Keyword spotting in degraded document using mixed OCR and word shape coding

Yong Xia; Guangri Quan; Yongdong Xu; Yushan Sun

doi:10.1109/ICICISYS.2010.5658616

Keyword spotting in degraded document using mixed OCR and word shape coding

Yong Xia^*
, Guangri Quan
, Yongdong Xu
, Yushan Sun

^*Corresponding author for this work

School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

This paper presents a new way for keyword spotting in degraded imaged document. Two prevalent word indexing, OCR and word shape coding, are combined compactly based on the recognition confidence evaluation. The basic procedures are as follows. First, OCR candidates are used for OCR indexing. Second, a new stoke feature and convex-concave feature of word are adopted for word shape coding. Furthermore, an intelligent indexing based on recognition confidence is introduced, which is adaptive to image quality. Finally, an inexact matching is used for word spotting. A collection from NLM, including 1553 scanned imaged documents, is used to evaluate our method. The results confirm the validity of our method.

Original language	English
Title of host publication	Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010
Pages	411-414
Number of pages	4
DOIs	https://doi.org/10.1109/ICICISYS.2010.5658616
State	Published - 2010
Externally published	Yes
Event	2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010 - Xiamen, China Duration: 29 Oct 2010 → 31 Oct 2010

Publication series

Name	Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010
Volume	3

Conference

Conference	2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010
Country/Territory	China
City	Xiamen
Period	29/10/10 → 31/10/10

Keywords

Degraded imaged document
Keyword spotting
OCR indexing
Word shape coding

Access to Document

10.1109/ICICISYS.2010.5658616

Cite this

Xia, Y., Quan, G., Xu, Y., & Sun, Y. (2010). Keyword spotting in degraded document using mixed OCR and word shape coding. In Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010 (pp. 411-414). Article 5658616 (Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010; Vol. 3). https://doi.org/10.1109/ICICISYS.2010.5658616

@inproceedings{336282b30c5e46f990bec99821336c75,

title = "Keyword spotting in degraded document using mixed OCR and word shape coding",

abstract = "This paper presents a new way for keyword spotting in degraded imaged document. Two prevalent word indexing, OCR and word shape coding, are combined compactly based on the recognition confidence evaluation. The basic procedures are as follows. First, OCR candidates are used for OCR indexing. Second, a new stoke feature and convex-concave feature of word are adopted for word shape coding. Furthermore, an intelligent indexing based on recognition confidence is introduced, which is adaptive to image quality. Finally, an inexact matching is used for word spotting. A collection from NLM, including 1553 scanned imaged documents, is used to evaluate our method. The results confirm the validity of our method.",

keywords = "Degraded imaged document, Keyword spotting, OCR indexing, Word shape coding",

author = "Yong Xia and Guangri Quan and Yongdong Xu and Yushan Sun",

year = "2010",

doi = "10.1109/ICICISYS.2010.5658616",

language = "英语",

isbn = "9781424465835",

series = "Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010",

pages = "411--414",

booktitle = "Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010",

note = "2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010 ; Conference date: 29-10-2010 Through 31-10-2010",

}

Xia, Y, Quan, G, Xu, Y & Sun, Y 2010, Keyword spotting in degraded document using mixed OCR and word shape coding. in Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010., 5658616, Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010, vol. 3, pp. 411-414, 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010, Xiamen, China, 29/10/10. https://doi.org/10.1109/ICICISYS.2010.5658616

Keyword spotting in degraded document using mixed OCR and word shape coding. / Xia, Yong; Quan, Guangri; Xu, Yongdong et al.
Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010. 2010. p. 411-414 5658616 (Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Keyword spotting in degraded document using mixed OCR and word shape coding

AU - Xia, Yong

AU - Quan, Guangri

AU - Xu, Yongdong

AU - Sun, Yushan

PY - 2010

Y1 - 2010

N2 - This paper presents a new way for keyword spotting in degraded imaged document. Two prevalent word indexing, OCR and word shape coding, are combined compactly based on the recognition confidence evaluation. The basic procedures are as follows. First, OCR candidates are used for OCR indexing. Second, a new stoke feature and convex-concave feature of word are adopted for word shape coding. Furthermore, an intelligent indexing based on recognition confidence is introduced, which is adaptive to image quality. Finally, an inexact matching is used for word spotting. A collection from NLM, including 1553 scanned imaged documents, is used to evaluate our method. The results confirm the validity of our method.

AB - This paper presents a new way for keyword spotting in degraded imaged document. Two prevalent word indexing, OCR and word shape coding, are combined compactly based on the recognition confidence evaluation. The basic procedures are as follows. First, OCR candidates are used for OCR indexing. Second, a new stoke feature and convex-concave feature of word are adopted for word shape coding. Furthermore, an intelligent indexing based on recognition confidence is introduced, which is adaptive to image quality. Finally, an inexact matching is used for word spotting. A collection from NLM, including 1553 scanned imaged documents, is used to evaluate our method. The results confirm the validity of our method.

KW - Degraded imaged document

KW - Keyword spotting

KW - OCR indexing

KW - Word shape coding

UR - https://www.scopus.com/pages/publications/78651276744

U2 - 10.1109/ICICISYS.2010.5658616

DO - 10.1109/ICICISYS.2010.5658616

M3 - 会议稿件

AN - SCOPUS:78651276744

SN - 9781424465835

T3 - Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010

SP - 411

EP - 414

BT - Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010

T2 - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010

Y2 - 29 October 2010 through 31 October 2010

ER -

Xia Y, Quan G, Xu Y, Sun Y. Keyword spotting in degraded document using mixed OCR and word shape coding. In Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010. 2010. p. 411-414. 5658616. (Proceedings - 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2010). doi: 10.1109/ICICISYS.2010.5658616

Keyword spotting in degraded document using mixed OCR and word shape coding

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this