APPLYING MACHINE LEARNING TO IDENTIFY COUNTERFEIT FOODS

Aug 2, 2026

Uploaded by Noah

The article examines food fraud and adulteration arising from low-quality substitution, misleading labeling, and intentional misrepresentation of food, ingredients, or packaging. It focuses on how modern machine learning can automatically recognize and classify product images and text, enabling customers to compare items against trained templates for faster and more accurate counterfeit detection. A real-world scenario evaluates the technical feasibility of the proposed detection architecture and uses the MobileNetV2 model with multiclass classification to distinguish multiple products, supporting consumer protection and state-level control.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Food fraud and adulteration

Machine learning approach for detection

Model and evaluation

MobileNetV2 and multiclass classification

Distinguishing products for risk control

32 Scientific Journal of Astana IT University ISSN (P): 2707-9031 ISSN (E): 2707-904X VOLUME 13, MARCH 2023 DOI: 10.37943/13TFMT6695 Myrzabek Bekzat Kanatuly Master student in Machine Learning and Data Mining [begzat3007@gmail.com](begzat3007@gmail.com), [orcid.org/0000-0002-4410-1140](orcid.org/0000-0002-4410-1140)[ ](orcid.org/0000-0002-4410-1140)Al-Farabi Kazakh National University, Kazakhstan Tyulepberdinova GulnurAlpyskyzy Candidate of Physical and Mathematical Sciences[tyulepberdinova@gmail.com](tyulepberdinova@gmail.com), [orcid.org/0000-0002-4322-8983](orcid.org/0000-0002-4322-8983)[ ](orcid.org/0000-0002-4322-8983)Al-Farabi Kazakh National University, Kazakhstan APPLYING MACHINE LEARNING TO IDENTIFY COUNTERFEIT FOODS Abstract: Currently, the shelves of shops and supermarkets are filled with food that people consume daily, with many products coming from abroad. However, are all these products useful for the human body, and do they meet the standards? In this article, we will talk about how to identify low-quality products using modern machine learning. Recognition and classification of images and text based on machine learning can be a key technology in the fight against lowquality food. Automatic image and text recognition and classification of product information enable end customers to identify counterfeit products accurately and quickly by comparing them to trained templates. However, it is clear that this does not apply to all food processing enterprises. In food production, low-quality and non-standard products are used to reduce the cost of the product. Manufacturers can change their products by replacing higher quality products with lower quality ones. They may use confusing terms on the label to mislead you. When buying and serving counterfeit products, consumers suffer in different ways. First, they may not be getting the nutrients they need, adulterated foods may not be safe for their health, and may also be an economic loss for consumers. We evaluate the technical feasibility of the components of this food fraud detection architecture using a real-world scenario, including machine learning models to distinguish multiple products from each other. It allows you to control the circulation of food products at the state level, thereby protecting the end consumer from purchasing low-quality and potentially dangerous goods. In this article, we used the MobileNetV2 model and multiclass classification and evaluated the model we received from different angles. Keywords: convolution neural network, classification, counterfeit foods, image, and text recognition, MobileNetV2. Introduction Food is made from plant or animal materials that enter the body in raw, processed, or semi-processed forms in order to support a variety of biochemical and physiological activities. In most cases, these products are spoiled or adulterated foods that harm the health of consumers. It includes false or misleading product claims for financial gain and intentional substitution, addition, adulteration, or misrepresentation of food, food ingredients, or food packaging. A specific sort of fraud occurs when actual ingredients are removed, replaced, or fake compounds are added without the buyer’s awareness in order to give the seller a financial advantage. Sometimes these nutrients in many of these outlets may have been prepared Copyright © 2023, Authors. This is an open access article under the Creative Commons CC BY license DOI: 10. 37943/13TFMT6695 © Myrzabek Bekzat, Tyulepberdinova Gulnur 33 using quality ingredients to appeal to and satisfy the palate, rather than providing a complete nutritious meal. These consumers’ health has severely worsened as a result. Researchers, the government, and regulatory authorities have focused their attention on the quality and safety of food, as well as the variables that may affect them, as important growing areas within the food supply chain. Among these various newly deve

FAQs

What problem does the article address in food markets?

It addresses the presence of low-quality and counterfeit food products that may not meet standards due to adulteration, misleading claims, and substitution of ingredients.

How does the proposed method detect counterfeit foods?

It uses machine learning to recognize and classify both images and text from product information, comparing inputs to trained templates to identify counterfeit items quickly and accurately.

Which model and evaluation strategy are used?

The article applies the MobileNetV2 model with multiclass classification and evaluates the resulting model from different angles to distinguish multiple products.

Aug 2, 2026

Uploaded by Noah