欢迎访问《农学学报》,

农学学报 ›› 2024, Vol. 14 ›› Issue (11): 1-6.doi: 10.11923/j.issn.2095-4050.cjas2023-0225

• 农艺农学 生理生化 •    下一篇

基于HSV的烤烟叶片青杂检测研究

李更新1(), 臧传江1, 赵湘江1, 王德权1, 董玉双2(), 古明光1, 高阳1, 谭新伟1, 苗壮1, 赵溪清1, 李阳3   

  1. 1 山东潍坊烟草有限公司,山东潍坊 261031
    2 中央民族大学信息工程学院,北京 100081
    3 北方工业大学计算机系,北京 100144
  • 收稿日期:2023-10-12 修回日期:2024-06-20 出版日期:2024-11-20 发布日期:2024-11-19
  • 通讯作者:
    董玉双,男,1983年出生,黑龙江密山人,讲师,博士,现从事云计算、大数据,人工智能等研究。通信地址:100081 北京市海淀区中关村南大街27号 中央民族大学信息工程学院,Tel:010-68932970,E-mail:
  • 作者简介:

    李更新,男,1970年出生,山东青州人,高级农艺师,在职研究生,现从事烟草农业现代化、烟叶生产经营管理、企业管理等。通信地址:261205 山东省潍坊市健康东街6787号 山东潍坊烟草有限公司,E-mail:

  • 基金资助:
    山东潍坊烟草有限公司2021年度科学基金项目“烟叶智能分级及收购成包全程自动化研究与应用”(2021-40)

Green Impurity Detection of Flue-cured Tobacco Leaf Based on HSV

LI Gengxin1(), ZANG Chuanjiang1, ZHAO Xiangjiang1, WANG Dequan1, DONG Yushuang2(), GU Mingguang1, GAO Yang1, TAN Xinwei1, MIAO Zhuang1, ZHAO Xiqing1, LI Yang3   

  1. 1 Shandong Weifang Tobacco Co., Ltd., Weifang 261031, Shandong, China
    2 School of Information Engineering, Minzu University of China, Beijing 100081, China
    3 College of Computer, North China University of Technology, Beijing 100144, China
  • Received:2023-10-12 Revised:2024-06-20 Online:2024-11-20 Published:2024-11-19

摘要:

为研究烟叶收购过程中快速高效的青杂检测方法,以山东诸城烟叶收购中的青杂检测为研究背景,以提升青杂检测的自动化和高效能为目的,分别对含青烟叶样本、含杂烟叶样本和合格烟叶样本进行数据采集,结合图像识别技术,进行烤烟青杂检测的样本处理和主流检测手段优劣性剖析。利用256段波段高光谱相机获取数据信息,通过调取RGB波段映射RGB颜色空间,进而转换为HSV颜色空间进行叶片含青、含杂率检测。结果显示,通过大量实验测量,获得青杂的HSV颜色色域范围,精确给出青杂色的像素点数,进而给出烤烟叶片青含杂比例。待测烤烟的含青、含杂像素点的精确标注给出可视化的检测结果,结合烟叶RGB图像,使得算法的青杂检测具有较强的可解释性。研究发现,基于高光谱数据和HSV颜色空间的自动化烟叶青杂检测方法,青杂检测算法执行时延在4 s左右,在青杂检测准确率方面已经满足烟叶收购需求。

关键词: 色调-饱和度-明度, 高光谱, 青杂检测, 机器视觉, 自动化

Abstract:

Through the analysis of the advantages and disadvantages of the sample processing methods and mainstream detection methods for the detection of flue-cured tobacco leaf impurities, a set of detection schemes that fully reflect the superiority and high comprehensive performance is proposed. The 256-band hyperspectral camera was used to obtain data information, and the RGB color space was mapped by calling the RGB band, and then converted to the HSV color space for detection of green and impurity content in tobacco leaves. The HSV color gamut range of green impurity was obtained through amounts of real experimental measurements, and the number of green and impurity pixels of the tobacco leaves to be tested was accurately given, and the proportion of green and impurity pixels in the flue-cured tobacco leaves was given. The precise labeling of green and impurity pixels of the flue-cured tobacco to be tested provided a visual detection results. Combined with the RGB tobacco leaves, the algorithm of green and impurity detection had strong interpretability. Meanwhile, the execution delay of the proposed detection algorithm was about 4 s. The flue-cured tobacco leaf green impurity detection scheme not only meets the actual acquisition needs, but also has high visualization and interpretability.

Key words: hue-saturation-value (HSV), hyperspectral, green impurity detection, machine vision, automation