Enhanced structural perceptual feature extraction model for Arabic literal amount recognition

Abstract

One of the important applications for document recognition is the bank cheque processing, which is known as cheque literal amount. A few studies focused on Arabic bank cheque processing system compared to other systems, such as Latin and Chinese. The Arabic script has a number of characteristics that makes it unique among other scripts. It is known that humans are the best pattern recognisers. As such, the features detected while human reads the script can get better recognition rates. Therefore, proposing human reading inspired features (which are called perceptual features) can overcome the unique technical challenges in Arabic literal amount recognition. In this paper, the enhanced structural perceptual feature extraction model (PFM) has been proposed. Two main groups of features, which are the components and dots features and the loops and characters shapes features were combined to construct the PFM. This model was evaluated on standard Arabic Handwriting DataBase (AHDB) dataset. The PFM results outperformed the results reported in the previous studies.