Study on Chironomid Larvae Recognition Based on DWT and Improved KNN  

基于小波分析及改进KNN的红虫识别研究

作　　者：赵晶莹[1] 郭海[1] 孙兴滨[2,3] 

机构地区：[1]大连民族学院计算机科学与工程学院,辽宁大连116600 [2]哈尔滨工业大学市政环境工程学院,黑龙江哈尔滨150001 [3]东北林业大学环境科学系,黑龙江哈尔滨150040

出　　处：《Agricultural Science & Technology》2009年第4期146-149,共4页农业科学与技术（英文版）

基　　金：Supported by the National Natural Science Foundation of China(50778048)(60803096);the Natural Science Foundation of Hei-longjiang Province(E200812);China Postdoctoral ScienceFoundation Funded Project(20070420882)~~

摘　　要：A chironomid larvae images recognition method based on wavelet energy feature and improved KNN is developed. Wavelet decomposition and color information entropy are selected to construct vectors for KNN that is used to classify of the images. The distance function is modified according to the weight determined by the correlation degree between feature and class, which effectively improves classification accuracy. The result shows the mean accuracy of classification rate is up to 95.41% for freshwater plankton images, such as chironomid larvae, cyclops and harpacticoida.1淡水浮游生物特征提取1．1颜色特征提取由于红虫、剑水蚤、猛水蚤图像在颜色上有明显区别，所以先提取图像颜色信息，将其作为分类的一项重要特征。颜色直方图以及其组成的空间可以作为图像识别的训练集（数据库）中颜色特征的表示。利用信息论的方法扩展基于颜色信息的图像属性特征。根据颜色直方图的定义可以推出该图像的概率密度函数如公式（1）所示：

关 键 词：Freshwater plankton Chironomid larvae Wavelet decomposition Color features K-Nearest Neighbor （KNN） 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] O174.2[自动化与计算机技术—计算机科学与技术]