Последнее обновление: 25.10.2006   Статьи / Определение типа шрифта

Определение типа шрифта

A Study of Document Image Degradation Effects on Font Recognition Авторы: Abdelwahab Zramdini and Rolf Ingold
Организация: Institute of Informatics, University of Fribourg
Дата: ориентировочно 1996-2000 год
Кол-во страниц: 4
A font recognition system allowing the identification of font families, weights, slopes and sizes with an accuracy of 99% for weights and slopes and 96% for families and sizes, has been developed. Our system uses a knowledge base of 240 fonts models, which have been created from a training set of text images written with these different fonts. In this paper, a study of image degradations effects on the system performances, is presented. The evaluation that has been carried out, shows that the system is robust against natural degradations such as those introduced by scanning and photocopying, but its performances decrease with very degraded document images. In order to avoid this weakness, a degradation modeling strategy has been adopted, allowing an automatic adaptation of the system to these degradations. The adaptation is derived from statistical analysis of features behavior against degradations and is performed by specific transformations applied to the system knowledge base. Some promising results are reported.
 Скачать файл (39 Кб)

Italic Font Recognition Using Stroke Pattern Analysis on Wavelet Decomposed Word Images Авторы: Li Zhang, Yue Lu, Chew Lim Tan
Организация: Department of Computer Science, School of Computing National University of Singapore
Дата: ориентировочно 2002-2005 год
Кол-во страниц: 4
This paper describes an italic font recognition method using stroke pattern analysis on wavelet decomposed word images. The word images are extracted from scanned text documents containing word objects in various fonts and styles. Earlier font recognition methods mainly focus on slanted texture or pattern analysis on single character or large text blocks, which are sensitive to noise and subject to font and style variations such as size, serifness, boldness, etc. Our method takes advantage of 2-D wavelet decomposition on each word image and performs statisticalanalysisonstrokepatternsobtainedfromwavelet decomposed sub-images. Experiments are carried out with 22,384 frequently used word images in both normal and italic styles of four different fonts. On average, a recognition accuracy of 95.76% for normal style and 96.49% for italic style is achieved. Experiments conducted on word images extracted from scanned documents with scattered italicwords also show an encouraging result.
 Скачать файл (110 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.