AN EFFICIENT TEXT EXTRACTION METHOD FOR GRAY SCALE IMAGE USING MORPHOLOGICAL OPERATORS

Abstract

The detection and extraction of scene and caption (artificial) text from unconstrained,, general-purpose image is an important research problem in the context of content-based retrieval and summarization of visual information. The current state of the art for extracting text from image either makes simplistic assumptions as to the nature of the text to be found, or restricts itself to a subclass of the wide variety of text that can occur in image. Most published methods only work on captions text that is composited on the image. Also, these methods have been developed for extracting text from images that have been applied to video frames. They do not use the additional temporal information in image to good effect. In addition, no comprehensive system has been developed which can robustly detect a large variety of text from image. This dissertation presents a reliable system for extracting text from unconstrained, general-purpose image. In developing methods for extraction of text from images it was observed that no single algorithm could detect all forms of text. This dissertation presents a morphological technique for text extraction from images. It makes use of edge information to extract textual blocks from gray scale images. It aims at detecting textual regions on heavy noise infected images and separate them from graphical regions. The proposed morphological technique is. insensitive to noise, skew and text orientation. From using the edge properties, it can successfully retrieve directional placed text blocks easily. The system can operate on TIFF images. It is also possible to operate the methods individually and independently. It is implemented on C++ platform.