Integrated Segmentation and Recognition of Hand-Printed Numerals

Abstract

Neural network algorithms have proven useful for recognition of individ(cid:173) ual, segmented characters. However, their recognition accuracy has been limited by the accuracy of the underlying segmentation algorithm. Con(cid:173) ventional, rule-based segmentation algorithms encounter difficulty if the characters are touching, broken, or noisy. The problem in these situations is that often one cannot properly segment a character until it is recog(cid:173) nized yet one cannot properly recognize a character until it is segmented. We present here a neural network algorithm that simultaneously segments and recognizes in an integrated system. This algorithm has several novel features: it uses a supervised learning algorithm (backpropagation), but is able to take position-independent information as targets and self-organize the activities of the units in a competitive fashion to infer the positional information. We demonstrate this ability with overlapping hand-printed numerals.