Perceptual hashing for color image based on color opponent component and quadtree structure

Shen, Qi; Zhao, Yan

doi:10.1016/j.sigpro.2019.107244

Cited by 37 publications

(33 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When P FPR is 0, the P TPR of this algorithm is 0.9998, whereas the P TPR of scheme [28], scheme [13], scheme [14], and scheme [23] are 0.998, 0.991, 0.9827 and 0.953 respectively. When P TPR is close to 1, the P FPR of proposed algorithm is 4.13 × 10 −6 , whereas the P FPR of scheme [28], scheme [13], scheme [14], and scheme [23] are 2.22 × 10 −5 , 0.1273, 9.4 × 10 −3 , and 0.4749 respectively. When P FPR is 0, the P TPR of other algorithms are lower than proposed algorithm.…”

Section: F Performance Comparisonmentioning

confidence: 95%

“…The hash sequence was constructed by extracting statistical values, such as the mean and variance of each block. Shen et al [28] used the color opponent component as the color features of the image to generate the hash sequence. The algorithm extracted redgreen, blue-yellow color opponent component of the secondary image, and applied the LBP operation to the mean matrix of the subblocks of the opponent component image to construct the color features of the image.…”

Section: Based On Color Featurementioning

confidence: 99%

“…(2) Compared with scheme [28], which also uses color opponent component as color feature, our scheme has the advantages of shorter hash length, better classification performance, and shorter average time to generate the hash. The specific comparison with [28] will be explained in the experimental part of Section III-F.…”

Section: Based On Color Featurementioning

confidence: 99%

“…In order to compare the performance of the algorithm, the proposed algorithm is compared with shen et al's scheme [28], Davarzani et al's scheme [13], Tang et al's scheme [14], and Tang et al's scheme [23]. The experimental parameter setting of the comparison algorithm is consistent with the original paper.…”

Section: F Performance Comparisonmentioning

confidence: 99%

“…In order to ensure the fairness of comparison, each comparison algorithm is simulated on the MATLAB R2014a platform of the same computer, 499500 different image pairs and 210000 similar image pairs adopted in subsection III-C are used to verify their classification performance. ROC curves of proposed scheme and the schemes [13], [14], [28], and [23].…”

Section: F Performance Comparisonmentioning

confidence: 99%

See 4 more Smart Citations

Perceptual Image Hashing Based on Color Structure and Intensity Gradient

Zhao

Yuan

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In order to improve classification performance of the hash algorithm for color images, this paper presents an hash algorithm that based on three-dimensional color structure features and luminance gradient feature. Firstly, the algorithm preprocesses the input image to produce a secondary image, and extracts the color opponent component from the secondary image. Secondly, three-dimensional external structural features are constructed by using the peak curve, mean curve, and valley curve of the color opponent component. Thirdly, the overlapping points of the peak points in different visual angles and the valley points in different visual angles are selected as the salient points. The position information of the salient points are used to construct internal features. The gradient feature is constructed by using pixel changes in four directions of Y component of luminance image in YCbCr color space. Finally, the three-dimensional color structure features and luminance gradient feature are combined and disturbed to obtain the final hash sequence. Experiment results show that the proposed scheme has preferable robustness and discrimination. Compared with some existing schemes, the proposed scheme has better classification performance, shorter hash length and less average time of hash generation, and it has good detection performance in image copy detection and image tampered detection. INDEX TERMS Image hashing, copy and tampered detection, luminance gradient, three-dimensional color features.

show abstract