Off-line handwritten word recognition with hidden markov models은닉 마르코프 모델을 이용한 오프라인 필기 단어 인식

In this thesis, a new method for modeling and recognizing cursive words with hidden Markov models (HMM) is presented. Hidden Markov models have been successfully applied to speech recognition tasks, and recently, there have been approaches for applying it to character recognition. However, it is difficult to find a system that extensively made use of the abundant experiences accumulated in speech recognition. We have employed HMM as the main statistical framework, utilizing many of the efficient tools provided in the literature. The framework is described in terms of three processes: Encoding, Modeling, and Recognition. In the proposed method, a sequence of thin fixed-width vertical frames are extracted from the image, capturing the local features of the handwriting. Each frame is considered as a segmentation hypothesis by the recognition algorithm. This can be distinguished from the previous approaches with HMM, where the character segmentation points were heuristically hypothesized and, thus, had the risk of missing the actual segmentation points. By quantizing the frames, the input word image is represented as a Markov chain of discrete symbols. A handwritten word is regarded as a sequence of characters and three types of character junctures. Therefore, the junctures are also explicitly modeled. This can be distinguished from the general view of regarding a word as a sequence of characters only. With this view, an interconnection network of character and juncture HMMs is constructed to model words of indefinite length. This model can ideally describe any form of handwritten words including discretely spaced words, pure cursive words, and unconstrained words of mixed styles. Each character and juncture models are trained with the Baum-Welch method. The recognition algorithm follows the maximum a posteriori decoding rule. Various efficient implementations of the Viterbi search is proposed and evaluated. They are based on the forward and backward evaluation sco...
Advisors
Kim, Jin-Hyung(김진형)researcher
Publisher
한국과학기술원
Issue Date
1995
Identifier
99167/325007 / 000885474
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전산학과, 1995.2, [ [ii], 99 p. ]

Keywords

은닉 마르코프 모델; 단어 인식

URI
http://hdl.handle.net/10203/33033
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=99167&flag=t
Appears in Collection
CS-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.
  • Hit : 74
  • Download : 0
  • Cited 0 times in thomson ci

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0