基于DCT系数分布的含密图像识别算法(英文)  

Stego-images Recognition Based on DCT Coefficients Distributing

作　　者：刘一均[1] 柴毅[1] 柏森[2] 郭茂耘[1] 

机构地区：[1]重庆大学自动化学院,重庆400044 [2]重庆通信学院信息与通信工程系,重庆400035

出　　处：《广西师范大学学报（自然科学版）》2007年第2期190-193,共4页Journal of Guangxi Normal University:Natural Science Edition

基　　金：Nature Science Foundation of Chongqing(2005BB2208)

摘　　要：提出了一种基于DCT系数统计分布的含密图像(stego-images)和掩护图像(cover-images)的识别算法。实验表明:该算法能快速识别各种JPEG和BMP格式的基于变换域和空间域的含密图像和非含密图像,并且优于其他含密图像识别方法。A fast and effective stego-images recognition method based on statistical distributions of DCT coefficients is proposed. The approach can distinguish stego-image and cover-image. The method is tested on a diverse set of test images that include both raw and processed images in the JPEG and BMP formats. Experiment results show the superiority of our approach over other stego-images recognition techniques.

关 键 词：含密图像识别 掩密术 模式识别 DCT系数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]