Robust image hashing using ring partition-PGNMF and local features

Abstract

BackgroundImage authentication is one of the challenging research areas in the multimedia technology due to the availability of image editing tools. Image hash may be used for image authentication which should be invariant to perceptually similar image and sensitive to content changes. The challenging issue in image hashing is to design a system which simultaneously provides rotation robustness, desirable discrimination, sensitivity and localization of forged area with minimum hash length.MethodsIn this paper, a perceptually robust image hashing technique based on global and local features has been proposed. The Global feature was extracted using ring partition and projected gradient nonnegative matrix factorization (PGNMF). The ring partitioning technique converts a square image into a secondary image that makes the system rotation invariant. The PGNMF which is usually faster than the other NMFs has been used to reduce the dimension of the secondary image to generate the shorter hash sequence. The local features extracted from the salient regions of the image help to localize the forged region in the maliciously manipulated images. The image hashing techniques that use only global features are limited in discrimination.ResultsThe experimental results reveal that the proposed image hashing method based on global and local features provides better discrimination capability. The proposed hashing method is tested on large image sets collected from the different standard database. It is observed from the experimental results that the proposed system is robust to content-preserving operations and is capable of localizing the counterfeit area.ConclusionsThe combination of global and local features is robust against the content-preserving operations, which has a desirable discriminative capability. The proposed system may be used in image authentication, forensic evidence, and image retrieval, etc.

SSL: A Novel Image Hashing Technique Using SIFT Keypoints with Saliency Detection and LBP Feature Extraction against Combinatorial Manipulations

“…This method can be applied to image authentication and can detect malicious tampering. Karsh et al [22,23] also use global features and local features to generate image hash. The global features are obtained by using ring partition and projected gradient nonnegative 3 matrix factorization [22] or statistical feature distance [23], and the local features are extracted from the salient regions of an image.…”

Robust image hashing based on structural and perceptual features for authentication of color images

“…The hashes are reportedly rotation invariant, robust, and are useful against image security. A robust technique proposed in [19] extracts global and local features using projected gradient non-negative matrix factorization (PNMF) for content preserving objective and localization of the affected area. The propositions in [20] concern local binary pattern (LBP), noise resistant local binary pattern (NRLBP) and center-symmetrical local binary pattern (CSLBP) with singular value decomposition (SVD) for prevention of image tampering.…”

Adaptive CSLBP compressed image hashing

“…Following represents various global and local features pairs for content change location locally as well as globally. DWT-SVD and Saliency object detection using spectral residual model; Projected Gradient Non-negative Matrix Factorization (PGNMF), ring partition and saliency detection; Zernike moment and Salient point detection; Zernike moment and Haralick local features; Zernike moments, MOD-LBP and Haralick texture features; Invariant moments from Radon coefficients and statistical measures from Radon coefficients; DCT coefficients of Watson's visual model and SIFT key points; Color vector angle and Salient edge points [5][6][7][8][9][10][11][12].…”