摘要
高光谱成像技术包含图像信息和光谱信息.本文利用高光谱成像技术检测苹果摔伤, 主要采用主成分分析、 波段比算法和支持向量机分析所采集的高光谱图像数据.实验结果表明, 波段比算法和主成分分析法分类识别正确率为93.3%, 与支持向量机相比更适用于苹果摔伤的实时快速检测.
Hyper-spectral imaging technology includes image information and spectral information. This paper used hyperspectral imaging technology to detect apple fall. In the process of experiment, principal component analysis,band ratio algorithm and support vector machine were used to analyze hyperspectral image data collected. The experi.mental results showed that the accuracy of band ratio algorithm and principal component analysis was 93. 3%, which was more suitable for real time and fast detection of apple fall than support vector machine.
作者
韩浩然
李蒙
杜德伟
明康
王鑫野
HAN Haoran1,2 ,LI Meng1,2 ,DU Dewei1,2 ,PAN Mingkang1,2 ,WANG Xinye1,2(1.College of Physics and Electronic, Yunnan Normal University,Kunming Yunnan 650500;2.Provincial Key Laboratory for Opto-electronic Information Technology,Kunming Yunnan 65050)
出处
《河南科技》
2018年第10期28-32,共5页
Henan Science and Technology
基金
国家自然科学基金(61168003)
国家级大学生创新创业训练计划项目(201510681004)
云南省科技计划项目(2016FB108).
关键词
水果损伤
高光谱
波段比算法
主成分分析
支持向量机
fruit injury;hyper-spectral;band ratio algorithm;principal component analysis;support vector machine