Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion

Xiao Jie Jin; Qiu Feng Wang; Xinwen Hou; Cheng Lin Liu

doi:10.1109/ACPR.2013.7

Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion

Xiao Jie Jin, Qiu Feng Wang, Xinwen Hou, Cheng Lin Liu

Department of Intelligent Science

CAS - Institute of Automation

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

16 Citations (Scopus)

Abstract

The recognition of character strings in visual gestures has many potential applications, yet the segmentation of characters is a great challenge since the pen lift information is not available. In this paper, we propose a visual gesture character string recognition method using the classification-based segmentation strategy. In addition to the character classifier and character geometry models used for evaluating candidate segmentation-recognition paths, we introduce deletion geometry models for deleting stroke segments that are likely to be ligatures. To perform experiments, we built a Kinect-based fingertip trajectory capturing system to collect gesture string data. Experiments of digit string recognition show that the deletion geometry models improve the string recognition accuracy significantly. The string-level correct rate is over 80%.

Original language	English
Title of host publication	2013 2nd IAPR Asian Conference on Pattern Recognition
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	120-124
Number of pages	5
ISBN (Electronic)	978-1-4799-2190-4
DOIs	https://doi.org/10.1109/ACPR.2013.7
Publication status	Published - 2013
Event	2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013 - Naha, Okinawa, Japan Duration: 5 Nov 2013 → 8 Nov 2013

Conference

Conference	2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013
Country/Territory	Japan
City	Naha, Okinawa
Period	5/11/13 → 8/11/13

Keywords

Deletion geometry model
Kinect
Over-segmentation
String recognition
Visual gesture character string

Access to Document

10.1109/ACPR.2013.7

Cite this

@inproceedings{6d8eca430b014469a1585355cbf9b3eb,

title = "Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion",

abstract = "The recognition of character strings in visual gestures has many potential applications, yet the segmentation of characters is a great challenge since the pen lift information is not available. In this paper, we propose a visual gesture character string recognition method using the classification-based segmentation strategy. In addition to the character classifier and character geometry models used for evaluating candidate segmentation-recognition paths, we introduce deletion geometry models for deleting stroke segments that are likely to be ligatures. To perform experiments, we built a Kinect-based fingertip trajectory capturing system to collect gesture string data. Experiments of digit string recognition show that the deletion geometry models improve the string recognition accuracy significantly. The string-level correct rate is over 80%.",

keywords = "Deletion geometry model, Kinect, Over-segmentation, String recognition, Visual gesture character string",

author = "Jin, {Xiao Jie} and Wang, {Qiu Feng} and Xinwen Hou and Liu, {Cheng Lin}",

year = "2013",

doi = "10.1109/ACPR.2013.7",

language = "English",

pages = "120--124",

booktitle = "2013 2nd IAPR Asian Conference on Pattern Recognition",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013 ; Conference date: 05-11-2013 Through 08-11-2013",

}

Jin, XJ, Wang, QF, Hou, X & Liu, CL 2013, Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion. in 2013 2nd IAPR Asian Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., pp. 120-124, 2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013, Naha, Okinawa, Japan, 5/11/13. https://doi.org/10.1109/ACPR.2013.7

Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion. / Jin, Xiao Jie; Wang, Qiu Feng; Hou, Xinwen et al.
2013 2nd IAPR Asian Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., 2013. p. 120-124.

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

TY - GEN

T1 - Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion

AU - Jin, Xiao Jie

AU - Wang, Qiu Feng

AU - Hou, Xinwen

AU - Liu, Cheng Lin

PY - 2013

Y1 - 2013

N2 - The recognition of character strings in visual gestures has many potential applications, yet the segmentation of characters is a great challenge since the pen lift information is not available. In this paper, we propose a visual gesture character string recognition method using the classification-based segmentation strategy. In addition to the character classifier and character geometry models used for evaluating candidate segmentation-recognition paths, we introduce deletion geometry models for deleting stroke segments that are likely to be ligatures. To perform experiments, we built a Kinect-based fingertip trajectory capturing system to collect gesture string data. Experiments of digit string recognition show that the deletion geometry models improve the string recognition accuracy significantly. The string-level correct rate is over 80%.

AB - The recognition of character strings in visual gestures has many potential applications, yet the segmentation of characters is a great challenge since the pen lift information is not available. In this paper, we propose a visual gesture character string recognition method using the classification-based segmentation strategy. In addition to the character classifier and character geometry models used for evaluating candidate segmentation-recognition paths, we introduce deletion geometry models for deleting stroke segments that are likely to be ligatures. To perform experiments, we built a Kinect-based fingertip trajectory capturing system to collect gesture string data. Experiments of digit string recognition show that the deletion geometry models improve the string recognition accuracy significantly. The string-level correct rate is over 80%.

KW - Deletion geometry model

KW - Kinect

KW - Over-segmentation

KW - String recognition

KW - Visual gesture character string

UR - http://www.scopus.com/inward/record.url?scp=84899060434&partnerID=8YFLogxK

U2 - 10.1109/ACPR.2013.7

DO - 10.1109/ACPR.2013.7

M3 - Conference Proceeding

AN - SCOPUS:84899060434

SP - 120

EP - 124

BT - 2013 2nd IAPR Asian Conference on Pattern Recognition

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013

Y2 - 5 November 2013 through 8 November 2013

ER -

Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this