Abstract
[Objective] Refining the accuracy and intelligence of passion fruit quality assessment. [Methods] The study used the capabilities of OpenCV along with a compact neural network architecture, MobileNetV3_large_ssld, to accurately determine the fruit's diameter, ripeness, and the degree of its wrinkling. The diameter measurement was achieved by analyzing the short side of the fruit's minimum bounding rectangle. The ripeness assessment was based on the pixel ratio of H component values within specific ranges （H∈[0,10]∪[156,180], [11,25], [26,34], [125,155]） in the HSV color space. Furthermore, the study developed a MobileNetV3_large_ssld model to evaluate the wrinkling of the fruit's skin. Leveraging these three key indicators, a comprehensive fruit quality evaluation model was established using a rating scale approach, and an online detection and sorting system was subsequently developed. This system employed KNN background subtraction to extract the fruits target, excludes stems, and used interval frame sampling method to capture single image for each fruit from the video. The comprehensive evaluation model was utilized to assess the quality of passion fruits, which were then sorted into their appropriate grade channels through a sorting mechanism. [Results] The test results indicated a high degree of consistency between the system's sorting and manual sorting, with an overall accuracy of 97.02%. The consistency rates for top-grade fruits, first-grade, and second-grade fruits were 95.51%, 97.84%, and 100%, respectively. [Conclusion] This system could be used for online detection and sorting of passion in different quality grades.
Publication Date
7-22-2024
First Page
130
Last Page
137,142
DOI
10.13652/j.spjx.1003.5788.2023.80701
Recommended Citation
Xuan, CHU; Jialong, HONG; Gengxin, FENG; Zhenquan, YAO; and Zhiyu, MA
(2024)
"Online detection and sorting of passion fruit quality based on machine vision using multi-indicator,"
Food and Machinery: Vol. 40:
Iss.
6, Article 18.
DOI: 10.13652/j.spjx.1003.5788.2023.80701
Available at:
https://www.ifoodmm.cn/journal/vol40/iss6/18
References
[1] 熊荣园, 蔡韵凝, 魏玲, 等. 响应面法分析柑橘百香果复合果汁的工艺品质[J]. 粮油食品科技, 2022, 30（2）: 106-112.
XIONG R Y, CAI Y N, WEI L, et al. The technology and quality research of citrus passion fruit compound juice by response surface methodology[J]. Science and Technology of Cereals, Oils and Foods, 2022, 30（2）: 106-112.
[2] 郭靖, 陈于陇, 王萍, 等. 百香果采后特性与保鲜技术研究综述[J]. 食品与发酵工业, 2021, 47（1）: 334-340.
GUO J, CHEN Y L, WANG P, et al. Research progress on postharvest characteristics and preservation technology of passion fruits[J]. Food and Fermentation Industries, 2021, 47（1）: 334-340.
[3] 田芳, 彭彦昆, 魏文松, 等. 基于机器视觉的马铃薯黑心病检测机构设计与试验[J]. 农业工程学报, 2017, 33（5）: 287-294.
TIAN F, PENG Y K, WEI W S, et al. Design and experiment of detection mechanism for potato blackheart based on machine vision[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33（5）: 287-294.
[4] 彭彦昆, 孙晨, 刘乐, 等. 苹果外部缺陷全表面在线检测分选装置研发[J]. 农业工程学报, 2022, 38（23）: 266-275.
PENG Y K, SUN C, LIU L, et al. Development of full-surface online detection and sorting device for external defects of apples[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38（23）: 266-275.
[5] 李浪, 文韬, 代兴勇, 等. 柑橘全表面色泽在线检测与分级系统[J]. 食品与机械, 2022, 38（12）: 121-126.
LI L, WEN T, DAI X Y, et al. Online detection and grading system for citrus full-surface color[J]. Food & Machinery, 2022, 38（12）: 121-126.
[6] FAN S X, LI J B, ZHANG Y H, et al. On line detection of defective apples using computer vision system combined with deep learning methods[J]. Journal of Food Engineering, 2020, 286: 110102.
[7] PISE D, UPADHYE G D. Grading of harvested mangoes quality and maturity based on machine learning techniques[C]// 2018 International Conference on Smart City and Emerging Technology （ICSCET）. Mumbai: IEEE, 2018: 1-6.
[8] ARAKERIA M P, LAKSHMANA. Computer vision based fruit grading system for quality evaluation of tomato in agriculture industry[J]. Procedia Computer Science, 2016, 79: 426-433.
[9] 唐熔钗. 基于深度学习的百香果成熟度实时检测算法研究[D]. 桂林: 桂林电子科技大学, 2021: 45-48.
TANG R C. Research on real-time detection algorithm of passion fruit maturity via deep learning[D]. Guilin: Gunlin University of Electronic Technology, 2021: 45-48.
[10] 黄才贵. 基于机器视觉的百香果采摘分级机器人平台的设计[J]. 农业技术与装备, 2022（1）: 54-56.
HUANG C G. Design of passion fruit picking grading robot platform based on machine vision[J]. Agricultural Technology & Equipment, 2022（1）: 54-56.
[11] TU S Q, XUE Y J, CHAN Z, et al. Detection of passion fruits and maturity classification using red-green-blue depth images[J]. Biosystems Engineering, 2018, 175: 156-167.
[12] 代泽繁, 秦剑锋, 江英杰, 等. 百香果分拣装置的设计与研究[J]. 轻工科技, 2019, 35（10）: 39-40, 107.
DAI Z F, QIN J F, JIANG Y J, et al. Design and research of passion fruit sorting device[J]. Light Industry Science and Technology, 2019, 35（10）: 39-40, 107.
[13] SIDEHABI S W, SUYUTI A, ARENI I S, et al. Classification on passion fruit's ripeness using K-means clustering and artificial neural network[C]// International Conference on Information and Communications Technology. Yogyakarta: IEEE, 2018: 304-309.
[14] SIDEHABI S W, SUYUTI A, ARENI I S, et al. The development of machine vision system for sorting passion fruit using multiclass support vector machine[J]. Journal of Engineering Science and Technology Review, 2018, 11（5）: 178-184.
[15] 汪伯军, 郭保银, 黄富饶, 等. 基于HSV颜色空间的烟叶烘烤阶段判别模型研究[J]. 南方农机, 2023, 54（13）: 5-9.
WANG B J, GUO B Y, HUANG F R, et al. Study on discrimination model of tobacco curing stage based on HSV color space[J]. South Forum, 2023, 54（13）: 5-9.
[16] 陈启, 陈慈发, 邓向武, 等. 基于移动端轻量模型的杂草分类方法研究[J]. 中国农机化学报, 2022, 43（2）: 163-170.
CHEN Q, CHEN C F, DENG X W, et al. Research on weed classification method based on mobile light weight model[J]. Journal of Chinese Agricultural Mechanization, 2022, 43（2）: 163-170.
[17] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul: IEEE, 2019: 1 314-1 324.