A Survey on Detecting Image Visual Saliency

Size: px
Start display at page:

Download "A Survey on Detecting Image Visual Saliency"

Transcription

1 1/29 A Survey on Detecting Image Visual Saliency Hsin-Ho Yeh Institute of Information Science, Acamedic Sinica, Taiwan {hhyeh}@iis.sinica.edu.tw 2010/12/09

2 2/29 Outline 1 Conclusions

3 3/29 What is visual saliency? Saliency: some regions in an image, and these regions motivate most of the visual attention when people see it at a first glance. (a) (b)

4 4/29 Outline 1 Conclusions

5 1 Depending on the salient region detector, saliency maps have ill-defined object boundary. For example, the range of spatial frequencies in the original image are reduced when it has downsized severely. On the other hand, some methods highlight the salient object boundaries, but they fail to map the entire salient region uniformly. These shortcomings result from the limited range of spatial frequencies retained from the original image in computing the final saliency map. 1 Radhakrishna Achanta et al.. In: CVPR /29

6 The author examines 5 state-of-the-art methods from a frequency domain perspective: IT 2, MZ 3, GB 4, SP 5, and AC 6. 2 Laurent Itti, Christof Koch, and Ernst Niebur. A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. In: IEEE Trans. Pattern Anal. Mach. Intell (1998). 3 Yu-Fei Ma and Hong-Jiang Zhang. Contrast-based image attention analysis by using fuzzy growing. In: ACM Multimedia Jonathan Harel, Christof Koch, and Pietro Perona. Graph-based visual saliency. In: NIPS Xiaodi Hou and Liqing Zhang. Saliency detection: A spectral residual approach. In: CVPR Radhakrishna Achanta et al. Salient region detection and segmentation. In: Tsotsos (Eds.), Computer Vision Systems (2008). 6/29

7 Figure 3. Visual comparison of saliency maps. (a) original image, (b) saliency maps using the method presented by, Itti [16], (c) Ma and 7/29 Spatial Frequency Observation Method Frequency range Resolution Complexity IT [π/256, π/16] S/256 (k IT N) MZ [0, π/10] S/100 (k MZ N) GB [π/128, π/8] S/64 (k GB N 4 K ) SR [0, π/5] (k SR N) AC (0, π] S (k AC N) IG (0, π/2.75] S (k IG N) (a) Original (b) IT [16] (c) MZ [22] (d) GB [10] (e) SR [12] (f) AC [1] (g) IG

8 8/29 Requirement for A Saliency Map Emphasize the largest salient object. Uniformly highlight whole salient regions. Establish well-defined boundaries of salient objects. Disregard high frequency arising from texture, noise, and blocking artifacts. Efficiency output full resolution saliency map.

9 A Band-pass Filter DoG(x, y, σ 1, σ 2 ) = 1 2π [ 1 σ 2 1 exp x 2 +y 2 2σ σ2 2 = G(x, y, σ 1 ) G(x, y, σ 2 ), exp x 2 +y 2 2σ 2 2 ] where σ 1 and σ 2 are the standard deviation (σ 1 > σ 2 ). By combining several narrow band-pass DoG filters ( σ 1 = ρσ and σ 2 = σ). A summation over DoG results in: N 1 n=0 G(x, y, ρ n+1 σ) G(x, y, ρ n σ) = G(x, y, σρ N ) G(x, y, σ), where ρ = 1.6. ω lc = σ 1 = inf and ω hc = σ 2 = π/2.75 for removing high frequency noise and textures and retaining more than twice high-frequency content than SR. 9/29

10 10/29 A Band-pass Filter S(x, y) = I u (x, y) I whc (x, y) l2, where I u is the mean image, I whc is the corresponding image in the gaussian blurred version by 5 5 separable binomial kernel, that is [1, 4, 6, 4, 1]. 1 16

11 Experimental Results Data: Refine the MSRA image saliency dataset 7 into 1,000 images in a precise way. prec = ST GT, rec = ST ST GT, GT where ST and ST stand for the thresholded foreground and background regions of the detected saliency, GT and GT are the foreground and background saliency maps. regions in ground truth, and. indicates the number of pixels in the region. Figure 4. Ground truth examples. Left to Right, original image, ground truth rectangles from [28], and our ground truth, which is both more accurate and treats multiple objects separately. a fixed threshold to binarize the saliency maps. In the second experiment, we perform image-adaptive binarization of In order to obtain an objective comparison of segmentation results, we use a ground truth image database. We derived the database from the publicly available database used by Liu et al. [20]. This database provides bounding boxes drawn around salient regions by nine users. However, a bounding box-based ground truth is far from accurate, as also stated by Wang and Li [28]. Thus, we created an accurate object-contour based ground truth database 2 of 1000 images (examples in Fig. 4). Figure 5. Precision-recall curve for naïve thresholding of saliency maps. Our method IG is compared against the five methods of IT [16], MZ [22], GB [10], SR [12], and AC [1] on 1000 images. methods than simple thresholding. Saliency maps produced by Itti s approach have been used in unsupervised object segmentation. Han et al. [9] use a Markov random field to 7 T. Liu et al. Learning to Detect A Salient Object. In: TPAMI (2010). 11/29

12 12/29 Outline 1 Conclusions

13 8 W. Wang et al. Measuring visual saliency by Site Entropy Rate. In: CVPR /29 8 Intuition Beginning from the information maximization principle via running a random walks on the fully-connected graph to simulate the information transmission among the interconnected neurous.

14 14/29 Framework in Steps 1. Filter the input image with a number of sparse coding bases because sparse coding as an efficient coding strategy for optimal information transmission. 2. Adopt a fully-connected graph representation to capture the long range relation between two sites in an image. 3. Adopt random walker on each sub-band graph to model the information transmission among the neurons, and propose site-entropy rate (SER) which describes the accumulative effects of all the interactions between neurons. 4. Sum all the sub-band SER into the final saliency map. 5. (Option) In video, the novel signal and the change of the signal at a site make the site salient.(accounting the temporal change of neuron response.)

15 neuron connectivity we adopt a fully-connected graph representation for the feature maps. The full connectedness is able to capture the long range relation between two sites in an image. (3) A random walk is adopted on each sub-band feature responses from the corresponding sub-band feature map of the previous frames. Then we still run random walks on the fully-connected graphs of the updated feature maps to obtain the SER maps and finally the saliency map.15/29 Framework in Figure Figure 1. The proposed framework. An input image is filtered by sparse coding basis functions to obtain the corresponding sub-band feature maps. A fully-connected graph is constructed for each feature map, and a random walk is run on each graph to compute a SER map of each channel. Finally, the saliency map is generated by summing over all the SER maps.

16 where G k is the inverse/pseudoinverse of B k. In this paper, ICA 9 is adopted for learning bases. The filter response of G k form the k th sub-band feature map F k. 9 J. H. Van Hateren and A. Van Der Schaaf. Independent component filters of natural images compared with simple cells in primary visual cortex. In: R. Soc. Lond. B /29 The Sparse Coding Bases An image I is a linear superposition of a number of image bases B k, where k indexes for the location, orientation and scale. I = k a k B k, where p(a k ) e α a k is the high-order statistics prior to enforce the sparsity. The coefficient is computed by its corresponding filter function G k a k = x,y G k (x, y)i(x, y),

17 Sub-band Graph Representation A full-connected graph G k = {V k, E k } for feature map F k, where V k = {v k1,..., v kn }, v ki = (x i, y i, f k (x i, y i )) 10. E k = {e kij, i, j = 1,..., n}, e kij = (i, j, w kij ) is the set of weighted edges connecting every pair of nodes, where w kij = φ kij d ij. 11 φ kij = exp{ f k (x i, y i ) f k (x j, y j ) /M k } d ij = exp{ λ (x i, y i ) (x j, y j ) l2 }, D where M k is the largest feature difference, D = max(hgt, wdt), and λ = location and feature parts 11 φ kij denotes feature dissimilarity and d ij represents the spatial distance. 17/29

18 Site-Entropy Rate - Markov Assumption 12 The transition probability from site i to site j is defined as: P ij = w ij j w ij Stochastic assumption: πp = π, where π is the stationary distribution that π i = W i 2W W i = w ij, W = j i,j:j>i w ij 12 Random walk is a stochastic process of a sequence of RVs 18/29

19 19/29 Site-Entropy Rate The author assumes that the information transmission among each site is determined by : the transmission frequency and the amount of information at each transmission. That is site-entropy rate at site i is defined as: SER i = π i P ij log P ij, j where π i defines the frequency at which a random walker visit node i, and j P ij log P ij measures the uncertainty of node i to others at one step. Finally, the saliency value at pixel i is defined: S i = k SER ki, where k is sub-band index.

20 Experimental Results Dataset: Color image 13 : 20 subjects on the 120 color images Area Under the roc Curve (AUC) Itti et al Bruce et al Gao et al Hou et al The author proposed Neil Bruce and John Tsotsos. Saliency Based on Information Maximization. In: NIPS Itti, Koch, and Niebur, A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. 15 Bruce and Tsotsos, Saliency Based on Information Maximization. 16 Dashan Gao, Vijay Mahadevan, and Nuno Vasconcelos. The discriminant center-surround hypothesis for bottom-up saliency. In: NIPS Xiaodi Hou and Liqing Zhang. Dynamic visual attention: searching for coding length increments. In: NIPS /29

21 21/29 Outline 1 Conclusions

22 Segmenting Salient Objects from Images and Videos 18 In the previous works, band-pass filtering and sliding-window approach have resulted in the best performance; hence, the author proposes a sliding-window saliency detection method Besides, a segmentation method is proposed by incorporating the detected saliency and Conditional Random Field (CRF) framework. (Option) This method is directly applicable to both still image and videos. 18 E. Rahtu et al. Segmenting salient objects from images and Videos. In: ECCV /29

23 23/29 Intuitions in Figure Intuition: a pixel x is salient (close to 1) if the feature at x is similar to 36 the features at points of the inner window. W B K Fig. 2. Illustration of saliency map computation

24 Intuitions in Mathematics Consider a rectangle window W divided into two disjoint parts: K (kernel window, salient) and B(border window, background). H 0, H 1, and F(x) for the events Z K, Z B, and F(Z ) Q F (x), respectively 19. S 0 (x) = P(Z K F(Z ) Q F (x) ) [0, 1], x K P(F(x) H 0 )P(H 0 ) = P(F(x) H 0 )P(H 0 ) + P(F(x) H 1 )P(H 1 ) h K (x)p 0 = h K (x)p 0 + h B (x)(1 p 0 ), h K (x) = P(F (x) H 0 ) = 1 p(w)dw P(H 0 ) h B (x) = P(F(x) H 1 ), K F 1 (Q F(x) ) where Q F (x) denotes the bin which contains F(x) and 0 < p 0 < Z is a RV describing the distribution of pixels in W. 24/29

25 The saliency map is achieved by sliding the window W with different scales over the image, and the final saliency value is taken as the maximum over all windows containing a particular pixel x. In practice, the author uses a regular grid with step size equal to 1% max(hgt, wdt) and four scales of grid size {25%, 10%; 30%, 30%; 50%, 50%; 70%, 40%} max(hgt, wdt), respectively. 20 For frames in videos, the author combine CIELab and motion information into feature map. That is F (x) = (L(x), a(x), b(x), Y (x)). 21 h K (x) = h L K (L(x)) h a K (a(x)) h b K (b(x)) h Y K (Y (x)) for frames in video. 25/29 Intuitions in Mathematics The feature map 20 at a point x in CIELab color space F(x) = (L(x), a(x), b(x)) Based on the independent assumption, h k (x) 21 is defined as: h K (x) = h L K (L(x)) ha K (a(x)) hb K (b(x)).

26 26/29 Intuitions in Mathematics 375 Mean precision soft CRF trh CRF proposed measure Rahtu VS09 Achanta CVPR09 Guo CVPR Mean recall Precision Recall F beta Fig. 3. Left: Mean precision-recall curves using comparison methods and the proposed approach. Right: Mean precision, recall, and F-measure values for comparison method [26] (1), our method with thresholding (2), and our method with soft assignments (3). Notice that β =0.3 (used according to [26]) strongly emphasizes precision.

27 27/29 Outline Conclusions 1 Conclusions

28 28/29 Conclusions Conclusions They retain a reasonable range of spatial frequency by the proposed band-pass filter to highlight the whole salient object. However, they inaccurately analyze the object saliency since they cannot significantly highlight local contrasts. SER achieses a nice salient detection performance in images. However, The learnt bases cannot fit to all images because they are content-dependent. They observe that a distinctive-colour rectangle contains high contrast information; hence, the salient degree of a pixel in a rectangle is determined by the number of colour-similar pixels. However, without knowing the object size, the sliding-window approaches must vary the window size to locate the object; hence, the problem of object-size variation degrades their performance.

29 29/29 Conclusions Conclusions Thank you

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

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

Frequency-tuned Salient Region Detection

Frequency-tuned Salient Region Detection Frequency-tuned Salient Region Detection Radhakrishna Achanta, Sheila Hemami, Francisco Estrada, and Sabine Süsstrunk School of Computer and Communication Sciences (IC) Ecole Polytechnique Fédérale de

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

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

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

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

Random Walks on Graphs to Model Saliency in Images

Random Walks on Graphs to Model Saliency in Images Random Walks on Graphs to Model Saliency in Images Viswanath Gopalakrishnan Yiqun Hu Deepu Rajan School of Computer Engineering Nanyang Technological University, Singapore 639798 visw0005@ntu.edu.sg yqhu@ntu.edu.sg

More information

Hierarchical Saliency Detection Supplementary Material

Hierarchical Saliency Detection Supplementary Material Hierarchical Saliency Detection Supplementary Material Qiong Yan Li Xu Jianping Shi Jiaya Jia The Chinese University of Hong Kong {qyan,xuli,pshi,leoia}@cse.cuhk.edu.hk http://www.cse.cuhk.edu.hk/leoia/proects/hsaliency/

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

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

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

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

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

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

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

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

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

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

Saliency Detection via Dense and Sparse Reconstruction

Saliency Detection via Dense and Sparse Reconstruction 23 IEEE International Conference on Computer Vision Saliency Detection via Dense and Sparse Reconstruction Xiaohui Li, Huchuan Lu, Lihe Zhang, Xiang Ruan 2, and Ming-Hsuan Yang 3 Dalian University of Technology

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

Speaker: Ming-Ming Cheng Nankai University 15-Sep-17 Towards Weakly Supervised Image Understanding

Speaker: Ming-Ming Cheng Nankai University   15-Sep-17 Towards Weakly Supervised Image Understanding Towards Weakly Supervised Image Understanding (WSIU) Speaker: Ming-Ming Cheng Nankai University http://mmcheng.net/ 1/50 Understanding Visual Information Image by kirkh.deviantart.com 2/50 Dataset Annotation

More information

Focusing Attention on Visual Features that Matter

Focusing Attention on Visual Features that Matter TSAI, KUIPERS: FOCUSING ATTENTION ON VISUAL FEATURES THAT MATTER 1 Focusing Attention on Visual Features that Matter Grace Tsai gstsai@umich.edu Benjamin Kuipers kuipers@umich.edu Electrical Engineering

More information

Image Resizing Based on Gradient Vector Flow Analysis

Image Resizing Based on Gradient Vector Flow Analysis Image Resizing Based on Gradient Vector Flow Analysis Sebastiano Battiato battiato@dmi.unict.it Giovanni Puglisi puglisi@dmi.unict.it Giovanni Maria Farinella gfarinellao@dmi.unict.it Daniele Ravì rav@dmi.unict.it

More information

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

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

IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 14, NO. 4, AUGUST

IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 14, NO. 4, AUGUST IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 14, NO. 4, AUGUST 2012 1275 Unsupervised Salient Object Segmentation Based on Kernel Density Estimation and Two-Phase Graph Cut Zhi Liu, Member, IEEE, Ran Shi, Liquan

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

Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference

Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference Minh Dao 1, Xiang Xiang 1, Bulent Ayhan 2, Chiman Kwan 2, Trac D. Tran 1 Johns Hopkins Univeristy, 3400

More information

An Efficient Salient Feature Extraction by Using Saliency Map Detection with Modified K-Means Clustering Technique

An Efficient Salient Feature Extraction by Using Saliency Map Detection with Modified K-Means Clustering Technique International Journal of Computational Engineering & Management, Vol. 15 Issue 5, September 2012 www..org 63 An Efficient Salient Feature Extraction by Using Saliency Map Detection with Modified K-Means

More information

Saliency Detection Using Quaternion Sparse Reconstruction

Saliency Detection Using Quaternion Sparse Reconstruction Saliency Detection Using Quaternion Sparse Reconstruction Abstract We proposed a visual saliency detection model for color images based on the reconstruction residual of quaternion sparse model in this

More information

THE HUMAN visual system interprets the world in a

THE HUMAN visual system interprets the world in a 1150 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 23, NO. 7, JULY 2013 Visual Saliency by Selective Contrast Qi Wang, Yuan Yuan, Senior Member, IEEE, and Pingkun Yan, Senior Member,

More information

Edge and local feature detection - 2. Importance of edge detection in computer vision

Edge and local feature detection - 2. Importance of edge detection in computer vision Edge and local feature detection Gradient based edge detection Edge detection by function fitting Second derivative edge detectors Edge linking and the construction of the chain graph Edge and local feature

More information

Hierarchical Saliency Detection

Hierarchical Saliency Detection Hierarchical Saliency Detection Qiong Yan Li Xu Jianping Shi Jiaya Jia The Chinese University of Hong Kong {qyan,xuli,jpshi,leojia}@cse.cuhk.edu.hk http://www.cse.cuhk.edu.hk/leojia/projects/hsaliency/

More information

Separating Objects and Clutter in Indoor Scenes

Separating Objects and Clutter in Indoor Scenes Separating Objects and Clutter in Indoor Scenes Salman H. Khan School of Computer Science & Software Engineering, The University of Western Australia Co-authors: Xuming He, Mohammed Bennamoun, Ferdous

More information

Regional Principal Color Based Saliency Detection

Regional Principal Color Based Saliency Detection Regional Principal Color Based Saliency Detection Jing Lou, Mingwu Ren*, Huan Wang School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China Abstract

More information

Data-driven Saliency Region Detection Based on Undirected Graph Ranking

Data-driven Saliency Region Detection Based on Undirected Graph Ranking Data-driven Saliency Region Detection Based on Undirected Graph Ranking Wenjie Zhang ; Qingyu Xiong 2 ; Shunhan Chen 3 College of Automation, 2 the School of Software Engineering, 3 College of Information

More information

Filters. Advanced and Special Topics: Filters. Filters

Filters. Advanced and Special Topics: Filters. Filters Filters Advanced and Special Topics: Filters Dr. Edmund Lam Department of Electrical and Electronic Engineering The University of Hong Kong ELEC4245: Digital Image Processing (Second Semester, 2016 17)

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

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

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

A Parametric Spectral Model for Texture-Based Salience

A Parametric Spectral Model for Texture-Based Salience A Parametric Spectral Model for Texture-Based Salience Kasim Terzić, Sai Krishna and J.M.H. du Buf {kterzic,dubuf}@ualg.pt Vision Laboratory/LARSys, University of the Algarve Abstract. We present a novel

More information

Animated Non-Photorealistic Rendering in Multiple Styles

Animated Non-Photorealistic Rendering in Multiple Styles Animated Non-Photorealistic Rendering in Multiple Styles Ting-Yen Chen and Reinhard Klette Department of Computer Science The University of Auckland, New Zealand Abstract. This paper presents an algorithm

More information

Saliency Detection via Nonlocal L 0 Minimization

Saliency Detection via Nonlocal L 0 Minimization Saliency Detection via Nonlocal L 0 Minimization Yiyang Wang, Risheng Liu 2, Xiaoliang Song, and Zhixun Su School of Mathematical Sciences, Dalian University of Technology, China 2 School of Software Technology,

More information

Iterative CT Reconstruction Using Curvelet-Based Regularization

Iterative CT Reconstruction Using Curvelet-Based Regularization Iterative CT Reconstruction Using Curvelet-Based Regularization Haibo Wu 1,2, Andreas Maier 1, Joachim Hornegger 1,2 1 Pattern Recognition Lab (LME), Department of Computer Science, 2 Graduate School in

More information

FASA: Fast, Accurate, and Size-Aware Salient Object Detection

FASA: Fast, Accurate, and Size-Aware Salient Object Detection FASA: Fast, Accurate, and Size-Aware Salient Object Detection Gökhan Yildirim, Sabine Süsstrunk School of Computer and Communication Sciences École Polytechnique Fédérale de Lausanne Abstract. Fast and

More information

Salient Region Detection by UFO: Uniqueness, Focusness and Objectness

Salient Region Detection by UFO: Uniqueness, Focusness and Objectness 2013 IEEE International Conference on Computer Vision Salient Region Detection by UFO: Uniqueness, Focusness and Objectness Peng Jiang 1 Haibin Ling 2 Jingyi Yu 3 Jingliang Peng 1 1 School of Computer

More information

Visual Saliency Based Object Tracking

Visual Saliency Based Object Tracking Visual Saliency Based Object Tracking Geng Zhang 1,ZejianYuan 1, Nanning Zheng 1, Xingdong Sheng 1,andTieLiu 2 1 Institution of Artificial Intelligence and Robotics, Xi an Jiaotong University, China {gzhang,

More information

Automatic Trimap Generation for Digital Image Matting

Automatic Trimap Generation for Digital Image Matting Automatic Trimap Generation for Digital Image Matting Chang-Lin Hsieh and Ming-Sui Lee Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, R.O.C. E-mail:

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

People Tracking and Segmentation Using Efficient Shape Sequences Matching

People Tracking and Segmentation Using Efficient Shape Sequences Matching People Tracking and Segmentation Using Efficient Shape Sequences Matching Junqiu Wang, Yasushi Yagi, and Yasushi Makihara The Institute of Scientific and Industrial Research, Osaka University 8-1 Mihogaoka,

More information

SALIENT OBJECT DETECTION VIA BACKGROUND CONTRAST

SALIENT OBJECT DETECTION VIA BACKGROUND CONTRAST SALIENT OBJECT DETECTION VIA BACKGROUND CONTRAST Quan Zhou,, Nianyi Li 2,, Jianxin Chen, Liang Zhou, and Longin Jan Latecki 3 Key Lab of BB WL Comm & Sen Net Tech, Nanjing Univ of Posts & Telecom, Nanjing,

More information

Saliency Level Set Evolution

Saliency Level Set Evolution Saliency Level Set Evolution Jincheng Mei and Bao-Liang Lu,2, Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education

More information

Neuromorphic Bayesian Surprise for Far-Range Event Detection

Neuromorphic Bayesian Surprise for Far-Range Event Detection Neuromorphic Bayesian Surprise for Far-Range Event Detection Randolph C. Voorhies, Lior Elazary and Laurent Itti Department of Computer Science, University of Southern California Abstract In this paper

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

Logo Matching and Recognition for Avoiding Duplicate Logos

Logo Matching and Recognition for Avoiding Duplicate Logos Logo Matching and Recognition for Avoiding Duplicate Logos Lalsawmliani Fanchun 1, Rishma Mary George 2 PG Student, Electronics & Ccommunication Department, Mangalore Institute of Technology and Engineering

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 10 130221 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Canny Edge Detector Hough Transform Feature-Based

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

Exploiting Depth Camera for 3D Spatial Relationship Interpretation

Exploiting Depth Camera for 3D Spatial Relationship Interpretation Exploiting Depth Camera for 3D Spatial Relationship Interpretation Jun Ye Kien A. Hua Data Systems Group, University of Central Florida Mar 1, 2013 Jun Ye and Kien A. Hua (UCF) 3D directional spatial relationships

More information

SEMI-BLIND IMAGE RESTORATION USING A LOCAL NEURAL APPROACH

SEMI-BLIND IMAGE RESTORATION USING A LOCAL NEURAL APPROACH SEMI-BLIND IMAGE RESTORATION USING A LOCAL NEURAL APPROACH Ignazio Gallo, Elisabetta Binaghi and Mario Raspanti Universitá degli Studi dell Insubria Varese, Italy email: ignazio.gallo@uninsubria.it ABSTRACT

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

FOREGROUND SEGMENTATION BASED ON MULTI-RESOLUTION AND MATTING

FOREGROUND SEGMENTATION BASED ON MULTI-RESOLUTION AND MATTING FOREGROUND SEGMENTATION BASED ON MULTI-RESOLUTION AND MATTING Xintong Yu 1,2, Xiaohan Liu 1,2, Yisong Chen 1 1 Graphics Laboratory, EECS Department, Peking University 2 Beijing University of Posts and

More information

2 Proposed Methodology

2 Proposed Methodology 3rd International Conference on Multimedia Technology(ICMT 2013) Object Detection in Image with Complex Background Dong Li, Yali Li, Fei He, Shengjin Wang 1 State Key Laboratory of Intelligent Technology

More information

A Phase Discrepancy Analysis of Object Motion

A Phase Discrepancy Analysis of Object Motion A Phase Discrepancy Analysis of Object Motion Bolei Zhou 1,2, Xiaodi Hou 3, Liqing Zhang 1 1 MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Department of Computer Science

More information

Saliency Detection via Graph-Based Manifold Ranking

Saliency Detection via Graph-Based Manifold Ranking Saliency Detection via Graph-Based Manifold Ranking Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan 2, and Ming-Hsuan Yang 3 Dalian University of Technology 2 OMRON Corporation 3 University of California

More information

ACCORDING to the principle of human visual perception,

ACCORDING to the principle of human visual perception, IEEE SIGNAL PROCESSING LETTERS, VOL. XX, NO. XX, XXXX 2016 1 Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis Multiple Cues Fusion Runmin Cong, Student Member, IEEE, Jianjun

More information

Edges, interpolation, templates. Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth)

Edges, interpolation, templates. Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth) Edges, interpolation, templates Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth) Edge detection edge detection has many applications in image processing an edge detector implements

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

Salient Region Extraction for 3D-Stereoscopic Images

Salient Region Extraction for 3D-Stereoscopic Images Salient Region Extraction for 3D-Stereoscopic Images Leena Chacko, Priyadarsini S, Arya Jayakumar Department of Computer Engineering, College of Engineering, Chengannur, leenachacko52492@gmail.com, 9048182219

More information

Saliency Detection in Aerial Imagery

Saliency Detection in Aerial Imagery Saliency Detection in Aerial Imagery using Multi-scale SLIC Segmentation Samir Sahli 1, Daniel A. Lavigne 2 and Yunlong Sheng 1 1- COPL, Image Science group, Laval University, Quebec, Canada 2- Defence

More information

AUTOMATIC OBJECT EXTRACTION IN SINGLE-CONCEPT VIDEOS. Kuo-Chin Lien and Yu-Chiang Frank Wang

AUTOMATIC OBJECT EXTRACTION IN SINGLE-CONCEPT VIDEOS. Kuo-Chin Lien and Yu-Chiang Frank Wang AUTOMATIC OBJECT EXTRACTION IN SINGLE-CONCEPT VIDEOS Kuo-Chin Lien and Yu-Chiang Frank Wang Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan {iker, ycwang}@citi.sinica.edu.tw

More information

This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore.

This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. Title Saliency density maximization for efficient visual objects discovery Author(s) Luo, Ye; Yuan, Junsong;

More information

Spatio-temporal Saliency Detection Using Phase Spectrum of Quaternion Fourier Transform

Spatio-temporal Saliency Detection Using Phase Spectrum of Quaternion Fourier Transform Spatio-temporal Saliency Detection Using Phase Spectrum of Quaternion Fourier Transform Chenlei Guo, Qi Ma and Liming Zhang Department of Electronic Engineering, Fudan University No.220, Handan Road, Shanghai,

More information

Object Extraction Using Image Segmentation and Adaptive Constraint Propagation

Object Extraction Using Image Segmentation and Adaptive Constraint Propagation Object Extraction Using Image Segmentation and Adaptive Constraint Propagation 1 Rajeshwary Patel, 2 Swarndeep Saket 1 Student, 2 Assistant Professor 1 2 Department of Computer Engineering, 1 2 L. J. Institutes

More information

VIsual saliency attempts to determine the amount of. Visual Saliency Detection Based on Multiscale Deep CNN Features

VIsual saliency attempts to determine the amount of. Visual Saliency Detection Based on Multiscale Deep CNN Features 1 Visual Saliency Detection Based on Multiscale Deep CNN Features Guanbin Li and Yizhou Yu arxiv:1609.02077v1 [cs.cv] 7 Sep 2016 Abstract Visual saliency is a fundamental problem in both cognitive and

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

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

Video annotation based on adaptive annular spatial partition scheme

Video annotation based on adaptive annular spatial partition scheme Video annotation based on adaptive annular spatial partition scheme Guiguang Ding a), Lu Zhang, and Xiaoxu Li Key Laboratory for Information System Security, Ministry of Education, Tsinghua National Laboratory

More information

An Approach for Reduction of Rain Streaks from a Single Image

An Approach for Reduction of Rain Streaks from a Single Image An Approach for Reduction of Rain Streaks from a Single Image Vijayakumar Majjagi 1, Netravati U M 2 1 4 th Semester, M. Tech, Digital Electronics, Department of Electronics and Communication G M Institute

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

Semantically-based Human Scanpath Estimation with HMMs

Semantically-based Human Scanpath Estimation with HMMs 0 IEEE International Conference on Computer Vision Semantically-based Human Scanpath Estimation with HMMs Huiying Liu, Dong Xu, Qingming Huang, Wen Li, Min Xu, and Stephen Lin 5 Institute for Infocomm

More information

Boundaries and Sketches

Boundaries and Sketches Boundaries and Sketches Szeliski 4.2 Computer Vision James Hays Many slides from Michael Maire, Jitendra Malek Today s lecture Segmentation vs Boundary Detection Why boundaries / Grouping? Recap: Canny

More information

Blind Image Deblurring Using Dark Channel Prior

Blind Image Deblurring Using Dark Channel Prior Blind Image Deblurring Using Dark Channel Prior Jinshan Pan 1,2,3, Deqing Sun 2,4, Hanspeter Pfister 2, and Ming-Hsuan Yang 3 1 Dalian University of Technology 2 Harvard University 3 UC Merced 4 NVIDIA

More information

Image Segmentation and Registration

Image Segmentation and Registration Image Segmentation and Registration Dr. Christine Tanner (tanner@vision.ee.ethz.ch) Computer Vision Laboratory, ETH Zürich Dr. Verena Kaynig, Machine Learning Laboratory, ETH Zürich Outline Segmentation

More information

Feature extraction. Bi-Histogram Binarization Entropy. What is texture Texture primitives. Filter banks 2D Fourier Transform Wavlet maxima points

Feature extraction. Bi-Histogram Binarization Entropy. What is texture Texture primitives. Filter banks 2D Fourier Transform Wavlet maxima points Feature extraction Bi-Histogram Binarization Entropy What is texture Texture primitives Filter banks 2D Fourier Transform Wavlet maxima points Edge detection Image gradient Mask operators Feature space

More information

Image Redundancy and Non-Parametric Estimation for Image Representation

Image Redundancy and Non-Parametric Estimation for Image Representation Image Redundancy and Non-Parametric Estimation for Image Representation Charles Kervrann, Patrick Pérez, Jérôme Boulanger INRIA Rennes / INRA MIA Jouy-en-Josas / Institut Curie Paris VISTA Team http://www.irisa.fr/vista/

More information

MOTION VECTOR REFINEMENT FOR FRUC USING SALIENCY AND SEGMENTATION

MOTION VECTOR REFINEMENT FOR FRUC USING SALIENCY AND SEGMENTATION MOTION VECTOR REFINEMENT FOR FRUC USING SALIENCY AND SEGMENTATION Natan Jacobson, Yen-Lin Lee, Vijay Mahadevan, Nuno Vasconcelos, Truong Q. Nguyen ECE Department, University of California, San Diego La

More information

Discriminative classifiers for image recognition

Discriminative classifiers for image recognition Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study

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

IMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION. Maral Mesmakhosroshahi, Joohee Kim

IMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION. Maral Mesmakhosroshahi, Joohee Kim IMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION Maral Mesmakhosroshahi, Joohee Kim Department of Electrical and Computer Engineering Illinois Institute

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

Synthetic Saliency. Ben Weems Stanford University. Anthony Perez Stanford University. Karan Rai Stanford University. Abstract. 1.

Synthetic Saliency. Ben Weems Stanford University. Anthony Perez Stanford University. Karan Rai Stanford University. Abstract. 1. Synthetic Saliency Anthony Perez Stanford University aperez8@stanford.edu Karan Rai Stanford University karanrai@stanford.edu Ben Weems Stanford University bweems@stanford.edu Abstract There are many existing

More information

Spatio-temporal Feature Classifier

Spatio-temporal Feature Classifier Spatio-temporal Feature Classifier Send Orders for Reprints to reprints@benthamscience.ae The Open Automation and Control Systems Journal, 2015, 7, 1-7 1 Open Access Yun Wang 1,* and Suxing Liu 2 1 School

More information

Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation

Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation Alaa E. Abdel-Hakim Electrical Engineering Department Assiut University Assiut, Egypt alaa.aly@eng.au.edu.eg Mostafa Izz Cairo

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

HYBRID CENTER-SYMMETRIC LOCAL PATTERN FOR DYNAMIC BACKGROUND SUBTRACTION. Gengjian Xue, Li Song, Jun Sun, Meng Wu

HYBRID CENTER-SYMMETRIC LOCAL PATTERN FOR DYNAMIC BACKGROUND SUBTRACTION. Gengjian Xue, Li Song, Jun Sun, Meng Wu HYBRID CENTER-SYMMETRIC LOCAL PATTERN FOR DYNAMIC BACKGROUND SUBTRACTION Gengjian Xue, Li Song, Jun Sun, Meng Wu Institute of Image Communication and Information Processing, Shanghai Jiao Tong University,

More information

Superpixels Generating from the Pixel-based K-Means Clustering

Superpixels Generating from the Pixel-based K-Means Clustering Superpixels Generating from the Pixel-based K-Means Clustering Shang-Chia Wei, Tso-Jung Yen Institute of Statistical Science Academia Sinica Taipei, Taiwan 11529, R.O.C. wsc@stat.sinica.edu.tw, tjyen@stat.sinica.edu.tw

More information

Bilevel Sparse Coding

Bilevel Sparse Coding Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013 Outline 1 2 The learning model The learning algorithm 3 4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional

More information

Adaptive Multi-Level Region Merging for Salient Object Detection

Adaptive Multi-Level Region Merging for Salient Object Detection FU, et al: ADAPTIVE MULTI-LEVEL REGION MERGING FOR SALIENT OBJECT DETECTION Adaptive Multi-Level Region Merging for Salient Object Detection Keren Fu,2 fkrsuper@sjtu.edu.cn,keren@chalmers.se Chen Gong

More information

ELEC Dr Reji Mathew Electrical Engineering UNSW

ELEC Dr Reji Mathew Electrical Engineering UNSW ELEC 4622 Dr Reji Mathew Electrical Engineering UNSW Review of Motion Modelling and Estimation Introduction to Motion Modelling & Estimation Forward Motion Backward Motion Block Motion Estimation Motion

More information