Recognizing Text in Low Resolution Born-Digital Images

摘要

Since born-digital images usually have low resolution, they are distinctly different from natural scene images. Extracting text information from born-digital images has been an increasing interest in document analysis and recognition field. We propose an automatic method to recognize word from low-resolution color image. First, the image is smoothed by using the bilateral filter, which preserves edge information. Then, it is binarized using global thresholding method and cleaned from noise. Finally, the open source Optical Character Recognition engine, with the incorporation of a post-processor trained on knowledge of English language, is applied to obtain meaningful words from the binary image. We experiment the proposed system on ICDAR 2011 and music sheet dataset, and the result shows better performance than several previous works.