Browsing Heterogeneous Document Collections by a Segmentation-free Word Spotting Method

被引：78

作者：

Rusinol, Marcal ^{[1
]}

Aldavert, David ^{[1
]}

Toledo, Ricardo ^{[1
]}

Llados, Josep ^{[1
]}

机构：

[1] Univ Autonoma Barcelona, Comp Vis Ctr, Dept Ciencies Comput, Bellaterra 08193, Barcelona, Spain

来源：

11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011) | 2011年

关键词：

Word Spotting; Heterogeneous Document Collections; Dense SIFT Features; Latent Semantic Indexing; RETRIEVAL;

D O I：

10.1109/ICDAR.2011.22

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present a segmentation-free word spotting method that is able to deal with heterogeneous document image collections. We propose a patch-based framework where patches are represented by a bag-of-visual-words model powered by SIFT descriptors. A later refinement of the feature vectors is performed by applying the latent semantic indexing technique. The proposed method performs well on both handwritten and typewritten historical document images. We have also tested our method on documents written in non-Latin scripts.

引用

页码：63 / 67

页数：5

共 50 条

[31] A segmentation-free isogeometric extended mortar contact method
Duong, Thang X.
De Lorenzis, Laura
Sauer, Roger A.
[J]. COMPUTATIONAL MECHANICS, 2019, 63 (02) : 383 - 407
[32] Online Handwritten Cursive Word Recognition Using Segmentation-free and Segmentation-based Methods
Zhu, Bilan
Shivram, Arti
Govindaraju, Venu
Nakagawa, Masaki
[J]. Proceedings 3rd IAPR Asian Conference on Pattern Recognition ACPR 2015, 2015, : 161 - 165
[33] A segmentation-free isogeometric extended mortar contact method
Thang X. Duong
Laura De Lorenzis
Roger A. Sauer
[J]. Computational Mechanics, 2019, 63 : 383 - 407
[34] Online handwritten cursive word recognition by combining segmentation-free and segmentation-based methods
Zhu, Bilan
Shivram, Arti
Govindaraju, Venu
Nakagawa, Masaki
[J]. PROCEEDINGS OF 2016 15TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2016, : 417 - 422
[35] A word spotting method for Farsi machine-printed document images
Pourasad, Yaghoub
Hassibi, Houshang
Ghorbani, Azam
[J]. TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2013, 21 (03) : 734 - 746
[36] Segmentation-Free Quasi-Newton Method for Polyenergetic CT Reconstruction
Humphries, T.
Faridani, A.
[J]. 2014 IEEE NUCLEAR SCIENCE SYMPOSIUM AND MEDICAL IMAGING CONFERENCE (NSS/MIC), 2014,
[37] Fusion of explicit segmentation based system and segmentation-free based system for on-line Arabic handwritten word recognition
Khlif, Hanen
Prum, Sophea
Kessentini, Yousri
Kanoun, Slim
Ogier, Jean Marc
[J]. PROCEEDINGS OF 2016 15TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2016, : 399 - 404
[38] Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniques
Mohamed, M
Gader, P
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (05) : 548 - 554
[39] Segmentation-based Historical Handwritten Word Spotting using Document-Specific Local Features
Zagoris, Konstantinos
Pratikakis, Ioannis
Gatos, Basil. Is
[J]. 2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 9 - 14
[40] A segmentation-free method for image classification based on pixel-wise matching
Ma, Jun
Zheng, Long
Dong, Mianxiong
He, Xiangjian
Guo, Minyi
Yaguchi, Yuichi
Oka, Ryuichi
[J]. JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 2013, 79 (02) : 256 - 268

← 1 2 3 4 5 →