Connected component based approach for text extraction from color image

Abstract

Image based text extraction is one of the fastest growing research areas in the field of multimedia technology. The extraction of text from a complex or more colorful images is a challenging problem. Text data present in images contains useful information for habitual explanation, indexing, and structuring of images. Extraction of this information involves detection, localization, tracking, extraction, enhancement, and recognition of the text from a given image. For fast extracting text from images, we have proposed a connected component based approach which identifies more accurately for small or large texts in the image. The text extraction process starts with conversion of the color image to gray scale image and then it converts the gray scale image into a binary image. Then each text region is marked and the text is extracted from the image. Finally, the extracted text is written into another gray scale image. The experimental results demonstrate that the performance of the proposed method is superior compared to some recent approaches.