RECEIPT MANAGEMENT PORTAL ON SMART PHONE USING OCR ZIA

Abstract

The objective of this project is to develop image recognition mobile application to recognize handwriting on receipts and management of those receipts. This report explores different techniques used for the recognition of handwriting and management of receipts. Different stages involving image processing like the preprocessing stage, segmentation and feature extraction will be studied and discussed. Finally the end product will be developed in the software called Sencha touch. Several features have been addressed in this project. For example De-skew, Despeckle, Binarization, Line removal, Layout analysis or "zoning" , Line and word detection , Normalize aspect ratio and scale and Segmentation. Segmentation of fixed-pitch fonts is accomplished relatively simply by aligning the image to a uniform grid based on where vertical grid lines will least often intersect black areas. Recommendations for future development and conclusions are also included in the Report.