Filters








563 Hits in 4.5 sec

Hierarchical Contour Closure-Based Holistic Salient Object Detection

Qing Liu, Xiaopeng Hong, Beiji Zou, Jie Chen, Zailiang Chen, Guoying Zhao
2017 IEEE Transactions on Image Processing  
To better compute the saliency for complicated images, we propose a hierarchical contour closure based holistic salient object detection method, in which two saliency cues, i.e., closure completeness and  ...  Such fine-grained contrast based salient object detection methods are stuck with saliency attenuation of the salient object and saliency overestimation of the background when the image is complicated.  ...  CONTOUR CLOSURE BASED SALIENCY DETECTION The proposed framework is illustrated in Fig. 4 , in which two closure based maps are generated for the salient object detection in the hierarchical segmentation  ... 
doi:10.1109/tip.2017.2703081 pmid:28500000 fatcat:rxkjth3jqraqjcatmrzizzm6pe

A century of Gestalt psychology in visual perception: II. Conceptual and theoretical foundations

Johan Wagemans, Jacob Feldman, Sergei Gepshtein, Ruth Kimchi, James R. Pomerantz, Peter A. van der Helm, Cees van Leeuwen
2012 Psychological bulletin  
The third considers how Gestalt percepts (e.g., groups, objects) are optimal given the available stimulation, with optimality specified in Bayesian terms.  ...  ., integral dimensions, emergent features, configural superiority, global precedence, primacy of holistic/configural properties) and a refined understanding of its psychological implications (e.g., at  ...  The key factor in obtaining a CSE appears to be the creation of salient emergent features when the context C is added to the base elements A and B.  ... 
doi:10.1037/a0029334 pmid:22845750 pmcid:PMC3728284 fatcat:tqnakmbxhbctxlannhyszazvz4

The many faces of configural processing

Daphne Maurer, Richard Le Grand, Catherine J. Mondloch
2002 Trends in Cognitive Sciences  
We distinguish three types of configural processing: detecting the first-order relations that define faces (i.e. two eyes above a nose and mouth), holistic processing (glueing the features together into  ...  We provide evidence for their separability based on behavioral marker tasks, their sensitivity to experimental manipulations, and their patterns of development.  ...  It seems logical that the three types operate in the functional and neural order that we described: detection of the face based on first-order relations as a necessary first step before holistic processing  ... 
doi:10.1016/s1364-6613(02)01903-4 pmid:12039607 fatcat:vfguwwvdivghdaw7xyefbzwsfy

Perceptual organization in computer vision: a review and a proposal for a classificatory structure

S. Sarkar, K.L. Boyer
1993 IEEE Transactions on Systems, Man and Cybernetics  
Their hypothetical system has three components: a boundary contour system, a feature contour system, and an object recognition system.  ...  This algorithm is used by Chung and Nevatia [45] in their hierarchical stereo system with explicit occlusion detection.  ... 
doi:10.1109/21.229452 fatcat:ivufwdix4bgrdim476wcgefdgy

Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation

Hongyuan Zhu, Fanman Meng, Jianfei Cai, Shijian Lu
2016 Journal of Visual Communication and Image Representation  
around 180 publications, we give an overview of broad areas of segmentation topics including not only the classic bottom-up approaches, but also the recent development in superpixel, interactive methods, object  ...  In a typical contour based interactive method, the user first places a contour close to the object boundary, and then the contour will evolve to snap to the nearby salient object boundary.  ...  Hence, in some sense general object proposal problem is correlated with the popular salient object detection problem.  ... 
doi:10.1016/j.jvcir.2015.10.012 fatcat:siynj55yxrdqlj5vcrpfm7nyhe

Beyond Pixels: A Comprehensive Survey from Bottom-up to Semantic Image Segmentation and Cosegmentation [article]

Hongyuan Zhu, Fanman Meng, Jianfei Cai, Shijian Lu
2015 arXiv   pre-print
Covering 180 publications, we give an overview of broad areas of segmentation topics including not only the classic bottom-up approaches, but also the recent development in superpixel, interactive methods, object  ...  In a typical contour based interactive method, the user first places a contour close to the object boundary, and then the contour will evolve to snap to the nearby salient object boundary.  ...  [7] proposed to use hierarchical regions for object detection, instead of bounding boxes.  ... 
arXiv:1502.00717v1 fatcat:3ykejbslgjgi3fe3sry35j7ibq

Video Object Segmentation and Tracking: A Survey [article]

Rui Yao, Guosheng Lin, Shixiong Xia, Jiaqi Zhao, Yong Zhou
2019 arXiv   pre-print
First, we provide a hierarchical categorization existing approaches, including unsupervised VOS, semi-supervised VOS, interactive VOS, weakly supervised VOS, and segmentation-based tracking methods.  ...  Object segmentation and object tracking are fundamental research area in the computer vision community.  ...  [149] present a video salient object detection method using pyramid dilated bidirectional ConvLSTM architecture, and apply it to the unsupervised VOS.  ... 
arXiv:1904.09172v3 fatcat:nm3zptbidvgxfkxezqjekwdpdi

A Gestaltist approach to contour-based object recognition: Combining bottom-up and top-down cues

Ching L. Teo, Cornelia Fermüller, Yiannis Aloimonos
2015 The international journal of robotics research  
This paper proposes a method for detecting generic classes of objects from their representative contours that can be used by a robot with vision to find objects in cluttered environments.  ...  Using the operator's output, a novel contour-based descriptor is created that extends the shape context descriptor to include boundary ownership information and accounts for rotation.  ...  In this work, we argue that by exploiting midlevel contour grouping mechanisms, we are able to effectively address all the above issues in a simple, holistic object-detection framework.  ... 
doi:10.1177/0278364914558493 fatcat:lrrmjkpidzfwvjxh77ca6gf52m

Vision-based Robotic Grasp Detection From Object Localization, Object Pose Estimation To Grasp Estimation: A Review [article]

Guoguang Du, Kai Wang, Shiguo Lian, Kaiyong Zhao
2020 arXiv   pre-print
This paper presents a comprehensive survey on vision-based robotic grasp detection methods.  ...  In detail, object localization task contains object localization without classification, object detection and object instance segmentation.  ...  ., 2017] trained a CNN-based model which fuses different low level saliency cues into hierarchical features for detecting salient objects in RGBD images. Chen et al.  ... 
arXiv:1905.06658v2 fatcat:6u3k2ltwifaanjpp2nkayyj2f4

Building holistic descriptors for scene recognition

Li Liu, Ling Shao, Xuelong Li
2013 Proceedings of the 21st ACM international conference on Multimedia - MM '13  
Specifically, a set of primitive operators and filters are first randomly assembled in the MOGP framework as tree-based combinations, which are then evaluated by two objective fitness criteria i.e., the  ...  We address this as an optimization problem by using multi-objective genetic programming (MOGP).  ...  For local feature-based methods, unsupervised techniques (e.g., Harris corner detector [4] and Harris-Laplace detector [12] ) are applied to detect interest points around which the most salient features  ... 
doi:10.1145/2502081.2502095 dblp:conf/mm/LiuSL13 fatcat:qjbuj7dit5htffrzrvny4pntqy

Toward a better approach to goodness: Comments on Van der Helm and Leeuwenberg (1996)

Johan Wagemans
1999 Psychological review  
Some resularities are more salient to the visual system than others. P. A. van der Helm and E. L. J.  ...  Casual observations with polygons (Stevens, 1980) , as well as a few experimental results (Wagemans, 1993) , suggest that polygons (which are more representative for object contours than dot patterns  ...  Surface contours embedded in 3-D objects may even be less affected, as seems to be implied by our recent finding that the skewed symmetry of top and side surfaces of cubes affects the perceived global  ... 
doi:10.1037//0033-295x.106.3.610 fatcat:3wsvg4nlrnh7fhks5kc6q65e7m

Toward a better approach to goodness: Comments on Van der Helm and Leeuwenberg (1996)

Johan Wagemans
1999 Psychological review  
Some resularities are more salient to the visual system than others. P. A. van der Helm and E. L. J.  ...  Casual observations with polygons (Stevens, 1980) , as well as a few experimental results (Wagemans, 1993) , suggest that polygons (which are more representative for object contours than dot patterns  ...  Surface contours embedded in 3-D objects may even be less affected, as seems to be implied by our recent finding that the skewed symmetry of top and side surfaces of cubes affects the perceived global  ... 
doi:10.1037/0033-295x.106.3.610 fatcat:4p2nh2vssbgzzdqigwxtnbxz6y

A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure–ground organization

Johan Wagemans, James H. Elder, Michael Kubovy, Stephen E. Palmer, Mary A. Peterson, Manish Singh, Rüdiger von der Heydt
2012 Psychological bulletin  
., proximity, similarity, common fate, good continuation, closure, symmetry, parallelism) and new (e.g., synchrony, common region, element and uniform connectedness), and their role in contour integration  ...  We then review classic and new image-based principles of figure-ground organization, how it is influenced by past experience and attention, and how it relates to shape and depth perception.  ...  Closure. The role of closure in contour integration has been debated.  ... 
doi:10.1037/a0029333 pmid:22845751 pmcid:PMC3482144 fatcat:ob2i5wa6zzf37gg5fqnoo3tonu

Neuropsychological evidence for the temporal dynamics of category-specific naming

Sven Panis, Katrien Torfs, Celine R. Gillebert, Johan Wagemans, Glyn W. Humphreys
2017 Visual Cognition  
Some suggest that category-specific deficits may be caused by a deficit in recurrent processing between the levels of a hierarchically organized visual object recognition system.  ...  We studied how shape complexity, object category, and fragment curvature influence the timing of correct object identification.  ...  of information in reciprocally connected hierarchical cortical areas can be organized to produce recognition of objects through the detection of combinations of features, and how the serial process of  ... 
doi:10.1080/13506285.2017.1330790 pmid:29238759 pmcid:PMC5706980 fatcat:fxjaipuhpvd6jegspgxuh4kqje

Where there is no object formation, there is no perceptual organization: evidence from the configural superiority effect

Junjun Zhang, Xiaoyan Yang, Zhenlan Jin, Ling Li
2021 NeuroImage  
Thus, our results suggest that the EF of closure, which leads to the configural superiority effect, only emerges for objects but not for holes, and only in the LOC but not the EVC.  ...  Behaviorally, we found that the EF of closure facilitated oddball discrimination on objects, as demonstrated by previous studies, but did not facilitate oddball discrimination on holes with the same shape  ...  We predict that configural superiority, which means that the detection of triangles is faster than the detection of bars, may only be effective with objects but not holes.  ... 
doi:10.1016/j.neuroimage.2021.118108 pmid:33940152 fatcat:nmgsbsozonefjfa2zi4tet5ete
« Previous Showing results 1 — 15 out of 563 results