Off-line character recognition using HMM by multiple directional feature extraction and voting with bagging algorithm

Nishimura, Hiromitsu; Kobayashi, M.; Maruyama, Mitsuru; Nakano, Yasuaki

doi:10.1109/icdar.1999.791722

Cited by 21 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few researchers have implemented ensemble of classifiers to improve both accuracy and reliability of the handwriting recognition systems (Nishimura et al 1999;Günter and Bunke 2003;Oliveira et al 2003a;Morita et al 2004;Liu and Narukawa 2004) Few researchers have followed the strategy of verification on the bargaining of speed. Such kind of scheme has been successfully applied to handwriting recognition in (Takahashi and Griffin 1993;Zhou et al 2000;Britto et al 2002;Oliveira et al 2003b).…”

Section: Script Recognition Using Fused Classifiersmentioning

confidence: 99%

Off-line cursive script recognition: current advances, comparisons and remaining problems

Rehman

Saba

2011

Artif Intell Rev

View full text Add to dashboard Cite

This paper presents detailed review in the field of off-line cursive script recognition. Various methods are analyzed that have been proposed to realize the core of script recognition in a word recognition system. These methods are discussed in view of the two most important properties of such systems: size and nature of the lexicon involved and whether or not a segmentation stage is present. Script recognition techniques are classified into three categories: firstly, segmentation-free methods or holistic approaches, that compare a sequence of observations derived from whole word image with similar references of words in the small lexicon. Secondly, segmentation-based methods, that look for the best match between consecutive sequences of primitive segments and letters of a possible word similar to human-like reading technique, in which secure features found all over the word are used to boot-strap a few candidates for a final evaluation phase; thirdly, hybrid approaches. Additionally, different feature extraction techniques are elaborated in conjunction with the classification process. In this scenario, implications of single and multiple classifiers are also observed. Finally, remaining problems are highlighted along with possible suggestion and strategies to solve them.

show abstract

Section: Script Recognition Using Fused Classifiersmentioning

confidence: 99%

Off-line cursive script recognition: current advances, comparisons and remaining problems

Rehman

Saba

2011

Artif Intell Rev

View full text Add to dashboard Cite

show abstract

“…The two well‐known applications of HMMs are automatic speech recognition (Rabiner & Juang, 1993), where sequences of spoken utterances are modeled to recognize complete words, and biological sequence analysis (Durbin, Eddy, Krogh, & Mitchinson, 2000), where sequences of aminoacids or proteins are modeled for a number of bioinformatics applications. In addition, HMMs have been also applied to handwriting recognition (Nishimura, Kobayashi, Maruyama, & Nakano, 1999), automatic music accompaniment (Orio, 2001), and fault detection (Smyth, 1994).…”

Section: Hidden Markov Modelsmentioning

confidence: 99%

Design, implementation, and evaluation of a methodology for automatic stemmer generation

Melucci

Orio

2007

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

The authors describe a statistical approach based on hidden Markov models (HMMs), for generating stemmers automatically. The proposed approach requires little effort to insert new languages in the system even if minimal linguistic knowledge is available. This is a key advantage especially for digital libraries, which are often developed for a specific institution or government because the program can manage a great amount of documents written in local languages. The evaluation described in the article shows that the stemmers implemented by means of HMMs are as effective as those based on linguistic rules.

show abstract

“…An exception is [25], but this paper addresses only the classification of isolated characters, while the focus of the present paper is on the recognition of cursive words. Some papers of the authors addressed the use of ensemble methods for handwritten word recognition (e.g.…”

Section: Inputmentioning

confidence: 99%

Ensembles of Classifiers for Handwritten Word Recognition Specialized on Individual Handwriting Style

Günter

Bunke

2004

Document Analysis Systems VI

View full text Add to dashboard Cite

Abstract. The study of multiple classifier systems has become an area of intensive research in pattern recognition recently. Also in handwriting recognition, systems combining several classifiers have been investigated. Recently, new methods for the generation of multiple classifier systems, called ensemble methods, have been proposed in the field of machine learning, which generate an ensemble of classifiers from a single classifier automatically. In this paper a new ensemble method is proposed. It is characterized by training each individual classifier on a particular writing style. The new ensemble method is tested on two large scale handwritten word recognition tasks.

show abstract

Off-line character recognition using HMM by multiple directional feature extraction and voting with bagging algorithm

Cited by 21 publications

References 8 publications

Off-line cursive script recognition: current advances, comparisons and remaining problems

Off-line cursive script recognition: current advances, comparisons and remaining problems

Design, implementation, and evaluation of a methodology for automatic stemmer generation

Ensembles of Classifiers for Handwritten Word Recognition Specialized on Individual Handwriting Style

Contact Info

Product

Resources

About