Perceptual organization of occluding contours of opaque surfaces
Computer Vision and Image Understanding - Special issue on perceptual organization in computer vision
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
A Hierarchical Markov Random Field Model for Figure-Ground Segregation
EMMCVPR '01 Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Visual Organization for Figure/Ground Separation
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Measuring Convexity for Figure/Ground Separation
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Scale-Invariant Contour Completion Using Conditional Random Fields
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Recovering human body configurations: combining segmentation and recognition
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Multiscale conditional random fields for image labeling
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Context Driven Focus of Attention for Object Detection
Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint
International Journal of Computer Vision
An intuitive model of perceptual grouping for HCI design
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Occlusion Boundaries from Motion: Low-Level Detection and Mid-Level Reasoning
International Journal of Computer Vision
A framework for visual-context-aware object detection in still images
Computer Vision and Image Understanding
Simultaneous segmentation and figure/ground organization using angular embedding
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Boundary detection using f-measure-, filter- and feature- (F3) boost
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Figure-ground image segmentation helps weakly-supervised learning of objects
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Recovering Occlusion Boundaries from an Image
International Journal of Computer Vision
Embedding Gestalt laws on conditional random field for image segmentation
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
NPAR '12 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering
Occlusion cues for image scene layering
Computer Vision and Image Understanding
Shape sharing for object segmentation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Accurate Junction Detection and Characterization in Natural Images
International Journal of Computer Vision
Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition
International Journal of Computer Vision
Hi-index | 0.00 |
Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and allowing high-level processing to focus on non-accidental shapes of figural regions. In this paper, we develop a computational model for figure/ground assignment in complex natural scenes. We utilize a large dataset of images annotated with human-marked segmentations and figure/ground labels for training and quantitative evaluation. We operationalize the concept of familiar configuration by constructing prototypical local shapes, i.e. shapemes, from image data. Shapemes automatically encode mid-level visual cues to figure/ground assignment such as convexity and parallelism. Based on the shapeme representation, we train a logistic classifier to locally predict figure/ground labels. We also consider a global model using a conditional random field (CRF) to enforce global figure/ground consistency at T-junctions. We use loopy belief propagation to perform approximate inference on this model and learn maximum likelihood parameters from ground-truth labels. We find that the local shapeme model achieves an accuracy of 64% in predicting the correct figural assignment. This compares favorably to previous studies using classical figure/ground cues [1]. We evaluate the global model using either a set of contours extracted from a low-level edge detector or the set of contours given by human segmentations. The global CRF model significantly improves the performance over the local model, most notably when using human-marked boundaries (78%). These promising experimental results show that this is a feasible approach to bottom-up figure/ground assignment in natural images.