Chair: Jan Allebach,
Krishna S. Nathan, IBM Research (USA)
Homayoon S.M. Beigi, IBM Research (USA)
Jayashree Subrahmonia, IBM Research (USA)
Gregory J. Clary, IBM Research (USA)
Hiroshi Maruyama, IBM Research (USA)
We address the problem of automatic recognition of unconstrained handwritten text. Statistical methods, such as hidden Markov models (HMMs) have been used successfully for speech recognition and they have recently been applied to the problem of handwriting recognition as well. In this paper, we will discuss a general recognition system for large vocabulary, writer independent, unconstrained handwritten text. ``Unconstrained'' implies that the user may write in any style e.g. printed, cursive or in any combination of styles. This is more representative of typical handwritten text where one seldom encounters purely printed or purely cursive forms. Furthermore, a key characteristic of the system described in this paper is that it performs recognition in real-time on 486 class PC platforms without the large amounts of memory required for traditional HMM based systems. We focus mainly on the writer independent task. Some initial writer dependent results are also reported. An error rate of 18.9% is achieved for a writer-independent 21,000 word vocabulary task in the absence of any language models.
Mou-Yen Chen, ITRI (REPUBLIC OF CHINA)
Amlan Kundu, U.S. West Advanced Technologies (USA)
In this paper, a novel approach for handwritten word recognition using Multi-Level Hidden Markov Models (MLHMM) is introduced. The MLHMM is a doubly embedded network of HMM's where each character is modeled by an HMM while a word is modeled by a higher- level HMM. By introducing the technique called `tied transition', i.e., the segments which have the same semantic meaning will be `tied' together, each character is modeled by an HMM with 4 states, 5 observations ( or symbols ) and 7 transitions. At the character level, the model parameters are optimized by the re-estimation algorithm; and the best model is chosen as the recognition result. So, the character model is purely a model discriminant HMM (MD-HMM) based approach. For the word model, on the other hand, both the MD-HMM and the path discriminant HMM (PD-HMM) approaches are used and their respective performances are demonstrated.
Antai Peng, Georgia Tech (USA)
Monson H. Hayes, Georgia Tech (USA)
Human facial expression modeling has been an active research area recently. Most of the existing systems do not provide an easy way to adjust the model such that different levels of detail of expressions can be modeled. In this paper, we propose a method for modeling the human facial expressions at different resolutions. Our method is based on the FACS developed by Ekman and Freisen [8]. Although the facial expressions we are mainly interested in are those related to speech either directly or indirectly, the modeling method can be extended to apply to facial expressions that are not related to speech.
Eveline J. Bellegarda, Apple Computer Inc.
Jerome R. Bellegarda, Apple Computer Inc.
David Nahamoo, IBM Research (USA)
Krishna S. Nathan, IBM Research (USA)
One area where on-line handwriting recognition technology is most critical is the domain of small portable platforms. Because such platforms have limited resources, it is not presently practical to consider a continuous parameterization for the hidden Markov models used in the recognition. On the other hand, discrete parameter techniques such as used in speech recognition are difficult to apply, because there is no well-understood handwriting equivalent to phonological rules. A possible solution is to extract this information directly from the data, by constructing an alphabet of sub-character, elementary handwriting units. The performance of this method is illustrated on a discrete handwriting recognition task with an alphabet of 81 characters.
S. Comes, Universite Catholique de Louvain (BELGIUM)
O. Bruyndonckx, Universite Catholique de Louvain (BELGIUM)
B. Macq, Universite Catholique de Louvain (BELGIUM)
This paper investigates the development of a new image quality criterion based on the psychovisual model of tuned channels and more particularly the phenomenon of masking. The masking model parameters have been evaluated by psychovisual tests assuming a logarithmic relationship between the visibility threshold and the contrast value of the background for a given perceptual channel. The masking has the consequence that only a part of the noise of a noisy image is really visible and affects the visual quality of the image. The idea of the proposed criterion is to evaluate image quality after the cancellation of the masked noise defined as the invisible noise. The criterion has been used in order to compare different coders and different post- processings of noisy images.