Image fusion binarization method based on SOFM neural network

PAN Mei-sen; RONG Qiu-sheng

doi:null

您当前的位置：

首页 >

文章列表页 >

Image fusion binarization method based on SOFM neural network

更新时间：2020-08-12

- Image fusion binarization method based on SOFM neural network
- Optics and Precision Engineering Vol. 15, Issue 3, Pages: 401-406(2007)
- 作者机构：
  
  湖南文理学院计算机科学与技术系,湖南常德,415000
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP183;TP391
- Received：24 November 2006，
  
  Revised：14 January 2007，
  
  Published Online：30 June 2007，
  
  Published：30 June 2007
- 稿件说明：
移动端阅览
PAN Mei-sen, RONG Qiu-sheng. Image fusion binarization method based on SOFM neural network[J]. Optics and precision engineering, 2007, 15(3): 401-406.
DOI：

PAN Mei-sen, RONG Qiu-sheng. Image fusion binarization method based on SOFM neural network[J]. Optics and precision engineering, 2007, 15(3): 401-406. DOI：

摘要

提出了一种基于自组织特征映射(SOFM)神经网络的图像融合二值化方法。介绍了SOFM神经网络的特点及学习算法

根据SOFM的聚类确定图像第一阈值作为循环迭代的初始值

对整幅图像进行循环迭代得到第二阈值

使用第二阈值对原始图像进行二值化

得到第一幅待融合图像;通过改进的Bernsen方法对原始图像进行二值化

得到第二幅待融合图像;最后根据图像灰度值选小的原则作为图像融合方法

得到最终的二值化图像。该方法既能有效地消除伪影

又能较好地分离字符和文字。模拟实验结果表明

该方法的二值化效果明显优于Bernsen方法和Ostu方法

且具有良好的适应性。

Abstract

An image fusion binarization method based on Self-organization Feature Map(SOFM) neural network is presented. The characteristic and the learning algorithm of SOFM neural network are introduced. The first threshold of the image is derived from the clustering characteristic of SOFM

and it is treated as a initialization of the circulated iteration method to obtain the second threshold of the image. The binarization for the original image is carried on using the second threshold to obtain the first fusing image. Then

the binarization for the original image is performed more again using the improved Bernsen method to obtain the second fusing image. Finally

two fusing images are merged based on the minimum principle of image gray values to get the final binarization image. This method can effectively eliminate the ghost and can also separate the characters very well. Experimental results show that the method is effective

and its binarization effect surpasses Bernsen method and Ostu method obviously

moreover it has good compatibility.

关键词

Keywords

references

. 何永义,夏俊昇. 工程图像的矢量化技术[J]. 光学精密工程,2002,10(8):374-378. HE Y Y,XIA J SH.Vectorization technology for engineering image[J].Opt. Precision Eng.,2002,10(8):374-378. (in Chinese)

. 陈丹,张蜂,贺贵明. 一种改进的文本图像二值化算法[J]. 计算机工程,2003,29(13):85-86. CHEN D,ZHANG F,HE G M. An improved binarization algorithm for document image [J]. Comput. Eng.,2003,29(13):85-86. (in Chinese)

. 高隽.人工神经网络原理及仿真实例[M]. 北京:机械工业出版社,2003. GAO J.Artificial Neural Networks Principle and Simulation Example[M].Beijing: Mechanical Industry Press,2003.(in Chinese)

. 黄勇,陈琳. 一种基于SOFM 聚类的星图识别算法 . 光学精密工程,2004,12(6):346-351. HUANG Y,CHEN L.Star pattern recognition algorithm based SOFM clustering function[J].Opt. Precision Eng.,2004,12(6):346-351. (in Chinese)

. 黄志斌. 面向车辆牌照的L快速二值化算法[J]. 华侨大学学报(自然科学版),2002,23(4):427-430. HUANG ZH B. Algorithm of L quick binarization catering to license plate of vehicle[J]. J. Huaqiao Univ. (Natural Science),2002,23(4):427-430.(in Chinese)

. 程英蕾,赵荣椿,李卫华,等. 基于像素级的图像融合方法研究[J]. 计算机应用研究,2004,23(5):169-172. CHENG Y L,ZHAO R CH,LI W H,et al..Overview of methods of data fusion for images based on pixel-level[J]. Appl. Res. Comput.,2004,23(5):169-172.(in Chinese)

Views

372

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Infrared and visible image fusion based on multi-scale spatial attention complementary

Adaptive color compensation and multi-scale fusion for underwater image enhancement

X-ray image fusion for ancient bronze mirror based on intuitionistic fuzzy set entropy measure and salient feature detection

Conditional diffusion and multi-channel high-low frequency parallel fusion of infrared and visible light images

Visible-polarized image fusion for nighttime dispersal of mines

Related Author

ZHANG Yongxing

LIAN Bowen

GU Naiting

LI Fangzhao

LI Yang

LIU Cuiyin

JING Tengyun

WANG Feng

Related Institution

National Key Laboratory of Adaptive Optics

Institute on Optics and Electronics Technology， Chinese Academy of Sciences

University of Chinese Academy of Sciences

College of Frontier Interdisciplinary Sciences， National University of Defense Technology

School of Information Engineering and Automation， Kunming University of Science and Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰