Goal-oriented evaluation of binarization algorithms for historical document images
Binarization is of significant importance in document analysis systems. It is an essential first step, prior to further stages such as Optical Character Recognition (OCR), document segmentation, or enhancement of readability of the document after some restoration stages. Hence, proper evaluation of binarization methods to verify their effectiveness is of great value to the document analysis community. In this work, we perform a detailed goal-oriented evaluation of image quality assessment of the 18 binarization methods that participated in the DIBCO 2011 competition using the 16 historical document test images used in the contest. We are interested in the image quality assessment of the outputs generated by the different binarization algorithms as well as the OCR performance, where possible. We compare our evaluation of the algorithms based on human perception of quality to the DIBCO evaluation metrics. The results obtained provide an insight into the effectiveness of these methods with respect to human perception of image quality as well as OCR performance. © 2013 SPIE-IS&T.
Document image analysis, evaluation, Human-machine interactions, image enhancement, perception quantification, quality metrics
Obafemi-Ajayi, Tayo, and Gady Agam. "Goal-oriented evaluation of binarization algorithms for historical document images." In Document Recognition and Retrieval XX, vol. 8658, p. 86580S. International Society for Optics and Photonics, 2013.
Proceedings of SPIE - The International Society for Optical Engineering