Text Extraction from Images Using Connected Component Method

Arvind Belure; Mohamed Rafi

Abstract

Text information from image serves as an important clue for many image based applications. it has been used in many different applications such as; document analysis, vehicle licence plate extraction, content based information indexing, To name a few, the detection and extraction of text regions in images is a well-known problem in computer vision and image processing. However, variation of these texts due to differences in size, orientation style, and alignment, as well as low image contrast and complex background make problem of automatic text detection and extraction tremendously difficult and challenging one. Here the connected component method applied on the dataset which includes the images which categorized according to the language of the scene textcaptured.

Abstract

Keywords