Degraded Text Recognition Using Word Collocation and Visual Inter-Word Constraints

Degraded Text Recognition Using Word Collocation and Visual Inter-Word Constraints Tao Hong and Jonathan J. Hull Center of Excellence for Document Analysis and Recognition Department of Computer Science State University of New York at Buffalo Buffalo, New York 14260 taohong@cs.buffalo, edu hull©cs.buffalo, edu Abstract Given a noisy text page, a word recognizer can generate a set of candidates for each word image. A relaxation algorithm was proposed previously by the authors that uses word collocation statistics to select the candidate for each word that has the highest probability of being the correct decision. Because word collocation is a lo- cal constraint and collocation data trained from corpora are usually incomplete, the algorithm cannot select the correct candidates for some images. To overcome this limitation, contextual information at the image level is now exploited inside the relaxation algorithm. If two word images can match with each other, they should have same symbolic identity. Visual inter-word rela- tions provide a way to link word images in the text and to interpret them systematically. By integrating visual inter-word constraints with word collocation data, the performance of the relaxation algorithm is improved. Introduction Word collocation is one source of information that has been proposed as a useful tool to post-process word recognition results([1, 4]). It can be considered as a constraint on candidate selection so that the word can- didate selection problem can be formalized as an in- stance of constraint satisfaction. Relaxation is a typ- ical method for constraint satisfaction problems. One of the advantages of relaxation is that it can achieve a global effect by using local constraints. Previously, a probabilistic relaxation algorithm was proposed for word candidate re-evaluation and selection([2]). The basic idea of the algorithm is to use word collocation constraints to select the word candi- dates that have a high probability of occurring simulta- neously with word candidates at other nearby locations. The algorithm runs iteratively. In each iteration, the probability of each word candidate is upgraded based on its previous probability, the probabilities of its neigh- bors and word collocation data. The initial probability of each word candidate is provided by a word recognizer. The relaxation process terminates when the probabil- ity of each word candidate becomes stable. After relax- ation finishes, for each word image, the word candidate with highest probabilistic score will be selected as the decision word. Because the window size of word collocation is usually small, word collocation is a local constraint. Because word collocation data are derived from text corpora, it usually is incomplete and unbalanced. Those properties limit the usefulness of word collocation for candidate se- lection. By analyzing the performance of the algorithm, three sources of errors were identified: (1). the local context cannot provide enough information to distin- guish the competitive candidates; (2). word collocation data trained from corpora are not complete so that it does not include the statistical data needed to select the correct candidate; and (3). word collocation data trained from unbalanced corpora are biased so that …

Content truncated to 500 words