Dragon fruit weight estimation based on machine vision and machine learning

Authors

LIANG Ying-kai, College of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China;Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence, Guangzhou, Guangdong 510642, China;Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, Guangzhou, Guangdong 510642, China
SHANG Feng-nan, College of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China;Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence, Guangzhou, Guangdong 510642, China;Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, Guangzhou, Guangdong 510642, China
CHEN Qiao, College of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China;Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence, Guangzhou, Guangdong 510642, China;Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, Guangzhou, Guangdong 510642, China
XIAO Ming-wei, College of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China;Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence, Guangzhou, Guangdong 510642, China;Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, Guangzhou, Guangdong 510642, China
LUO Chen-di, College of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China;Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence, Guangzhou, Guangdong 510642, China;Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, Guangzhou, Guangdong 510642, China
LI Wen-tao, College of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China;Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence, Guangzhou, Guangdong 510642, China;Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, Guangzhou, Guangdong 510642, China
ZHOU Xue-cheng, College of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China;Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence, Guangzhou, Guangdong 510642, China;Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, Guangzhou, Guangdong 510642, ChinaFollow

Corresponding Author(s)

周学成（1968—），男，华南农业大学教授，博士。E-mail：zxcem@scau.edu.cn

Abstract

Objective: In order to solve the problem of manual weighting of dragon fruit, including time-consuming, laborious and expensive, an automated weight estimation method based on machine vision and machine learning was proposed in this research. Methods: Firstly, 106 dragon fruits were weighed, recorded and photographed, and images of dragon fruits were constructed. Secondly, binary images were obtained after denoising and segmentation. Moreover, the three features of pixel area, major axis pixel length and minor axis pixel length of dragon fruits were extracted on the basis of binary images. The three features of each image and their corresponding weights were combined into a set of data, which was divided into training set and test set according to the ratio of 7∶3. Finally, the training set was input into the Gradient Boosting, Random Forest, K-Neighbors and Artificial Neural Networks machine-learning models for training, and the test sets were used for model evaluation. Results: The evaluation index of the Artificial Neural network performed well compared with other models, with R² of 0.986 and RMSE of 13.091. Conclusion: The experimental result demonstrates that the method proposed in this research can accomplish the weight estimation of dragon fruit effectively, and meet the weight estimation requirements of dragon fruit.

Publication Date

10-20-2023

First Page

99

Last Page

103

DOI

10.13652/j.spjx.1003.5788.2022.81065

Recommended Citation

Ying-kai, LIANG; Feng-nan, SHANG; Qiao, CHEN; Ming-wei, XIAO; Chen-di, LUO; Wen-tao, LI; and Xue-cheng, ZHOU (2023) "Dragon fruit weight estimation based on machine vision and machine learning," Food and Machinery: Vol. 39: Iss. 7, Article 15.
DOI: 10.13652/j.spjx.1003.5788.2022.81065
Available at: https://www.ifoodmm.cn/journal/vol39/iss7/15

References

[1] 吴刚, 陈海平, 谭乐和. 中国特色热带果树产业现状及发展对策[J]. 热带农业科学, 2014, 34（12）: 105-110. WU G, CHEN H P, TAN L H. Status of tropical fruit industry in China and development countermeasures[J]. Chinese Journal of Tropical Agriculture, 2014, 34（12）: 105-110.
[2] 中华人民共和国农业农村部. 火龙果等级规格: NY/T 3601—2020[S]. 北京: 中国农业出版社, 2020. Ministry of Agriculture and Rural Affairs of the People's Republic of China. Grades and specifications of pitahayas: NY/T 3601—2020[S]. Beijing: China Agricultural Press, 2020.
[3] 徐磊磊, 金琰, 侯媛媛, 等. 我国火龙果市场与产业调查分析报告[J]. 农产品市场, 2021（8）: 43-45. XU L L, JIN Y, HOU Y Y, et al. China dragon fruit market and industry survey analysis report[J]. Agricultural Products Market, 2021（8）: 43-45.
[4] 唐应志, 黄建祥, 苏明, 等. 海南火龙果鲜果的包装技术规范[J]. 果农之友, 2022（7）: 78-81. TANG Y Z, HUANG J X, SU M, et al. Technical specifications for the packaging of fresh fruit from Hainan dragon fruit[J]. Fruit Growers' Friend, 2022（7）: 78-81.
[5] 苏明, 彭寿宏, 黄建祥, 等. 大红火龙果采收的外观分级技术规范[J]. 果农之友, 2022（6）: 65-67. SU M, PENG S H, HUANG J X, et al. Technical specifications for grading the appearance of large red dragon fruit for harvesting[J]. Fruit Growers' Friend, 2022（6）: 65-67.
[6] 罗兵威. 火龙果种植技术现状及发展建议探究[J]. 南方农业, 2021, 15（30）: 83-84. LUO B W. Exploring the current situation of dragon fruit cultivation technology and development proposals[J]. South China Agriculture, 2021, 15（30）: 83-84.
[7] ZHANG Z, LU Y, LU R. Development and evaluation of an apple infield grading and sorting system[J]. Postharvest Biology and Technology, 2021, 180: 111588.
[8] NYALALA I, OKINDA C, KUNJIE C, et al. Weight and volume estimation of poultry and products based on computer vision systems: A review[J]. Poult Sci, 2021, 100（5）: 101072.
[9] 张恩宇. 苹果田间分级关键技术研究[D]. 咸阳: 西北农林科技大学, 2020: 7. ZHANG E Y. Research on key techniques for grading apples in the field[D]. Xianyang: Northwest A & F University, 2020: 7.
[10] NYALALA I, OKINDA C, NYALALA L, et al. Tomato volume and mass estimation using computer vision and machine learning algorithms: Cherry tomato model[J]. Journal of Food Engineering, 2019, 263: 288-298.
[11] 何婷婷, 李志伟, 张馨, 等. 基于图像处理的番茄重量预测[J]. 食品与机械, 2022, 38（10）: 17-23. HE T T, LI Z W, ZHANG X, et al. Tomato weight prediction based on image processing[J]. Food & Machinery, 2022, 38（10）: 17-23.
[12] OMID M, KHOJASTEHNAZHAND M, TABATABAEEFAR A. Estimating volume and mass of citrus fruits by image processing technique[J]. Journal of Food Engineering, 2010, 100（2）: 315-321.
[13] Scikit-learn: Machine learning in Python-scikit-learn 1.1.2 documentation\. （2022-09-26） [2022-10-26]. https://scikit-learn.org/stable/index.html.
[14] FRIEDMAN J H. Greedy function approximation: A gradient boosting machine[J]. The Annals of Statistics, 2001, 29（5）: 1 189-1 232.
[15] 高秀香, 孙曦媚. 统计学原理[M]. 北京: 北京理工大学出版社, 2017: 228-232. GAO X X, SUN X M. Principles of statistics[M]. Beijing: Beijing University of Technology Press, 2017: 228-232.
[16] CALIXTO R R, PINHEIRO NETO L G, CAVALCANTE T D S, et al. A computer vision model development for size and weight estimation of yellow melon in the Brazilian northeast[J]. Scientia Horticulturae, 2019, 256: 108521.