摘要
该文以中国普遍种植的黄玉米为研究对象,通过对不同品种玉米籽粒数字图像信息的分析对比,发现玉米籽粒白色部分(胚部)与黄色部分(冠部)的面积、颜色等信息可以作为识别玉米品种的特征。采用基于支持向量机的遗传算法结合SPSS统计软件进行试验验证,得出玉米籽粒白色部分与黄色部分的面积比例、黄色部分的蓝色分量与饱和度在玉米品种识别方面具有显著价值。
The yellow corn which is popular in China was selected for the study, then the ratio of white part（embryo） to yellow part（crown） of corn seed was found out. Their color and shape are useful to identify corn vatieties by analyzing and contrasting the images and data of different varieties of corn seeds. Experiments were conducted using support vector machine （SVM） combined with genetic algorithm（GA） and Statistical Program for Social Sciences （SPSS）. Experimental results indicate that the ratio of white part to yellow part is valuable and the color characteristics of the yellow area are better than that of the whole corn seeds to identify corn varieties.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2008年第6期193-195,共3页
Transactions of the Chinese Society of Agricultural Engineering
基金
河北省自然科学基金资助项目(E2005000291)
河北农业大学非生命学科和新兴学科科研发展基金项目(Fsy200503)
关键词
玉米
品种识别
图像处理
白黄比例
特征参数
corn
variety identification
image processing
the ratio of white part to yellow part
characteristics
