| 基于小波分析及改进KNN的红虫识别研究 |
| |
| 引用本文： | 赵晶莹,郭海,孙兴滨. 基于小波分析及改进KNN的红虫识别研究[J]. 农业科学与技术, 2009, 10(4): 146-149 |
| |
| 作者姓名： | 赵晶莹 郭海 孙兴滨 |
| |
| 作者单位： | 赵晶莹,郭海(大连民族学院计算机科学与工程学院,辽宁大连,116600);孙兴滨(哈尔滨工业大学市政环境工程学院,黑龙江哈尔滨,150001;东北林业大学环境科学系,黑龙江哈尔滨,150040) |
| |
| 基金项目： | the National Natural Science Foundation of China(50778048)，the Natural Science Foundation of Heilongjiang Province，China Postdoctoral Science Foundation Funded Project(20070420882).国家自然科学基金(50778048)，黑龙江省自然科学基金，中国博士后基金资助项目 |
| |
| 摘 要： | 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： | 图像识别 小波分析 红虫 颜色特征提取 KNN 颜色直方图 概率密度函数 颜色信息 |
Study on Chironomid Larvae Recognition Based on DWT and Improved KNN |
| |
| ZHAO Jing-ying,GUO Hai,SUN Xing-bin. Study on Chironomid Larvae Recognition Based on DWT and Improved KNN[J]. Agricultural Science ＆ Technology, 2009, 10(4): 146-149 |
| |
| Authors: | ZHAO Jing-ying GUO Hai SUN Xing-bin |
| |
| Affiliation: | 1. Department of Computer Science and Engineering of Dalian Nationalities University, Dalian 116600; 2. School of Munici. ＆ Envir. Eng Harbin Institute of Technology, Harbin 150001 ; 3. Department of Enviromental Science, Northeast Forestry University, Harbin 150040) |
| |
| Abstract: | 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. |
| |
| Keywords: | Freshwater plankton Chironomid larvae Wavelet decomposition Color features K-Nearest Neighbor (KNN) |
| 本文献已被 维普 万方数据 等数据库收录！ |
