Figure/Ground Assignment in Natural Images
- Xiaofeng RenAffiliated withLancaster UniversityComputer Science Division, University of California at Berkeley
- , Charless C. FowlkesAffiliated withLancaster UniversityComputer Science Division, University of California at Berkeley
- , Jitendra MalikAffiliated withLancaster UniversityComputer Science Division, University of California at Berkeley
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 . 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.
- Figure/Ground Assignment in Natural Images
- Book Title
- Computer Vision – ECCV 2006
- Book Subtitle
- 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part II
- pp 614-627
- Print ISBN
- Online ISBN
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- Series ISSN
- Springer Berlin Heidelberg
- Copyright Holder
- Springer Berlin Heidelberg
- Additional Links
- Industry Sectors
- eBook Packages
- Editor Affiliations
- 16. University of Ljubljana
- 17. Institute for Computer Graphics and Vision, TU Graz
- 18. Vision-based Measurement Group, Inst. of El. Measurement and Meas. Sign. Proc. Graz, University of Technology
- Author Affiliations
- 19. Computer Science Division, University of California at Berkeley, Berkeley, CA, 94720, USA
To view the rest of this content please follow the download PDF link above.