Extraction of Text from Cheque Using ML and OCR

Banking system worldwide suffers from huge dependencies upon manpower and written documents thus making conventional banking processes tedious and time-consuming. Existing methods for processing transactions made through cheques causes a delay in the processing as the details have to be manually entered. Optical Character Recognition (OCR) finds usage in various fields of data entry and identification purposes. The technology of optical character recognition (OCR) was used to transform printed text into editable text (cheque image to text). Text preparation and segmentation techniques can influence OCR accuracy. Because of the image's varying size, style, orientation, and intricate backdrop, retrieving text from it might be challenging at times. We begin by discussing the Optical Character Recognition (OCR) technology, its design, and the experimental results of OCR conducted by Tesseract on medical data images. We end this work with a comparison of this tool with other detection methods in order to improve detection accuracy.

Keywords: Text Extraction, Deep learning, Image processing, Tesseract, OCR technology, OpenCV.