Automatic video scene segmentation to separate script and recognition

Abstract

Text or character detection in images or videos is a challenging problem to achieve video contents retrieval. In this paper work we propose to improved VTDAR (Video Text Detection and Recognition) Template Matching algorithm that applied for the automatic extraction of text from image and video frames. Video Optical Character Recognition using template matching is a system model that is useful to recognize the character, upper, lower alphabet, digits& special character by comparing two images of the alphabet. The objectives of this system model are to develop a model for the Video Text Detection and Recognition system and to implement the template matching algorithm in developing the system model. The template matching techniques are more sensitive to font and size variations of the characters than the feature classification methods. This system tested the 50 videos with 1250 video keyframes and text line 1530. In this system 92.15% of the Character gets recognized successfully using Texture-based approaches to automatic detection, segmentation and recognition of visual text occurrences in images and video frames.