Search Articles

Home / Articles

PERFORMANCE OPTIMIZATION OF TEXT EXTRACTION TECHNIQUE FOR COMPLEX DEGRADED IMAGES

. Abhishek Gupta, Ramapati Mishra and Ashutosh Kumar Singh


Abstract

In recent years, there has been a growing demand to preserve historical documents, books and convert them into digital format. Moreover, the fast development of data innovation and the speedy propagation of the Internet have also lead to the huge amount of image and video data. The texts present in the image and video help us in the analysis of those images and videos as well as used in indexing, archiving, and retrieval. An image can be easily affected by various noises like Gaussian noise, salt and pepper noise, speckle noise etc. To remove these different noises from images various image filtering algorithms such as Gaussian filter, mean filter, median filter etc. are used. The effect of various pre-processing techniques like Thresholding, Morphology, and Blurring processes to optimize the text extraction technique are analysed in this article. The results obtained from the experiment show that the pre-processing techniques certainly enhance the document’s visual and structural quality.

Keywords- Complex degraded image, Thresholding, Morphology, Edge detection, OCR

Download :