26,028 Hits in 9.6 sec

Discovering salient objects from videos using spatiotemporal salient region detection

Rajkumar Kannan, Gheorghita Ghinea, Sridhar Swaminathan
2015 Signal processing. Image communication  
The spatial saliency is computed estimating of color contrast cue and color distribution cue by exploiting patch level and region level image abstractions in a unified way.  ...  Usually, images patches are compared with each other to compute color contrast and color distribution cues for salient region detection.  ...  [40] also proposed a color and orientation distribution based spatial salient region detection approach.  ... 
doi:10.1016/j.image.2015.07.004 fatcat:tourjl47njbnfiim37tq4iuzg4

Center-surround divergence of feature statistics for salient object detection

Dominik A. Klein, Simone Frintrop
2011 2011 International Conference on Computer Vision  
In this paper, we introduce a new method to detect salient objects in images.  ...  The approach is based on the standard structure of cognitive visual attention models, but realizes the computation of saliency in each feature dimension in an information-theoretic way.  ...  By means of the Kullback-Leibler Divergence, we determine the contrast of the center and the surround distribution of features for the dimensions intensity, color, and orientation.  ... 
doi:10.1109/iccv.2011.6126499 dblp:conf/iccv/KleinF11 fatcat:n2jev25rrbey5k53o4n2tkkhmy

Visual Saliency Models for Text Detection in Real World

Renwu Gao, Seiichi Uchida, Asif Shahab, Faisal Shafait, Volkmar Frinken, Joy J. Geng
2014 PLoS ONE  
A visualization of the distribution of scene texts and non-texts in the space constructed by three kinds of saliency maps, which are calculated using Itti's visual saliency model with intensity, color  ...  and orientation features, is given.  ...  Acknowledgments The pictures of Fig. 1, Fig. 2, Fig. 3 Fig. 9 : tuppus. Fig. 11 : hannah.rosen. Fig. 12 : me'nthedogs, sanchom, adactio, psd.  ... 
doi:10.1371/journal.pone.0114539 pmid:25494196 pmcid:PMC4262416 fatcat:kmses7mzdrgrdgeg4tfywjbvv4

Saliency detection based on directional patches extraction and principal local color contrast

Muwei Jian, Wenyin Zhang, Hui Yu, Chaoran Cui, Xiushan Nie, Huaxiang Zhang, Yilong Yin
2018 Journal of Visual Communication and Image Representation  
In this paper, we propose a novel computational model for saliency detection by integrating the holistic centerdirectional map with the principal local color contrast (PLCC) map.  ...  In the proposed framework, perceptual directional patches are firstly detected based on discrete wavelet frame transform (DWFT) and sparsity criterion, then the center of the spatial distribution of the  ...  Based on color contrast scheme by calculating each pixel's color difference between the average image color, a frequency-tuned approach was proposed for salient region detection in [19] . Rahtu et al  ... 
doi:10.1016/j.jvcir.2018.10.008 fatcat:nndomtfxgjc2nanklt7pqbsxiq

Spatiotemporal Saliency Detection and Its Applications in Static and Dynamic Scenes

Wonjun Kim, Chanho Jung, Changick Kim
2011 IEEE transactions on circuits and systems for video technology (Print)  
To this end, our spatiotemporal approach combines the spatial saliency by computing distances between ordinal signatures of edge and color orientations obtained from the center and the surrounding regions  ...  and the temporal saliency by simply computing the sum of absolute difference between temporal gradients of the center and the surrounding regions.  ...  Unlike existing methods based on the center-surround framework, we propose a novel solution for detecting salient regions by using SORM instead of directly using sample values of local feature distributions  ... 
doi:10.1109/tcsvt.2011.2125450 fatcat:6stl4b6bzfgm5jrtibd4b3hc3i

Saliency Detection with Flash and No-flash Image Pairs [chapter]

Shengfeng He, Rynson W. H. Lau
2014 Lecture Notes in Computer Science  
These photometric cues from the two observations are independent of visual attributes like color, and they provide new and robust distinctiveness to support salient object detection.  ...  In this paper, we propose a new saliency detection method using a pair of flash and no-flash images. Our approach is inspired by two observations.  ...  This work was partially supported by a SRG grant from City University of Hong Kong (Project Number: 7002768).  ... 
doi:10.1007/978-3-319-10578-9_8 fatcat:cyv6pjzrnjgidjng4pengu7aqq

Bottom-Up Saliency Detection Model Based on Human Visual Sensitivity and Amplitude Spectrum

Yuming Fang, Weisi Lin, Bu-Sung Lee, Chiew-Tong Lau, Zhenzhong Chen, Chia-Wen Lin
2012 IEEE transactions on multimedia  
We use the amplitude spectrum of QFT to represent the color, intensity, and orientation distributions for image patches.  ...  The experiment results show that the proposed saliency detection model outperforms the state-of-the-art detection models.  ...  built a saliency detection model based on the color and orientation distributions in images [11] . Recently, a saliency detection model by Valenti et al.  ... 
doi:10.1109/tmm.2011.2169775 fatcat:qdk3mj44ffdtlfuvckmvedom4i

Superpixel-based saliency detection

Zhi Liu, Le Meur, Shuhua Luo
2013 2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)  
In this paper, we propose an effective superpixel-based saliency model. First, the original image is simplified by performing superpixel segmentation and adaptive color quantization.  ...  Experimental results on a dataset containing 1,000 test images with ground truths demonstrate that the proposed saliency model outperforms state-of-the-art saliency models.  ...  In [11] , both global color distribution and orientation distribution are fully utilized to selectively generate the saliency map.  ... 
doi:10.1109/wiamis.2013.6616119 dblp:conf/wiamis/LiuML13 fatcat:jup775pgvzbbjbtrj6rplb5kia

Global-Context Based Salient Region Detection in Nature Images

Hong BAO, De XU, Yingjun TANG
2012 IEICE transactions on information and systems  
One of the main aims of visual attention in computer vision is to detect and segment the salient regions in an image.  ...  In this paper, we employ matrix decomposition to detect salient object in nature images.  ...  Thus, if the saliency in an image is dominated by color content, the salient regions are well covered by the global color modeling proposed in this paper.  ... 
doi:10.1587/transinf.e95.d.1556 fatcat:ji2mrqku6rf2do6cwlm447xlo4

Saliency detection: A self-ordinal resemblance approach

Wonjun Kim, Chanho Jung, Changick Kim
2010 2010 IEEE International Conference on Multimedia and Expo  
In saliency detection, regions attracting visual attention need to be highlighted while effectively suppressing non-salient regions for the semantic scene understanding.  ...  To address this problem, we propose a method for detecting salient regions based on a self-ordinal resemblance measure (SORM).  ...  by using the edge and color orientation information.  ... 
doi:10.1109/icme.2010.5583287 dblp:conf/icmcs/KimJK10 fatcat:ud2otm2q6nfcvk6wwrden44itq

Exploiting global priors for RGB-D saliency detection

Jianqiang Ren, Xiaojin Gong, Lu Yu, Wenhui Zhou, Michael Ying Yang
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
A two-stage RGB-D salient object detection framework is presented. It first integrates the region contrast, together with the background, depth, and orientation priors to achieve a saliency map.  ...  Inspired by the effectiveness of global priors for 2D saliency analysis, this paper aims to explore those particular to RGB-D data.  ...  Figure 3a and Figure 3b illustrate the depth distribution of salient objects and the distribution for all scenes, respectively, corresponding to the probabilities P (D|S) and P (D).  ... 
doi:10.1109/cvprw.2015.7301391 dblp:conf/cvpr/RenGYZY15 fatcat:kpmgelrsnnelvkwpi7ai4rejoi

How Salient is Scene Text?

Asif Shahab, Faisal Shafait, Andreas Dengel, Seiichi Uchida
2012 2012 10th IAPR International Workshop on Document Analysis Systems  
Initial results indicate that saliency maps produced by these attention models can be used for aiding scene text detection algorithms by suppressing non-text regions.  ...  Computational models of visual attention use image features to identify salient locations in an image that are likely to attract human attention.  ...  Firstly, because of the high dimensionality of colored images and secondly, because of the variety of color, font, size and orientation in which the text can occur in a natural scene.  ... 
doi:10.1109/das.2012.42 dblp:conf/das/ShahabSDU12 fatcat:hz2sieg53bh4vezb6vmk4pxdp4

A Survey on Various Saliency Detection Methods

Elsa Sebastian, Neenu Daniel
2017 International Journal of Computer Applications  
One of the main objectives of the work is to perform a detail study in the field of Saliency detection by keeping focus on the different bottom-up computational models and the methods used to predict saliency  ...  Detecting and segmenting salient objects, also known as salient object detection is used to extract the most interesting object/objects in a scene and has resulted in many applications.  ...  Furthermore, compute the global saliency by utilizing the global color distribution model embedded with color coherence, together with the multiple edge saliency.  ... 
doi:10.5120/ijca2017913187 fatcat:t72h4ja4rjbixodutttc6zwkby

Autonomous Salient Feature Detection through Salient Cues in an HSV Color Space for Visual Indoor Simultaneous Localization and Mapping

Yong-Ju Lee, Jae-Bok Song
2010 Advanced Robotics  
The robot estimates its pose by using the detected features and builds a grid map of the unknown environment by using a range sensor. The feature positions are stored in the grid map.  ...  Then, the saliency of each pixel is computed by measuring the level of similarity between the selected features and the given image.  ...  Acknowledgements This paper was produced for the Intelligent Robotics Development Program, one of the 21st Century Frontier R&D Programs funded by the Ministry of Commerce, Industry and Energy of South  ... 
doi:10.1163/016918610x512613 fatcat:d7jbn6jrsrgstpfemmkvyk25mu

Salient Region Detection by Fusing Foreground and Background Cues Extracted from Single Image

Qiangqiang Zhou, Weidong Zhao, Lin Zhang, Zhicheng Wang
2016 Mathematical Problems in Engineering  
the third is global color distribution map.  ...  In this paper, we propose a novel salient object detection algorithm which takes both background and foreground cues into consideration and integrate a bottom-up coarse salient regions extraction and a  ...  Acknowledgments The paper is supported by the National Science and Technology Support Project under Grant 2015IM030300.  ... 
doi:10.1155/2016/2138747 fatcat:qrajb4tbxjdonmq5xsfc3ceswa
« Previous Showing results 1 — 15 out of 26,028 results