Image Hashing Based on CS-LBP and DCT for Copy Detection

In order to improve the accuracy and speed of copy detection, we propose an image hashing algorithm based on local feature and global feature in this paper. Firstly, input image is converted to a normalized image. Then, wavelet decomposition is applied to the preprocessed image to produce approximate image and high-frequency information. Center symmetric local binary pattern (CS-LBP) is applied to approximate image to produce a CS-LBP texture image. The local feature is extracted by dividing blocks and selecting mean, variance, third moment, fourth moment statistics feature in CS-LBP texture image. The global feature is extracted by selecting the discrete cosine transform (DCT) coefficients of high frequency-information. Finally, local features and global features are combined to generate image hashing. Experiment with open images are carried out and the results show that the proposed algorithm is robust and discriminative. The precision rate and the recall rate (P-R) curve comparisons show that our hashing algorithm outperforms some existing hashing algorithms in copy detection.

[1]  Xingming Sun,et al.  Effective and Efficient Global Context Verification for Image Copy Detection , 2017, IEEE Transactions on Information Forensics and Security.

[2]  Hefei Ling,et al.  Iterated local search optimized hashing for image copy detection , 2014, Multimedia Tools and Applications.

[3]  Zhenjun Tang,et al.  Robust image hashing with dominant DCT coefficients , 2014 .

[4]  Hefei Ling,et al.  Efficient Image Copy Detection Using Multiscale Fingerprints , 2012, IEEE MultiMedia.

[5]  Shang-Lin Hsieh,et al.  A novel approach to detecting duplicate images using multiple hash tables , 2014, Multimedia Tools and Applications.

[6]  Shin'ichi Satoh,et al.  Improving the performance of SIFT and CSLBP for image copy detection , 2013, 2013 36th International Conference on Telecommunications and Signal Processing (TSP).

[7]  Shinfeng D. Lin,et al.  An effective content-based copy detection scheme for image authentication , 2014, 2014 International Conference on Machine Learning and Cybernetics.

[8]  Xinpeng Zhang,et al.  Robust Hashing for Image Authentication Using Zernike Moments and Local Features , 2013, IEEE Transactions on Information Forensics and Security.

[9]  Changick Kim,et al.  Content-based image copy detection , 2003, Signal Process. Image Commun..

[10]  Thierry Pun,et al.  Performance evaluation in content-based image retrieval: overview and proposals , 2001, Pattern Recognit. Lett..

[11]  Xingming Sun,et al.  Combination of SIFT Feature and Convex Region-Based Global Context Feature for Image Copy Detection , 2014, IWDW.

[12]  C. Schmid,et al.  Description of Interest Regions with Center-Symmetric Local Binary Patterns , 2006, ICVGIP.

[13]  Zhenxing Qian,et al.  Robust Image Hashing via Random Gabor Filtering and DWT , 2018 .

[14]  K. Rhee,et al.  A key-dependent secure image hashing scheme by using Radon transform , 2009, 2009 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS).

[15]  Shichao Zhang,et al.  Robust Image Hashing With Ring Partition and Invariant Vector Distance , 2016, IEEE Transactions on Information Forensics and Security.

[16]  Hefei Ling,et al.  Feature fusion based hashing for large scale image copy detection , 2014, Fifth International Conference on Intelligent Control and Information Processing.

[17]  Vishal Monga,et al.  Robust and Secure Image Hashing via Non-Negative Matrix Factorizations , 2007, IEEE Transactions on Information Forensics and Security.

[18]  Jamshed Siddiqui,et al.  Robust image hashing based on statistical features for copy detection , 2016, 2016 IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics Engineering (UPCON).

[19]  Yun Lin,et al.  Weighted Sparse Image Classification based on Low Rank Representation , 2018 .