Image segmentation based on activity degree with pulse coupled neural networks

ZHENG Xin; PENG Zhen-ming

doi:10.3788/OPE.20132103.0821

您当前的位置：

首页 >

文章列表页 >

Image segmentation based on activity degree with pulse coupled neural networks

更新时间：2020-08-12

- Image segmentation based on activity degree with pulse coupled neural networks
- Optics and Precision Engineering Vol. 21, Issue 3, Pages: 821-827(2013)
- 作者机构：
  
  电子科技大学光电信息学院,四川成都,610054
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132103.0821
  CLC： TP391.4
- Received：18 December 2012，
  
  Revised：09 January 2013，
  
  Published Online：20 March 2013，
  
  Published：15 March 2013
- 稿件说明：
移动端阅览
郑欣彭真明. 基于活跃度的脉冲耦合神经网络图像分割[J]. 光学精密工程, 2013,21(3): 821-827

ZHENG Xin PENG Zhen-ming. Image segmentation based on activity degree with pulse coupled neural networks[J]. Editorial Office of Optics and Precision Engineering, 2013,21(3): 821-827
郑欣彭真明. 基于活跃度的脉冲耦合神经网络图像分割[J]. 光学精密工程, 2013,21(3): 821-827 DOI： 10.3788/OPE.20132103.0821.

ZHENG Xin PENG Zhen-ming. Image segmentation based on activity degree with pulse coupled neural networks[J]. Editorial Office of Optics and Precision Engineering, 2013,21(3): 821-827 DOI： 10.3788/OPE.20132103.0821.

摘要

针对脉冲耦合神经网络(PCNN)在图像分割中需多次人工调整网络参数的问题，提出了一种基于PCNN模型的图像自动分割方法。分析了图像中影响PCNN参数设置的因素，提出了一种图像自适应分块策略。将图像划分为内部复杂程度相近的子块，克服了同一参数无法同时对图像中复杂度差异较大的不同区域准确分割的不足。利用本文提出的局部图像活跃度(ADLA)指标对不同子块自适应地确定PCNN模型参数，有效解决了传统PCNN图像分割时需要人工确定关键参数的问题。最后，采用最大二维Tallis熵准则从分割后的二值结果序列中选择最佳结果。实验表明，本文方法的分割结果轮廓清晰、完整，即使在对比度低、背景呈大范围内连续变化等复杂情况下，也具有优异的性能。与传统PCNN分割方法相比，本文方法能自动、快速、准确地确定PCNN模型参数，且区域一致性测度(UM)，区域对比度(CR)，形状测度(SM)，综合指标(CI)等客观评价的量化指标均优于传统PCNN分割方法12%以上。

Abstract

As Pulse Coupled Neural Network(PCNN) in image segmentation has to adjust the network parameters by manual operation for several times

this paper proposed a automatic image segmentation method based on the PCNN. The effect factors on setting PCNN parameters in an image were analyzed and an adaptive segment protocol was invited to divide the images into several sub-pieces with the similar inside complexities. By which

the weakness that the same parameter could not segment exactly the region with quite different complexities in an image at the same time was overcome. Furthermore

the index of Activity Degree of Local Area(ADLA) proposed by the paper was used to determine the PCNN model parameters for different sub-pieces adaptively and to avoid the manual operation for important parameter selection in the traditional PCNN image segmentation. Finally

the best result was chosen from the binary-result sequences with the max two-dimension Tallis entropy protocol. The experiments proved that segmented figure is clear

complete and has excellent performance

even in conditions of a low contrast or a changeable background. Compared with the traditional PCNN segmentation methods

the proposed method not only can determine the PCNN model parameters automatically

and its indexes on quantitative evaluation of the segmentation result

such as Uniformity Measure(UM)

Regional Contrast (CR)

Shape Measure (SM) and Comprehensive Index (CI) are all 12% better than those of the traditional PCNN method.

关键词

Keywords

references

何志勇，孙立宁，黄伟国. 基于Otsu准则和直线截距直方图的阈值分割[J]. 光学精密工程, 2012, 20(10): 2315-2323. HE ZH Y, SUN L N, HUANG W G. Thresholding segmentation algorithm based on Otsu criterion and line intercept histogram[J]. Opt. Precising Eng., 2012, 20(10): 2315-2323. (in Chinese)[2]STEWART R D, FERMIN I, OPPER M. Region growing with pulse-coupled neural networks: An alternative to seeded region growing[J]. IEEE Transaction on Neural Networks, 2002, 13(6): 1557-1562.[3]聂仁灿, 周东明,赵东风.基于Unit_LinkingPCNN和图像熵的图像分割新方法[J]. 系统仿真学报, 2008,20(1): 222-227.NIE R C, ZHOU D M, ZHAO D F. Image segmentation new methods using unit-linking PCNN and images entropy[J]. Journal of System Simulation, 2008, 20(1): 222-227. (in Chinese)[4]张煜东.吴乐南.基于二维Tsallis熵的改进PCNN图像分割[J]. 东南大学学报: 自然科学版, 2008,38(4): 579-584. ZHANG Y D, WU L N. Image segmentation based on 2D Tsallis entropy with improved pulse coupled neural networks[J]. Journal of Southeast University: Natural Science Edition, 2008, 38(4): 579-584. (in Chinese)[5]祝双武,郝重阳. 一种基于改进型PCNN的织物疵点图像自适应分割方法[J]. 电子学报, 2012,40(3): 611-616. ZHU SH W, HAO CH Y. An approach for fabric defect image segmentation based on the improved conventional PCNN model[J]. Acta Electronica Sinica, 2012, 40(3): 611-616. (in Chinese)[6]彭真明，蒋彪，肖峻. 基于脉冲耦合神经网络的空中扩展目标检测方法[J]. 强激光与粒子束，2007, 19（12）：2011-2016.PENG ZH M, JIANG B, XIAO J. Aerial extended target detection based on unit-linking pulse coupled neural networks [J]. High Power Laser And Particle Beams, 2007, 19(12): 2011-2016.[7]马义德, 奇春亮. 基于遗传算法的脉冲耦合神经网络自动系统的研究[J]. 系统仿真学报, 2006, 18(3): 722-725.MA Y D, QI CH L. Study of automated PCNN system based on genetic algorithm [J]. Journal of System Simulation, 2006, 18(3): 722-725. (in Chinese)[8]彭真明，蒋彪，肖峻. 基于并行点火PCNN模型的图像分割新方法[J]. 自动化学报, 2008, 34(9): 1169-1173. PENG ZH M, JIANG B, XIAO J. A novel method of image segmentation based on parallelized firing PCNN [J]. Acta Automatica Sinica, 2008, 34(9): 1169-1173. (in Chinese)[9]汪源源，焦静. 改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域[J]. 光学精密工程, 2011, 19(6): 1398-1405. WANG Y Y, JIAO J. Detection of regions of interest from breast tumor ultrasound images using improved PCNN[J]. Opt. Precising Eng., 2011, 19(6): 1398-1405. (in Chinese)[10]王晓云, 苑玮琦, 郭金玉. 基于局部灰度梯度特征点的快速人耳身份鉴别[J]. 光电子激光, 2012,23(5): 980-985. WANG X Y, YUAN W Q, GUO J Y. A fast ear identification alogorithm based on local gray gradient feature points [J]. Journal of OptoelectronicsLaser, 2012, 23(5): 980-985. (in Chinese)[11]李云红，伊欣. 基于脉冲耦合神经网络模型的小波自适应斑点噪声滤除算法[J]. 光学精密工程, 2012, 20(9): 2060-2067. LI Y H, YI X. Wavelet adaptive denoising method basded on PCNN[J]. Opt. Precising Eng., 2012, 20(9): 2060-2067. (in Chinese)[12]刘钢, 额日其太, 朱希娟.巡航导弹蒙皮红外辐射特性的反向蒙特卡罗法模拟[J]. 科学技术与工程, 2011, 11(5): 1012-1017.LIU G, ER Q T, ZHU X J. Simulation of infrared radiation characteristics of cruise missile skin by backward Monte Carlo method[J]. Science Technology and Engineering, 2011, 11(5): 1012-1017. (in Chinese)

Views

134

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Automated image segmentation based on pulse coupled neural network with partide swarm optimization and comprehensive evaluation

Computed tomography image segmentation of cell pole piece via strip attention mechanism

Sand microscopic image segmentation with enhanced tuna swarm optimization exponential entropy

Brain tumor image segmentation based on Semantic Flow Guided Sampling and Attention Mechanism

Automatic segmentation of aggregate images with MET optimized by chaos SSA

Related Author

Kun-hua ZHANG

Zhi-heng TAN

bin LI

LIU Zefang

LONG Chao

LIU Xueshuan

HAN Yan

TAN Chuandong

Related Institution

Shenzhen key laboratory of media information content security

College of Information Engineering, Shenzhen University

Project Management Center， Equipment Department of Rocket Force

ICT Research Center， Key Laboratory of Optoelectronic Technology and Systems of Ministry of Education， Chongqing University

College of Optoelectronic Engineering， Chongqing University

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