Localizing and Analyzing the Infographics in Document Using Deep Learning

Abstract

In explaining complicated concepts, infographics are a far more effective medium of communication than regular prose. In recent years, deep learning has seen a lot of success in a range of applications requiring pattern identification and artificial intelligence. One of these applications is image recognition. There are many kinds of infographics that may be used in resumes and CVs to demonstrate the degree of competence. The objective was to identify those infographics that were already existing in the CV and to determine the word that corresponded to each infographic before attempting to measure each infographic using numeric characters. The YOLO algorithm was used to identify infographics, while OCR was utilized in order to identify associated words. The filled component of the infographic was distinguished from the unfilled area by using the image intensity histogram analysis, thresholding and contours.