{"title":"基于叶片颜色识别桃子品种的机器学习模型评估","authors":"Daniel Ayala-Niño, J. M. González-Camacho","doi":"10.47163/agrociencia.v56i4.2810","DOIUrl":null,"url":null,"abstract":"Machine learning and deep learning approaches are applied in different areas of the agricultural sector, particularly in the digital image-based identification of characteristics of interest in crops. In this research, the performance of three machine learning classifiers was evaluated: support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP). The aim was to identify four varieties of peach (Prunus persica L. Batsch) (CP-03-06, Oro Azteca, Oro San Juan, and Cardenal), based on the color of digital images of the upper and lower side of leaves, represented by two color spaces: RGB (red, green, blue) and HSV (hue, saturation, value). The classifiers were trained and evaluated based on six data input scenarios, defined by the combinations of the upper, lower, and both sides of the leaf with the RGB and HSV color spaces. The three machine learning classifiers (SVM, RF, and MLP) achieved their best prediction performance when they examined the color characteristics of the upper side of leaves transformed to the HSV color space. The SVM classifier outperformed RF and MLP. SVM achieved a global average correct classification accuracy of 84.1 %, F1 macro of 83.7 %, and area under the ROC curve (AUC macro) of 0.93. The Oro Azteca variety reached the highest classification rate with a F1 score of 87.9 % and the Oro San Juan variety obtained the lowest rate with a F1 of 71.3 %.","PeriodicalId":50836,"journal":{"name":"Agrociencia","volume":"1 1","pages":""},"PeriodicalIF":0.5000,"publicationDate":"2022-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EVALUATION OF MACHINE LEARNING MODELS TO IDENTIFY PEACH VARIETIES BASED ON LEAF COLOR\",\"authors\":\"Daniel Ayala-Niño, J. M. González-Camacho\",\"doi\":\"10.47163/agrociencia.v56i4.2810\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Machine learning and deep learning approaches are applied in different areas of the agricultural sector, particularly in the digital image-based identification of characteristics of interest in crops. In this research, the performance of three machine learning classifiers was evaluated: support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP). The aim was to identify four varieties of peach (Prunus persica L. Batsch) (CP-03-06, Oro Azteca, Oro San Juan, and Cardenal), based on the color of digital images of the upper and lower side of leaves, represented by two color spaces: RGB (red, green, blue) and HSV (hue, saturation, value). The classifiers were trained and evaluated based on six data input scenarios, defined by the combinations of the upper, lower, and both sides of the leaf with the RGB and HSV color spaces. The three machine learning classifiers (SVM, RF, and MLP) achieved their best prediction performance when they examined the color characteristics of the upper side of leaves transformed to the HSV color space. The SVM classifier outperformed RF and MLP. SVM achieved a global average correct classification accuracy of 84.1 %, F1 macro of 83.7 %, and area under the ROC curve (AUC macro) of 0.93. The Oro Azteca variety reached the highest classification rate with a F1 score of 87.9 % and the Oro San Juan variety obtained the lowest rate with a F1 of 71.3 %.\",\"PeriodicalId\":50836,\"journal\":{\"name\":\"Agrociencia\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.5000,\"publicationDate\":\"2022-06-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Agrociencia\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.47163/agrociencia.v56i4.2810\",\"RegionNum\":4,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"AGRICULTURE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Agrociencia","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.47163/agrociencia.v56i4.2810","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
摘要
机器学习和深度学习方法被应用于农业部门的不同领域,特别是在基于数字图像的农作物特征识别方面。本研究评估了支持向量机(SVM)、随机森林(RF)和多层感知器(MLP)这三种机器学习分类器的性能。目的是根据叶片上下两侧的数字图像的颜色识别四个品种(Prunus persica L. Batsch) (CP-03-06, Oro Azteca, Oro San Juan和Cardenal),由两个颜色空间表示:RGB(红、绿、蓝)和HSV(色调、饱和度、值)。分类器基于六个数据输入场景进行训练和评估,这些数据输入场景由叶子的上、下和两侧与RGB和HSV颜色空间的组合定义。三种机器学习分类器(SVM, RF和MLP)在检查转换为HSV颜色空间的叶子上部的颜色特征时获得了最佳预测性能。SVM分类器优于RF和MLP。SVM的全球平均正确分类准确率为84.1%,F1宏为83.7%,ROC曲线下面积(AUC宏)为0.93。奥罗阿兹特克品种的一级分类率最高,为87.9%,奥罗圣胡安品种的一级分类率最低,为71.3%。
EVALUATION OF MACHINE LEARNING MODELS TO IDENTIFY PEACH VARIETIES BASED ON LEAF COLOR
Machine learning and deep learning approaches are applied in different areas of the agricultural sector, particularly in the digital image-based identification of characteristics of interest in crops. In this research, the performance of three machine learning classifiers was evaluated: support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP). The aim was to identify four varieties of peach (Prunus persica L. Batsch) (CP-03-06, Oro Azteca, Oro San Juan, and Cardenal), based on the color of digital images of the upper and lower side of leaves, represented by two color spaces: RGB (red, green, blue) and HSV (hue, saturation, value). The classifiers were trained and evaluated based on six data input scenarios, defined by the combinations of the upper, lower, and both sides of the leaf with the RGB and HSV color spaces. The three machine learning classifiers (SVM, RF, and MLP) achieved their best prediction performance when they examined the color characteristics of the upper side of leaves transformed to the HSV color space. The SVM classifier outperformed RF and MLP. SVM achieved a global average correct classification accuracy of 84.1 %, F1 macro of 83.7 %, and area under the ROC curve (AUC macro) of 0.93. The Oro Azteca variety reached the highest classification rate with a F1 score of 87.9 % and the Oro San Juan variety obtained the lowest rate with a F1 of 71.3 %.
期刊介绍:
AGROCIENCIA is a scientific journal created and sponsored by the Colegio de Postgraduados. Its main objective is the publication and diffusion of agricultural, animal and forestry sciences research results from mexican and foreign scientists. All contributions are peer reviewed. Starting in the year 2000, AGROCIENCIA became a bimonthly and fully bilingual journal (Spanish and English versions in the same issue). Since 2007 appears every month and a half (eight issues per year). In addition to the printed issues, the full content is available in electronic format.