欢迎您访问《智慧农业(中英文)》官方网站! English

Smart Agriculture ›› 2021, Vol. 3 ›› Issue (1): 86-95.doi: 10.12133/j.smartag.2021.3.1.202102-SA007

• 专题--作物表型前沿技术与应用 • 上一篇    下一篇

基于轮廓坐标系转换拟合的柚子果形检测分级方法

李燕1(), 沈杰1, 谢航1, 高广垠1, 刘建雄1, 刘洁1,2,3()   

  1. 1.华中农业大学 工学院,湖北 武汉 430070
    2.农业农村部长江中下游农业装备重点实验室,湖北 武汉 430070
    3.农业农村部柑橘全程机械化科研基地,湖北 武汉 430070
  • 收稿日期:2021-02-05 修回日期:2021-03-01 出版日期:2021-03-30
  • 基金资助:
    中央高校基本科研业务费专项基金资助(2662020GXPY011);现代农业(柑橘)产业技术体系建设专项资金项目(CARS-27);国家重点研发计划(2018YFD0701105-2)
  • 作者简介:李 燕(1998-),女,硕士研究生,研究方向为图像处理。E-mail:747783109@qq.com
  • 通信作者:

Detection and Grading Method of Pomelo Shape Based on Contour Coordinate Transformation and Fitting

LI Yan1(), SHEN Jie1, XIE Hang1, GAO Guangyin1, LIU Jianxiong1, LIU Jie1,2,3()   

  1. 1.College of Engineering, Huazhong Agricultural University, Wuhan 430070, China
    2.Key Laboratory of Agricultural Equipment in Mid-lower Yangtze River, Ministry of Agriculture and Rural Affairs, Wuhan 430070, China
    3.Citrus Mechanization Research Base, Ministry of Agriculture and Rural Affairs, Wuhan 430070, China
  • Received:2021-02-05 Revised:2021-03-01 Online:2021-03-30

摘要:

针对柚子果形和尺寸分级依赖人工经验判断的现状,本研究提出一种采用轮廓坐标系转换拟合、果形特征提取结合方向角补偿算法检测柚子纵、横径尺寸并基于果形指数对柚子形状缺陷进行判断的方法。以CMOS相机、点阵式LED光源、平面镜、计算机、箱体和支架搭建图像采集装置,获取168个不同尺寸与形状等级的沙田柚样本全表面图像数据。选择G-B分量灰度图像进行去噪与分割,利用Laplacian算子边缘检测算法提取果实的边缘像素,采用多项式拟合方式完成直角坐标向极坐标的转换从而简化果形描述,利用特征点极角值补偿样本纵横径的随机方向,继而区别类球形和类梨形两种类型计算柚子的纵径和横径。以广东梅州沙田柚为对象进行试验,结果表明,利用轮廓坐标系转换拟合、果形特征提取结合方向角补偿算法的方法检测柚子纵径的平均绝对误差、最大绝对误差和平均相对误差分别为2.23 mm、7.39 mm和1.6%,横径的平均绝对误差、最大绝对误差和平均相对误差分别为2.21 mm、7.66 mm和1.4%。从柚子轮廓极坐标的拟合函数中提取3个峰值高度、3个波峰宽度和1个波谷值差值7个特征值,利用BP神经网络算法建立柚子果形判别模型并用独立验证集进行验证,形状判别的总识别率为83.7%。本方法能为柚子尺寸和形状的自动化检测与分级提供快速无损方法。

关键词: 柚子轮廓, 果形检测, BP神经网络, 坐标系转换, 图像处理, 果形判别模型

Abstract:

Automatic grading method of pomelo fruit according to the shape and size is urgently needed in the industry since the work mainly depends on artificial judgment currently. In this research, a method, which detected the vertical and horizontal size of pomelo by using contour coordinate transformation fitting, fruit shape feature extraction and direction angle compensation algorithm, while it determined the shape defects based on fruit shape index, was proposed. The image acquisition system was self-designed and built up with a CMOS camera, a dot matrix LED light source, a plane mirror, the computer, a box and brackets. The image data containing whole surface information of Shatian pomelo samples with different sizes and shapes were collected by this system. The G-B component grayscale image was chosen for denoising and segmentation. The Laplacian edge detection algorithm was implemented to extract the edge pixels of the fruit. The polynomial fitting method was applied to converse the rectangular coordinates to polar coordinates so that the fruit shape description was simplified. The characteristic point polar angle value was used to compensate the random direction of the vertical and horizontal diameters of the sample. Then the vertical and horizontal diameters of fruit were calculated after classifying the sample shapes into the spherical and the pear-like categories. For the involved 168 pomelo samples, the average error, maximum absolute error and average relative error of the vertical diameters were 2.23 mm, 7.39 mm and 1.6% respectively, while these parameters of the horizontal diameters were 2.21 mm, 7.66 mm and 1.4% respectively. The fruit shape discriminant model was established by using BP neural network algorithm based on the seven features extracted from the fitting function and verified by independent validation set including 3 peak heights, 3 peak widths and 1 trough value difference. The total recognition rate of shape identification was 83.7%. The results illustrated that the method had the potential to measuring the pomelo size and shape for grading fast and non-destructively.

Key words: pomelo contour, fruit shape detection, back propagation neural network, coordinate system conversion, image processing, fruit shape discriminant model

中图分类号: