Efficient shape-LUT classification for document image restoration

Tayo Obafemi-Ajayi; Gady Agam; Ophir Frieder

doi:10.1117/12.806168

Translator Disclaimer

19 January 2009 Efficient shape-LUT classification for document image restoration

Tayo Obafemi-Ajayi, Gady Agam, Ophir Frieder

Author Affiliations +

Proceedings Volume 7247, Document Recognition and Retrieval XVI; 72470N (2009) https://doi.org/10.1117/12.806168
Event: IS&T/SPIE Electronic Imaging, 2009, San Jose, California, United States

Abstract

In previous work we showed that Look Up Table (LUT) classifiers can be trained to learn patterns of degradation and correction in historical document images. The effectiveness of the classifiers is directly proportional to the size of the pixel neighborhood it considers. However, the computational cost increases almost exponentially with the neighborhood size. In this paper, we propose a novel algorithm that encodes the neighborhood information efficiently using a shape descriptor. Using shape descriptor features, we are able to characterize the pixel neighborhood of document images with much fewer bits and so obtain an efficient system with significantly reduced computational cost. Experimental results demonstrate the effectiveness and efficiency of the proposed approach.

Citation Download Citation

Tayo Obafemi-Ajayi, Gady Agam, and Ophir Frieder "Efficient shape-LUT classification for document image restoration", Proc. SPIE 7247, Document Recognition and Retrieval XVI, 72470N (19 January 2009); https://doi.org/10.1117/12.806168

ACCESS THE FULL ARTICLE