Authors : Channabasavanna B G

Volume/Issue : Volume 10 - 2025, Issue 5 - May

Google Scholar : https://tinyurl.com/mryrur7f

DOI : https://doi.org/10.38124/ijisrt/25may1153

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : In the wake of increasing health awareness and food safety demands, accurately determining the freshness and nutritional value of fruits remains a persistent challenge. Traditional inspection methods are either subjective or require costly instruments, making them inaccessible to everyday consumers. This paper presents SmartSnacks, an innovative, AI- driven system that leverages computer vision and deep learning to assess fruit freshness and estimate nutritional quality using just an image captured via a smartphone. The system employs a Convolutional Neural Network (CNN) to classify fruits into various freshness categories and detect spoilage indicators. It then cross-references scientific nutritional databases to estimate nutrient degradation based on freshness levels. SmartSnacks offers real-time, user-friendly insights that support healthier eating habits, reduce food waste, and promote transparency in food quality. Designed for accessibility and scalability, this system holds significant potential for consumers, retailers, dietitians, and agriculture stakeholders alike.

Keywords : SmartSnacks, Fruit Freshness, Nutritional Quality, AI in Food, Artificial Intelligence, Deep Learning, Machine Learning, Food Analysis, Fruit Quality, Nutrition Detection, Computer Vision, Fruit Recognition, Food Spoilage, Food Safety, AI Detection System, Freshness Detection, Food Tech, Healthy Eating, CNN Model, Convolutional Neural Network, Image Classification, Object Detection, Feature Extraction, Training Dataset, Data Augmentation, Labeling, Model Training, Model Evaluation, AI Modeling, Image Preprocessing.

References :

1. H. D. Nguyen, D. T. Nguyen, and H. D. Nguyen, “Fruit classification using computer vision and deep learning,” IEEE Access, vol. 8, pp. 20267–20275, 2020. doi: 10.1109/ACCESS.2020.2969384
2. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, Apr. 2018. doi: 10.1016/j.compag.2018.02.016
3. M. S. Rehman, S. Mahmud, and N. Ehsan, “Automated fruit grading system using machine learning,” in Proc. Int. Conf. Robotics and Emerging Allied Technologies in Engineering (iCREATE), Islamabad, 2016, pp. 122–126. doi: 10.1109/iCREATE.2016.7850023
4. U.S. Department of Agriculture, “FoodData Central,” USDA Agricultural Research Service, 2023. [Online]. Available: https://fdc.nal.usda.gov/
5. T. Withanage, A. Jayarathna, and S. Weerakoon, “Smart fruit quality identification system using image processing and machine learning,” in Proc. 2020 Int. Conf. on Intelligent Computing (ICIC), pp. 1–6. doi: 10.1109/ICIC50835.2020.9289749
6. V. Singh, A. Misra, and S. Goel, “Detection of fruit ripeness using deep learning techniques,” in Proc. 2021 Int. Conf. on Computing, Communication, and Intelligent Systems (ICCCIS), pp. 401–406. doi: 10.1109/ICCCIS51004.2021.9397120
7. H. P. Nguyen et al., “A computer vision-based real-time fruit recognition and classification system,” Sustainable Computing: Informatics and Systems, vol. 30, pp. 100512, Sept. 2021. doi: 10.1016/j.suscom.2021.100512
8. S. Chhikara et al., “Nutritional quality evaluation of fruits and vegetables using machine learning: A review,” Journal of Food Science and Technology, vol. 60, pp. 452–464, 2023. doi: 10.1007/s13197-022-05554-0