An Efficient Detector for Automatic Tomato Classification Systems

Project Code :TEMBMA3701

Objective

The main objectives of this project are to design an efficient detector for automatic classification of tomatoes based on ripeness, size, and quality. It employs computer vision and deep learning techniques to ensure accurate and real-time sorting. The system aims to streamline post-harvest processing, reduce manual effort, and improve grading consistency in tomato supply chains.

Abstract

This project presents an efficient automatic tomato classification system using Raspberry Pi, a web camera, LCD display, and the YOLOv8 deep learning algorithm. The proposed system is designed to detect and classify tomatoes into four categories: ripe, unripe, old, and damaged. The web camera captures real-time images of tomatoes, and the Raspberry Pi processes the images using the trained YOLOv8 model for accurate identification and classification. The classification results are displayed on an LCD screen, making the system simple and user-friendly for monitoring purposes. The proposed model helps reduce manual sorting effort, improves accuracy, and saves time in agricultural and food processing applications. The system is low-cost, portable, and suitable for smart farming environments. Experimental results show that the system provides fast detection speed and reliable performance under different lighting and environmental conditions.

Keywords: Raspberry Pi, YOLOv8, Tomato Classification, Deep Learning, Image Processing, Smart Agriculture, Web Camera, LCD Display, Object Detection, Ripe Tomato Detection, Damaged Tomato Detection, Automated Sorting System.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.