基于交叉熵的图像过渡区提取与压缩研究  

Research on image transition region extraction and compression based on cross entropy

作　　者：袁胜智[1] 李洪周[1] 杨利斌[1] 

机构地区：[1]海军航空工程学院兵器科学与技术系,山东烟台264001

出　　处：《计算机应用研究》2009年第8期3195-3197,共3页Application Research of Computers

基　　金：高等学校骨干教师基金资助项目

摘　　要：改进过渡区提取算法,将最小交叉熵应用于红外图像过渡区提取中,提出基于交叉熵的图像过渡区算法,并将该过渡区分割法应用于红外图像感兴趣区域的自动提取,最后提出了一种基于JPEG2000框架红外图像感兴趣区压缩方案进行分类压缩。经图像实验充分验证了该方法的有效性、实时性,其具有重要的应用价值。To improve the performances of transition region extraction algorithm, this paper proposed a novel transition region algorithm based on minimum cross entropy. Then applied it to detect ROI automatically. Finally, realized the ROI compression scheme for infrared image on the frame of JPEG2000. It is proves that the method of image compression based on region of interest automatic detected is reliable effective, and significant in applications.

关 键 词：过渡区 交叉熵 感兴趣区 红外图像 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]