Title :
Connectionist network for feature extraction and classification of English alphabetic characters
Author :
Khobragade, Shyam W. ; Ray, Ajoy K.
Author_Institution :
Tata Inst. of Fundamental Res., Pune, India
Abstract :
An nonadaptive connectionist architecture based feature extractor (CAFE) for English alphabetic patterns is presented. Two different adaptive connectionist networks, i.e., the multi-layer backpropagation network (MBPN) and the counter propagation network (CPN) were implemented for classification of the patterns. Their performance analysis is reported. The system is tolerant to translation and deformation and is observed to classify noisy and distorted patterns correctly
Keywords :
backpropagation; character recognition; feature extraction; feedforward neural nets; CAFE; English alphabetic characters; counter propagation network; deformation; distorted patterns; feature extraction; multi-layer backpropagation network; nonadaptive connectionist architecture; performance analysis; translation; Adaptive systems; Counting circuits; Feature extraction; Neural networks; Optical arrays; Optical distortion; Optical noise; Optical sensors; Performance analysis; Sensor arrays;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298796
