家蚕微粒子图像的分割技术研究Research on segmentation technology for pebrine image
胡新宇,钱磊,张道德,吴良溢
摘要(Abstract)：
针对家蚕微粒子图像存在背景复杂、光照不均及微小彩色目标图像分割处理问题,研究彩色家蚕微粒子图像在复杂场景下的分割技术。该方法首先通过模糊对比度增强预处理方法,增强微粒子目标图像和复杂背景的对比度;然后,采用颜色特征提取准则从非目标杂质图像中直接分离出彩色目标图像,减少了疑似孢子引起误识别的可能性,同时提高了二维Otsu分割方法对彩色微粒子小目标图像分割的有效性。实验结果表明该方法对微粒子图像分割处理效果良好。
关键词(KeyWords)： 家蚕微粒子;彩色图像分割;模糊增强;二维Otsu;颜色特征提取;HSI模型
基金项目(Foundation): 湖北省科技厅自然科学基金项目(2016CFB653)~~
作者(Author): 胡新宇,钱磊,张道德,吴良溢
DOI: 10.16652/j.issn.1004-373x.2018.04.011
参考文献(References)：
- [1]孙育红,王浩.农村原蚕生产防控家蚕微粒子病的体会[J].江苏蚕业,2015,37(4):26-28.SUN Yuhong,WANG Hao.Prevention and control of silkworm micromonopathies in rural silkworm production[J].Jiangsu sericulture,2015,37(4):26-28.
- [2]KHARE R K,SINHA G R.Fuzzy based contrast enhancement method for lung cancer CT images[J].International journal of engineering and computer science,2017,6(5):21201-21204.
- [3]胡新宇.基于机器视觉的家蚕微粒子图像识别方法的研究[D].武汉:武汉理工大学,2011.HU Xinyu.Research on the image recognition method of pebrine disease based on computer vision[D].Wuhan:Wuhan University of technology,2011.
- [4]OTSU N.A threshold selection method from gray-level histograms[J].IEEE transactions on system,man,and cybernetics,1979,9(1):62-66.
- [5]CHEN Lianqing,GAO Liguo.Image segmentation based on iterative threshold and Otsu[J].Journal of Jilin University(Engineering and technology edition),2007,37:139-143.
- [6]HARALICK R M,SHAPIRO L G.Image segmentation techniques[J].Computer graphics image processing,1985,29:100-132.
- [7]WANG Haiyang,PAN Delu,XIA Deshen.A fast algorithm for two-dimensional Otsu adaptive threshold algorithm[J].Journal of image&graphics,2005,33(9):968-971.
- [8]KIM C W,SON H,KIM C M.Automated color model-based concrete detection in construction-site images by using machine learning algorithms[J].Journal of computing in civil engineering,2012,26(3):421-433.
- [9]SUN T Y,TSAI S J,CHAN V.HSI color model based lanemarking detection[C]//Proceedings of IEEE Intelligent Transportation Systems Conference.Toronto:IEEE,2006:1168-1172.
- [10]ZHOU C,TIAN L,ZHAO H,et al.A method of two-dimensional Otsu image threshold segmentation based on improved firefly algorithm[C]//Proceedings of IEEE International Conference on Cyber Technology in Automation,Control,and Intelligent Systems.Shenyang:IEEE,2015:1420-1424.