Textons, the fundamental elements in preattentive vision and perception of textures
Readings in computer vision: issues, problems, principles, and paradigms
Neural networks and natural intelligence
Information processing strategies and pathways in the primate retina and visual cortex
An introduction to neural and electronic networks
Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
The feature extraction and analysis of flaw detection and classification in BGA gold-plating areas
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
A neural network architecture for the segmentation and recognition ofcolored and textured visual stimuli is presented. The architecture is basedon the Boundary Contour System and Feature Contour System (BCS/FCS) of S.Grossberg and E. Mingolla. The architecture proposes abiologically-inspired mechanism for color processing based on antagonistinteractions. It suggests how information from different modalities (i.e.color or texture) can be fused together to form a coherent segmentation ofthe visual scene. It identifies two stages of visual pattern recognition,namely, a global preattentive recognition of the visual scene followed by alocal attentive recognition within a particular visual context. The globaland local classification and recognition of visual stimuli use ART-typemodels of G. Carpenter and S. Grossberg for pattern learning andrecognition based on color and texture. One example is presentedcorresponding to an figure-figure separation task. The architectureprovides a mechanism for segmentation, categorization and recognition ofimages from different classes based on self-organizing principles ofperception and pattern recognition.