An image representation method based on retina mechanism for the promotion of SIFT and segmentation

Authors:
Hui Wei;Bo Lang;Qing-Song Zuo
Affiliations:
Department of Computer Science and Technology, University of Fudan, Shanghai, China;Department of Computer Science and Technology, University of Fudan, Shanghai, China;Department of Computer Science and Technology, University of Fudan, Shanghai, China
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V
Year:
2012

Citing 9
Cited 0

Are Edges Incomplete?

International Journal of Computer Vision - Special issue on computer vision research at NEC Research Institute
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A possible mechanism of zero-crossing detection using the concept of the extended classical receptive field of retinal ganglion cells

Biological Cybernetics
Geometric Context from a Single Image

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Boundary Extraction in Natural Images Using Ultrametric Contour Maps

CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
3-D Depth Reconstruction from a Single Still Image

International Journal of Computer Vision
Contour Detection and Hierarchical Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
An efficient color representation for image retrieval

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a bio-inspired neural network was constructed. It could represent images effectively and provide a processing method for image understanding. Our model adopted the retinal ganglion cells (GCs) and their non-classical receptive field (nCRF) can dynamic self-adjusts according to the characteristics of the image. Extensive experimental evaluations to demonstrate that this kind of representation method was able to make for SIFT detector for focus on foreground object more correctly, and promote the result of image segmentation significantly.