Последнее обновление: 25.10.2006   Статьи / Предобработка страниц

Предобработка страниц

A pattern-based method for document structure recognition Авторы: Lyse Robadey, Oliver Hitz, Rolf Ingold
Организация: DIUF, University of Fribourg, Switzerland
Дата: 2001-2005 год
Кол-во страниц: 4
This paper describes a classification method applied to the recognition of documents with complex structure. The classification is driven by a model in two parts: static configuration construction rules and a dynamic pattern database. The method has been applied to segment and frame classification and test results are good enough to be used in further recognition steps. A strong point of the methodis itsability to improve with use. We are now working on making the configuration construction rules dynamic. The anticipated benefit will be that the system, driven by the user, will find the ideal level of specificity of the model. As seen in previous point, highly specific models lead to long learning phases. On the other hand, generalmodels lead to conflicts. With sucha modification we expect sensible improvements.
 Скачать файл (343 Кб)

Automated Page Orientation and Skew Angle Detection for Binary Document Images Авторы: D. X. Le, G. Thoma, H. Weschler
Организация: Pattern Recognition, Volume 27, Number 10, pp. 1325-1344
Дата: 1994 год
Кол-во страниц: 16
We describe the development and implementation of algorithms for detecting the page orientation (portrait/landscape) and the degree of skew for documents available as binary images. A new and fast approach is advanced herein whereby skew angle detection takes advantage of information found using the page orientation algorithm. Page orientation is accomplished using local analysis, while skew angle detection is implemented based on the processing of pixels of the last black runs of binary image objects. The experiments carried out on a variety of medical journals show the feasibility of the new approach and indicate that detection accuracy can be improved by minimizing the effects of non-textual data.
 Скачать файл (60 Кб)

Tools for Automatic Recognition of Character Strings in Maps Авторы: Line Eikvil, Kjersti Aas, Marit Holden
Организация: Norwegian Computing Center, Norway
Дата: 1993-1997 год
Кол-во страниц: 6
This paper describes tools for character string recognition on maps. Single character recognition is performed using elliptical Fourier descriptors applying a statistical classifier. The recognized characters are grouped into strings, and the syntax of these strings are then analysed to detect and correct errors. As training of the classifier is essential, tools for manual and automatic training and updating are included.
 Скачать файл (92 Кб)

Improved nearest neighbor based approach to accurate document skew estimation Авторы: Yue Lu, Chew Lim Tan
Организация: Department of Computer Science, School of Computing, National University of Singapore
Дата: 2003-2005 год
Кол-во страниц: 5
The nearest-neighbor based document skew detection methods do not require the presence of a predominant text area, and are not subject to skew angle limitation. However, the accuracy of these methods is not perfect in general. In this paper, we present an improved nearest-neighbor based approach to perform accurate document skew estimation. Size restriction is introduced to the detection of nearest-neighbor pairs. Then the chains with a largest possible number of nearest-neighbor pairs areselected,andtheirslopesarecomputedtogivetheskew angle of document image. Experimental results on various types of documents containing different linguistic scripts and diverse layouts show that the proposed approach has achieved an improved accuracy for estimating document image skew angle and has an advantage of being language independent.
 Скачать файл (351 Кб)

Separation of Overlapping Text from Graphics Авторы: Ruini Cao, Chew Lim Tan
Организация: School of Computing, National University of Singapore
Дата: 2003-2005 год
Кол-во страниц: 5
The separation of overlapping text from graphics is a challenging problem in document image analysis. This paper proposes a specific method for detecting and extracting characters that are touching graphics. It is based on the observation that the constituent strokes of characters are usually short segments in comparison with those of graphics. It combines line continuation with the feature line width to decompose and reconstruct segments underlying the region of intersection. Experimental results showed that the proposed method improved the percentage of correctly detected text as well as the accuracy of character recognition significantly.
 Скачать файл (119 Кб)

Text Extraction from Gray Scale Document Images Using Edge Information Авторы: Q. Yuan, C. L. Tan
Организация: Dept. of Computer Science, School of computing National University of Singapore
Дата: 2000-2003 год
Кол-во страниц: 5
In this paper we present a well designed method that makes use of edge information to extract textual blocks from gray scale document images. It aims at detecting textual regions on heavy noise infected newspaper images and separate them from graphical regions. The algorithm traces the feature points in different entities and then groups those edge points of textual regions. From using the technology of line approximation and layout categorization, it can successfully retrieve directional placed text blocks. Finally feature based connected component merging was introduced to gather homogeneous textual regions together within the scope of its bounding rectangles. We can obtain correct page decomposition with efficient computation and reduced memory size by handling line segments instead of small pixels. The proposed method has been tested on a large group of newspaper images with multiple page layouts, promising results approved the effectiveness of our method.
 Скачать файл (259 Кб)

Text Retrieval from Document Images based on Word Shape Analysis Авторы: Chew Lim Tan, Weihua Huang, Sam Yuan Sung, Zhaohui Yu and Yi Xu
Организация: School of Computing, National University of Singapore
Дата: 2000-2003 год
Кол-во страниц: 15
In this paper, we propose a method of text retrieval from document images using a similarity measure based on word shape analysis. We directly extract image features instead of using optical character recognition. Document images are segmented into word units and then features called vertical bar patterns are extracted from these word units through local extrema points detection. All vertical bar patterns are used to build document vectors. Lastly, we obtain the pair-wise similarity of document images by means of the scalar product of the document vectors. Four corpora of news articles were used to test the validity of our method. During the test, the similarity of document images using this method was compared with the result of ASCII version of those documents based on the N-gram algorithm for text documents.
 Скачать файл (50 Кб)

Text/Graphics Separation in Maps Авторы: Ruini Cao, Chew Lim Tan
Организация: School of Computing, National University of Singapore
Дата: 2000-2003 год
Кол-во страниц: 10
The separation of overlapping text and graphics is a challenging problem in document image analysis. This paper proposes a specific method of detecting and extracting characters that are touching graphics. It is based on the observation that the constituent strokes of characters are usually short segments in comparison with those of graphics. It combines line continuation with the feature line width to decompose and reconstruct segments underlying the region of intersection. Experimental results showed that the proposed method improved the percentage of correctly detected text as well as the accuracy of character recognition significantly.
 Скачать файл (85 Кб)

Word Searching in Document Images Using Word Portion Matching Авторы: Yue Lu and Chew Lim Tan
Организация: Department of Computer Science, School of Computing, National University of Singapore
Дата: 2002 год
Кол-во страниц: 10
An approach with the capability of searching a word portion in document images is proposed in this paper, to facilitate the detection and location of the user-specified query words. A feature string is synthesized according to the character sequence in the user-specified word, and each word image extracted from documents are represented by a feature string. Then, an inexact string matching technology is utilized to measure the similarity between the two feature strings, based on which we can estimate how the document word image is relevant to the user-specified word and decide whether its portion is the same as the user-specified word. Experimental results on real document images show that it is a promising approach, which is capable of detecting and locating the document words that entirely match or partially match with the user-specified word.
 Скачать файл (118 Кб)

WORD SHAPE RECOGNITION FOR IMAGE-BASED DOCUMENT RETRIEVAL Авторы: Weihua Huang, Chew Lim Tan, Sam Yuan Sung and Yi Xu
Организация: School of Computing, National University of Singapore
Дата: 2000-2003 год
Кол-во страниц: 4
In this paper, we propose a word shape recognition method for retrieving image-based documents. Document images are segmented at the word level first. Then the proposed method detects local extrema points in word segments to form so-called vertical bar patterns. These vertical bar patterns form the feature vector of a document. Scalar product of two document feature vectors is calculated to measure the pair-wise similarity of document images. The proposed method is robust to changing fonts and styles, and is less affected by degradation of document qualities. Three groups of words in different fonts and image qualities were used to test the validity of our method. Real-life document images were also used to test the method's ability of retrieving relevant documents.
 Скачать файл (35 Кб)


Поддержите проект материально!

рублей Яндекс.Деньгами
на счёт 41001275511292 (cr-online.ru)

Вы используете мой ресурс? Буду вам очень благодарен, если накоплю хотя бы на оплату хостинга.