A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Constrained Restoration and the Recovery of Discontinuities
IEEE Transactions on Pattern Analysis and Machine Intelligence
Variational methods in image segmentation
Variational methods in image segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture LIbraries
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Class-Specific, Top-Down Segmentation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Common Framework for Curve Evolution, Segmentation and Anisotropic Diffusion
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Image Parsing: Unifying Segmentation, Detection, and Recognition
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Towards a Mathematical Theory of Primal Sketch and Sketchability
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Fast, robust total variation-based reconstruction of noisy, blurred images
IEEE Transactions on Image Processing
Benchmarking Image Segmentation Algorithms
International Journal of Computer Vision
Proceedings of the 2010 ACM Symposium on Applied Computing
A framework for unsupervised segmentation of multi-modal medical images
CVAMIA'06 Proceedings of the Second ECCV international conference on Computer Vision Approaches to Medical Image Analysis
Hi-index | 0.00 |
The recent establishment of a large-scale ground-truth database of image segmentations [11] has enabled the development of learning approaches to the general segmentation problem. Using this database, we present an algorithm that learns how to segment images using region-based, perceptual features. The image is first densely segmented into regions and the edges between them using a variant of the Mumford-Shah functional. Each edge is classified as a boundary or non-boundary using a classifier trained on the ground-truth, resulting in an edge image estimating humandesignated boundaries. This novel approach has a few distinct advantages over filter-based methods such as local gradient operators. First, the same perceptual features can represent texture as well as regular structure. Second, the features can measure relationships between image elements at arbitrary distances in the image, enabling the detection of Gestalt properties at any scale. Third, texture boundaries can be precisely localized, which is difficult when using filter banks. Finally, the learning system outputs a relatively small set of intuitive perceptual rules for detecting boundaries. The classifier is trained on 200 images in the groundtruth database, and tested on another 100 images according to the benchmark evaluation methods. Edge classification improves the benchmark F-score from 0.54, for the initial Mumford-Shah-variant segmentation, to 0.61 on grayscale images. This increase of 13% demonstrates the versatility and representational power of our perceptual features, as the score exceeds published results for any algorithm restricted to one type of image feature such as texture or brightness gradient.