一种基于正则化和Watson视觉模型的图像指纹算法  

Robust Image Fingerprint Algorithm Based on Image Normalization and Watson Visual Model

作　　者：郑淑丽[1] 张云玲[1] 胡东辉[1] 李丹丹[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《图学学报》2015年第4期557-562,共6页Journal of Graphics

基　　金：国家自然科学基金资助项目(61272540);安徽省自然基金资助项目(1508085MF115;1308085QF116)

摘　　要：大量多媒体应用的发展使得数字图像很容易地被非法操作和篡改,提出一种基于图像正则化和视觉特性的图像指纹算法,可以有效地实现图像的认证和识别。首先对图像进行正则化预处理,消除几何形变对图像的影响,然后对图像进行分块DCT变换,利用Watson视觉模型对DCT系数进行处理,增大人眼敏感的频域系数在计算图像特征时的权重,经过量化形成最终的指纹序列。在图像指纹序列生成过程中,加入密钥控制,提高了指纹的安全性。实验结果表明,该方法的冲突概率在10–7数量级,对JPEG压缩、旋转、缩放等操作具有较好的稳健性。With the development of multimedia application, digital images are easy to be manipulatedor tampered illegally. A novel image fingerprint algorithm is proposed which can be used for imageauthentication and identification. The image is firstly normalized to make it robust against any affinetransforms. Then the normalized image is divided into 8x8 blocks and discrete cosine transform isapplied to each block. The DCT coefficients are weighted by the contrast masking matrix of Watsonvisual model. Then weighted DCT coefficients is quantified to be bit sequences to form the imagefingerprint. Since a key is used in the algorithm, the fingerprint is hard to be forged. The experimentalresults indicate that the proposed method is robust against modification including geometrictransformation such as rotation and scaling.

关 键 词：图像指纹 图像正则化 视觉模型 图像认证 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]