Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174100,
        author = {Khushal. R. Bhavsar and Dr. Jyotsna. S. Gawai and Sanchit Shahare},
        title = {SMART WASTE SEGREGATION SYSTEM USING IMAGE PROCESSING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {2772-2778},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174100},
        abstract = {The Smart trash Segregation System Using Image Processing employs computer vision along with deep learning to preprocess trash classification. Traditional trash segregation is time-consuming and inefficient, which often leads to improper disposal and environmental degradation. Convolutional Neural Networks (CNNs) are employed in this system to classify garbage into numerous categories, such as organic waste, paper, plastic, and metal. For determination of the optimum deep learning model, various models were analyzed by using precision, recall, F1-score, and accuracy. MobileNetV2, ResNet50, InceptionV3, EfficientNetB0, and VGG16 models were considered among them. System takes waste photos and sorts them into their corresponding bins automatically by processing them using trained models. The technology increases eco-friendly recycling methods and makes waste management accurate and efficient through the reduction in human intervention. Artificial intelligence incorporation enables garbage to be sorted faster and more accurately, thus minimizing landfill waste and enhancing the utilization of resources. In addition, the system can operate in different environments, such as households and business waste treatment plants, due to real-time image processing. Through solving the increasing issue of waste mismanagement, the implementation of this smart technology assists in establishing cleaner environments. The primary objective of the project is scalability, which ensures that it can be utilized for large-scale waste management in smart cities. The machine learning capability of the system ensures constant improvement in the accuracy of trash identification. The study also explores whether the incorporation of IOT for data processing and remote monitoring is possible. Deep learning minimizes the chances of human sorting errors in trash separation significantly, enhancing operational efficiency. The system can go fully autonomous in the future with robotic integration for self-garbage disposal. The project presents an innovative solution to trash segregation issues by integrating automation, AI, and image processing. The Smart Waste Segregation System is a step toward a more environmentally friendly along with futuristic approach to waste management.},
        keywords = {Smart Waste Segregation, Image Processing, Deep Learning, CNN, Recycling, Automation, Sustainability, Waste Management.},
        month = {March},
        }