NPen/sup ++/: a writer independent, large vocabulary on-line cursive handwriting recognition system

Manke, S.; Finke, Michael; Waibel, Alexander

doi:10.1109/icdar.1995.599023

Cited by 39 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to evaluate the proposed approach, we have developed a prototype system using the NPen++, an online handwriting recognition system developed in our lab (Manke et al 1995). We collected some repair data with four users.…”

Section: Discussionmentioning

confidence: 99%

Interactive error repair for an online handwriting interface

Huerst

Yang

Waibel

1998

CHI 98 Conference Summary on Human Factors in Computing Systems

View full text Add to dashboard Cite

Current online handwriting recognition systems have very limited error recovery mechanisms. In this paper, we discuss the problem of error repair in an online handwriting interface. Based on user study of common repair patterns found in human handwriting, we propose an approach that allows users to recover from recognition errors. The basic idea is to handle the error repair at the interface level by interacting with users. The method requires few modifications on original recognition engine and imposes few restrictions on users. We have developed a prototype system to demonstrate the proposed concept and perform user study when the system provides error recovery mechanisms.

show abstract

Section: Discussionmentioning

confidence: 99%

Interactive error repair for an online handwriting interface

Huerst

Yang

Waibel

1998

CHI 98 Conference Summary on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…A MS-TDNN is a connectionist recognizer that integrates recognition and segmentation into a single network architecture. This architecture was originally proposed for continuous-speech recognition tasks [10,16,23]. We adopted this technique, including the training procedure described in the next section, and have applied it to the handwriting recognition problem.…”

Section: Multi-state Time Delay Neural Network (Ms-tdnn)mentioning

confidence: 99%

Online handwriting recognition: the NPen++ recognizer

Jaeger¹,

Manke²,

Reichert³

et al. 2001

IJDAR

Self Cite

223

110

View full text Add to dashboard Cite

This paper presents the online handwriting recognition system NPen++ developed at the University of Karlsruhe and Carnegie Mellon University. The NPen++ recognition engine is based on a multi-state time delay neural network and yields recognition rates from 96% for a 5,000 word dictionary to 93.4% on a 20,000 word dictionary and 91.2% for a 50,000 word dictionary. The proposed tree search and pruning technique reduces the search space considerably without losing too much recognition performance compared to an exhaustive search. This enables the NPen++ recognizer to be run in real-time with large dictionaries. Initial recognition rates for whole sentences are promising and show that the MS-TDNN architecture is suited to recognizing handwritten data ranging from single characters to whole sentences.

show abstract

“…Finally, the emergence of neural networks (NNs) as universal approximators and their natural ability to introduce explicitly low-level context, led to their being coupled with HMMs in SR [7]. This resulted in robust "hybrid systems" for sequence recognition [8], then successfully used in handwriting [9][10][11][12][13][14]. In such systems, NNs are in fact used for classification, that is, to produce posterior probabilities of belonging to a given class (often letters, sometimes pseudo-letters), when a portion of the word is given as input.…”

Section: Introductionmentioning

confidence: 99%

“…In such systems, NNs are in fact used for classification, that is, to produce posterior probabilities of belonging to a given class (often letters, sometimes pseudo-letters), when a portion of the word is given as input. The HMM then post-processes the emission probabilities (likelihoods) in most cases approximated from these posterior probabilities, using the Bayes rule [10,11,13,14]. This paper proposes an original hybrid modeling approach for online handwritten word recognition with a large vocabulary, in an extended writer-dependent framework.…”

Section: Introductionmentioning

confidence: 99%

Maximum mutual information training for an online neural predictive handwritten word recognition system

Garcia-Salicetti

Dorizzi²,

Gallinari

et al. 2001

IJDAR

View full text Add to dashboard Cite

In this paper, we present a hybrid online handwriting recognition system based on hidden Markov models (HMMs). It is devoted to word recognition using large vocabularies. An adaptive segmentation of words into letters is integrated with recognition, and is at the heart of the training phase. A word-model is a left-right HMM in which each state is a predictive multilayer perceptron that performs local regression on the drawing (i.e., the written word) relying on a context of observations. A discriminative training paradigm related to maximum mutual information is used, and its potential is shown on a database of 9,781 words.

show abstract

NPen/sup ++/: a writer independent, large vocabulary on-line cursive handwriting recognition system

Cited by 39 publications

References 10 publications

Interactive error repair for an online handwriting interface

Interactive error repair for an online handwriting interface

Online handwriting recognition: the NPen++ recognizer

Maximum mutual information training for an online neural predictive handwritten word recognition system

Contact Info

Product

Resources

About