Text-independent writer identification using SIFT descriptor and contour-directional feature
Text-independent writer identification using SIFT descriptor and contour-directional feature
复制标题
DOI：
10.1109/icdar.2015.7333732
复制
发表时间：
2015-08
期刊：
影响因子：
--
通讯作者：
Yu-Jie Xiong;Y. Wen;P. Wang;Yue Lu
中科院分区：
文献类型：
--
作者：
Yu-Jie Xiong;Y. Wen;P. Wang;Yue Lu
本文提出了一种基于SIFT描述子和轮廓方向特征（CDF）的文本无关作者识别方法。所提出的方法包括两个阶段。在第一阶段中，局部纹理模式的码本是通过聚类一组SIFT描述符从图像中提取。使用该码本，计算出现直方图以确定不同图像之间的相似性。对于每个图像，我们获得参考图像的候选列表。下一阶段是使用轮廓方向特征和SIFT描述符来细化候选列表。该方法使用两个数据集进行评估：ICFHR 2012-Latin数据集和ICDAR 2013数据集。实验结果表明，该方法优于现有的算法，并取得了最佳的性能。
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.