Issue No. 11 - November (1999 vol. 21)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.809116
<p><b>Abstract</b>—A robust system is proposed to automatically detect and extract text in images from different sources, including video, newspapers, advertisements, stock certificates, photographs, and checks. Text is first detected using multiscale texture segmentation and spatial cohesion constraints, then cleaned up and extracted using a histogram-based binarization algorithm. An automatic performance evaluation scheme is also proposed.</p>
Text reading, character recognition, multimedia indexing, text detection, texture segmentation, filters, hierarchical processing, binarization, connected-components.
V. Wu, R. Manmatha and E. M. Riseman, "TextFinder: An Automatic System to Detect and Recognize Text In Images," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 21, no. , pp. 1224-1229, 1999.