Fast Two-Level HMM Decoding Algorithm for Large Vocabulary Handwriting Recognition

Koerich, Alessandro L.; Sabourin, Robert; Suen, Ching Y.

doi:10.1109/iwfhr.2004.42

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Os HMMs têm sido amplamente utilizados em sistemas de reconhecimento de palavras manuscritas [50], [23], [51], [52], [19], [53], [54], [55], [56], [25], [57], [58], [36], [59], [60], [61], [62], [63], [64].…”

Section: B Modelos De Markov Escondidosunclassified

Introdução ao Reconhecimento de Palavras Manuscritas

Veloso¹,

Madeiro²

2012

RTIC

View full text Add to dashboard Cite

Resumo-O avanço do conhecimento, a expansão da memória e a comunicação estão entre os benefícios proporcionados pela escrita, que constitui-se em um dos objetos daárea de processamento de documentos. Dentre os desenvolvimentos relacionados a estaárea, podem ser citados: sistemas de reconhecimento de caracteres manuscritos, de assinaturas, de numerais manuscritos, de palavras manuscritas e sistemas de filtragem frente-verso. Este artigo apresenta uma introdução ao reconhecimento de palavras manuscritas. São abordadas etapas importantes do sistemas de reconhecimento: pré-processamento, segmentação e classificação. O artigo aborda, ainda, técnicas utilizadas para o propósito do reconhecimento, com destaque para os modelos de Markov escondidos, as redes neurais artificiais e os métodos híbridos. Palavras-Chave-Processamento de documentos, reconhecimento de manuscritos, reconhecimento de palavras manuscritas, processamento digital de imagens, reconhecimento de padrões.

show abstract

Section: B Modelos De Markov Escondidosunclassified

Introdução ao Reconhecimento de Palavras Manuscritas

Veloso¹,

Madeiro²

2012

RTIC

View full text Add to dashboard Cite

show abstract

“…segmentation boundaries of the word hypothesis into characters (S n ) which are obtained by the backtracking of the best state sequence by the decoding algorithm [28], [29]. It is given as a sequence of L segments S n ¼ ðx…”

Section: Output Of the Handwriting Recognition Systemmentioning

confidence: 99%

“…Nevertheless, this important aspect may diminish the usability of the recognition system in practical applications that deal with large and very large vocabularies. A lot of effort has been devoted to building a fast handwriting recognition system [29], [33]. Therefore, at this point, it is worthwhile to ascertain the impact of the VS on the whole recognition process, that is, in both the recognition rate and the recognition time.…”

Section: Evaluation Of the Overall Recognition And Verification Systemmentioning

confidence: 99%

Recognition and verification of unconstrained handwritten words

Koerich

Sabourin

Suen

2005

IEEE Trans. Pattern Anal. Machine Intell.

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents a novel approach for the verification of the word hypotheses generated by a large vocabulary, offline handwritten word recognition system. Given a word image, the recognition system produces a ranked list of the N-best recognition hypotheses consisting of text transcripts, segmentation boundaries of the word hypotheses into characters, and recognition scores. The verification consists of an estimation of the probability of each segment representing a known class of character. Then, character probabilities are combined to produce word confidence scores which are further integrated with the recognition scores produced by the recognition system. The N-best recognition hypothesis list is reranked based on such composite scores. In the end, rejection rules are invoked to either accept the best recognition hypothesis of such a list or to reject the input word image. The use of the verification approach has improved the word recognition rate as well as the reliability of the recognition system, while not causing significant delays in the recognition process. Our approach is described in detail and the experimental results on a large database of unconstrained handwritten words extracted from postal envelopes are presented.

show abstract

Automatic recognition of handwritten medical forms for search engines

Milewski

Govindaraju

Bhardwaj

2009

IJDAR

View full text Add to dashboard Cite

A new paradigm, which models the relationships between handwriting and topic categories, in the context of medical forms, is presented. The ultimate goals are (i) the recognition of medical handwriting, and (ii) the use of such information for practical applications such as a medical form search engine. Medical forms have diverse, complex and large lexicons consisting of English, Medical and Pharmacology corpus. Our technique shows that a few recognized characters, returned by handwriting recognition, can be used to construct a linguistic model capable of representing a medical topic category. This allows (i) a reduced lexicon to be constructed, thereby improving handwriting recognition performance, and (ii) PCR forms to be tagged with a topic category and subsequently searched by information retrieval systems. We present an improvement of 8% in raw recognition rate and a search precision of 0.86 at the 0.1 recall position on a data set of unconstrained handwritten medical forms filled in emergency environments.

show abstract

Fast Two-Level HMM Decoding Algorithm for Large Vocabulary Handwriting Recognition

Abstract: Abstract

Cited by 4 publications

References 12 publications

Introdução ao Reconhecimento de Palavras Manuscritas

Introdução ao Reconhecimento de Palavras Manuscritas

Recognition and verification of unconstrained handwritten words

Automatic recognition of handwritten medical forms for search engines

Contact Info

Product

Resources

About