计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (3): 120-121.

• 研发、测试 • 上一篇    下一篇

一种基于ICA的数字图像特征保护方法

赵 娜,胡 净,王万良   

  1. 浙江工业大学 信息工程学院,杭州 310014
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-01-21 发布日期:2008-01-21
  • 通讯作者: 赵 娜

ICA-based image feature protecting algorithm

ZHAO Na,HU Jing,WANG Wan-liang   

  1. College of Information Engineering,Zhejiang University of Technology,Hangzhou 310014,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-01-21 Published:2008-01-21
  • Contact: ZHAO Na

摘要: 提出一种利用数字图像的特征值对该数字图像进行保护的方法。该方法利用DCT变化原理,提取数字图像的特征值,然后采用信息论中熵的原理和独立分量分析方法评价特征值的变异程度,对数字图像进行保护。该方法不需要对原图进行修改,有较高的实用性。

关键词: 特征值, 图像保护, 熵, 独立分量分析(ICA)

Abstract: In this paper the author proposes a method to protect image by its eigenvalue.The discrete cosine transform principle is used to extract eigenvalue of the images,then principle of entropy on informatics.And Independent Component Analysis method is adopted to estimate the differentiation of eigenvalue,also perform the image protection.The original image modification is not needed,therefore,this approach is promising in practice.

Key words: eigenvalue, image protecting, entropy, Independent Component Analysis(ICA)