Online handwriting recognition: The NPen++ recognizer

被引：155

作者：

Jaeger S. ^{[1
,2
]}

Manke S. ^{[1
,2
]}

Reichert J. ^{[1
,2
]}

Waibel A. ^{[1
,2
]}

机构：

[1] Interactive Systems Laboratories, University of Karlsruhe, Computer Science Department

[2] Interactive Systems Laboratories, Carnegie Mellon University, School of Computer Science, Pittsburgh

来源：

International Journal on Document Analysis and Recognition | 2001年 / Springer Verlag卷 / 03期

关键词：

Human-computer interaction; Neural networks; Online handwriting recognition; Pattern recognition; Pen-based computing;

D O I：

10.1007/PL00013559

中图分类号：

TN7 [基本电子电路];

学科分类号：

080902 ;

摘要：

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. © 2001 Springer-Verlag Berlin Heidelberg.

引用

页码：169 / 180

页数：11

共 23 条

[1]

Abramowski S., Muller H., Geometrisches Modellieren (in German), 75, (1991)

[2]

Bengio Y., Cun Y.L., Word Normalization for On-Line Handwritten Word Recognition, Proc. Int. Conf. on Pattern Recognition, pp. 409-413, (1994)

[3]

Boccignone G., Chianese A., Cordella L.P., Marcelli A., Recovering Dynamic Information from Static Handwriting, Pattern Recognition, 26, 3, pp. 409-418, (1993)

[4]

Caesar T., Gloger J.M., Mandler E., Preprocessing and Feature Extraction for a Handwriting Recognition System, 2nd IAPR Int. Conf. on Document Analysis and Recognition, pp. 408-411, (1993)

[5]

Dempster A.P., Laird N.M., Rubin D.B., Maximum Likelihood from Incomplete Data via the EM Algorithm, J. R. Stat. Soc, 39, pp. 1-38, (1977)

[6]

Doermann D.S., Rosenfeld A., Recovery of Temporal Information from Static Images of Handwriting, Int. J. Comput. Vision, 15, pp. 143-164, (1995)

[7]

Dolfing J.G.A., Haeb-Umbach R., Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition, Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, (1997)

[8]

Guyon I., Albrecht P., Le Cun Y., Denker J., Hubbard W., Design of a Neural Network Character Recognizer for a Touch Terminal, Pattern Recognition, 24, 2, pp. 105-119, (1991)

[9]

Hild H., Buchstabiererkennung mit neuronalen Netzen in Auskunftssystemen, (1997)

[10]

Hild H., Waibel A., Speaker-Independent Connected Letter Recognition with a Multi-State Time Delay Neural Network, 3rd European Conf. on Speech, Communication and Technology (EUROSPEECH), 2, pp. 1481-1484, (1993)

← 1 2 3 →