Using Deep Learning-Based Features and Image Augmentation to Predict Brix Values of Strawberries for Quality Control

Using Deep Learning-Based Features and Image Augmentation to Predict Brix Values of Strawberries for Quality Control
  IJETT-book-cover           
  
© 2023 by IJETT Journal
Volume-71 Issue-7
Year of Publication : 2023
Author : Ameetha Junaina T. K, R. Kumudham, Ebenezer Abishek. B, Mohamed Shakir
DOI : 10.14445/22315381/IJETT-V71I7P231

How to Cite?

Ameetha Junaina T. K, R. Kumudham, Ebenezer Abishek. B, Mohamed Shakir, "Using Deep Learning-Based Features and Image Augmentation to Predict Brix Values of Strawberries for Quality Control," International Journal of Engineering Trends and Technology, vol. 71, no. 7, pp. 326-342, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I7P231

Abstract
The fields of Computer Vision and Artificial Intelligence are rapidly developing technologies that hold promise for enhancing the economic viability of the Agriculture industry. This is an initiative to help strawberry exporters and growers to choose high-quality strawberries concerning their sweetness by automatically predicting the Brix values from their images. Using a novel dataset of 150 Strawberry images and their corresponding Brix values as labels, a deep learning algorithm called ResNet101 is utilized for feature extraction and different machine learning-based regression models are used for predicting Brix values. The image dataset is generated using a Logitech C920 HD camera, and each sample's instrumental Brix readings are collected using a Brix refractometer. Image augmentation is employed for the dataset enhancement. 70% of the entire dataset is used for training, and the remaining 30% for testing. With a high degree of Brix prediction accuracy, 96.3142%, the squared exponential GPR model is proven to be the best-fit model for this dataset. This method can significantly help provide high-quality control requirements for the strawberry sector. An RMSE value of 0.4772 and a coefficient of determination value of 0.8648 are the obtained performance evaluation metrics values during the prediction phase. Also, the MAE and MSE values obtained are 0.0233 and 0.2277, respectively. These findings show the possibility of combining deep learning with image enhancement to increase the precision of Brix value predictions for strawberries, and they may be a useful tool for enhancing the effectiveness and precision of quality control measures in the fruit business.

Keywords
Automated strawberry brix prediction, Gaussian process regression model, Image data augmentation, Machine learning and deep learning techniques, Resnet101.

References
[1] Iqbal H. Sarker, “Deep Learning, A Comprehensive Overview on Techniques, Taxonomy, Applications, and Research Directions,” SN Computer Science, vol. 2, p. 420, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] TechTarget, Website 2022. [Online]. Available: https://www.techtarget.com/searchenterpriseai/definition/deep-learning-deep-neural-network/
[3] Mrs. T K Ameetha Junaina et al., “A Survey on Fresh Produce Grading Algorithms Using Machine Learning and Image Processing Techniques,” IOP Conference Series, Materials Science and Engineering, vol. 981, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Anjali Chandavale et al., “Automated Systems for Smart Agriculture,” IEEE Pune Section International Conference (PuneCon2019), pp. 1-6, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Zeynep Ünal, “Smart Farming Becomes Even Smarter with Deep Learning—A Bibliographical Analysis”, in IEEE Access, vol. 8, pp. 105587-105609, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Kirtan Jha et al., “A Comprehensive Review on Automation in Agriculture Using Artificial Intelligence,” Artificial Intelligence in Agriculture, vol. 2, pp. 1–12, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[7] M. Sowmiya, and S. Krishnaveni, “Deep Learning Techniques to Detect Crop Disease and Nutrient Deficiency - A Survey," International Conference on System, Computation, Automation, and Networking, pp. 1-5, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Muhammad Hammad Saleem, Johan Potgieter, and Khalid Mahmood Arif, “Automation in Agriculture by Machine and Deep Learning Techniques: A Review of Recent Developments,” Precision Agriculture, vol. 22, pp. 2053-2091, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] A. Subeesh, and C.R. Mehta, “Automation and Digitization of Agriculture using Artificial Intelligence and Internet of Things,” Artificial Intelligence in Agriculture, vol. 5, pp. 278-291, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Mohammad Amin Amani, and Francesco Marinello, “A Deep Learning-Based Model to Reduce Costs and Increase Productivity in the Case of Small Datasets: A Case Study in Cotton Cultivation,” Agriculture, vol. 12, no.2, p. 267, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Alberto Gutierrez-Torre et al, “Automatic Distributed Deep Learning Using Resource-Constrained Edge Devices,” IEEE Internet of Things Journal, vol. 9, no. 16, pp. 15018-15029, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Arteep Kumar et al., “Students' Academic Performance Prediction using Regression: A Case Study,” International Conference on System, Computation, Automation and Networking (ICSCAN), pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Redhat Website, 2022. [Online]. Available: https://www.redhat.com/en/topics/automation/how-predictive-analytics-improve-it-performance/
[14] Xin Jia, “Image Recognition Method based on Deep Learning,” 29th Chinese Control and Decision Conference (CCDC), pp. 4730-4735, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Roberto Luciani, Giovanni Laneve, and Munzer JahJah, “Agricultural Monitoring, an Automatic Procedure for Crop Mapping and Yield Estimation: The Great Rift Valley of Kenya Case,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 7, pp. 2196-2208, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Shubham Prabhu et al., “Soil Analysis and Crop Prediction,” International Journal of Scientific Research in Science and Technology, pp. 117-123, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Dhivya Elavarasan, and P. M. Durairaj Vincent, “Crop Yield Prediction Using Deep Reinforcement Learning Model for Sustainable Agrarian Applications,” IEEE Access, vol. 8, pp. 86886-86901, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Xiaojun Jin, Jun Che, and Yong Chen, “Weed Identification Using Deep Learning and Image Processing in Vegetable Plantation,” IEEE Access, vol. 9, pp. 10940-10950, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Lili Li, Shujuan Zhang, and Bin Wang, “Plant Disease Detection and Classification by Deep Learning—A Review,” IEEE Access, vol. 9, pp. 56683-56698, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Rupesh Gupta et al., “Automatic Identification of Paddy Crop Diseases using Deep Learning Approach,” 3rd International Conference on Electronics and Sustainable Communication Systems, pp. 915-920, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Liu Liu et al., “Deep Learning Based Automatic Multiclass Wild Pest Monitoring Approach Using Hybrid Global and Local Activated Features,” IEEE Transactions on Industrial Informatics, vol. 17, no. 11, pp. 7589-7598, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Arnav Kumar et al., "Fruit-CNN: An Efficient Deep learning-based Fruit Classification and Quality Assessment for Precision Agriculture," 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), Brno, Czech Republic, pp. 60-65, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Anuja Bhargava, and Atul Bansal, “Fruits and Vegetables Quality Evaluation using Computer Vision: A Review,” Journal of King Saud University - Computer and Information Sciences, vol. 33, no. 3, pp. 243-257, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Yanxiang Yang et al., “Deep Reinforcement Learning-Based Irrigation Scheduling,” Transactions of the ASABE, vol. 63, no. 3, pp. 549-556, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Khadijeh Alibabaei et al., “Irrigation Optimization with a Deep Reinforcement Learning Model: Case Study on a Site in Portugal,” Agricultural Water Management, vol. 263, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Pallavi V. Jirapure, and Prarthana A. Deshkar, “Qualitative Data Analysis using Regression Method for Agricultural Data,” World Conference on Futuristic Trends in Research and Innovation for Social Welfare (Startup Conclave), pp. 1-6, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Veera Sellam, and Eswaran Poovammal, “Prediction of Crop Yield using Regression Analysis,” Indian Journal of Science and Technology, vol. 9, no. 38, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Swapna A. Jaywant, Harshpreet Singh, and Khalid Mahmood Arif, “Sensors and Instruments for Brix Measurement: A Review,” Sensor, vol. 22, no. 6, p. 2260, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Bowonsak Srisungsittisunti, “Forward Feature Selection for Ensembles to Predict Brix Values in Mango Fruits based on NIR Spectroscopy Technique,” International Journal of Science, vol. 15, no. 2, pp. 43-57, 2018.
[Google Scholar] [Publisher Link]
[30] Mustafa Ahmed Jalal Al-Sammarraie et al., “Predicting Fruit’s Sweetness Using Artificial Intelligence—Case Study: Orange,” Applied Sciences, vol. 12, no. 16, p. 8233, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[31] TK Ameetha Junaina et al., “Maturity Level Detection of Strawberries-A Deep Color Learning-Based Futuristic Approach,” Futuristic Communication and Network Technologies, Springer, Singapore, vol. 995, pp. 153-163, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[32] The Wikipedia Website, 2023. [Online]. Available: https://en.wikipedia.org/wiki/Brix/
[33] Amazon Website, Brix Refractometer. [Online]. Available: https://www.amazon.in/Refractometer-Hydrometer-Measuring-Saccharimeter-calibration/dp/B0B6DRM1DH/
[34] Matlab Website. [Online]. Available: https://in.mathworks.com/help/matlab/ref/matlab.io.datastore.imagedatastore.html
[35] Matlab. [Online]. Available: https://in.mathworks.com/help/deeplearning/ug/extract-image-features-using-pretrained-network.html
[36] Kaiming He et al., "Deep Residual Learning for Image Recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Matlab Website. [Online]. Available: https://in.mathworks.com/help/deeplearning/ref/resnet101.html
[38] AnalyticsVidya Website. [Online]. Available: https://www.analyticsvidhya.com/blog/2021/10/evaluation-metric-for-regression-models/
[39] Arzu Yazici, Gulgun Yildiz Tiryaki, and Huseyin Ayvaz, “Determination of Pesticide Residual Levels in Strawberry (Fragaria) by Near-Infrared Spectroscopy,” Journal of the Science of Food and Agriculture, vol. 100, no. 5, pp. 1980-1989, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[40] M. Amirthalingam, and R. Ponnusamy, "Intelligent Wireless Endoscopic Image Classification using Gannet Optimization with Deep Learning Model," SSRG International Journal of Electrical and Electronics Engineering, vol. 10, no. 3, pp. 104-113, 2023.
[Google Scholar] [Publisher Link]
[41] Tanachart Sripaurya et al., “Gros Michel Banana Soluble Solids Content Evaluation and Maturity Classification using a Developed Portable 6 Channel NIR Device Measurement,” Measurement, vol. 173, p. 108615, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[42] Manuel Larrain, AndrÉs R. Guesalaga, and Eduardo Agosin, “A Multipurpose Portable Instrument for Determining Ripeness in Wine Grapes using NIR Spectroscopy,” IEEE Transactions on Instrumentation and Measurement, vol. 57, no. 2, pp. 294–302, 2008.
[CrossRef] [Google Scholar] [Publisher Link]
[43] Shyam N. Jha, and T. Matsuoka, “Non-Destructive Determination of Acid–Brix Ratio of Tomato Juice using Near-Infrared Spectroscopy,” International Journal of Food Science & Technology, vol. 39, no. 4, pp. 425–430, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[44] Kim Seng Chia et al., “Pre-Dispersive Near-Infrared Light Sensing in Non-Destructively Classifying the Brix of Intact Pineapples,” Journal of Food Science and Technology volume, vol. 57, pp. 4533–4540, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[45] Manuela Mancini et al., “Application of the Non-Destructive NIR Technique for the Evaluation of Strawberry Fruits Quality Parameters,” Foods, vol. 9, no. 4, p. 441, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[46] R. Dhiman, N. Garg, and M. Gupta, “Quality Characteristics of Strawberry Juice during Storage,” Journal of Food Science and Technology, vol. 50, no. 1, pp. 111–115, 2021.
[47] Hayato Seki et al., “Visualization of Sugar Content Distribution of White Strawberry by Near-Infrared Hyperspectral Imaging,” Foods, vol. 12, no. 5, p. 931, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[48] Wanhyun Cho et al., “Automatic Prediction of Brix and Acidity in Stages of Ripeness of Strawberries Using Image Processing Techniques,” 34th International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC), pp. 1-4, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[49] Rasool Khodabakhshian et al., “A Comparative Study of Reflectance and Transmittance Modes of Vis/NIR Spectroscopy Used in Determining Internal Quality Attributes in Pomegranate Fruits,” Journal of Food Measurement and Characterization, vol. 13, pp. 3130–3139, 2019.
[CrossRef] [Google Scholar] [Publisher Link]