Automated Bell Pepper Quality Assessment: Robotic Gripper Sorting System with Transfer Learning
Article Sidebar
Main Article Content
Abstract
Sorting is an activity during post-harvest that separates fresh produce depending on certain parameters. If this activity is manually done, it is time-consuming and sometimes inconsistent. The marketability of fruits and vegetables often relies on customers’ standards and satisfaction. When these standards are not met, this will result in food wastage in the long run. In this study, the researchers aim to develop a sorting system using three (3) transfer learning algorithms with a robotic gripper application – which has not been majorly explored in previous studies. Moreover, this study also intends to aid bell pepper retailers in preventing food loss due to unsatisfied customer preferences. The process starts with image acquisition for data gathering. The collected data is subjected to data splitting for training and testing. Three pre-trained algorithms were used namely; VGG-16, Resnet50, and GoogleNet. Each of which undergone three train-test splits of; 70-30%, 75-25%, and 80-20% to see their accuracy. VGG-16 obtains an accuracy of 98.38% for both 70-30% and 75-25% train-test split. GoogleNet on the other hand, has the highest accuracy on 80-20% split with 97.84%. ResNet50 has the lowest accuracy having 90.23% for train-test split of 75-25%.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
I. Assanga, “Cell growth curves for different cell lines and their relationship with biological activities,” International Journal of Biotechnology and Molecular Biology Research, Vol. 4 (4), pp. 60–70, 2013. doi: 10.5897/ijbmbr2013.0154
R. Kabir. PERFORMANCE OF BELL PEPPER (Capsicum annuum L.) AT DIFFERENT SPACING UNDER IPIL-IPIL BASED AGROFORESTRY SYSTEM. Mater of Science. Agroforestry and Environment. DINAJPUR University, 2022. doi: 10.13140/RG.2.2.20185.60004
L. M. Anaya-Esparza, Z. V. de la Mora, O. Vázquez-Paulino, F. Ascencio, and A. Villarruel-López. “Bell peppers (Capsicum annum l.) losses and wastes: Source for food and pharmaceutical applications,” Molecules, Vol. 26 (17). p. 5341, 2021. doi: 10.3390/molecules26175341
W. M. Budzianowski. “High-value low-volume bioproducts coupled to bioenergies with potential to enhance business development of sustainable biorefineries,” Renewable and Sustainable Energy Reviews, Vol. 70, pp. 793–804, 2017. doi: 10.1016/j.rser.2016.11.260
A. Cheema et al. “Postharvest hexanal vapor treatment delays ripening and enhances shelf life of greenhouse grown sweet bell pepper (Capsicum annum L.),” Postharvest Biol Technol, Vol. 136, pp. 80–89, 2018, doi: 10.1016/j.postharvbio.2017.10.006
A. Ullah, N. A. Abbasi, M. Shafique, and A. A. Qureshi, “Influence of Edible Coatings on Biochemical Fruit Quality and Storage Life of Bell Pepper cv. ‘Yolo Wonder,’” J Food Qual, vol. 2017, 2017, doi: 10.1155/2017/2142409.
E. M. Yahia, J. M. Fonseca, and L. Kitinoja, “Postharvest losses and waste,” in Postharvest Technology of Perishable Horticultural Commodities, Elsevier, 2019, pp. 43–69. doi: 10.1016/B978-0-12-813276-0.00002-X.
Q. O. Tiamiyu, S. E. Adebayo, and N. Ibrahim. “Recent advances on postharvest technologies of bell pepper: A review,” Heliyon, Vol. 9 (4), p. e15302, 2023. doi: 10.1016/j.heliyon.2023.e15302
A. Tariq et al. “First report of fruit rot of bell pepper caused by Fusarium incarnatum in Pakistan,” Plant Disease, Vol. 102 (12) p. 2645, 2018. doi: 10.1094/PDIS-02-18-0221-PDN
A. Konishi, S. Terabayashi, and A. Itai. “Relationship of cuticle development with water loss and texture of pepper fruit,” Canadian Journal of Plant Science, Vol. 102 (1), pp. 103–111, 2022. doi: 10.1139/cjps-2021-0031.
M. Rasekh, H. Karami, S. Fuentes, M. Kaveh, R. Rusinek, and M. Gancarz. “Preliminary study non-destructive sorting techniques for pepper (Capsicum annuum L.) using odor parameter,” LWT, Vol. 164, p. 113667, 2022. doi: 10.1016/j.lwt.2022.113667
A. Bhargava and A. Bansal. “Fruits and vegetables quality evaluation using computer vision: A review,” Journal of King Saud University - Computer and Information Sciences, Vol. 33 (3), pp. 243–257, 2021. doi: 10.1016/j.jksuci.2018.06.002.
USDA National Nutrient data base. (14 February 2024). Peppers, sweet, red, raw. [Online] Available : https://fdc.nal.usda.gov/fdc-app.html#/food-details/170108/nutrients
V. S. Govindarajan, D. Rajalakshmi, and N. Chand. “Capsicum-production, technology, chemistry, and quality. Part IV. Evaluation of quality,” C R C Critical Reviews in Food Science and Nutrition, Vol. 25 (3), pp. 185–282, 1987. doi: 10.1080/10408398709527453
J. F. I. Nturambirwe and U. L. Opara. “Machine learning applications to non-destructive defect detection in horticultural products,” Biosystems Engineering, Vol. 189, pp. 60–83, 2020. doi: 10.1016/j.biosystemseng.2019.11.011.
M. Soltani Firouz and H. Sardari. “Defect Detection in Fruit and Vegetables by Using Machine Vision Systems and Image Processing,” Food Engineering Reviews, Vol. 14 (3), pp. 353–379, 2022. doi: 10.1007/s12393-022-09307-1
M. A. Rosales, J. A. V. Magsumbol, M. G. B. Palconit, A. B. Culaba, and E. P. Dadios, “Artificial Intelligence: The Technology Adoption and Impact in the Philippines”. IEEE International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM). 3-7 December. Manila, Philippines : pp. 1-6, 2020. doi: 10.1109/HNICEM51456.2020.9400025
J. W. Lee, T. Moon, and J. E. Son. “Development of growth estimation algorithms for hydroponic bell peppers using recurrent neural networks,” Horticulturae, Vol. 7 (9), 2021. doi: 10.3390/horticulturae7090284
M. J. Villaseñor-Aguilar et al. “A maturity estimation of bell pepper (Capsicum annuum L.) by artificial vision system for quality control,” Applied Sciences (Switzerland), Vol. 10 (15), p. 1-18, 2020. doi: 10.3390/app10155097
B. Cemek, A. Ünlükara, A. Kurunç, and E. Küçüktopcu. “Leaf area modeling of bell pepper (Capsicum annuum L.) grown under different stress conditions by soft computing approaches,” Comput Electron Agric, Vol. 174, p. 105514, 2020. doi: 10.1016/j.compag.2020.105514
K. Mohi-Alden, M. Omid, M. Soltani Firouz, and A. Nasiri. “A machine vision-intelligent modelling based technique for in-line bell pepper sorting,” Information Processing in Agriculture, Vol. 10 (4), pp. 491–503, 2023. doi: 10.1016/j.inpa.2022.05.003
A. Moghimi, M. Hosein Aghkhani, M. Reza Golzarian, A. Rohani, and C. Yang, “A Robo-vision Algorithm for Automatic Harvesting of Green Bell Pepper”. ASABE Annual International Meetin.26-29 July. New Orleans, Louisiana : pp. 1-9, 2015. doi:10.13031/aim.20152189355
M. Bhagat, R. Mahmood, M. Kumar, D. Kumar, and B. Pati, “Bell Pepper Leaf Disease Classification Using CNN”. International Conference on Data, Engineering and Applications (IDEA). 28-29 February. Bhopal, India : pp. 1-5, 2020. doi: 10.1109/IDEA49133.2020.9170728
Y. Zhuang et al. “Analysis of Mechanical Characteristics of Stereolithography Soft-Picking Manipulator and Its Application in Grasping Fruits and Vegetables,” Agronomy, Vol. 13 (10), pp. 1-16, 2023. doi: 10.3390/agronomy13102481
B. Wang. (14 February 2024). Scholarship at UWindsor Scholarship at UWindsor Electronic Theses and Dissertations Theses, Dissertations, and Major Papers Design and Development of a Soft Robotic Gripper for Fabric Design and Development of a Soft Robotic Gripper for Fabric Material Handling Material Handling. [Online] Available : https://scholar.uwindsor.ca/etd/8406
J. J. Dela Cruz, J. De Leon, C. A. Bundoc, M. Geroleo, M. L. Lazatin, and M. Rosales, “ARES: An Automated Rotten Egg Sorter Utilizing the Egg’s Physical Properties and Artificial Neural Network”. IEEE International Conference on ICT Convergence. 23-24 August. Melaka, Malaysia : pp. 452–456, 2023. doi: 10.1109/ICoICT58202.2023.10262767
K. Chen et al. “A Soft Gripper Design for Apple Harvesting with Force Feedback and Fruit Slip Detection,” Agriculture (Switzerland), Vol. 12 (11), pp. 2022. doi: 10.3390/agriculture12111802
P. Eizentals, Picking System for Automatic Harvesting of Sweet Pepper Sensing and Mechanism. Doctor of Engineering. Kochi University of Technology, 2016.
C. Ortiz, C. Blanes, P. Gonzalez-Planells, and F. Rovira-Más. “Non-Destructive Evaluation of White-Flesh Dragon Fruit Decay with a Robot,” Horticulturae, Vol. 9 (12), pp. 1-11, 2023. doi: 10.3390/horticulturae9121286
R. G. De Luna et al., “Non-Invasive Transport Tier Classification of Banana ‘Señorita’ (Musa Acuminata) Using Machine Learning Techniques”. IEEE Region 10 Annual International Conference, Proceedings/TENCON. 31 October. Chiang Mai, Thailand : pp. 1040–1045, 2023. doi: 10.1109/TENCON58879.2023.10322463
D. Lorente, N. Aleixos, J. Gómez-Sanchis, S. Cubero, O. L. García-Navarrete, and J. Blasco. “Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment,” Food and Bioprocess Technology, Vol. 5 (4), pp. 1121–1142, 2012. doi: 10.1007/s11947-011-0725-1
X. Li et al. “SSC and pH for sweet assessment and maturity classification of harvested cherry fruit based on NIR hyperspectral imaging technology,” Postharvest Biol Technol, Vol. 143, pp. 112–118, 2018. doi: 10.1016/j.postharvbio.2018.05.003
W. Si, J. Xiong, Y. Huang, X. Jiang, and D. Hu. “Quality Assessment of Fruits and Vegetables Based on Spatially Resolved Spectroscopy: A Review,” Foods, Vol. 11 (9), pp. 1-21, 2022. doi: 10.3390/foods11091198
J. F. Elfferich, D. Dodou, and C. Della Santina. “Soft Robotic Grippers for Crop Handling or Harvesting: A Review,” IEEE Access, Vol. 10, pp. 75428–75443, 2022. doi: 10.1109/ACCESS.2022.3190863
A. Ren et al. “Machine Learning Driven Approach towards the Quality Assessment of Fresh Fruits Using Non-Invasive Sensing,” IEEE Sens J, Vol. 20 (4), pp. 2075-2083, 2020. doi: 10.1109/JSEN.2019.2949528
Y. Suryawanshi, K. PATIL, and P. Chumchu. (14 February 2024). VegNet: Vegetable Dataset with quality (Unripe, Ripe, Old, Dried and Damaged). [Online] Available : https://data.mendeley.com/datasets/6nxnjbn9w6/1 doi: 10.17632/6NXNJBN9W6.1
RAGHAV RPOTDAR and et al. (14 February 2024). Fresh and Stale Images of Fruits and Vegetables. [Online] Available : https://www.kaggle.com/datasets/raghavrpotdar/fresh-and-stale-images-of-fruits-and-vegetables
AqibRehman PirZada. (14 February 2024). Red Capsicum Harvesting Dataset. [Online] Available : https://www.kaggle.com/datasets/aqibrehmanpirzada/red-capsicum-harvesting-dataset
R. G. De Luna, E. P. Dadios, A. A. Bandala, and R. R. P. Vicerra, “Tomato Fruit Image Dataset for Deep Transfer Learning-based Defect Detection”. Proceedings of the IEEE International Conference on Cybernetics and Intelligent Systems and Robotics, Automation and Mechatronics, CIS and RAM. 18-20 November. Bangkok, Thailand : pp. 356–361, 2019. doi: 10.1109/CIS-RAM47153.2019.9095778
M. Swapna, Yogesh Kumar Sharma, B M G Prasadh. “CNN Architectures: Alex Net, Le Net, VGG, Google Net, Res Net,” International Journal of Recent Technology and Engineering (IJRTE), Vol. 8 (6), pp. 953-959, 2020. doi: 10.35940/ijrte.F9532.038620
