Genetic Programming IV: Routine Human-Competitive Machine Intelligence
Genetic Programming IV: Routine Human-Competitive Machine Intelligence
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues
IEEE Transactions on Pattern Analysis and Machine Intelligence
Supervised Learning of Edges and Object Boundaries
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Automatic construction of invariant features using genetic programming for edge detection
AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence
Figure of merit based fitness functions in genetic programming for edge detection
SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
PhenoGP: combining programs to avoid code disruption
EuroGP'13 Proceedings of the 16th European conference on Genetic Programming
Genetic programming for automatic construction of variant features in edge detection
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Automatic construction of gaussian-based edge detectors using genetic programming
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Genetic programming for edge detection using multivariate density
Proceedings of the 15th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
Boundary detection constitutes a crucial step in many computer vision tasks. We present a learning approach for automatically constructing high-performance local boundary detectors for natural images via genetic programming (GP). Our GP system is unique in that it combines filter kernels that were inspired by models of processing in the early stages of the primate visual system, but makes no assumptions about what constitutes a boundary, thus avoiding the need to make ad hoc intuitive definitions. By testing our evolved boundary detectors on a highly challenging benchmark set of natural images with associated human-marked boundaries, we show performance that outperforms most existing approaches.