Paper Contents
Abstract
Food adulteration is a major concern in India, especially in staple food items like pulses. Toor dal, being one of the most widely consumed pulses, is often subjected to adulteration with substandard grains, stones, or other pulses, which reduces quality and poses health risks to consumers. Traditional methods of detection are time-consuming, labor-intensive, and prone to human error. To overcome these challenges, automated systems based on image processing and machine learning techniques have been developed for efficient and accurate grain analysis. The proposed Toor Dal Grain Detection system captures images of grain samples and processes them using preprocessing techniques such as noise removal, segmentation, and enhancement. Key features like color, texture, size, and shape are extracted and analyzed using Convolutional Neural Networks or other machine learning algorithms. The system then classifies the grains as pure or adulterated and provides an impurity percentage to ensure quality assessment. A user-friendly interface presents the results in the form of reports or dashboards, enabling real-time decision-making. This automated approach ensures accuracy, speed, and scalability, making it suitable for farmers, food industries, and quality control agencies. By implementing such systems, food safety can be improved, and consumers can be protected from adulterated products.
Copyright
Copyright © 2025 Chaya RM. This is an open access article distributed under the Creative Commons Attribution License.
