A document recognition system and its applications

Yamashita, Atsushi; Amano, Tomio; Hirayama, Yoshikazu; Itoh, Nobuyasu; Katoh, Shunji; Mano, Takashi; Toyokawa, Kazuharu

doi:10.1147/rd.403.0341

Cited by 7 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous works for geometric structure analysis are classified into three categories: top-down [3], [15], [16], bottom-up [4], [10], [11], [17], [18], [19], [20], and hybrid techniques [21], [22], [23], [24], [25]. Especially, the recent paper by Jain and Yu [4] contains a brief chronological survey of previous works on geometric layout analysis.…”

Section: Related Workmentioning

confidence: 99%

“…Paper-based documents are less efficient than electronic documents from the perspective of document processing, such as storage, retrieval, and modification. Therefore, there has recently been a growing interest in a document image analysis and understanding [1], [2], [3], [4], [5], [6], [7] which consists of two phases: geometric structure analysis and logical structure analysis, to transform a paper-based document into its electronic version.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geometric structure analysis of document images: a knowledge-based approach

Lee

Choy

Cho

2000

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

ÐGeometric structure analysis is a prerequisite to create electronic documents from logical components extracted from document images. This paper presents a knowledge-based method for sophisticated geometric structure analysis of technical journal pages. The proposed knowledge base encodes geometric characteristics that are not only common in technical journals but also publication-specific in the form of rules. The method takes the hybrid of top-down and bottom-up techniques and consists of two phases: region segmentation and identification. Generally, the result of the segmentation process does not have a one-to-one matching with composite layout components. Therefore, the proposed method identifies nontext objects, such as images, drawings, and tables, as well as text objects, such as text lines and equations, by splitting or grouping segmented regions into composite layout components. Experimental results with 372 images scanned from the IEEE Transactions on Pattern Analysis and Machine Intelligence show that the proposed method has performed geometric structure analysis successfully on more than 99 percent of the test images, resulting in impressive performance compared with previous works.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Geometric structure analysis of document images: a knowledge-based approach

Lee

Choy

Cho

2000

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

show abstract

“…Over the past few decades, many methods for text block identification have been proposed [1,2,3,4,5,6,7,8,9,10,11,12,13], following either the top-down or the bottomup strategy. In general, top-down approaches start from the whole image and then segment it recursively into subregions [9].…”

Section: Introductionmentioning

confidence: 99%

Image patches analysis for text block identification

Zhong

Cheriet

2012

2012 11th International Conference on Information Science, Signal Processing and Their Applications (ISSPA)

View full text Add to dashboard Cite

In this paper, we propose a novel text block identification method for ancient document understanding. Unlike traditional top-down and bottom-up approaches, our method is based on supervised learning on the patches of document images, which can be considered as an intermediate level method but integrates essential advantages of both the top-down and the bottom-up strategies. In our method, the document images are firstly partitioned into small patches, and then positive and negative patches are selected to form an active training set. Gabor features are extracted on each patch, while multi-linear discriminant analysis (MDA) is employed to reduce the dimensionality of the data. To deal with unseen documents, a random forest classifier is learned on the new representations of the patches. Compared to traditional approaches, our method can not only capture local texture features of each patch, but also preserve the global information of the training images. Furthermore, MDA is guaranteed to learn a low dimensional tensor subspace, which significantly avoids the curse of dimensionality dilemma. Moreover, the random forest classifier can automatically select useful features and deliver satisfactory identification results. Extensive experiments on some scripts of ancient document images demonstrated the effectiveness of our method.

show abstract

Tensor representation learning based image patch analysis for text identification and recognition

Zhong

Cheriet

2015

Pattern Recognition

View full text Add to dashboard Cite

A document recognition system and its applications

Cited by 7 publications

References 9 publications

Geometric structure analysis of document images: a knowledge-based approach

Geometric structure analysis of document images: a knowledge-based approach

Image patches analysis for text block identification

Tensor representation learning based image patch analysis for text identification and recognition

Contact Info

Product

Resources

About