品质至上,客户至上,您的满意就是我们的目标
技术文章
当前位置: 首页 > 技术文章
科学家利用Videometerlab多光谱成像系统发表辣椒种子识别文章
发表时间:2020-10-20 13:46:54点击:1140
最近,科学家利用VideometerLab多光谱成像系统发表了题为Discrimination of pepper seed varieties by multispectral imaging combined with machine learning的文章。
VideometerLab是款多功能多光谱成像系统,采用了图谱合一技术,集成有成熟分析软件,广泛用于植物种质资源、种子表型以及食品安全等各个领域。
Discrimination of pepper seed varieties by multispectral imaging combined with machine learning
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org
Citation:Applied Engineering in Agriculture. (in press). (doi: 10.13031/aea.13794) @2020
Authors:Xingwang Li, Xiaofei Fan, Lili Zhao, Sheng Huang, Yi He, Xuesong Xue Suo
Keywords:multispectral imaging; one-dimensional convolutional neural network; pepper seed; variety classification
Highlights
This study revealed the feasibility of to classify pepper seed varieties using multispectral imaging combined with one-dimensional convolutional neural network (1D-CNN).
Convolutional neural networks were adopted to develop models for prediction of seed varieties, and the performance was compared with KNN and SVM.
In this experiment, the classification effect of the SVM classification model is the best, but the 1D-CNN classification model is relatively easy to implement.
Abstract
When non-seed materials are mixed in seeds or seed varieties of low value are mixed in high value varieties, it will cause losses to growers or businesses. Thus, the successful discrimination of seed varieties is critical for improvement of seed ralue. In recent years, convolutional neural networks (CNNs) have been used in classification of seed varieties. The feasibility of using multispectral imaging combined with one-dimensional convolutional neural network (1D-CNN) to classify pepper seed varieties was studied. The total number of three varieties of samples was 1472, and the average spectral curve between 365nm and 970nm of the three varieties was studied. The data were analyzed using full bands of the spectrum or the feature bands selected by successive projection algorithm (SPA). SPA extracted 9 feature bands from 19 bands (430, 450, 470, 490, 515, 570, 660, 780, and 880 nm). The classification accuracy of the three classification models developed with full band using K nearest neighbors (KNN), support vector machine (SVM) and 1D-CNN were 85.81%, 97.70%, and 90.50%, respectively. With full bands, SVM and 1D-CNN performed significantly better than KNN, and SVM performed slightly better than 1D-CNN. With feature bands, the testing accuracies of SVM and 1D-CNN were 97.30% and 92.6%, respectively. Although the classification accuracy of 1D-CNN was not the highest, the ease of operation made it the most feasible method for pepper seed variety prediction.