by spatio-temporal sampling and sparse matrix decomposition * Faculty of Information Science and Engineering Ningbo University Ningbo 315211 CHINA shaofeng@nbu.edu.cn Abstract:

More information

ImgSeek: Capturing User s Intent For Internet Image Search

ImgSeek: Capturing User s Intent For Internet Image Search ImgSeek: Capturing User s Intent For Internet Image Search Abstract - Internet image search engines (e.g. Bing Image Search) frequently lean on adjacent text features. It is difficult for them to illustrate

More information

Dynamic visual attention: competitive versus motion priority scheme

Dynamic visual attention: competitive versus motion priority scheme Dynamic visual attention: competitive versus motion priority scheme Bur A. 1, Wurtz P. 2, Müri R.M. 2 and Hügli H. 1 1 Institute of Microtechnology, University of Neuchâtel, Neuchâtel, Switzerland 2 Perception

More information

Wavelet Based Image Retrieval Method

Wavelet Based Image Retrieval Method Wavelet Based Image Retrieval Method Kohei Arai Graduate School of Science and Engineering Saga University Saga City, Japan Cahya Rahmad Electronic Engineering Department The State Polytechnics of Malang,

More information

The Vehicle Logo Location System based on saliency model

The Vehicle Logo Location System based on saliency model ISSN 746-7659, England, UK Journal of Information and Computing Science Vol. 0, No. 3, 205, pp. 73-77 The Vehicle Logo Location System based on saliency model Shangbing Gao,2, Liangliang Wang, Hongyang

More information

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Abstract Automatic linguistic indexing of pictures is an important but highly challenging problem for researchers in content-based

More information

Selection of Scale-Invariant Parts for Object Class Recognition

Selection of Scale-Invariant Parts for Object Class Recognition Selection of Scale-Invariant Parts for Object Class Recognition Gy. Dorkó and C. Schmid INRIA Rhône-Alpes, GRAVIR-CNRS 655, av. de l Europe, 3833 Montbonnot, France fdorko,schmidg@inrialpes.fr Abstract

More information

Evaluation of regions-of-interest based attention algorithms using a probabilistic measure

Evaluation of regions-of-interest based attention algorithms using a probabilistic measure Evaluation of regions-of-interest based attention algorithms using a probabilistic measure Martin Clauss, Pierre Bayerl and Heiko Neumann University of Ulm, Dept. of Neural Information Processing, 89081

More information

Supplementary Material for submission 2147: Traditional Saliency Reloaded: A Good Old Model in New Shape

Supplementary Material for submission 2147: Traditional Saliency Reloaded: A Good Old Model in New Shape Supplementary Material for submission 247: Traditional Saliency Reloaded: A Good Old Model in New Shape Simone Frintrop, Thomas Werner, and Germán M. García Institute of Computer Science III Rheinische

More information

Supplementary Materials for Salient Object Detection: A

Supplementary Materials for Salient Object Detection: A Supplementary Materials for Salient Object Detection: A Discriminative Regional Feature Integration Approach Huaizu Jiang, Zejian Yuan, Ming-Ming Cheng, Yihong Gong Nanning Zheng, and Jingdong Wang 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

SkyFinder: Attribute-based Sky Image Search

SkyFinder: Attribute-based Sky Image Search SkyFinder: Attribute-based Sky Image Search SIGGRAPH 2009 Litian Tao, Lu Yuan, Jian Sun Kim, Wook 2016. 1. 12 Abstract Interactive search system of over a half million sky images Automatically extracted

More information

CAP 5415 Computer Vision Fall 2012

CAP 5415 Computer Vision Fall 2012 CAP 5415 Computer Vision Fall 01 Dr. Mubarak Shah Univ. of Central Florida Office 47-F HEC Lecture-5 SIFT: David Lowe, UBC SIFT - Key Point Extraction Stands for scale invariant feature transform Patented

More information

A Semi-Automatic 2D-to-3D Video Conversion with Adaptive Key-Frame Selection

A Semi-Automatic 2D-to-3D Video Conversion with Adaptive Key-Frame Selection A Semi-Automatic 2D-to-3D Video Conversion with Adaptive Key-Frame Selection Kuanyu Ju and Hongkai Xiong Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China ABSTRACT To

More information

A Novel Approach for Saliency Detection based on Multiscale Phase Spectrum

A Novel Approach for Saliency Detection based on Multiscale Phase Spectrum A Novel Approach for Saliency Detection based on Multiscale Phase Spectrum Deepak Singh Department of Electronics & Communication National Institute of Technology Rourkela 769008, Odisha, India Email:

More information

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images Karthik Ram K.V & Mahantesh K Department of Electronics and Communication Engineering, SJB Institute of Technology, Bangalore,

More information

Salient Region Detection and Segmentation

Salient Region Detection and Segmentation Salient Region Detection and Segmentation Radhakrishna Achanta, Francisco Estrada, Patricia Wils, and Sabine Süsstrunk School of Computer and Communication Sciences (I&C), Ecole Polytechnique Fédérale

More information

Fast and Robust Earth Mover s Distances

Fast and Robust Earth Mover s Distances Fast and Robust Earth Mover s Distances Ofir Pele and Michael Werman School of Computer Science and Engineering The Hebrew University of Jerusalem {ofirpele,werman}@cs.huji.ac.il Abstract We present a

More information

CONTENT BASED IMAGE RETRIEVAL SYSTEM USING IMAGE CLASSIFICATION

CONTENT BASED IMAGE RETRIEVAL SYSTEM USING IMAGE CLASSIFICATION International Journal of Research and Reviews in Applied Sciences And Engineering (IJRRASE) Vol 8. No.1 2016 Pp.58-62 gopalax Journals, Singapore available at : www.ijcns.com ISSN: 2231-0061 CONTENT BASED

More information

Saliency Detection using Region-Based Incremental Center-Surround Distance

Saliency Detection using Region-Based Incremental Center-Surround Distance Saliency Detection using Region-Based Incremental Center-Surround Distance Minwoo Park Corporate Research and Engineering Eastman Kodak Company Rochester, NY, USA minwoo.park@kodak.com Mrityunjay Kumar

More information

Image Querying. Ilaria Bartolini DEIS - University of Bologna, Italy

Image Querying. Ilaria Bartolini DEIS - University of Bologna, Italy Image Querying Ilaria Bartolini DEIS - University of Bologna, Italy i.bartolini@unibo.it http://www-db.deis.unibo.it/~ibartolini SYNONYMS Image query processing DEFINITION Image querying refers to the

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

Normalized Texture Motifs and Their Application to Statistical Object Modeling

Normalized Texture Motifs and Their Application to Statistical Object Modeling Normalized Texture Motifs and Their Application to Statistical Obect Modeling S. D. Newsam B. S. Manunath Center for Applied Scientific Computing Electrical and Computer Engineering Lawrence Livermore

More information

Design & Implementation of Saliency Detection Model in H.264 Standard

Design & Implementation of Saliency Detection Model in H.264 Standard Design & Implementation of Saliency Detection Model in H.264 Standard Sheeba Shabnam 1, H.N. Latha 2 Student, Department of Electronics & Communication, BMS College of Engineering, Bangalore, India Assistant

More information

Consistent Line Clusters for Building Recognition in CBIR

Consistent Line Clusters for Building Recognition in CBIR Consistent Line Clusters for Building Recognition in CBIR Yi Li and Linda G. Shapiro Department of Computer Science and Engineering University of Washington Seattle, WA 98195-250 shapiro,yi @cs.washington.edu

More information

Moving Object Segmentation Method Based on Motion Information Classification by X-means and Spatial Region Segmentation

Moving Object Segmentation Method Based on Motion Information Classification by X-means and Spatial Region Segmentation IJCSNS International Journal of Computer Science and Network Security, VOL.13 No.11, November 2013 1 Moving Object Segmentation Method Based on Motion Information Classification by X-means and Spatial

More information

An Improved CBIR Method Using Color and Texture Properties with Relevance Feedback

An Improved CBIR Method Using Color and Texture Properties with Relevance Feedback An Improved CBIR Method Using Color and Texture Properties with Relevance Feedback MS. R. Janani 1, Sebhakumar.P 2 Assistant Professor, Department of CSE, Park College of Engineering and Technology, Coimbatore-

More information

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,

More information

Robust Shape Retrieval Using Maximum Likelihood Theory

Robust Shape Retrieval Using Maximum Likelihood Theory Robust Shape Retrieval Using Maximum Likelihood Theory Naif Alajlan 1, Paul Fieguth 2, and Mohamed Kamel 1 1 PAMI Lab, E & CE Dept., UW, Waterloo, ON, N2L 3G1, Canada. naif, mkamel@pami.uwaterloo.ca 2

More information

International Conference on Information Sciences, Machinery, Materials and Energy (ICISMME 2015)

International Conference on Information Sciences, Machinery, Materials and Energy (ICISMME 2015) International Conference on Information Sciences, Machinery, Materials and Energy (ICISMME 2015) Brief Analysis on Typical Image Saliency Detection Methods Wenwen Pan, Xiaofei Sun, Xia Wang, Wei Zhang

More information

Short Survey on Static Hand Gesture Recognition

Short Survey on Static Hand Gesture Recognition Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of

More information

An efficient face recognition algorithm based on multi-kernel regularization learning

An efficient face recognition algorithm based on multi-kernel regularization learning Acta Technica 61, No. 4A/2016, 75 84 c 2017 Institute of Thermomechanics CAS, v.v.i. An efficient face recognition algorithm based on multi-kernel regularization learning Bi Rongrong 1 Abstract. A novel

More information

A Feature Level Fusion in Similarity Matching to Content-Based Image Retrieval

A Feature Level Fusion in Similarity Matching to Content-Based Image Retrieval A Feature Level Fusion in Similarity Matching to Content-Based Image Retrieval Md. Mahmudur Rahman, Bipin C. Desai Computer Science Department Concordia University Montreal, QC, CANADA mah rahm@cs.concordia.ca

More information

PERFORMANCE ANALYSIS OF COMPUTING TECHNIQUES FOR IMAGE DISPARITY IN STEREO IMAGE

PERFORMANCE ANALYSIS OF COMPUTING TECHNIQUES FOR IMAGE DISPARITY IN STEREO IMAGE PERFORMANCE ANALYSIS OF COMPUTING TECHNIQUES FOR IMAGE DISPARITY IN STEREO IMAGE Rakesh Y. Department of Electronics and Communication Engineering, SRKIT, Vijayawada, India E-Mail: rakesh.yemineni@gmail.com

More information

Beyond Mere Pixels: How Can Computers Interpret and Compare Digital Images? Nicholas R. Howe Cornell University

Beyond Mere Pixels: How Can Computers Interpret and Compare Digital Images? Nicholas R. Howe Cornell University Beyond Mere Pixels: How Can Computers Interpret and Compare Digital Images? Nicholas R. Howe Cornell University Why Image Retrieval? World Wide Web: Millions of hosts Billions of images Growth of video

More information

Video shot segmentation using late fusion technique

Video shot segmentation using late fusion technique Video shot segmentation using late fusion technique by C. Krishna Mohan, N. Dhananjaya, B.Yegnanarayana in Proc. Seventh International Conference on Machine Learning and Applications, 2008, San Diego,

More information

Image Classification based on Saliency Driven Nonlinear Diffusion and Multi-scale Information Fusion Ms. Swapna R. Kharche 1, Prof.B.K.

Image Classification based on Saliency Driven Nonlinear Diffusion and Multi-scale Information Fusion Ms. Swapna R. Kharche 1, Prof.B.K. Image Classification based on Saliency Driven Nonlinear Diffusion and Multi-scale Information Fusion Ms. Swapna R. Kharche 1, Prof.B.K.Chaudhari 2 1M.E. student, Department of Computer Engg, VBKCOE, Malkapur

More information

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY A PATH FOR HORIZING YOUR INNOVATIVE WORK REVIEW ON CONTENT BASED IMAGE RETRIEVAL BY USING VISUAL SEARCH RANKING MS. PRAGATI

More information

DYNAMIC BACKGROUND SUBTRACTION BASED ON SPATIAL EXTENDED CENTER-SYMMETRIC LOCAL BINARY PATTERN. Gengjian Xue, Jun Sun, Li Song

DYNAMIC BACKGROUND SUBTRACTION BASED ON SPATIAL EXTENDED CENTER-SYMMETRIC LOCAL BINARY PATTERN. Gengjian Xue, Jun Sun, Li Song DYNAMIC BACKGROUND SUBTRACTION BASED ON SPATIAL EXTENDED CENTER-SYMMETRIC LOCAL BINARY PATTERN Gengjian Xue, Jun Sun, Li Song Institute of Image Communication and Information Processing, Shanghai Jiao

More information

FRACTAL DIMENSION BASED TECHNIQUE FOR DATABASE IMAGE RETRIEVAL

FRACTAL DIMENSION BASED TECHNIQUE FOR DATABASE IMAGE RETRIEVAL FRACTAL DIMENSION BASED TECHNIQUE FOR DATABASE IMAGE RETRIEVAL Radu DOBRESCU*, Florin IONESCU** *POLITEHNICA University, Bucharest, Romania, radud@aii.pub.ro **Technische Hochschule Konstanz, fionescu@fh-konstanz.de

More information

Automatic Texture Segmentation for Texture-based Image Retrieval

Automatic Texture Segmentation for Texture-based Image Retrieval Automatic Texture Segmentation for Texture-based Image Retrieval Ying Liu, Xiaofang Zhou School of ITEE, The University of Queensland, Queensland, 4072, Australia liuy@itee.uq.edu.au, zxf@itee.uq.edu.au

More information

Supplementary Figure 1. Decoding results broken down for different ROIs

Supplementary Figure 1. Decoding results broken down for different ROIs Supplementary Figure 1 Decoding results broken down for different ROIs Decoding results for areas V1, V2, V3, and V1 V3 combined. (a) Decoded and presented orientations are strongly correlated in areas

More information

An Improved Image Resizing Approach with Protection of Main Objects

An Improved Image Resizing Approach with Protection of Main Objects An Improved Image Resizing Approach with Protection of Main Objects Chin-Chen Chang National United University, Miaoli 360, Taiwan. *Corresponding Author: Chun-Ju Chen National United University, Miaoli

More information

Content Based Image Retrieval Using Curvelet Transform

Content Based Image Retrieval Using Curvelet Transform Content Based Image Retrieval Using Curvelet Transform Ishrat Jahan Sumana, Md. Monirul Islam, Dengsheng Zhang and Guojun Lu Gippsland School of Information Technology, Monash University Churchill, Victoria

More information

Open Access Self-Growing RBF Neural Network Approach for Semantic Image Retrieval

Open Access Self-Growing RBF Neural Network Approach for Semantic Image Retrieval Send Orders for Reprints to reprints@benthamscience.ae The Open Automation and Control Systems Journal, 2014, 6, 1505-1509 1505 Open Access Self-Growing RBF Neural Networ Approach for Semantic Image Retrieval

More information

Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang

Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang NICTA & CSE UNSW COMP9314 Advanced Database S1 2007 jzhang@cse.unsw.edu.au Reference Papers and Resources Papers: Colour spaces-perceptual, historical

More information

Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features

Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features 1 Kum Sharanamma, 2 Krishnapriya Sharma 1,2 SIR MVIT Abstract- To describe the image features the Local binary pattern (LBP)

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

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200,

More information

Unsupervised Saliency Estimation based on Robust Hypotheses

Unsupervised Saliency Estimation based on Robust Hypotheses Utah State University DigitalCommons@USU Computer Science Faculty and Staff Publications Computer Science 3-2016 Unsupervised Saliency Estimation based on Robust Hypotheses Fei Xu Utah State University,

More information

Using the Kolmogorov-Smirnov Test for Image Segmentation

Using the Kolmogorov-Smirnov Test for Image Segmentation Using the Kolmogorov-Smirnov Test for Image Segmentation Yong Jae Lee CS395T Computational Statistics Final Project Report May 6th, 2009 I. INTRODUCTION Image segmentation is a fundamental task in computer

More information

Robot localization method based on visual features and their geometric relationship

Robot localization method based on visual features and their geometric relationship , pp.46-50 http://dx.doi.org/10.14257/astl.2015.85.11 Robot localization method based on visual features and their geometric relationship Sangyun Lee 1, Changkyung Eem 2, and Hyunki Hong 3 1 Department

More information

Textural Features for Image Database Retrieval

Textural Features for Image Database Retrieval Textural Features for Image Database Retrieval Selim Aksoy and Robert M. Haralick Intelligent Systems Laboratory Department of Electrical Engineering University of Washington Seattle, WA 98195-2500 {aksoy,haralick}@@isl.ee.washington.edu

More information

Color-Texture Segmentation of Medical Images Based on Local Contrast Information

Color-Texture Segmentation of Medical Images Based on Local Contrast Information Color-Texture Segmentation of Medical Images Based on Local Contrast Information Yu-Chou Chang Department of ECEn, Brigham Young University, Provo, Utah, 84602 USA ycchang@et.byu.edu Dah-Jye Lee Department

More information

A Miniature-Based Image Retrieval System

A Miniature-Based Image Retrieval System A Miniature-Based Image Retrieval System Md. Saiful Islam 1 and Md. Haider Ali 2 Institute of Information Technology 1, Dept. of Computer Science and Engineering 2, University of Dhaka 1, 2, Dhaka-1000,

More information

Content Based Image Retrieval Using Combined Color & Texture Features

Content Based Image Retrieval Using Combined Color & Texture Features IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE) e-issn: 2278-1676,p-ISSN: 2320-3331, Volume 11, Issue 6 Ver. III (Nov. Dec. 2016), PP 01-05 www.iosrjournals.org Content Based Image Retrieval

More information

Image Enhancement Techniques for Fingerprint Identification

Image Enhancement Techniques for Fingerprint Identification March 2013 1 Image Enhancement Techniques for Fingerprint Identification Pankaj Deshmukh, Siraj Pathan, Riyaz Pathan Abstract The aim of this paper is to propose a new method in fingerprint enhancement

More information

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality

More information

A New Framework for Multiscale Saliency Detection Based on Image Patches

A New Framework for Multiscale Saliency Detection Based on Image Patches Neural Process Lett (2013) 38:361 374 DOI 10.1007/s11063-012-9276-3 A New Framework for Multiscale Saliency Detection Based on Image Patches Jingbo Zhou Zhong Jin Published online: 8 January 2013 Springer

More information

A Model of Dynamic Visual Attention for Object Tracking in Natural Image Sequences

A Model of Dynamic Visual Attention for Object Tracking in Natural Image Sequences Published in Computational Methods in Neural Modeling. (In: Lecture Notes in Computer Science) 2686, vol. 1, 702-709, 2003 which should be used for any reference to this work 1 A Model of Dynamic Visual

More information

Content Based Image Retrieval (CBIR) Using Segmentation Process

Content Based Image Retrieval (CBIR) Using Segmentation Process Content Based Image Retrieval (CBIR) Using Segmentation Process R.Gnanaraja 1, B. Jagadishkumar 2, S.T. Premkumar 3, B. Sunil kumar 4 1, 2, 3, 4 PG Scholar, Department of Computer Science and Engineering,

More information

Localized Content Based Image Retrieval

Localized Content Based Image Retrieval Localized Content Based Image Retrieval Rouhollah Rahmani Department of CSE Washington University St Louis, MO 63130 rahmani@wustl.edu Sally Goldman Department of CSE Washington University St Louis, MO

More information

Content-Based Image Retrieval Some Basics

Content-Based Image Retrieval Some Basics Content-Based Image Retrieval Some Basics Gerald Schaefer Department of Computer Science Loughborough University Loughborough, U.K. gerald.schaefer@ieee.org Abstract. Image collections are growing at a

More information

Main Subject Detection via Adaptive Feature Selection

Main Subject Detection via Adaptive Feature Selection Main Subject Detection via Adaptive Feature Selection Cuong Vu and Damon Chandler Image Coding and Analysis Lab Oklahoma State University Main Subject Detection is easy for human 2 Outline Introduction

More information

Research Article Image Retrieval using Clustering Techniques. K.S.Rangasamy College of Technology,,India. K.S.Rangasamy College of Technology, India.

Research Article Image Retrieval using Clustering Techniques. K.S.Rangasamy College of Technology,,India. K.S.Rangasamy College of Technology, India. Journal of Recent Research in Engineering and Technology 3(1), 2016, pp21-28 Article ID J11603 ISSN (Online): 2349 2252, ISSN (Print):2349 2260 Bonfay Publications, 2016 Research Article Image Retrieval

More information

Fast and Efficient Saliency Detection Using Sparse Sampling and Kernel Density Estimation

Fast and Efficient Saliency Detection Using Sparse Sampling and Kernel Density Estimation Fast and Efficient Saliency Detection Using Sparse Sampling and Kernel Density Estimation Hamed Rezazadegan Tavakoli, Esa Rahtu, and Janne Heikkilä Machine Vision Group, Department of Electrical and Information

More information

Schedule for Rest of Semester

Schedule for Rest of Semester Schedule for Rest of Semester Date Lecture Topic 11/20 24 Texture 11/27 25 Review of Statistics & Linear Algebra, Eigenvectors 11/29 26 Eigenvector expansions, Pattern Recognition 12/4 27 Cameras & calibration

More information

Relevance Feedback for Content-Based Image Retrieval Using Support Vector Machines and Feature Selection

Relevance Feedback for Content-Based Image Retrieval Using Support Vector Machines and Feature Selection Relevance Feedback for Content-Based Image Retrieval Using Support Vector Machines and Feature Selection Apostolos Marakakis 1, Nikolaos Galatsanos 2, Aristidis Likas 3, and Andreas Stafylopatis 1 1 School

More information

Still Image Objective Segmentation Evaluation using Ground Truth

Still Image Objective Segmentation Evaluation using Ground Truth 5th COST 276 Workshop (2003), pp. 9 14 B. Kovář, J. Přikryl, and M. Vlček (Editors) Still Image Objective Segmentation Evaluation using Ground Truth V. Mezaris, 1,2 I. Kompatsiaris 2 andm.g.strintzis 1,2

More information

The Use of Attention and Spatial Information for Rapid Facial Recognition in Video

The Use of Attention and Spatial Information for Rapid Facial Recognition in Video * Manuscript The Use of Attention and Spatial Information for Rapid Facial Recognition in Video J. Bonaiuto & L. Itti Neuroscience Department University of Southern California Los Angeles, CA, 90089 Abstract

More information

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Outline Objective Approach Experiment Conclusion and Future work Objective Automatically establish linguistic indexing of pictures

More information

A Robust Wipe Detection Algorithm

A Robust Wipe Detection Algorithm A Robust Wipe Detection Algorithm C. W. Ngo, T. C. Pong & R. T. Chin Department of Computer Science The Hong Kong University of Science & Technology Clear Water Bay, Kowloon, Hong Kong Email: fcwngo, tcpong,

More information

Computer Vision I - Filtering and Feature detection

Computer Vision I - Filtering and Feature detection Computer Vision I - Filtering and Feature detection Carsten Rother 30/10/2015 Computer Vision I: Basics of Image Processing Roadmap: Basics of Digital Image Processing Computer Vision I: Basics of Image

More information