Combination of OCR engines for page segmentation based on performance evaluation
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessRestricted access - publisher's policy
In this paper we present a method to improve the performance of individual page segmentation engines based on the combination of the output of several engines. The rules of combination are designed after analyzing the results of each individual method. This analysis is performed using a performance evaluation framework that aims at characterizing each method according to its strengths and weaknesses rather than computing a single performance measure telling which is the "best" segmentation method.
CitationFerrer, M.; Valveny, E. Combination of OCR engines for page segmentation based on performance evaluation. A: International Conference on Document Analysis and Recognition. "Ninth International Conference on Document Analysis and Recognition, 2007: ICDAR 2007: 23-26 Sept. 2007, Curitiba, Paraná, Brazil: proceedings". Curitiba, Paraná: Institute of Electrical and Electronics Engineers (IEEE), 2007, p. 784-788.
|Combination of ... Performance Evaluation.pdf||Combination of OCR Engines for Page Segmentation Based on Performance Evaluation||3.314Mb||Restricted access|