Segmental K-Means Learning with Mixture Distribution for HMM Based Handwriting Recognition

被引：0

作者：

Bhowmik, Tapan Kumar ^{[1
]}

van Oosten, Jean-Paul ^{[1
]}

Schomaker, Lambert ^{[1
]}

机构：

[1] Univ Groningen, Fac Math & Nat Sci, NL-9700 AB Groningen, Netherlands

来源：

PATTERN RECOGNITION AND MACHINE INTELLIGENCE | 2011年 / 6744卷

关键词：

ALGORITHM;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper investigates the performance of hidden Markov models (HMMs) for handwriting recognition. The Segmental K-Means algorithm is used for updating the transition and observation probabilities, instead of the Baum-Welch algorithm. Observation probabilities are modelled as multi-variate Gaussian mixture distributions. A deterministic clustering technique is used to estimate the initial parameters of an HMM. Bayesian information criterion (BIC) is used to select the topology of the model. The wavelet transform is used to extract features from a grey-scale image, and avoids binarization of the image.

引用

页码：432 / 439

页数：8

共 50 条

[1] The Informativeness of k-Means for Learning Mixture Models
Liu, Zhaoqiang
Tan, Vincent Y. F.
[J]. 2018 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2018, : 26 - 30
[2] The Informativeness of k-Means for Learning Mixture Models
Liu, Zhaoqiang
Tan, Vincent Y. F.
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2019, 65 (11) : 7460 - 7479
[3] HANDWRITING IMAGE ENHANCEMENT USING LOCAL LEARNING WINDOWING, GAUSSIAN MIXTURE MODEL AND K-MEANS CLUSTERING
Kusetogullari, Huseyin
Grahn, Hakan
Lavesson, Niklas
[J]. 2016 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT), 2016, : 305 - 310
[4] A SEGMENTAL K-MEANS TRAINING PROCEDURE FOR CONNECTED WORD RECOGNITION
RABINER, LR
WILPON, JG
JUANG, BH
[J]. AT&T TECHNICAL JOURNAL, 1986, 65 (03): : 21 - 31
[5] Dynamic Time Warping-Based K-Means Clustering for Accelerometer-Based Handwriting Recognition
Jang, Minsu
Han, Mun-Sung
Kim, Jae-Hong
Yang, Hyun-Seung
[J]. DEVELOPING CONCEPTS IN APPLIED INTELLIGENCE, 2011, 363 : 21 - +
[6] Tibetan Character Recognition Based on Machine Learning of K-means Algorithm
Gong, Huiwen
Xiang, Wei
[J]. PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON COMPUTER MODELING, SIMULATION AND ALGORITHM (CMSA 2018), 2018, 151 : 340 - 342
[7] Convolutional Feature Learning and CNN Based HMM for Arabic Handwriting Recognition
Amrouch, Mustapha
Rabi, Mouhcine
Es-Saady, Youssef
[J]. IMAGE AND SIGNAL PROCESSING (ICISP 2018), 2018, 10884 : 265 - 274
[8] HMM-Based Recognition of Online Handwritten Mathematical Symbols Using Segmental K-means Initialization and A Modified Pen-up/down Feature
Hu, Lei
Zanibbi, Richard
[J]. 11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 457 - 462
[9] Segmental K-means algorithm based hidden Markov model for shape recognition and its applications
Bhowmik, Tapan Kumar
Parui, Swapan Kumar
Kar, Manika
Roy, Utpal
[J]. PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION, 2007, : 361 - +
[10] Morse Recognition Algorithm Based on K-means
Qu Shanhu
Liu Hongbo
Zhang Xu
[J]. 2019 CROSS STRAIT QUAD-REGIONAL RADIO SCIENCE AND WIRELESS TECHNOLOGY CONFERENCE (CSQRWC), 2019,

← 1 2 3 4 5 →