A Perceptual Visual Feature Extraction Method Achieved by Imitating V1 and V4 of the Human Visual System

Title
A Perceptual Visual Feature Extraction Method Achieved by Imitating V1 and V4 of the Human Visual System
Author(s)
김성호권순[권순]권인소[권인소]
Keywords
RECEPTIVE-FIELDS; CURVATURE; SYMMETRY; CORTEX; REPRESENTATION; DESCRIPTORS; INFORMATION; SELECTION; PATHWAY; SIFT
Issue Date
201312
Publisher
SPRINGER
Citation
COGNITIVE COMPUTATION, v.5, no.4, pp.610 - 628
Abstract
In this paper, we present a new shape encoding method for object recognition. We first introduce a neurophysiologically inspired visual part detector and shape encoder. The optimal form of the visual part detector is a combination of a circular symmetry detector and a corner-like structure detector. A perceptually novel shape descriptor, known as the curvature-orientation descriptor, is then discussed. This descriptor encodes the curvature as well as the dominant orientation. The perceptual shape encoder enhances the performance of feature matching and object recognition taken from standard test images. The results from the repeatability and object recognition tests validate the feasibility of the proposed perceptual feature extraction method.
URI
http://hdl.handle.net/YU.REPOSITORY/28045http://dx.doi.org/10.1007/s12559-012-9194-8
ISSN
1866-9956
Appears in Collections:
공과대학 > 전자공학과 > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE