Title :
Study on texture feature extraction from forensic images with watermark
Author :
Ying Liu ; Zong Li
Author_Institution :
Inst. of Image & Inf. Process., Xi´an Univ. of Posts & Telecommun., Xi´an, China
Abstract :
In order to protect the legitimacy and integrity of Criminal Scene Investigation image data, digital watermark can be embedded into the images, as evidence of identification of illegal infringement. This paper studies on texture feature extraction from forensic tyre tread patterns with watermark, in order for automatic tyre tread pattern retrieval. Intensive literature survey shows that this work is the first on feature extraction from forensic images with watermark. A new Tamura feature extraction algorithm is presented and compared with state-of-the-art texture feature extraction methods. Experimental results demonstrate the promising performance of the proposed algorithm in forensic tyre tread pattern image retrieval.
Keywords :
feature extraction; image forensics; image retrieval; image texture; image watermarking; Tamura feature extraction algorithm; automatic tyre tread pattern retrieval; criminal scene investigation image data; digital watermark; forensic images; forensic tyre tread pattern image retrieval; illegal infringement; texture feature extraction; Feature extraction; Forensics; Histograms; Image retrieval; Tires; Watermarking; Digital watermark; Image Retrieval; LSB algorithm; Statistical moments; Tamura feature;
Conference_Titel :
Industrial Electronics and Applications (ICIEA), 2014 IEEE 9th Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4799-4316-6
DOI :
10.1109/ICIEA.2014.6931401