Improving OCR accuracy through combination: a survey
John C. Handley · 2002
Optical character recognition is perhaps the most studied application of pattern recognition. Recent work has increased accuracy in two ways. Combination of individual classifier outputs overcomes deficiencies of features and trainability of single classifiers. OCR systems take page images as input and output strings of recognized characters. Due to character segmentation errors, characters can be split or merged preventing output combination character-by-character. Merging of output strings is done using string alignment algorithms.