Project Title: AI-Based Smart Waste Management and Classification System
Category: Image Processing
Project File: Download Project File
Anam Naveed
anam.naveed@vu.edu.pk
live:anam13dec
AI-Based Smart Waste Management and Classification System
Project Domain / Category
Artificial intelligence
Abstract:
Waste segregation is a major environmental concern in urban and rural areas. Improper disposal and lack of awareness lead to increased pollution, inefficient recycling, and health hazards. Manual segregation of waste is time-consuming and often inaccurate. This project proposes a Smart Waste Management System that uses Artificial Intelligence and Computer Vision to automatically classify waste into categories such as plastic, glass, organic, and metal using image recognition.
The system will capture/upload images of waste items, identify their type, and suggest appropriate disposal or recycling actions. The system can be deployed on a web interface and automate the classification of waste items using artificial intelligence techniques. It helps to improve the efficiency and accuracy pf waste segregation for concern department. It also helps to encourage the responsible disposal and recycling behavior. The application will provide a scalable solution for homes, schools and public places.
Functional Requirements:
Data set and image requirement (preprocess)
The system shall use a pre-collected or custom-built dataset for training and testing the model.
The model shall be trained offline and integrated into the live application for inference only.
The system shall accept image input from a camera (e.g., webcam)
The system shall allow users to upload waste images from local storage.
The system shall validate that uploaded files are valid image formats.
The system shall automatically resize and pre-process images before classification.’
Classification (AI model)
2.1 The system shall use a trained CNN (Convolutional Neural Network) to classify waste images. The system shall classify waste into one of the following categories:
Organic
Plastic
Glass
Metal
Paper, Other
The system shall display the classification result along with confidence level or probability score.
The system shall provide classification results in real-time (≤ 5 seconds).
The system shall automatically reprocess unclear or low-resolution images and notify the user if input is invalid.
Page 10 of 167
The system shall provide a user-friendly interface for users to upload or capture
images of waste items
The system shall display the classification result (e.g., Organic, Plastic, Glass,
Metal) after image analysis.
The system shall display additional information about how to dispose or recycle
the identified waste type.
The system shall allow users to view a history of previously classified waste items o The system shall provide visual feedback (e.g., color coding or icons) for different
waste categories.
o The system shall prevent users from uploading non-image files. o The system shall not store any user personal data
o The system shall generate appropriate disposal recommendations based on the waste type:
Compost for organic
Recycle bin for plastic, glass, metal
Special disposal for hazardous waste
Admin requirement
The system shall allow admin to add dataset for training model
The system shall allow admin to update the dataset or retrain the model
The system shall allow logging of classification results for performance monitoring. The system shall provide model evaluation reports
Tools:
Core Programming language: python
Web-based UI: HTML/CSS/JS
IDE: PyCharm
Supervisor:
Name: Anam Naveed
Email ID: anam.naveed@vu.edu.pk
MS Teams ID: anam13.vu@outlook.com
No schedules available for this project.
No reviews available for this project.