Skip to Main Content
The main objective of this paper is to verify bank cheques by using account number and account holder's signature present on the cheque image. Main problem is to exact localization of active regions among non-active contours in the image. Here, we locate the regions based on the prior knowledge of Cartesian coordinate space. It further involves various steps such as Gray-Scale conversion, Segmenting contour, Inner-localization of account number, Feature Extraction and Verification. Gray-scale conversion has been performed on cheque images for reducing dimensionality of cheque size, which are required for further processing. Segmentation and localization are employed together to extract active-regions-of-interests such as account number and signature. Furthermore, segmented account numbers are obtained into individual digits using inner-localization. Feature Extraction is implemented on both account number and signature with trained images using Hamming distance measures (HDM). Finally the verification is processed to identify the matching. Trained and testing features were compared.