Earticle

초록

영어

With the increasing number of users outsourcing images to cloud servers, privacy-preserving content-based image retrieval (PP-CBIR) has become a critical research area. Generating searchable cipher images that provide both robustness against attacks and efficient retrieval remains a challenge. Towards this, several PP-CBIR techniques are proposed; however, they often either compromise on search accuracy, lack sufficient security resilience, or suffer from high computational complexity. To address these challenges, we propose a PP-CBIR scheme that integrates sub-block processing-based perceptual encryption with the Color Edge Directivity Descriptor (CEDD). This method enables the calculation of feature histograms in the encrypted domain, striking a better balance between accuracy, security, and computational efficiency. Experimental evaluations conducted on the Coral-1K dataset demonstrate that both plain and cipher images exhibit comparable retrieval accuracy. Furthermore, we optimize the proposed scheme by analyzing the impact of varying feature block sizes and sub-block configurations, ensuring a comprehensive evaluation of its performance.

목차

Abstract
1. Introduction
2. Methods
2.1. Searchable image encryption
2.2. CEDD Feature Extraction
2.3. Feature Matching
3. Results and Discussions
3.1. Retrieval Performance Analysis
3.2. Security Analysis
4. Conclusion
Acknowledgement
References

저자

• 우잘 엠디 샤흐리아르 [ Md Shahriar Uzzal | 조선대학교 ]
• 아흐마드 이자즈 [ Ijaz Ahmad | 고려대학교 ]
• 신석주 [ Seokjoo Shin | 조선대학교 ] Corresponding Author

참고문헌