Perceptual image hashing using center-symmetric local binary patterns
| Autor: | Khashayar Yaghmaie, Reza Davarzani, Saeed Mozaffari |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Computer Networks and Communications
Local binary patterns Computer science Feature vector Feature extraction Hash function ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Locality-sensitive hashing 0202 electrical engineering electronic engineering information engineering Media Technology Computer vision Digital watermarking Universal hashing business.industry Dynamic perfect hashing 020207 software engineering Pattern recognition Watermark Hardware and Architecture Feature (computer vision) Locality preserving hashing 020201 artificial intelligence & image processing Feature hashing Artificial intelligence business Software |
| Zdroj: | Multimedia Tools and Applications. 75:4639-4667 |
| ISSN: | 1573-7721 1380-7501 |
| DOI: | 10.1007/s11042-015-2496-6 |
| Popis: | Perceptual image hashing finds increasing attention in several multimedia security applications such as image identification/authentication, tamper detection, and watermarking. Robust feature extraction is the main challenge in hashing schemes. Local binary pattern (LBP) is a new feature which is due to its simplicity, discriminative power, computational efficiency, and robustness to illumination changes has been used in various image applications. In this paper, we propose a robust image hashing scheme using center-symmetric local binary patterns (CSLBP). In the proposed image hashing, CSLBP features are extracted from each non-overlapping block within the original gray-scale image. For each block, the final hash code is obtained by inner product of its CSLBP feature vector and a pseudorandom weight vector. Furthermore, singular value decomposition (SVD) is combined with CSLBP to introduce a more robust hashing method called SVD-CSLBP. Performances of the proposed hashing schemes are evaluated with two groups of popular applications in perceptual image hashing schemes: image identification and image authentication. Experimental results show that the proposed methods are robust to a wide range of distortions and attacks such as additive noise, blurring, brightness changes and JPEG compression. Moreover, the proposed methods have this capability to localize the tampering area, which is not possible in all hashing schemes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink