應用雜湊技術之複製影像比對機制

AN IMAGE COPY DETECTION SCHEME USING HASHING TECHNOLOGY

陳川仁(Chuan-Ren Chen)

指導教授 ： 謝尚琳

大同大學/電機資訊學院/資訊工程學系所/碩士(2009年)

摘要

本研究提出一個新的複製影像比對機制，並以影像祕密分享為基礎，應用雜湊
技術來改善搜尋龐大資料庫時的效率。本機制將版權影像及欲保護影像的特徵編碼
產生出專屬的數位指紋，並將之分類存進資料庫中。日後若需要判斷待測影像是否
為受保護的影像時，僅比對影像資料庫中與待測影像來源相同的受保護影像，以達
到減少比對次數的目的。此外，本機制利用數位指紋中的特徵向量資訊來建立雜湊
池，並再根據特徵向量計算出的相位角資訊以快速地取回可能被複製的影像。另一
方面，實驗數據顯示了本機制在對龐大的資料庫進行比對時，其取回率(recall rate)
和正確率(precision rate)上有很好的表現。這證明本機制不僅能夠迅速地找出被複製
的受保護影像，且其搜尋結果的正確率和取回率與傳統搜尋方式相近。

關鍵字

數位指紋 ； 特徵向量 ； 雜湊技術 ； 影像祕密分享

並列摘要

This thesis presents a new image copy detection scheme based on Image Secret
Sharing (ISS) technology. It employs hash functions to cope with the large number of
fingerprints extracted from the images. Moreover, it utilizes an authentication logo and
the extracted features of the host image to generate a fingerprint, which is then classified
in the database systematically. When the authentication of suspect images is needed, the
scheme only compares the matches that from the same image to decrease the comparison
time. The scheme uses the feature vector from the fingerprints to build a hash pool
structures, and utilizes the phase angle calculated from the feature vector to query the
possible duplicated images in the image database. On the other hand, the experimental
results show that the presented scheme performs well according to the recall and
precision rate, hence demonstrating the effectiveness of the presented scheme that can
query the images in a large image database correctly and efficiently.

並列關鍵字

fingerprint ； hash functions ； Image Secret Sharing ； feature vector

參考文獻

[2] J. S. Lee and K. S. Yoon, "The System Integration of DRM and Fingerprinting," The 8th International Conference on Advanced Communication Technology, Vol. 3, Feb. 2006.

[4] J. L Dugelay, S. Roche, C. Rey, and G. Doerr, "Still Image Watermarking Robust to Local Geometric Distortions," IEEE Transactions on Image Processing, pp. 2831-2842, Sep. 2006.

[5] L. A. Elrefaey, M. E. Allam, and H. A. Selim, "Robust Blind Image-Adaptive Watermarking," National Radio Science Conference, Mar. 2008.

[6] I. K. Kong and C. M. Pun, "Digital Image Watermarking with Blind Detection for Copyright Verification," 2008 Congress on Image and Signal Processing, Vol. 1, pp. 504-508, May 27-30, 2008.

[7] J. Eakins, and M. Graham, "Content-based Image Retrieval," JISC Technology Applications Programme Report 39, Oct. 1999.