Title :
Image recognition with fuzzy ADALINE neurons
Author :
Paul, B. ; Konar, A. ; Mandal, A.K.
Author_Institution :
Dept. of Electron. & Telecommun. Eng., Jadavpur Univ., Calcutta, India
Abstract :
The paper aims at extending the scope of application of Widrow-Hoff´s ADALINE model from binary to gray level (fuzzy) pattern recognition. The condition of stability for the extended ADALINE model is derived, and the algorithm for training the multilayer feedforward neural net consisting of ADALINE neurons is presented. The time required for training the neural net is insignificantly small. The scheme for the recognition of objects from their gray level images using the fuzzy ADALINE model is translation, rotation and size invariant
Keywords :
feedforward neural nets; fuzzy neural nets; learning (artificial intelligence); object recognition; Widrow-Hoff; binary to gray level images; fuzzy ADALINE neurons; learning algorithm; multilayer feedforward neural net; pattern recognition; recognition recognition; Biomedical signal processing; Image recognition; Linearity; Multi-layer neural network; Neural networks; Neurons; Pattern recognition; Retina; Signal processing algorithms; Stability;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.682374
