Single Slice Grouping Mechanism for Recognition of Cursive Handwritten Courtesy Amounts of Malaysian Bank Cheques

Abstract

Mechanism to group single slice for recognition involves the process of cutting vertically across an image slice by slice, group every slice at a certain width and tested for recognition using a trained Neural network. The image contains cursive handwritten courtesy Amounts of Malaysian bank cheques. A three layer neural Network architecture with the new error function of Backpropagation learning algorithm is used. This approach yields good recognition results with faster convergence rates.