Title :
A modular neural system for handwritten alphabet recognition using invariant moment-based features
Author :
Benromdhane, Saida ; Salam, F.M.A.
Author_Institution :
Dept. of Electr. Eng., Michigan State Univ., East Lansing, MI, USA
Abstract :
A recognition system for identifying handwritten alphabets using a specific artificial neural network structure is described. Layers of feedforward networks preprocess the alphabets by extracting features that enhance the characters´ dissimilarity. The features approximate the moments and moment invariants which are invariant to translation, rotation, and scaling of the processed alphabets. The collective tasks of the feedforward network modules integrate feature extraction preprocessing with classification
Keywords :
character recognition; feature extraction; feedforward neural nets; artificial neural network structure; character recognition; classification; feature extraction; feedforward networks; handwritten alphabet recognition; invariant moment-based features; modular neural system; moment invariants; rotation; scaling; translation; Artificial neural networks; Data mining; Feature extraction; Feedforward neural networks; Handwriting recognition; Logistics; Neural networks; Neurons; Pixel; Testing;
Conference_Titel :
Systems Engineering, 1992., IEEE International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-0734-8
DOI :
10.1109/ICSYSE.1992.236883