|
|||||
|
|
| 基于压力和图像的鲜玉米果穗成熟度分级方法 | |
| 引用本文： | 王慧慧,孙永海,张贵林,张婷婷,李义,许秀颖.基于压力和图像的鲜玉米果穗成熟度分级方法[J].农业工程学报,2010,26(7):369-373. |
| 作者姓名： | 王慧慧 孙永海 张贵林 张婷婷 李义 许秀颖 |
| 作者单位： | 1. 吉林大学生物与农业工程学院,长春,130022 2. 吉林大学机械科学与工程学院,长春,130022 3. 吉林天景食品有限公司,长春,130123 |
| 基金项目： | 国家“863”高技术研究发展计划资助项目（2008AA100802） |
| 摘 要： | 为实现鲜玉米果穗成熟度等级的客观评定，提出了基于压力传感器和计算机视觉技术的综合分析方法。研制了玉米果穗成熟度检测装置，提取纹理信息所得惯性矩和压力检测装置所得最大压力值作为鲜玉米果穗成熟度等级评定的特征参数，通过系统聚类分级研究，确定成熟度等级为3级。采用主成分分析法对11个颜色特征进行优化筛选，用第一、二主成分可综合反映11个颜色特征的分级信息，实现了参数的降维。试验结果表明：以最大压力值、惯性矩、颜色特征主成分分析第一、二主成分值作为构建概率神经网络的输入，进行鲜玉米果穗成熟度等级评定，正确率为96.67%。结合压力传感器和计算机视觉技术可实现对鲜玉米果穗成熟度的准确分级。 |
| 关 键 词： | 分级，压力，图像处理，神经网络，颜色特征，鲜玉米果穗 |
| 收稿时间： | 2009/3/23 0:00:00 |
| 修稿时间： | 7/7/2010 12:00:00 AM |
Grading method of fresh corn ear maturity based on pressure and image |
|
| Wang Huihui,Sun Yonghai,Zhang Guilin,Zhang Tingting,Li Yi,Xu Xiuying.Grading method of fresh corn ear maturity based on pressure and image[J].Transactions of the Chinese Society of Agricultural Engineering,2010,26(7):369-373. | |
| Authors: | Wang Huihui Sun Yonghai Zhang Guilin Zhang Tingting Li Yi Xu Xiuying |
| Abstract: | In order to realize objective evaluation of maturity grading of fresh corn ear, a method using pressure sensor and computer vision was presented. Maturity grading detection device was developed. The inertia moment of texture information and the maximum pressure obtained from pressure detection device were used as maturity grading characteristic parameters of fresh corn ear. Maturity was classified into 3 grades through system cluster method. Eleven color characteristics were optimized and screened by principal components analysis. The first and the second principal components were applied to represent the eleven color characteristics in the grading, so dimension reduction was implemented. Results showed that inertia moment, maximum pressure, the first and the second principal component values of color characteristics were used as inputs of the probabilistic neural network developed for maturity grading of fresh corn ear, with grading accuracy 96.67%. Fresh corn ear maturity grading can be implemented accurately by combination of pressure sensor and computer vision technology. |
| Keywords: | grading pressure image processing neural networks color characteristics fresh corn ear |
| 本文献已被 万方数据 等数据库收录！ | |
| 点击此处可从《农业工程学报》浏览原始摘要信息 | |
| 点击此处可从《农业工程学报》下载免费的PDF全文 | |