Ote-OCR based text recognition and extraction from video frames

Abstract

The goal of this paper is to provide a new method to detect and recognize the text from the video frames. The task performed is divided into three step approach that combines the text detection and text recognition from the video frame. The video frame creation involves in dividing the video into an individual frames. The individual frame is grabbed and passed to the rest two phases. The text detection is a two-step approach, which involves text localization phase and the text verification phase. The text recognition involves in text verification phase and the optical character recognition phase. The final outcome of this paper is the detection of the text from the video frames in a word file. Experimental results demonstrating the proposed approach was also included, which shows the accuracy level of Optical character recognition(OCR) in terms of text extraction.