Title: Finding URLs in images by text extraction in DCT domain, recognition and matching in dictionary

Authors: Antoaneta Popova; Johan Garcia; Nikolay Neshov; Ivo Draganov; Darko Brodic

Addresses: Deceased; formerly of: Faculty of Telecommunications-Audio and Video Technologies Division, Technical University of Sofia, 8 Kliment Ohridski Blvd., Sofia 1000, Bulgaria ' Computer Science Department, University of Karlstad, 651 88 Karlstad, Sweden ' Faculty of Telecommunications-Audio and Video Technologies Division, Technical University of Sofia, 8 Kliment Ohridski Blvd., Sofia 1000, Bulgaria ' Faculty of Telecommunications-Audio and Video Technologies Division, Technical University of Sofia, 8 Kliment Ohridski Blvd., Sofia 1000, Bulgaria ' Technical Faculty in Bor, University of Belgrade, Vojske Jugoslavije 12, 19210 Bor, Serbia

Abstract: Automatic and fast detection of overlaid URLs and text in images and video with adult content can be an important aid for children protection in the internet. In this paper, we propose a method and associated algorithms for URL and text extraction from images and video frames based on combined processing in the compressed and spatial domains. It includes an improved approach for text detection and extraction in the discrete cosine transform (DCT) domain. It also includes an adaptive local binarisation with background compensation in the spatial domain to create an image appropriate for optical character recognition (OCR). As a final step, text recognition and verification is performed by matching to an URL dictionary. The proposed algorithms are quantitatively and qualitatively tested against other contemporary techniques, and encouraging results are obtained. Experimental tests over 3,000 images have been conducted highlighting the efficiency of the proposed approach.

Keywords: text extraction; URL extraction; DCT domain; discrete cosine transform; image adaptive binarisation; local contrast; text recognition; OCR; optical character recognition; off centre-surround cells; document image analysis; dictionary matching; URLs; sexual images; video content; adult content; child protection; internet regulation; URL dictionary.

DOI: 10.1504/IJRIS.2015.070916

International Journal of Reasoning-based Intelligent Systems, 2015 Vol.7 No.1/2, pp.78 - 92

Published online: 31 Jul 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article