Robust image hashing with multidimensional scaling

Tang, Zhenjun; Huang, Ziqing; Zhang, Xianquan; Lao, Huan

doi:10.1016/j.sigpro.2017.02.008

Cited by 71 publications

(45 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method has poor hash length, AUC and computational efficiency because of its sensitive behavior against content changing manipulations. A multidimensional scaling (MDS) image hashing presented in [25] with high robustness because of its higher values of AUC than others but it has very poor results in terms of computational time and especially hash length because of the limitation of very rich featured hash. Results are also presented in Table 5 and Table 6.…”

Section: Review Of Image Hashing Shows That Researchers Have Worked Omentioning

confidence: 99%

“…Area under ROC curve (AUC) is a measure of the efficiency of ROC. Table 5 illustrates the comparison of AUC and hash length of proposed method with some latest schemes [14,[23][24][25]. We provided the hash length in both binary bits and decimal digits for K = 21 .…”

Section: Receiver Operating Characteristicsmentioning

confidence: 99%

“…Therefore it is evident that the proposed method is an efficient image hashing method with a high true positive rate and a very low false positive rate. [14] 0.9955 400 bits or 121 digits Hybrid hashing [23] 0.9947 343 bits or 104 digits Histogram hashing [24] 0.9572 448 bits or 135 digits MDS hashing [25] 0.9905 720 bits or 217 digits…”

Section: Receiver Operating Characteristicsmentioning

confidence: 99%

“…Computational cost of the proposed color image hashing algorithm is evaluated using MATLAB 2017 on a machine having core i3-4030U CPU at 1.9GHz. Results are compared with [14,[23][24][25] and found better among compared methods because of the limitations discussed in Section 1. Table 6 shows a comparison of average computational time and the hash length.…”

Section: Computational Costmentioning

confidence: 99%

See 3 more Smart Citations

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

Khan¹,

Monir²,

Naseem³

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Image hashing is one of the most celebrated techniques regarding the discipline of image forensics, image retrieval, image indexing, content verification, and zero watermarking. For such sensitive and complex problems, the generation of unique and robust image hash is an utmost prerequisite for an image identifier driven from the perceptual contents of an image. As a design perspective, it is essential for an image hash to have robustness and optimized discriminative capability. We propose a robust image hashing technique by acquiring perceptual features based on a novel distance magnitude profile utilizing color pixel incongruity among the contiguous pixels, as well as producing a structural image for discrimination. The combination of both results provide state-of-the-art robust profile that has efficient discriminative capacity and is impervious to usual signal processing violations.

show abstract

Section: Review Of Image Hashing Shows That Researchers Have Worked Omentioning

confidence: 99%

Section: Receiver Operating Characteristicsmentioning

confidence: 99%

Section: Receiver Operating Characteristicsmentioning

confidence: 99%

Section: Computational Costmentioning

confidence: 99%

See 2 more Smart Citations

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

Khan¹,

Monir²,

Naseem³

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…The scheme extracts significant features by using a wavelet based feature detection algorithm and uses an iterative procedure to obtain a set of feature points. Tang et al [19] extract a rotation-invariant feature matrix and compress the matrix with multidimensional scaling to generate an image hash. Tang et al [20] construct three-order tensor from an image and decompose the tensor to generate an image hash.…”

Section: Related Workmentioning

confidence: 99%

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

Xue

Yuan

Liu

et al. 2019

Security and Communication Networks

View full text Add to dashboard Cite

Image hashing schemes have been widely used in content authentication, image retrieval, and digital forensic. In this paper, a novel image hashing algorithm (SSL) by incorporating the most stable keypoints and local region features is proposed, which is robust against various content-preserving manipulations, even multiple combinatorial manipulations. The proposed algorithm combines S_cale invariant feature transform (SIFT) with S_aliency detection to extract the most stable keypoints. Then, the L_ocal binary pattern (LBP) feature extraction method is exploited to generate local region features based on these keypoints. After that, the information of keypoints and local region features are merged into a hash vector. Finally, a secret key is used to randomize the hash vector, which can prevent attackers from forging the image and the hash value. Experimental results demonstrate that the proposed hashing algorithm can identify visually similar images which are under both single and combinatorial content-preserving manipulations, even multiple combinations of manipulations. It can also identify maliciously forged images which are under various content-changing manipulations. The collision probability between hashes of different images is nearly zero. Besides, the evaluation of key-dependent security shows that the proposed scheme is secure that an attacker cannot forge or estimate the correct hash value without the knowledge of the secret key.

show abstract

Wearables, E-textiles, and Soft Robotics for Personalized Medicine

Martínez

2023

Springer Handbooks

View full text Add to dashboard Cite

Robust image hashing with multidimensional scaling

Cited by 71 publications

References 33 publications

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

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

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

Wearables, E-textiles, and Soft Robotics for Personalized Medicine

Contact Info

Product

Resources

About