Последнее обновление: 25.10.2006   Статьи / Сегментирование


Adaptive Region Growing Color Segmentation for Text using Irregular Pyramid Авторы: Poh Kok Loo and Chew Lim Tan
Организация: School of the Built Environment & Design, Singapore Polytechnic
Дата: 2003-2005 год
Кол-во страниц: 12
This paper presents the result of an adaptive region growing segmentation technique for color document images using an irregular pyramid structure. The emphasis is in the segmentation of textual components for subsequence extraction in document analysis. The segmentation is done in the RGB color space. A simple color distance measurement and a category of color thresholds are derived. The proposed method utilizes a hybrid approach where color feature based clustering followed by detailed region based segmentation is performed. Clustering is done by merging image color points surrounding a color seed selected dynamically. The clustered regions are then put through a detailed segmentation process where an irregular pyramid structure is utilized. Dynamic and repeating selection of the most suitable seed region, fitting changing local condition during the segmentation, is implemented. The growing of regions is done through the use of multiple seeds growing concurrently. The algorithm is evaluated according to 2 factors and compared with an existing method. The result is encouraging and demonstrates the ability and efficiency of our algorithm in achieving the segmentation task.
 Скачать файл (203 Кб)

Automated borders detection and adaptive segmentation for binary document images Авторы: Daniel X. Le, George R. Thoma
Организация: Harry Wechsler National Library of Medicine
Дата: 1997-2000 год
Кол-во страниц: 6
This paper describes two new and effective algorithms: one for detecting the page borders for documents available as binary images, and the other an adaptive segmentation algorithm using a bottom-up approach for segmenting binary images into blocks. The borders detection algorithm relies upon the classification of blank/textual/non-textual rows and columns, objects' segmentation, and an analysis of projection profiles and crossing counts. Segmentation, done by an adaptive smearing technique, is different from all previous bottom-up approaches because any decisions on merging and/or separating are based on the estimated font information in binary document images.
 Скачать файл (51 Кб)

Организация: Elsag spa Via Puccini 2 - 16154 Genova, - ITALY Polo Nazionale Bioelettronica Via Roma 28 57030 Marciana (LI) - ITALY
Дата: 2000 год
Кол-во страниц: 6
A simple procedure for cursive word oversegmentation is presented, which is based on the analysis of the handwritten profiles and on the extraction of “white holes”. It follows the policy of using simple rules on complex data and sophisticated rules on simpler data. Experimental results show robustness and performances comparable with the best ones presented in the literature.
 Скачать файл (45 Кб)

Организация: Dipartimento di Ing. Elettronica - Politecnico di Bari - Italy Dipartimento di Informatica - Universita di Bari - Italy
Дата: 2000 год
Кол-во страниц: 6
In the field of Optical Character Recognition (OCR), zoning is used to extract topological information from patterns. In this paper zoning is considered as the result of an optimisation problem and a new technique is presented for automatic zoning. More precisely, local analysis of feature distribution based on Shannon’s entropy estimation is performed to determine “core” zones of patterns. An iterative region-growing procedure is applied on the “core” zones to determine the final zoning.
 Скачать файл (59 Кб)

Word Separation in Handwritten Legal Amounts on Bank Cheques Based on Spatial Gap Distances Авторы: In Cheol Kim, Kyoung Min Kim, and Ching Y. Suen
Организация: CENPARMI, Concordia University, Montreal, Canada
Дата: 2004 год
Кол-во страниц: 10
This paper presents an efficient method of separating words in handwritten legal amounts on bank cheques based on the spatial gaps between connected components. Currently all typical existing gap measures suffer from poor performance due to the inherent problem of underestimation and overestimation. In order to decrease such burden, a modified version for each of those existing measures is explored. Also, a new method of combining three different types of distance measures based on 4-class clustering is proposed to reduce the errors generated by each measure. In experiments on real bank cheque database, the modified distance measures show about 3% of better separation rate than their original counterparts. In addition, by applying the combining method, further improvement in word separation was achieved.
 Скачать файл (256 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.