Freshness Detection of Food Ingredients Using Yolov5

Renate Yosefa, Shinta Estri Wahyuningrum

Abstract


Maintaining the quality and  freshness of food ingredients is vital, especially during storage. The freshness of food ingredients directly affects the health of those who consume them. Therefore, detecting the freshness of food ingredients is important to help prevent health risk. Unfortunately, traditional or manual methods for food freshness detection still lack speed and accuracy because they rely on someone’s subjective judgment and often lead to human error. Using YOLO for food freshness detection helps make the detection process faster and reduces the risk of human error. The model used in this project is YOLOv5, which is known as fast and lightweight versions of YOLO but still delivering a good performance in recognizing the food ingredient freshness levels. The dataset consists of food ingredient images such as plant-based  products (fruits and vegetables) and non-plant-based products.

Keywords


food_freshness;YOLO; YOLOv5; freshness_detection

Full Text:

PDF

References


Anas DF, Jaya I, Herdiyeni Y. Measurement and Analysis of Detecting Fish Freshness Levels Using Deep Learning Method.

Indonesian J Comput Cybern Syst; 18. Epub ahead of print 31 October 2024. DOI: 10.22146/ijccs.95054.

Pan Z, Huang M, Zhu Q, et al. Developing a Portable Fluorescence Imaging Device for Fish Freshness Detection. Sensors 2024;

: 1401.

Wang Y, Wu J, Deng H, et al. Food Image Recognition and Food Safety Detection Method Based on Deep Learning.

Computational Intelligence and Neuroscience 2021; 2021: 1268453.

Wei Z, Chang M, Zhong Y. Fruit Freshness Detection Based on YOLOv8 and SE attention Mechanism. AJST 2023; 6:

–197.

Gillani Fahad L, Fahad Tahir S, Rasheed U, et al. Fruits and Vegetables Freshness Categorization Using Deep Learning.

Computers, Materials & Continua 2022; 71: 5083–5098.

Mukhiddinov M, Muminov A, Cho J. Improved Classification Approach for Fruits and Vegetables Freshness Based on

Deep Learning. Sensors 2022; 22: 8192.

Zhao M, Cui B, Yu Y, et al. Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS.

Sensors 2025; 25: 2664.

Trinh TH, Nguyen HHC. Implementation of YOLOv5 for Real-Time Maturity Detection and Identification of Pineapples.

TS 2023; 40: 1445–1455.

Samaniego LA, Peruda SR, Brucal SGE, et al. Image Processing Model for Classification of Stages of Freshness of Bangus

using YOLOv8 Algorithm. In: 2023 IEEE 12th Global Conference on Consumer Electronics (GCCE). Nara, Japan: IEEE, pp. 401–403.

Cahyono DS, Wahyuningrum SE. ALPHABETS IMAGE IDENTIFICATION USING ADVANCED LOCAL BINARY

PATTERN AND CHAIN CODE ALGORITHM. proxies 2021; 2: 68.

Oksuz K, Cam BC, Kalkan S, et al. Imbalance Problems in Object Detection: A Review. Epub ahead of print 11 March

DOI: 10.48550/arXiv.1909.00169.

Gill MU, Rajendran P. Hyperparameter optimization of YOLO using differential evolution, multi-fidelity optimization, and

Bayesian optimization. Sci Rep. Epub ahead of print 10 April 2026. DOI: 10.1038/s41598-026-47827-6.




DOI: https://doi.org/10.24167/proxies.v10i1.15419

Copyright (c) 2026 Proxies : Jurnal Informatika



View My Stats