Cited 2 time in
Cited 3 time in
A Perceptual Visual Feature Extraction Method Achieved by Imitating V1 and V4 of the Human Visual System
- A Perceptual Visual Feature Extraction Method Achieved by Imitating V1 and V4 of the Human Visual System
- Kim, Sungho; Kwon, Soon; Kweon, In So
- DGIST Authors
- Kwon, Soon
- Issue Date
- Cognitive Computation, 5(4), 610-628
- Article Type
- Curvature; Detectors; Dominant Orientation; Encoding (Symbols); Feature Extraction; Human Visual System; Object Recognition; Object Recognition Tests; Perceptual Feature; Shape Encoding; Visual Feature; Visual Feature Extraction; Visual Part Detector
- In this paper, we present a new shape encoding method for object recognition. We first introduce a neuro-physiologically 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. © 2012 Springer Science+Business Media New York.
- Related Researcher
computer vision; deep learning; autonomous driving; parallel processing; vision system on chip
There are no files associated with this item.
- Convergence Research Center for Future Automotive Technology1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.