An Efficient Text Extraction Algorithm in Complex Images

This paper proposed an efficient text extraction algorithm in complex images. Earlier a number of methods have been proposed for text extraction in different types of images and video Text images. It elaborates a robust and efficient algorithm for text extraction in different types of text images. Essentially it works in three steps: edge map generation using Line edge detection mask, text area segmentation using vertical and the horizontal projection with Heuristic Filtering. At last, text recognition has been carried out on images and video frames. Different experiments were carried out to evaluate the performance of the proposed algorithm were compared with other existing methods. Finally it is verified that the proposed method is effective and useful. Existing and proposed methods were analyzed using various parameters like a precision and recall rates which determine the success and limitation of our methods. This paper has obtained a 99.61 % recall rate and its precision rate is 96.20% having an average computational time of 1.31 second /frames.