Automation of Cheque Transaction using Deep Learning and Optical Character Recognition

Abstract

Despite of swift advancements happening in digital technology, financial institutions like banks still rely upon conventional medium of processing the bank cheques by humans. The process is cumbersome and takes couple of days for actual transfer of money which involves verification by the intermediaries. This leads to high time and costs. In this paper, we propose an automated system which extracts relevant details on a bank cheque like Payee Name, Amount, Date, Bank Name using Optical Character Recognition and Deep Learning and verifies the signature on the cheque with the existing signature stored in the database using feature extraction and principal component analysis. The signature for a new user is stored using it's hash value for security purposes. The proposed system uses modified convolution neural network to extract the handwritten content on cheque leaf where in IAM dataset is used to train the model and get the optimized results. This system will facilitate the process and lead to reduction in time and costs. The efficiency and performance is measured on the self generated data set of bank cheques.