Multiresolution analysis in extraction of reference lines from documents with gray level background

Yuan Y. Tang; Hong Ma; Jiming Liu; Bing Fa Li; Dihua Xi

doi:10.1109/34.608296

Multiresolution analysis in extraction of reference lines from documents with gray level background

Yuan Y. Tang^*, Hong Ma, Jiming Liu, Bing Fa Li, Dihua Xi

^*Corresponding author for this work

Department of Computer Science

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

44 Citations (Scopus)

Abstract

Based on wavelets, a new theoretical method has been developed to process multi-gray level documents. In this method, two-dimensional multiresolution analysis, wavelet decomposition algorithm, and compactly supported orthonormal wavelets are used to transform a document image into sub-images. According to these sub-images, the reference lines of a multi-gray level document can be extracted, and knowledge about the geometric structure of the document can be acquired. Particularly, this approach is more efficient to process form documents with gray level background. Experiments indicate that this new method can be applied to process documents with promising results.

Original language	English
Pages (from-to)	921-926
Number of pages	6
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	19
Issue number	8
DOIs	https://doi.org/10.1109/34.608296
Publication status	Published - Aug 1997

Scopus Subject Areas

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

User-Defined Keywords

Compactly supported orthonormal wavelets
Document analysis
Sub-image
Two-dimensional multiresolution analysis
Wavelet decomposition algorithm
Wavelets

Access to Document

10.1109/34.608296

Cite this

@article{987b76143e47446d84cf80655634b1c3,

title = "Multiresolution analysis in extraction of reference lines from documents with gray level background",

abstract = "Based on wavelets, a new theoretical method has been developed to process multi-gray level documents. In this method, two-dimensional multiresolution analysis, wavelet decomposition algorithm, and compactly supported orthonormal wavelets are used to transform a document image into sub-images. According to these sub-images, the reference lines of a multi-gray level document can be extracted, and knowledge about the geometric structure of the document can be acquired. Particularly, this approach is more efficient to process form documents with gray level background. Experiments indicate that this new method can be applied to process documents with promising results.",

keywords = "Compactly supported orthonormal wavelets, Document analysis, Sub-image, Two-dimensional multiresolution analysis, Wavelet decomposition algorithm, Wavelets",

author = "Tang, {Yuan Y.} and Hong Ma and Jiming Liu and Li, {Bing Fa} and Dihua Xi",

note = "Funding Information: This work was supported by research grants received from Research Grant Council (RGC) of Hong Kong, and Faculty Research Grant (FRG) of Hong Kong Baptist University. This work was also supported by the Ministry of Education of the People{\textquoteright}s Republic of China, and Sichuan University, China. We wish to express our gratitude to Professors Zhisheng You, Jiansun Nie, Hui Li, and other staff members at the Hong Kong Baptist University and Sichuan University, China, for their assistance in our research project.",

year = "1997",

month = aug,

doi = "10.1109/34.608296",

language = "English",

volume = "19",

pages = "921--926",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE",

number = "8",

}

TY - JOUR

T1 - Multiresolution analysis in extraction of reference lines from documents with gray level background

AU - Tang, Yuan Y.

AU - Ma, Hong

AU - Liu, Jiming

AU - Li, Bing Fa

AU - Xi, Dihua

N1 - Funding Information: This work was supported by research grants received from Research Grant Council (RGC) of Hong Kong, and Faculty Research Grant (FRG) of Hong Kong Baptist University. This work was also supported by the Ministry of Education of the People’s Republic of China, and Sichuan University, China. We wish to express our gratitude to Professors Zhisheng You, Jiansun Nie, Hui Li, and other staff members at the Hong Kong Baptist University and Sichuan University, China, for their assistance in our research project.

PY - 1997/8

Y1 - 1997/8

N2 - Based on wavelets, a new theoretical method has been developed to process multi-gray level documents. In this method, two-dimensional multiresolution analysis, wavelet decomposition algorithm, and compactly supported orthonormal wavelets are used to transform a document image into sub-images. According to these sub-images, the reference lines of a multi-gray level document can be extracted, and knowledge about the geometric structure of the document can be acquired. Particularly, this approach is more efficient to process form documents with gray level background. Experiments indicate that this new method can be applied to process documents with promising results.

AB - Based on wavelets, a new theoretical method has been developed to process multi-gray level documents. In this method, two-dimensional multiresolution analysis, wavelet decomposition algorithm, and compactly supported orthonormal wavelets are used to transform a document image into sub-images. According to these sub-images, the reference lines of a multi-gray level document can be extracted, and knowledge about the geometric structure of the document can be acquired. Particularly, this approach is more efficient to process form documents with gray level background. Experiments indicate that this new method can be applied to process documents with promising results.

KW - Compactly supported orthonormal wavelets

KW - Document analysis

KW - Sub-image

KW - Two-dimensional multiresolution analysis

KW - Wavelet decomposition algorithm

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=0031212798&partnerID=8YFLogxK

U2 - 10.1109/34.608296

DO - 10.1109/34.608296

M3 - Journal article

AN - SCOPUS:0031212798

SN - 0162-8828

VL - 19

SP - 921

EP - 926

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 8

ER -

Multiresolution analysis in extraction of reference lines from documents with gray level background

Abstract

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this