Study on rotation-invariant texture feature extraction for tire pattern retrieval

详细信息    查看全文

• 作者：Ying Liu ; Haoyang Yan ; Keng-Pang Lim
• 关键词：Tire pattern retrieval ; Texture feature extraction ; Rotation invariance ; Radon transform ; Curvelet transform
• 刊名：Multidimensional Systems and Signal Processing
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：28
• 期：2
• 页码：757-770
• 全文大小：
• 刊物类别：Engineering
• 刊物主题：Circuits and Systems; Electrical Engineering; Signal,Image and Speech Processing; Artificial Intelligence (incl. Robotics);
• 出版者：Springer US
• ISSN：1573-0824
• 卷排序：28

文摘

One key task in forensic science is to perform criminal investigation through image database retrieval. Of the various images, tire pattern is an important type of image data for crime scene investigation. However, different rotation and direction of tire patterns are often encountered and is insufficient to use the conventional multi-scale texture feature extraction method which is not rotational invariant. To alleviate this problem, the paper proposed two new texture feature extraction methods based on the Radon transform and Curvelet transform. The experiments were conducted using a tire pattern database containing 400 images. The results show that the proposed methods effectively overcome the influences of rotation and significantly improve the retrieval efficiency.