摘要
特征提取是储粮害虫图像识别中的重要环节,是识别系统的难点所在。针对粮虫的二值化图像提取出17个形态学特征,并进行归一化处理;把交叉验证训练模型的识别率作为储粮害虫特征提取评价准则的一个重要因子,运用蚁群优化算法从粮虫的17维形态学特征中自动提取出面积、周长等7个特征的最优特征子空间;采用支持向量机分类器对9 类粮虫进行分类,识别率达到95%以上,证实了基于蚁群优化算法的粮虫特征提取的可行性。
The feature extraction is a very important and difficult part for the stored-grain insect detection system based on image recognition technology.The seventeen morphological features were extracted and normalized from the binary grain-insect images.The ant colony optimization algorithm was applied to the feature extraction of the stored-grain insects,and the recognition accuracy of the z-fold cross-validation training model was acted as an important factor for the evaluation principle of the feature extracti...
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2009年第2期126-130,共5页
Transactions of the Chinese Society of Agricultural Engineering
基金
国家自然科学基金项目(30871449)
江苏大学博士研究生创新基金资助项目
关键词
储粮害虫
图像识别
特征提取
蚁群优化算法
支持向量机
stored-grain insect
image recognition
feature extraction
ant colony optimization algorithm
support vector machine
