跳到主要导航 跳到搜索 跳到主要内容

Text-independent writer identification using SIFT descriptor and contour-directional feature

  • East China Normal University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

This paper presents a method for text-independent writer identification using SIFT descriptor and contour-directional feature (CDF). The proposed method contains two stages. In the first stage, a codebook of local texture patterns is constructed by clustering a set of SIFT descriptors extracted from images. Using this codebook, the occurrence histograms are calculated to determine the similarities between different images. For each image, we obtain a candidate list of reference images. The next stage is to refine the candidate list using the contour-directional feature and SIFT descriptor. The proposed method is evaluated with two datasets: the ICFHR2012-Latin dataset and the ICDAR2013 dataset. Experimental results show that the proposed method outperforms the state-of-the-art algorithms and archives the best performance.

源语言英语
主期刊名13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
出版商IEEE Computer Society
页91-95
页数5
ISBN(电子版)9781479918058
DOI
出版状态已出版 - 20 11月 2015
活动13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Nancy, 法国
期限: 23 8月 2015 → 26 8月 2015

丛书

姓名Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
卷2015-November
ISSN(电子版)2379-2140

会议

会议13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015
国家/地区法国
市Nancy
时期23/08/15 → 26/08/15

学术指纹

探究 'Text-independent writer identification using SIFT descriptor and contour-directional feature' 的科研主题。它们共同构成独一无二的学术指纹。

引用此