Title :
Perceptrons for image recognition
Author :
Lee, Chung-Nim ; Goh, Seung-Cheol
Author_Institution :
Dept. of Math., Pohang Inst. of Sci. & Technol., South Korea
Abstract :
The authors describe perceptrons with two hidden layers for recognizing convexity, connectedness and simple connectedness of a digital image. In fact, the perceptron for connectedness is designed to recognize the connectedness of an arbitrary graph. The perceptrons have been implemented in the C language on a Solbourne 5/600 workstation in a UNIX environment. They have been tested on many input digital images in a 16×16 grid
Keywords :
neural nets; pattern recognition; C language; Solbourne 5/600 workstation; UNIX environment; arbitrary graph; connectedness; convexity; digital image; hidden layers; image recognition; neural nets; pattern recognition; perceptrons; Character recognition; Digital images; Feedforward neural networks; Image recognition; Lattices; Mathematics; Neural networks; Neurons; Sensor arrays; Terminology;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170677
