A Theory of Character Recognition by Pattern Matching Method

Iijima, Taizo; Genchi, H.; Mori, Kenichi

doi:10.1007/978-1-4684-2106-4_22

Cited by 38 publications

(18 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…general information theoretic (Cover and Thomas, 1991) techniques based on maximizing mutual information to approaches specific to image processing (Iijima et al, 1973). Roughly speaking, one wants to obtain features that can distinguish among the patterns we care about, for a specific task or data set.…”

mentioning

confidence: 99%

Combining Generative and Discriminative Models in a Framework for Articulated Pose Estimation

Rosales

Sclaroff

2006

Int J Comput Vision

View full text Add to dashboard Cite

We develop a method for the estimation of articulated pose, such as that of the human body or the human hand, from a single (monocular) image. Pose estimation is formulated as a statistical inference problem, where the goal is to find a posterior probability distribution over poses as well as a maximum a posteriori (MAP) estimate. The method combines two modeling approaches, one discriminative and the other generative. The discriminative model consists of a set of mapping functions that are constructed automatically from a labeled training set of body poses and their respective image features. The discriminative formulation allows for modeling ambiguous, one-to-many mappings (through the use of multi-modal distributions) that may yield multiple valid articulated pose hypotheses from a single image. The generative model is defined in terms of a computer graphics rendering of poses. While the generative model offers an accurate way to relate observed (image features) and hidden (body pose) random variables, it is difficult to use it directly in pose estimation, since inference is computationally intractable. In contrast, inference with the discriminative model is tractable, but considerably less accurate for the problem of interest. A combined discriminative/generative formulation is derived that leverages the complimentary strengths of both models in a principled framework for articulated pose inference. Two efficient MAP pose estimation algorithms are derived from this formulation; the first is deterministic and the second non-deterministic. Performance of the framework is quantitatively evaluated in estimating articulated pose of both the human hand and human body.Keywords: human body pose, hand pose, nonrigid and articulated pose estimation, statistical inference, generative and discriminative models, mixture models, expectation maximization algorithm

show abstract

mentioning

confidence: 99%

Combining Generative and Discriminative Models in a Framework for Articulated Pose Estimation

Rosales

Sclaroff

2006

Int J Comput Vision

View full text Add to dashboard Cite

show abstract

“…Observing human eye movements while a subject is looking at an object, his/her gaze is fixed using reference points extracted from the object. Iijima [18] proved mathematically that the vertices of a polygon are stationary points of this eye movement. This theory is expressed using the determination of the region of interest (ROI) in the context of the scale-space theory.…”

Section: Discussion and Concluding Remarksmentioning

confidence: 99%

Motion Analysis by Random Sampling and Voting Process

Imiya¹,

Fermin²

1999

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…At the first workshop on pattern recognition, held in Puerto Rico in 1966, about one third of the papers dealt with character recognition [6]. Approaches such as blurring [7], directional pattern matching [8,9], hierarchical classification [10,11] and multiple classifiers combination [12,13] were first proposed by the character recognition community, and later evolved into attractive research fields.…”

Section: Introductionmentioning

confidence: 99%

Chinese character recognition: history, status and prospects

Liu

Dai

Xiao

2007

Front. Comput. Sc. China

View full text Add to dashboard Cite

Chinese character recognition (CCR) is an important branch of pattern recognition. It was considered as an extremely difficult problem due to the very large number of categories, complicated structures, similarity between characters, and the variability of fonts or writing styles. Because of its unique technical challenges and great social needs, the last four decades witnessed the intensive research in this field and a rapid increase of successful applications. However, higher recognition performance is continuously needed to improve the existing applications and to exploit new applications. This paper first provides an overview of Chinese character recognition and the properties of Chinese characters. Some important methods and successful results in the history of Chinese character recognition are then summarized. As for classification methods, this article pays special attention to the syntactic-semantic approach for online Chinese character recognition, as well as the metasynthesis approach for discipline crossing. Finally, the remaining problems and the possible solutions are discussed.

show abstract

A Theory of Character Recognition by Pattern Matching Method

Cited by 38 publications

References 1 publication

Combining Generative and Discriminative Models in a Framework for Articulated Pose Estimation

Combining Generative and Discriminative Models in a Framework for Articulated Pose Estimation

Motion Analysis by Random Sampling and Voting Process

Chinese character recognition: history, status and prospects

Contact Info

Product

Resources

About