文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > TWO-DIMENSIONAL ENTROPY METHOD BASED ON GENETIC ALGORITHM
侵权投诉

TWO-DIMENSIONAL ENTROPY METHOD BASED ON GENETIC ALGORITHM

Abstract-Image segmentation represents the first step in many applications in image understanding. Thresholding is a simple and important in image segmentation. One-dimensional entropy does not take into account the spatial correlation between the pixels i

TWO-DIMENSIONAL ENTROPY METHOD BASED ON GENETIC

ALGORITHM

WANG Lei, SHEN Ting-zhi

(Dept. of Electronic Engineering, Beijing Institute of Technology, Beijing, 100081, China)

Abstract-Image segmentation represents the first step in many applications in image understanding. Thresholding is a simple and important in image segmentation. One-dimensional entropy does not take into account the spatial correlation between the pixels in an image. Two-dimensional entropy uses both the gray value of an pixel and the local average gray value of it, and thus provides better results. But for more accurate thresholding one has to pay the price of time. The proposed method introduces Genetic Algorithm into two-dimensional entropy method to overcome its drawback of computationally expensive. Experimental results show that the proposed method can save computational time when it provides good quality segmentation.

Key words-image segmentation; Genetic Algorithm; entropic method; fitness function

Segmentation is a process of partitioning the image into some non-intersecting regions such that each region is homogeneous and the union of no two adjacent regions is homogeneous[1]. Segmentation is the first essential and important step of any automated image understanding process, and also remains an old and difficult problem. Thresholding of the gray-level values is a popular tool used in image segmentation. Since the segmentation quality relies much on the threshold, it is crucial to choose a proper threshold.

Let

(x,y) be the spatial coordinate of the image, and G={0,1,2, ,L 1} be a set of positive

integers representing gray levels (by convention, the gray level 0 is the darkest and the gray level lightest). The brightness (i.e., gray level) of a pixel with coordinate

Let

L 1 is the

(x,y) is denoted as f(x,y).

t∈G be a threshold and B={b0,b1} be a pair of binary gray level and b0,b1∈G. The result

f( , ) at gray level t is a binary image function ft, such that

of thresholding an image function

b

ft(x,y)= 0

b1

f(x,y)<t

,

f(x,y)≥t

t based on a certain criterion. If

In general, a thresholding method is one that determines the optical value

t is determined solely from the gray level of each pixel (e.g., the one-dimension histogram), the thresholding

method is point-dependent. If

t is determined from the local property in the neighborhood of each pixel (e.g.,

the two-dimension histogram or co-occurrence matrix), the thresholding method is region-dependent.

Let the number of pixels with gray level i be mi. Then the total number of pixels in a given image is

M=∑mi

i=0

L 1

,

The probability of occurrence of gray level i is defined as

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email