Visual cortex inspired junction detection

Authors:
Shuzhi Sam Ge;Chengyao Shen;Hongsheng He
Affiliations:
Social Robotics Lab, Interactive Digital Media Institute, National University of Singapore, Singapore;Social Robotics Lab, Interactive Digital Media Institute, National University of Singapore, Singapore;Social Robotics Lab, Interactive Digital Media Institute, National University of Singapore, Singapore
Venue:
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Year:
2011

Citing 3
Cited 0

Junctions: Detection, Classification, and Reconstruction

IEEE Transactions on Pattern Analysis and Machine Intelligence
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information

Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Computational predictions on the receptive fields and organization of v2 for shape processing

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a visual cortex inspired framework to detect and discriminate junction points in a visual scene. Inspired by the biological research in primary visual cortex V1 and secondary visual cortex V2, banks of filters are invented to simulate the response of complex cells, horizontal lateral connections and angle detectors. Before junction detection, contour enhancement and texture suppression are performed in determining the sketch of a scene. The proposed algorithm can extract primal sketch of the scene and detect the response of junction points in the scene. Experiments prove the good performance on scenes with man-made structures.