Abstract

Handwritten digit string recognition is more sophisticated than determining a single digit individually. The repeated recognition of single digits is applicable for recognizing a handwritten digit string. A similar approach is exercised in this paper. The proposed approach could be advantageous in banks to recognize the digits written on the cheque and processes the cheque. Further, the banks could send the audio message of the recognized handwritten digits to the cheque issuer for confirmation before cashing the cheque. The pro-posed model is developed in the python platform and is lightweight, robust, and cross-platform. In this approach, we have trained a neural network model with MNIST handwritten digits dataset and some samples of our own for recognizing the handwritten digits. The Convolution Neural network models are widely used in the present-day technologies for object recognition, image processing, segmentation, face recognizing and also many identifications related tasks. The CNN model used in the project determines the digit in the image provided. Finally, the system plays the [pre-]recorded audio and displays the output for the recognized digits in the given digit string.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.