A detection method for potato shape of commercial potatoes based on quantum-behaved particle swarm optimization and support vector machine

doi:10.14088/j.cnki.issn0439-8114.2025.12.036

Abstract

Abstract: Aiming at the problems of low accuracy and poor efficiency of existing potato shape detection methods for commercial potatoes, which made it difficult to meet the requirements of mechanized and automated sorting, a method for potato shape detection was investigated based on machine vision technology. Three potato shapes (spherical or subspherical, ellipsoidal, and irregular) were taken as research objects. First, a potato image acquisition system was built to collect images of the three shapes. Then, the images were preprocessed to obtain potato contour images. Subsequently, ten invariant moments of the potato images were extracted as feature parameters, and thesupport vector machine classifier was optimized using the quantum-behaved particle swarm optimization algorithm, ultimately achieving automatic detection of potato shape. The results showed that the detection accuracies for spherical or subspherical, ellipsoidal, and irregular potato shapes in the QPSO-SVM model were 97.0%, 94.0%, and 91.0%, respectively, with an average detection accuracy of 95.2%. This model could be used for the rapid detection of potato shape.

Key words: quantum-behaved particle swarm optimization, support vector machine, potato, commercial potato, potato shape

CLC Number:

S532
TP391.4

WAN Peng, XIONG Cheng-xin, CAI Jie, LIU Yan-fang, WU Xiao-long. A detection method for potato shape of commercial potatoes based on quantum-behaved particle swarm optimization and support vector machine[J]. HUBEI AGRICULTURAL SCIENCES, 2025, 64(12): 212-217.

References

[1] 曾凡逵,胡肖业,吕黄珍,等.中外马铃薯加工业的比较分析[J].中国马铃薯,2024,38(6):513-529.
[2] 周华迪. 马铃薯产业发展前景及高产栽培技术[J].现代农业科技,2016(16):95-96.
[3] 杨广辉,李红岭,张华,等.马铃薯品质无损检测技术的研究进展[J].粮油食品科技,2024,32(6): 161-169.
[4] 姜宏,于永波,章翔峰,等.马铃薯外部品质分级方法综述[J]. 科学技术与工程,2022,22(14):5519-5527.
[5] 刘浩,贺福强,李荣隆, 等. 基于机器视觉的马铃薯自动分级与缺陷检测系统设计[J].农机化研究,2022,44(1):73-78.
[6] 张永志,李旭英,高盛博. 辊式尼龙刷马铃薯清选分级机的设计与试验[J].农机化研究,2021,43(6):152-155,160.
[7] 邓立苗,杜宏伟,徐艳,等.基于机器视觉的马铃薯智能分选方法与实现[J].中国农机化学报,2015,36(5):145-150.
[8] BARNES M,DUCKETT T,CIELNIAK G,et al.Visual detection of blemishes in potatoes using minimalist boosted classifier[J]. Journal of food engineering,2010,98(3):339-346.
[9] GAMALE,SERGIO C,ENRIQUE M,et al.In-line sorting of irregular potatoes by using automated computer-based machine vision system[J].Journal of food engineering, 2012, 112(1-2):60-68.
[10] 周平,徐旭艳,杨兵.基于图像信息的马铃薯薯形检测方法研究[J].安徽农业大学学报,2013,40(5):883-885.
[11] 王红军,熊俊涛,黎邹邹,等.基于机器视觉图像特征参数的马铃薯质量和形状分级方法[J]. 农业工程学报,2016,32(8):272-277.
[12] 刘毅君. 基于机器视觉的马铃薯外部品质分级方法研究[D].北京:中国农业机械化科学研究院,2023.
[13] 郝敏,麻硕士,侯振杰.Zernike矩的不变性与计算实现[J].内蒙古农业大学学报(自然科学版),2009,30(2):222-225.
[14] 郝敏,麻硕士,郝小冬.基于Zernike矩的马铃薯薯形检测[J].农业工程学报,2010,26(2):347-350.
[15] 郝敏,麻硕士.基于机器视觉的马铃薯单薯质量检测技术研究[J].农机化研究,2009,31(9):61-63.
[16] 汤全武,何昊瀚,杨燕,等.马铃薯动态分级系统中多目相机同步采集方法[J].农业工程,2021,11(1):28-32
[17] 向静,何志良,汤林越,等.结合计算机视觉的马铃薯外部品质检测技术[J].计算机工程与应用,2018,54(5):165-169
[18] 李一波,刘佰仑. 基于改进Canny算子的图像边缘检测算法[J]. 科学技术创新, 2022 (2): 93-96.
[19] LONG Y,WANG Y,ZHAI Z,et al.Potato volume measurement based on RGB-D camera[J].IFAC-Papers on line,2018,51(17):515-20
[20] 周军,蔡建,郭俊先,等.基于机器视觉的核桃仁特征提取与分级方法研究[J].江苏农业科学,2018,46(11):175-179.
[21] WU Z,JIANG S,ZHOU X,et al.Application of image retrieval based on convolutional neural networks and Hu invariant moment algorithm in computer telecommunications[J].Computer communications,2020,150: 729-738.
[22] 黄朝兴. 基于机器人主动视觉的工件识别定位与抓取研究[D]. 福州: 福州大学,2016.
[23] 因晓倩. 基于支持向量机的交通标志识别[D].西安:长安大学,2019.
[24] 丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综[J].电子科技大学学报,2011,40(1):2-10
[25] HEINEMANN P H, PATHARE N P, MORROW C T.An automated inspection station for machine-vision grading of potatoes[J]. Machine vision and applications, 1996, 9: 14-19.
[26] 邵信光,杨慧中,陈刚.基于粒子群优化算法的支持向量机参数选择及其应用[J].控制理论与应用,2006(5):740-743,748.
[27] MARINO S, BEAUSEROY P, SMOLARZ A.Weakly-supervised learning approach for potato defects segmentation[J]. Engineering applications of artificial intelligence, 2019, 85: 337-346.