CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image

Xueming Qiao; Mingli Yin; Liang Kong; Bin Wang; Xiuli Chang; Qi Ma; Dongjie Zhu; Ning Cao

doi:10.1007/978-3-030-78618-2_16

CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image

Xueming Qiao
, Mingli Yin
, Liang Kong
, Bin Wang
, Xiuli Chang
, Qi Ma
, Dongjie Zhu^*
, Ning Cao

^*Corresponding author for this work

State Grid Weihai Power Supply Company
Shandong Institute of Shipbuilding Technology
Hainan University
School of Computer Science and Technology, Harbin Institute of Technology
Sanming University

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

Abstract

Natural scene images often contain a lot of important texts, which carry the information we need, so it has important practical value to locate text information. This paper proposes a Cascade Classifier Text Localization (CCTL) algorithm. Firstly, a cascade classification algorithm based on Real AdaBoost is proposed to improve the accuracy of text localization. Secondly, a perceptual-based grouping algorithm is proposed to establish a perceptual organization framework. The use of adjacency and similar rules to group texts can improve the effect of text grouping. The proposed algorithm is verified and evaluated on the ICDAR dataset. At the same time, it is compared with other algorithms. The experimental results show that the proposed method has superiority in natural scene text detection.

Original language	English
Title of host publication	Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings
Editors	Xingming Sun, Xiaorui Zhang, Zhihua Xia, Elisa Bertino
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	200-210
Number of pages	11
ISBN (Print)	9783030786175
DOIs	https://doi.org/10.1007/978-3-030-78618-2_16
State	Published - 2021
Externally published	Yes
Event	7th International Conference on Artificial Intelligence and Security, ICAIS 2021 - Dublin, Ireland Duration: 19 Jul 2021 → 23 Jul 2021

Publication series

Name	Communications in Computer and Information Science
Volume	1423
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	7th International Conference on Artificial Intelligence and Security, ICAIS 2021
Country/Territory	Ireland
City	Dublin
Period	19/07/21 → 23/07/21

Keywords

Cascade classifier
Perceptual organizational framework
Real AdaBoost
Scene text detection

Access to Document

10.1007/978-3-030-78618-2_16

Cite this

Qiao, X., Yin, M., Kong, L., Wang, B., Chang, X., Ma, Q., Zhu, D., & Cao, N. (2021). CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image. In X. Sun, X. Zhang, Z. Xia, & E. Bertino (Eds.), Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings (pp. 200-210). (Communications in Computer and Information Science; Vol. 1423). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-78618-2_16

Qiao, Xueming ; Yin, Mingli ; Kong, Liang et al. / CCTL : Cascade Classifier Text Localization Algorithm in Natural Scene Image. Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings. editor / Xingming Sun ; Xiaorui Zhang ; Zhihua Xia ; Elisa Bertino. Springer Science and Business Media Deutschland GmbH, 2021. pp. 200-210 (Communications in Computer and Information Science).

@inproceedings{b52dc00f38b64bd29d25c44bdcbc4f44,

title = "CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image",

abstract = "Natural scene images often contain a lot of important texts, which carry the information we need, so it has important practical value to locate text information. This paper proposes a Cascade Classifier Text Localization (CCTL) algorithm. Firstly, a cascade classification algorithm based on Real AdaBoost is proposed to improve the accuracy of text localization. Secondly, a perceptual-based grouping algorithm is proposed to establish a perceptual organization framework. The use of adjacency and similar rules to group texts can improve the effect of text grouping. The proposed algorithm is verified and evaluated on the ICDAR dataset. At the same time, it is compared with other algorithms. The experimental results show that the proposed method has superiority in natural scene text detection.",

keywords = "Cascade classifier, Perceptual organizational framework, Real AdaBoost, Scene text detection",

author = "Xueming Qiao and Mingli Yin and Liang Kong and Bin Wang and Xiuli Chang and Qi Ma and Dongjie Zhu and Ning Cao",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 7th International Conference on Artificial Intelligence and Security, ICAIS 2021 ; Conference date: 19-07-2021 Through 23-07-2021",

year = "2021",

doi = "10.1007/978-3-030-78618-2\_16",

language = "英语",

isbn = "9783030786175",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "200--210",

editor = "Xingming Sun and Xiaorui Zhang and Zhihua Xia and Elisa Bertino",

booktitle = "Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings",

address = "德国",

}

Qiao, X, Yin, M, Kong, L, Wang, B, Chang, X, Ma, Q, Zhu, D & Cao, N 2021, CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image. in X Sun, X Zhang, Z Xia & E Bertino (eds), Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings. Communications in Computer and Information Science, vol. 1423, Springer Science and Business Media Deutschland GmbH, pp. 200-210, 7th International Conference on Artificial Intelligence and Security, ICAIS 2021, Dublin, Ireland, 19/07/21. https://doi.org/10.1007/978-3-030-78618-2_16

CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image. / Qiao, Xueming; Yin, Mingli; Kong, Liang et al.
Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings. ed. / Xingming Sun; Xiaorui Zhang; Zhihua Xia; Elisa Bertino. Springer Science and Business Media Deutschland GmbH, 2021. p. 200-210 (Communications in Computer and Information Science; Vol. 1423).

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

TY - GEN

T1 - CCTL

T2 - 7th International Conference on Artificial Intelligence and Security, ICAIS 2021

AU - Qiao, Xueming

AU - Yin, Mingli

AU - Kong, Liang

AU - Wang, Bin

AU - Chang, Xiuli

AU - Ma, Qi

AU - Zhu, Dongjie

AU - Cao, Ning

PY - 2021

Y1 - 2021

N2 - Natural scene images often contain a lot of important texts, which carry the information we need, so it has important practical value to locate text information. This paper proposes a Cascade Classifier Text Localization (CCTL) algorithm. Firstly, a cascade classification algorithm based on Real AdaBoost is proposed to improve the accuracy of text localization. Secondly, a perceptual-based grouping algorithm is proposed to establish a perceptual organization framework. The use of adjacency and similar rules to group texts can improve the effect of text grouping. The proposed algorithm is verified and evaluated on the ICDAR dataset. At the same time, it is compared with other algorithms. The experimental results show that the proposed method has superiority in natural scene text detection.

AB - Natural scene images often contain a lot of important texts, which carry the information we need, so it has important practical value to locate text information. This paper proposes a Cascade Classifier Text Localization (CCTL) algorithm. Firstly, a cascade classification algorithm based on Real AdaBoost is proposed to improve the accuracy of text localization. Secondly, a perceptual-based grouping algorithm is proposed to establish a perceptual organization framework. The use of adjacency and similar rules to group texts can improve the effect of text grouping. The proposed algorithm is verified and evaluated on the ICDAR dataset. At the same time, it is compared with other algorithms. The experimental results show that the proposed method has superiority in natural scene text detection.

KW - Cascade classifier

KW - Perceptual organizational framework

KW - Real AdaBoost

KW - Scene text detection

UR - https://www.scopus.com/pages/publications/85111983501

U2 - 10.1007/978-3-030-78618-2_16

DO - 10.1007/978-3-030-78618-2_16

M3 - 会议稿件

AN - SCOPUS:85111983501

SN - 9783030786175

T3 - Communications in Computer and Information Science

SP - 200

EP - 210

BT - Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings

A2 - Sun, Xingming

A2 - Zhang, Xiaorui

A2 - Xia, Zhihua

A2 - Bertino, Elisa

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 19 July 2021 through 23 July 2021

ER -

Qiao X, Yin M, Kong L, Wang B, Chang X, Ma Q et al. CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image. In Sun X, Zhang X, Xia Z, Bertino E, editors, Advances in Artificial Intelligence and Security - 7th International Conference, ICAIS 2021, Proceedings. Springer Science and Business Media Deutschland GmbH. 2021. p. 200-210. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-78618-2_16

CCTL: Cascade Classifier Text Localization Algorithm in Natural Scene Image

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this