快速二维Renyi熵阈值分割方法  

Fast two-dimensional Renyi’s entropy threshold method

作　　者：彭秋[1] 余成波[1] 崔焱喆[1] 

机构地区：[1]重庆工学院远程测试与控制技术研究所,重庆400050

出　　处：《计算机工程与设计》2009年第18期4239-4241,共3页Computer Engineering and Design

摘　　要：提出一种基于二维Renyi熵的阈值二值化方法,该方法通过引入二维直方图不仅利用了图像像元点的灰度分布信息,而且充分考虑了像元点之间的空间相关信息,对于低对比度、低信噪比的物体,该方法具有良好的分割效果。运用二维Renyi熵的原理选择灰度阈值对图像进行分割,并且引入量化图像直方图概念讨论了一种快速二维Renyi熵阈值分割算法,该算法能够递推运算和自动寻找阈值,将计算复杂性大大降低。仿真对比实验结果表明,该算法提高了计算效率并具有更佳的分割效果。A fast shareholding method based on two dementional Renyi＇ s entropy is presented. The algorithm not only use gray information ofpixels each other but also considerate spatial information ofpixels in image by two-dimentional histogram. It performances well even on target image with low contrast and low SNR （signal to noise ratio）. The method choose gray threshold to segrnentate the image through two-dimensional Renyi＇ s entropy principle and quantized image histogram. The algorithm is calculated recursively and find the threshold value automatically, so computational complexity reduce. The simulation result shows that this algorithm has better effect and enhance efficiency.

关 键 词：二维RENYI熵 阈值分割 量化 直方图 二值化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]