LEREC - A NN/HMM HYBRID FOR ONLINE HANDWRITING RECOGNITION

被引：65

作者：

BENGIO, Y ^{[1
]}

LECUN, Y ^{[1
]}

NOHL, C ^{[1
]}

BURGES, C ^{[1
]}

机构：

[1] UNIV MONTREAL,DEPT IRO,MONTREAL,PQ H3C 3J7,CANADA

来源：

NEURAL COMPUTATION | 1995年 / 7卷 / 06期

关键词：

D O I：

10.1162/neco.1995.7.6.1289

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We introduce a new approach for on-line recognition of handwritten words written in unconstrained mixed style. The preprocessor performs a word-level normalization by fitting a model of the word structure using the EM algorithm. Words are then coded into low resolution ''annotated images'' where each pixel contains information about trajectory direction and curvature. The recognizer is a convolution network that can be spatially replicated. From the network output, a hidden Markov model produces word scores. The entire system is globally trained to minimize word-level errors.

引用

页码：1289 / 1303

页数：15

共 50 条

[21] Hybrid multiplier/cordic unit for online handwriting recognition
McInerney, S
Reilly, RB
ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 1909 - 1912
[22] A Hybrid Model for End to End Online Handwriting Recognition
Mukherjee, Partha S.
Bhattacharya, Ujjwal
Parui, Swapan K.
Chakraborty, Bappaditya
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 658 - 663
[23] HMM and NN for Gesture Recognition.
Delgado-Mata, Carlos
Lee Cosio, Blanca Miriam
2010 IEEE ELECTRONICS, ROBOTICS AND AUTOMOTIVE MECHANICS CONFERENCE (CERMA 2010), 2010, : 56 - 61
[24] Topology inference for an ANN HMM hybrid on-line handwriting recognition system
Li, HF
Artières, T
Gallinari, P
Dorizzi, B
ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 2479 - 2483
[25] Measuring HMM similarity with the Bayes probability of error and its application to online handwriting recognition
Bahlmann, C
Burkhardt, H
SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 406 - 411
[26] An HMM framework based on spherical-linear features for online cursive handwriting recognition
Samanta, Oendrila
Roy, Anandarup
Parui, Swapan K.
Bhattacharya, Ujjwal
INFORMATION SCIENCES, 2018, 441 : 133 - 151
[27] Applying Batch Normalization to Hybrid NN-HMM Model For Speech Recognition
Zhan, Hongjian
Chen, Guilin
Lu, Yue
PATTERN RECOGNITION (CCPR 2016), PT II, 2016, 663 : 427 - 435
[28] A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction
Rigoll, G
Willett, D
PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 9 - 12
[29] Online handwriting Mongolia words recognition combined both HMM and Nearest Neighbor Classifiers
Gao, GL
Wu, W
Proceedings of the 11th Joint International Computer Conference, 2005, : 888 - 890
[30] Comparing Hybrid NN-HMM and RNN for Temporal Modeling in Gesture Recognition
Granger, Nicolas
el Yacoubi, Mounim A.
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT II, 2017, 10635 : 147 - 156

← 1 2 3 4 5 →