Deep Perceptual Hash Based on Hash Center for Image Copyright Protection
At present, most of the perceptual hash methods for image copyright protection rely on manually designed feature extraction and mapping, whose detection accuracy is insufficient. Some schemes based on deep learning are designed to consider a limited variety of content retention operations, which are...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9950236/ |
| _version_ | 1811189196817170432 |
|---|---|
| author | Xiaohan Sun Jiting Zhou |
| author_facet | Xiaohan Sun Jiting Zhou |
| author_sort | Xiaohan Sun |
| collection | DOAJ |
| description | At present, most of the perceptual hash methods for image copyright protection rely on manually designed feature extraction and mapping, whose detection accuracy is insufficient. Some schemes based on deep learning are designed to consider a limited variety of content retention operations, which are not enough to deal with the increasingly severe situation of image copyright protection. In response to this situation, a novel Convolutional Neural Network (CNN)-based perceptual image hashing scheme is introduced in this paper. In this scheme, the training images are classified according to their original images and a Hadamard matrix is used to generate a hash center for each class in Hamming space. Then the Convolution Neural Network learns the feature extraction process of the image automatically, constrained by central quantization and distinct quantization, so that the hash code of each image converges to the hash center of their class, and generates the final hash sequence. The proposed scheme can successfully strike a balance between perceived robustness and discrimination capacity. Based on the test results on large-scale test sets, <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> scores, equal error rate (EER) and receiver operating characteristic (ROC) curves demonstrate the superiority of our scheme compared with some state-of-the-art schemes. |
| first_indexed | 2024-04-11T14:31:54Z |
| format | Article |
| id | doaj.art-591b2efd54c4453dbee8e3fe83bac5b3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T14:31:54Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-591b2efd54c4453dbee8e3fe83bac5b32022-12-22T04:18:33ZengIEEEIEEE Access2169-35362022-01-011012055112056210.1109/ACCESS.2022.32219809950236Deep Perceptual Hash Based on Hash Center for Image Copyright ProtectionXiaohan Sun0https://orcid.org/0000-0001-7908-5614Jiting Zhou1https://orcid.org/0000-0001-7534-9993Shanghai Film Academy, Shanghai University, Shanghai, ChinaShanghai Film Academy, Shanghai University, Shanghai, ChinaAt present, most of the perceptual hash methods for image copyright protection rely on manually designed feature extraction and mapping, whose detection accuracy is insufficient. Some schemes based on deep learning are designed to consider a limited variety of content retention operations, which are not enough to deal with the increasingly severe situation of image copyright protection. In response to this situation, a novel Convolutional Neural Network (CNN)-based perceptual image hashing scheme is introduced in this paper. In this scheme, the training images are classified according to their original images and a Hadamard matrix is used to generate a hash center for each class in Hamming space. Then the Convolution Neural Network learns the feature extraction process of the image automatically, constrained by central quantization and distinct quantization, so that the hash code of each image converges to the hash center of their class, and generates the final hash sequence. The proposed scheme can successfully strike a balance between perceived robustness and discrimination capacity. Based on the test results on large-scale test sets, <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> scores, equal error rate (EER) and receiver operating characteristic (ROC) curves demonstrate the superiority of our scheme compared with some state-of-the-art schemes.https://ieeexplore.ieee.org/document/9950236/Image hashingperceptual hashingcopy detectioncopyright protectionCNN |
| spellingShingle | Xiaohan Sun Jiting Zhou Deep Perceptual Hash Based on Hash Center for Image Copyright Protection IEEE Access Image hashing perceptual hashing copy detection copyright protection CNN |
| title | Deep Perceptual Hash Based on Hash Center for Image Copyright Protection |
| title_full | Deep Perceptual Hash Based on Hash Center for Image Copyright Protection |
| title_fullStr | Deep Perceptual Hash Based on Hash Center for Image Copyright Protection |
| title_full_unstemmed | Deep Perceptual Hash Based on Hash Center for Image Copyright Protection |
| title_short | Deep Perceptual Hash Based on Hash Center for Image Copyright Protection |
| title_sort | deep perceptual hash based on hash center for image copyright protection |
| topic | Image hashing perceptual hashing copy detection copyright protection CNN |
| url | https://ieeexplore.ieee.org/document/9950236/ |
| work_keys_str_mv | AT xiaohansun deepperceptualhashbasedonhashcenterforimagecopyrightprotection AT jitingzhou deepperceptualhashbasedonhashcenterforimagecopyrightprotection |