Font identification using the grating cell texture operator

Huanfeng Ma; David Doermann

doi:10.1117/12.586345

Font identification using the grating cell texture operator

Huanfeng Ma
, David Doermann

Department of Computer Science and Engineering

University of Maryland, College Park

Research output: Contribution to journal › Conference article › peer-review

12 Scopus citations

Abstract

In this paper, a new feature extraction operator, the grating cell operator, is applied to analyze the texture features and classify fonts of scanned document images. This operator is compared with the isotropic Gabor filter which was also employed for font classification. In order to improve the performance, a back-propagation neural network (BPNN) classifier was applied and compared with the simple weighted Euclidean distance (WED) classifier. Experimental results for five fonts of three scripts show that the grating cell operator performs better than the isotropic Gabor filter, and the BPNN classifier can provide more accurate classification results than the WED classifier.

Original language	English
Article number	17
Pages (from-to)	148-156
Number of pages	9
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5676
DOIs	https://doi.org/10.1117/12.586345
State	Published - 2005
Event	Proceedings of SPIE-IS and T Electronic Imaging - Document Recognition and Retrieval XII - San Jose, CA, United States Duration: Jan 19 2005 → Jan 20 2005

Keywords

Back-propagation Neural Network (BPNN)
Document Analysis
Font Identification
Gabor Filter
Grating Cell Operator
Optical Character Recognition (OCR)

Access to Document

10.1117/12.586345

Cite this

@article{73e3fcfb60b34508896355ef98b7064b,

title = "Font identification using the grating cell texture operator",

abstract = "In this paper, a new feature extraction operator, the grating cell operator, is applied to analyze the texture features and classify fonts of scanned document images. This operator is compared with the isotropic Gabor filter which was also employed for font classification. In order to improve the performance, a back-propagation neural network (BPNN) classifier was applied and compared with the simple weighted Euclidean distance (WED) classifier. Experimental results for five fonts of three scripts show that the grating cell operator performs better than the isotropic Gabor filter, and the BPNN classifier can provide more accurate classification results than the WED classifier.",

keywords = "Back-propagation Neural Network (BPNN), Document Analysis, Font Identification, Gabor Filter, Grating Cell Operator, Optical Character Recognition (OCR)",

author = "Huanfeng Ma and David Doermann",

year = "2005",

doi = "10.1117/12.586345",

language = "English",

volume = "5676",

pages = "148--156",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Proceedings of SPIE-IS and T Electronic Imaging - Document Recognition and Retrieval XII ; Conference date: 19-01-2005 Through 20-01-2005",

}

TY - JOUR

T1 - Font identification using the grating cell texture operator

AU - Ma, Huanfeng

AU - Doermann, David

PY - 2005

Y1 - 2005

N2 - In this paper, a new feature extraction operator, the grating cell operator, is applied to analyze the texture features and classify fonts of scanned document images. This operator is compared with the isotropic Gabor filter which was also employed for font classification. In order to improve the performance, a back-propagation neural network (BPNN) classifier was applied and compared with the simple weighted Euclidean distance (WED) classifier. Experimental results for five fonts of three scripts show that the grating cell operator performs better than the isotropic Gabor filter, and the BPNN classifier can provide more accurate classification results than the WED classifier.

AB - In this paper, a new feature extraction operator, the grating cell operator, is applied to analyze the texture features and classify fonts of scanned document images. This operator is compared with the isotropic Gabor filter which was also employed for font classification. In order to improve the performance, a back-propagation neural network (BPNN) classifier was applied and compared with the simple weighted Euclidean distance (WED) classifier. Experimental results for five fonts of three scripts show that the grating cell operator performs better than the isotropic Gabor filter, and the BPNN classifier can provide more accurate classification results than the WED classifier.

KW - Back-propagation Neural Network (BPNN)

KW - Document Analysis

KW - Font Identification

KW - Gabor Filter

KW - Grating Cell Operator

KW - Optical Character Recognition (OCR)

UR - https://www.scopus.com/pages/publications/21944453152

U2 - 10.1117/12.586345

DO - 10.1117/12.586345

M3 - Conference article

AN - SCOPUS:21944453152

SN - 0277-786X

VL - 5676

SP - 148

EP - 156

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

M1 - 17

T2 - Proceedings of SPIE-IS and T Electronic Imaging - Document Recognition and Retrieval XII

Y2 - 19 January 2005 through 20 January 2005

ER -

Font identification using the grating cell texture operator

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this