广西师范大学学报(自然科学版) ›› 2015, Vol. 33 ›› Issue (2): 22-28.doi: 10.16088/j.issn.1001-6600.2015.02.004

• • 上一篇    下一篇

基于小波变换与野草算法的细胞图像特征提取与识别

陈锦, 罗晓曙   

  1. 广西师范大学电子工程学院,广西桂林541004
  • 收稿日期:2015-01-06 出版日期:2015-02-10 发布日期:2018-09-20
  • 通讯作者: 罗晓曙(1972—),男,湖北应城人,广西师范大学教授,博士。E-mail: lxs@mailbox.gxnu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(21327007)

Extraction and Recognition of Cell Image Feature Basedon Wavelet Transform and Invasive Weed Optimization

CHEN Jin, LUO Xiao-shu   

  1. College of Electronic Engineering, Guangxi Normal University, Guilin Guangxi 541004,China
  • Received:2015-01-06 Online:2015-02-10 Published:2018-09-20

摘要: 本文在细胞图像小波多尺度分解的基础上,提出在小波域中进行细胞图像特征提取的方法。针对基于小波变换提取的细胞图像特征向量维数过大、冗余等问题,提出一种基于小波变换与野草优化算法相结合的细胞图像特征的提取方法,最后利用BP神经网络作为分类器进行细胞图像识别。计算机实验仿真结果表明,与现有的未进行特征优化的细胞图像特征提取识别方法相比,本文细胞图像特征提取、分析、识别方法所需时间更短,识别正确率更高,实时性、鲁棒性能更好。

关键词: 小波多尺度分解, 野草优化算法, 特征向量, BP神经网络, 细胞图像识别

Abstract: A cell image feature extraction algorithm in wavelet domain based on multi-scale wavelet cell image decomposition is proplsed. According to the problem of the large and redundancy cell image feature vector dimension based on wavelet transform, a method of cell image feature extraction based on wavelet transform and the invasive weed optimization algorithm is put forwart. Finally, the BP neural network is used as the classifier for cell image recognition. Computer simulation results show that,compared with the existing cell image feature extraction and recognition method in no feature optimization, this algorithm of cell image feature extraction, analysis and recognition algorithm of need shorter time but with higher recognition rate, better real-time performance and better robust performance performance.

Key words: multi-scale wavelet decomposition, weed optimization algorithm, feature vector, BP neural network, cell image recognition

中图分类号: 

  • TP391.4
[1] LEE,HEE H.Emerging intelligent computing technology and applications[M]. Heidelberg: Springer, 2009:187-192.
[2] YUAN Hua,ZHANG Xiao-ping,GUAN Ling.A statistical approach for image feature extraction in the wavelet domain[C].//Canadian Conference on Electrical and Computer Engineering. Montreal: IEEE,2003:1159-1162.
[3] GHAZALI K H, MANSOR M F, MUSTAFA MM, et al. Feature extraction technique discrete wavelet transform for image classification[C].//5th Student Conference on Research and Development. Selangor, Malaysia:IEEE, 2007:1-4.
[4] LI Xiao-li,HE Yong,QIU Zheng-jun.Textural feature extraction and optimization in wavelet sub-bands for discrimination of green tea brands[C]//International Conference on Machine Learning and Cybernetics.Kunming:IEEE,2008:1461-1466.
[5] ERGIN S,KILINC O.A new feature extraction framework based on wavelets for breast cancer diagnosis[J].Computers in Biology and Medicine,2014,51:171-182.
[6] AVCI E,SENGUR A,HANBAY D.An optimum feature extraction method for texture classification[J].Expert Systems with Applications,2009,36(3):6036-6043.
[7] NASCIMENTO D,MARTINS A,NEVES L,et al.Classification of masses in mammographic image using wavelet domain features and polynomia classifier[J].Expert Systems with Applications,2013,40:6213-6221.
[8] IMTIAZ H,FATTAH S A.A wavelet-based dominant feature extraction algorithm for palm-print recognition[J].Digital Signal Processing,2013,23(1):244-258.
[9] HUANG Zheng-hai,LI Wen-juan,WANG Jun,et al.Face recognition based on pixel-level and feature-level fusion of the top-level’s wavelet sub-bands[J].Information Fusio,2015,22:95-104.
[10] AGRAWAL P, VATSA M, SINGH R. Machine learning in medical imaging[M]. International Publishing: Springer, 2013:195-202.
[11] RAKSHIT P,BHOWMIK K.Detection of abnormal findings in human RBC in diagnosing sickle cell anaemia using image processing[J].Procedia Technology,2013,10:28-36.
[12] PHINYOMARK A,JITAREE S,PHUKPATTARANONT P,et.al.Texture analysis of Breast cancer cells in microscopic images using critical exponent analysis method[J].Procedia Engineering,2012,32:232-238.
[13] LEE H,YI Ping,CHEN P.Cell morphology based classification for red cells in blood smear images[J].Pattern Recognition Letters,2014,49(1):155-161.
[14] 陈锦,张晗博,殷奕,等.一种新的小波阈值去噪方法研究[J].信息化研究,2014,40(3):13-17.
[15] YANG Yan,WILIEM A,ALAVI A, et al. Visual learning and classification of human epithelial type 2 cell images through spontaneous activity patterns[J].Pattern Recognition,2014,47(7):2325-2337.
[16] 李亚标,王宝光,李温温.基于小波变换的图像纹理特征提取方法及其应用[J].传感技术学报,2009,22(9):1308-1311.
[17] MEHRABIAN A R,LUCASC C.A novel numerical optimization algorithm inspired from weed colonization[J]. Ecological Informatics,2006,1(4):355-366.
[18] 于蕾,周忠良,郑丽颖.基于入侵性杂草优化算法的图像识别的研究[J].计算机工程与应用,2014,50(16):188-191.
[19] 张帅,王营冠,夏凌楠.离散二进制入侵杂草算法[J].华中科技大学学报:自然科学版,2011,39(10):55-60.
[1] 刘欣, 罗晓曙, 赵书林. 基于BP神经网络的三轴增稳云台自抗扰控制[J]. 广西师范大学学报(自然科学版), 2020, 38(2): 115-120.
[2] 许伦辉, 陈凯勋. 基于改进萤火虫算法优化BP神经网络的路网速度分布预测[J]. 广西师范大学学报(自然科学版), 2019, 37(2): 1-8.
[3] 钟海鑫, 丘森辉, 罗晓曙, 唐堂, 杨力, 赵帅. 基于附加惯性项BP神经网络的四旋翼无人机姿态控制研究[J]. 广西师范大学学报(自然科学版), 2017, 35(2): 24-31.
[4] 彭新建,翁小雄. 基于萤火虫算法优化BP神经网络的公交行程时间预测[J]. 广西师范大学学报(自然科学版), 2017, 35(1): 28-36.
[5] 黄晶, 罗晓曙. 神经网络在输电线覆冰增长因素中的应用[J]. 广西师范大学学报(自然科学版), 2011, 29(4): 25-27.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报(自然科学版)编辑部
地址:广西桂林市三里店育才路15号 邮编:541004
电话:0773-5857325 E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发