HoG based Two-Directional Dynamic Time Warping for Handwritten Word Spotting

被引：0

作者：

Yao, Shunyi ^{[1
]}

Wen, Ying ^{[1
]}

Lu, Yue ^{[1
]}

机构：

[1] East China Normal Univ, Shanghai Key Lab Multidimens Informat Proc, Dept Comp Sci & Technol, Shanghai 200241, Peoples R China

来源：

2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR) | 2015年

关键词：

word spotting; handwritten documents; local features; two-directional Dynamic Time Warping;

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：

We present a Histogram of Oriented Gradient (HoG) based two-directional Dynamic Time Warping (DTW) matching method for handwritten word spotting. Firstly, we extract HoG descriptors from each cell in the normalized images. Then we connect the HoG descriptors in the same column and get a sequence of feature vectors. We do the same operation for the HoG descriptors in the same row. We then apply the two-directional DTW method to calculate the distance between the feature vectors sequences extracted from the query word and the candidate one. The experimental results show that the two-directional DTW is more robust to word deformation than the traditional DTW. And the local features such as HoG, LBP and SIFT combined with the two-directional DTW method outperform the method using the local feature descriptors directly. The HoG based two-directional DTW get the highest mean average precision on both the George Washington dataset and the CASIA-HWDB 2.1 dataset.

引用

页码：161 / 165

页数：5

共 50 条

[21] Word Spotting in Handwritten Text Using Contour-based Models
Giotis, Angelos R.
Gerogiannis, Demetrios R.
Nikou, Christophoros
[J]. 2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 399 - 404
[22] A Model-Based Sequence Similarity with Application to Handwritten Word Spotting
Rodriguez-Serrano, Jose A.
Perronnin, Florent
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) : 2108 - 2120
[23] Query-Based Word Spotting in Handwritten Documents Using HMM
Bharathi, V. C.
Veningston, K.
Rao, P. V. Venkateswara
[J]. DATA ENGINEERING AND COMMUNICATION TECHNOLOGY, ICDECT-2K19, 2020, 1079 : 31 - 39
[24] HMM word graph based keyword spotting in handwritten document images
Toselli, Alejandro Hector
Vidal, Enrique
Romero, Veronica
Frinken, Volkmar
[J]. INFORMATION SCIENCES, 2016, 370 : 497 - 518
[25] Keyword Spotting with Convolutional Deep Belief Networks and Dynamic Time Warping
Wicht, Baptiste
Fischer, Andreas
Hennebert, Jean
[J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II, 2016, 9887 : 113 - 120
[26] A New Feature Optimization Method Based on Two-directional 2DLDA For Handwritten Chinese Character Recognition
Gao, Xue
Wen, Wenhuan
Jin, Lianwen
[J]. 11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 232 - 236
[27] Keyword Spotting using Dynamic Time Warping and Convolutional Recurrent Networks
Albert, Erika-Timea
Lemnaru, Camelia
Dinsoreanu, Mihaela
Potolea, Rodica
[J]. 2019 IEEE 15TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING (ICCP 2019), 2019, : 53 - 60
[28] Dynamic handwritten keyword spotting based on the NSHP-HMM
Choisy, Christophe
[J]. ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2007, : 242 - 246
[29] Isolated Word Recognition using Dynamic Time Warping
Kaleka, Jagdev Singh
[J]. RECENT ADVANCES IN CIRCUITS, SYSTEMS AND SIGNALS, 2010, : 293 - +
[30] Word image matching using dynamic time warping
Rath, TM
Manmatha, R
[J]. 2003 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2003, : 521 - 527

← 1 2 3 4 5 →