Human recognition is much more robust than machine recognition in dealing with rotated and noisy patterns. In this paper, we present a multi-channel neural network (MCNN) approach for handwritten digit recognition based on the human recognition experience in the hope of achieving human-like performance. In this approach, three neural network modules are trained individually by using three different set of features, intensity-based, rotation invariant, and noise deducted features. The outputs of these three modules are then combined by a combination neural network which is trained separately. Experimental results on a database of 1900 digit patterns written by 190 people show that a recognition rate of 89.5% is obtained on an independent test set that includes both the rotated and noisy data.
|Number of pages||4|
|Journal||Proceedings - IEEE International Symposium on Circuits and Systems|
|Publication status||Published - 1 Jan 1997|
|Event||Proceedings of the 1997 IEEE International Symposium on Circuits and Systems, ISCAS'97. Part 4 (of 4) - Hong Kong, Hong Kong|
Duration: 9 Jun 1997 → 12 Jun 1997
ASJC Scopus subject areas
- Electrical and Electronic Engineering