Intelligent word recognition

About: Intelligent word recognition is a research topic. Over the lifetime, 2480 publications have been published within this topic receiving 45813 citations.

Script independent handwritten numeral recognition

Abstract: This paper presents an off-line handwritten recognition system for numerals that is independent of the script. Numeral set from five major Indian language and English language are selected for recognition. Wavelets that have been progressively used in pattern recognition and many character recognition systems are used in our system to extract the features of numerals. Neural classifiers have been effectively used for the classification of numerals. An overall recognition rate of 92.3% has been obtained. The recognition scheme in general can be used for any language and particularly for applications like postal address automation.

Exploiting Chinese character models to improve speech recognition performance

Abstract: The Chinese language is based on characters which are syllabic in nature. Since languages have syllabotactic rules which govern the construction of syllables and their allowed sequences, Chinese character sequence models can be used as a first level approximation of allowed syllable sequences. N-gram character sequence models were trained on 4.3 billion characters. Characters are used as a first level recognition unit with multiple pronunciations per character. For comparison the CU-HTK Mandarin word based system was used to recognize words which were then converted to character sequences. The character only system error rates for one best recognition were slightly worse than word based character recognition. However combining the two systems using log-linear combination gives better results than either system separately. An equally weighted combination gave consistent CER gains of 0.1-0.2% absolute over the word based standard system. Copyright © 2009 ISCA.

Deep-Belief-Network Based Rescoring Approach for Handwritten Word Recognition

Abstract: This paper presents a novel verification approach towards improvement of handwriting recognition systems using a word hypotheses rescoring scheme by Deep Belief Networks (DBNs) A recurrent neural network based sequential text recognition system is used at first to provide the N-best recognition hypotheses of word images Word hypotheses are aligned with the word image to obtain the character boundaries Then, a verification approach using a DBN classifier is performed for each character segments DBNs are recently proved to be very effective for a variety of machine learning problems The character probabilities obtained from DBNs are next combined with the base recognition system Finally, the N-best recognition hypotheses list is reranked according to the new score We have compared our proposed approach with an MLP based rescoring approach on the Rimes dataset The results obtained show that the verification approach using DBNs outperforms that of MLP systems

Handwriting recognition system and method using compound characters for improved recognition accuracy

Abstract: A handwriting recognition system and method whereby various character sequences (which are typically “slurred” together when handwritten) are each modelled as a single character (“compound character model”) so as to provide increased decoding accuracy for slurred handwritten character sequences. In one aspect of the present invention, a method for generating a handwriting recognition system having compound character models comprises the steps of: providing an initial handwriting recognition system having individual character models; collecting and labelling a set of handwriting data; aligning the labelled set of handwriting data; generating compound character data using the aligned handwriting data; and retraining the initial recognition system with the compound character data to generate a new recognition system having compound character models. Once these compound character models are trained, they may be used to accurately decode slurred handwritten character sequences for which compound character models were previously generated. Once recognized, the compound characters are expanded into the constituent individual characters comprising the compound character.