| 王伟生1，崔震浩1，郑小真1，王婧薷2，彭丹3，杜新波4.基于机器视觉的大豆油色泽预测模型研究[J].中国油脂,2025,50(12):.[WANG Weisheng1,CUI Zhenhao1，ZHENG Xiaozhen1，
WANG Jingru2,PENG Dan3，DU Xinbo4.Research on the prediction model of soybean oil color based on machine vision[J].China Oils and Fats,2025,50(12):.] |
| 基于机器视觉的大豆油色泽预测模型研究 |
| Research on the prediction model of soybean oil color based on machine vision |
| |
| DOI：10.19902/j.cnki.zgyz.1003-7969.240503 |
| 中文关键词: 机器视觉 支持向量回归 人工神经网络 油脂色泽 罗维朋比色法 |
| 英文关键词:machine vision support vector regression artificial neural network oil color Lovibond colorimetry |
| 基金项目:河南省科技攻关项目（242102320278） |
|
|
| 摘要点击次数: 818 |
| 全文下载次数: 320 |
| 中文摘要: |
| 旨在解决传统油脂色泽检测方法客观性不足的问题，建立了一种基于机器视觉的大豆油色泽预测模型。首先采集不同色泽等级大豆油的图像，使用中值滤波和Canny边缘检测算法对油样图像进行预处理并提取9个色泽特征，然后对提取的色泽特征进行主成分分析（PCA），选取累积方差贡献率达到99.23%的3个主成分（F1、F2、F3）作为输入变量，大豆油的罗维朋红值和黄值作为输出变量构建PCA-人工神经网络（ANN）模型和PCA-支持向量回归（SVR）模型，并使用LM算法、交叉验证和网络搜索算法分别对2个模型的参数进行优化，并对2个模型性能进行对比分析。结果表明，PCA-SVR模型预测大豆油色泽的效果更好，其决定系数（R2）为0.96，均方根误差为285。综上，基于机器视觉构建的大豆油色泽预测模型用于大豆油色泽的快速检测是完全可行的。 |
| 英文摘要: |
| In order to solve the problem of insufficient objectivity in traditional oil color detection methods, a machine vision based soybean oil color prediction model was established.Firstly, the images of soybean oil with different color grades were collected, and median filtering and Canny edge detection algorithm were used to pretreat the oil sample images and extract 9 color features. Then, principal component analysis (PCA) was applied to these features, and with the top three components (F1, F2, F3) that cumulatively explain 9923% of the variance were selected as inputs, Lovibond red and yellow values as outputs, two models of PCA-ANN and PCA-SVR were established. Model parameters were optimized using the LM algorithm, cross-validation, and grid search algorithm, and the performances of the two models were compared. The results showed that the PCA-SVR model had a better prediction effect on soybean oil color, with a coefficient of determination (R2) of 0.96 and a root mean square error of 2.85. In summary, the oil color detection model based on machine vision is completely feasible for rapid detection of soybean oil color. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
