DocumentCode :
1797303
Title :
V4 neural network model for visual saliency and discriminative local representation of shapes
Author :
Hui Wei ; Zheng Dong
Author_Institution :
Dept. of Comput. Sci., Fudan Univ., Shanghai, China
fYear :
2014
fDate :
6-11 July 2014
Firstpage :
3420
Lastpage :
3427
Abstract :
Visual area V4 lies in the middle of the ventral visual pathway in the primate brain. It is an intermediate stage in the visual processing for object discrimination. It plays an important role in the neural mechanism of visual attention and shape recognition. V4 neurons exhibit selectivity for salient features of contour conformation. In this paper, we propose a novel model of V4 neurons based on a multilayer neural network inspired by recent studies on V4. Its low-level layers consist of computational units simulating simple cells and complex cells in the primary visual cortex. These layers extract preliminary visual features including edges and orientations. The V4 computational units calculate the entropy of the extracted features as a measure of visual saliency. The salient features are then selected and encoded with a layer of Restricted Boltzmann Machine to generate an intermediate representation of object shapes. The model was evaluated in shape distinction, handwritten digits classification, feature detection, and feature matching experiments. The results demonstrate that this model generates discriminative local representation of object shapes. It provides clues to understand the high level representation of visual stimuli in the brain.
Keywords :
Boltzmann machines; brain; feature extraction; handwritten character recognition; image classification; image matching; image representation; shape recognition; V4 computational units; V4 neural network model; computational units; contour conformation; discriminative local shape representation; feature detection; feature matching experiments; handwritten digits classification; multilayer neural network; neural mechanism; object discrimination; primary visual cortex; primate brain; restricted Boltzmann machine; shape distinction; shape recognition; ventral visual pathway; visual attention; visual saliency; visual stimuli; Brain modeling; Computational modeling; Entropy; Gratings; Neurons; Shape; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks (IJCNN), 2014 International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-6627-1
Type :
conf
DOI :
10.1109/IJCNN.2014.6889392
Filename :
6889392
Link To Document :
بازگشت