GMM-based Handwriting Style Identification System for Historical Documents

被引：0

作者：

Slimane, Fouad ^{[1
,3
]}

Schassan, Torsten ^{[2
]}

Maergner, Volker ^{[1
]}

机构：

[1] Tech Univ Carolo Wilhelmina Braunschweig, Inst Commun Technol IfN, Braunschweig, Germany

[2] Herzog August Bibliothek Wolfenbuttel HAB, Braunschweig, Germany

[3] Ecole Polytech Fed Lausanne, Sch Comp & Commun Sci, Lausanne, Switzerland

来源：

2014 6TH INTERNATIONAL CONFERENCE OF SOFT COMPUTING AND PATTERN RECOGNITION (SOCPAR) | 2014年

关键词：

handwriting style; GMMs; local features; sliding window; historical German document collection; RECOGNITION;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper, we describe a novel method for handwriting style identification. A handwriting style can be common to one or several writer. It can represent also a handwriting style used in a period of the history or for specific document. Our method is based on Gaussian Mixture Models (GMMs) using different kind of features computed using a combined fixed-length horizontal and vertical sliding window moving over a document page. For each writing style a GMM is built and trained using page images. At the recognition phase, the system returns log-likelihood scores. The GMM model with the highest score is selected. Experiments using page images from historical German document collection demonstrate good performance results. The identification rate of the GMM-based system developed with six historical handwriting style is 100%.

引用

页码：387 / 392

页数：6

共 50 条

[41] GMM-BASED PARAMETERIZATION OF THE CHARACTERISTIC MELODY OF BIRD VOCALIZATIONS
Deneva, Prolet
Ganchev, Todor
PROCEEDINGS OF THE TWENTY-FIRST INTERNATIONAL CONFERENCE ON GEOMETRY, INTEGRABILITY AND QUANTIZATION, 2020, 21 : 118 - 126
[42] A Reconfigurable Co-processor for GMM-Based Classifier
Wang, Wei
Liang, Weiqian
IEEE INTERNATIONAL SOC CONFERENCE, PROCEEDINGS, 2009, : 343 - +
[43] GMM-based Audio Codec Detection with Application in Forensics
Draghicescu, Dragos
Pop, Gheorghe
Burileanu, Dragos
Burileanu, Corneliu
2015 38TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), 2015,
[44] Cantonese verbal information verification system using GMM-based anti-model
Qin, C
Lee, T
2004 INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2004, : 297 - 300
[45] GMM-BASED ACOUSTIC MODELING FOR EMBEDDED SPEECH RECOGNITION
Levy, Christophe
Linares, Georges
Bonastre, Jean-Francois
INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1726 - 1729
[46] Evaluation of GMM-based Features for SVM Speaker Verification
Liu, Minghui
Huang, Zhongwei
2008 7TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-23, 2008, : 5027 - 5030
[47] GMM-based a priori SNR estimation in speech enhancement
Lei, Jianjun
Wang, Jian
Liu, Gang
Guo, Jun
WCICA 2006: SIXTH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-12, CONFERENCE PROCEEDINGS, 2006, : 4293 - +
[48] A New Text-Independent GMM Writer Identification System Applied to Arabic Handwriting
Slimane, Fouad
Maergner, Volker
2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 708 - 713
[49] Smartwatch-Based Open-Set Driver Identification by Using GMM-Based Behavior Modeling Approach
Mardi Putri, Rekyan Regasari
Yang, Ching-Han
Chang, Chin-Chun
Liang, Deron
IEEE SENSORS JOURNAL, 2021, 21 (04) : 4918 - 4926
[50] Computer assisted handwriting style identification system for questioned document examination
Cha, SH
Yoon, S
Tappert, CC
Lee, YB
Image and Video Communications and Processing 2005, Pts 1 and 2, 2005, 5685 : 220 - 227

← 1 2 3 4 5 →