Feature Extraction Using Information-Theoretic Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Spectral features for Arabic word recognition
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 06
On image matrix based feature extraction algorithms
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
This paper presents a features extraction module for isolated handwritten Arabic characters. The collected core features are based on pixels orientations according to Freeman chain code. The input to this module is Arabic character (in its basic-shapes i.e. without diacritics). The features extractor module, fed with a skeleton of an isolated character basic-shape, yields global and local features. Feature vector of 12 elements are used. Two features are global while the remaining 10 elements are locals. Neural network classifier is used for aggregating the features for classification decision making.