https://github.com/kev-1729/waste_classification
Este proyecto clasifica residuos en diferentes categorías mediante Visión por Computadora y Deep Learning. Utiliza Python, TensorFlow, DenseNet121 y procesamiento de imágenes para mejorar la gestión de residuos y el reciclaje.
https://github.com/kev-1729/waste_classification
deep-learning python tensorflow
Last synced: about 2 months ago
JSON representation
Este proyecto clasifica residuos en diferentes categorías mediante Visión por Computadora y Deep Learning. Utiliza Python, TensorFlow, DenseNet121 y procesamiento de imágenes para mejorar la gestión de residuos y el reciclaje.
- Host: GitHub
- URL: https://github.com/kev-1729/waste_classification
- Owner: Kev-1729
- Created: 2024-08-24T18:51:38.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-03-05T02:01:43.000Z (over 1 year ago)
- Last Synced: 2025-03-05T03:18:11.539Z (over 1 year ago)
- Topics: deep-learning, python, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 3.8 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Organic and Inorganic Waste Classification
This project aims to train an image classification model that distinguishes between organic and inorganic waste using the DenseNet121 architecture. The model classifies waste into six categories: `organic`, `plastic`, `glass`, `metal`, `cardboard`, and `paper`.
## Project Description
The project seeks to automate waste identification using a pre-trained convolutional neural network (DenseNet121) to improve classification accuracy. This system can be integrated into smart recycling platforms or waste management applications, enabling more efficient material separation.
### Key Features:
- **Classification into Six Categories**: The model identifies and classifies waste images into `organic`, `plastic`, `glass`, `metal`, `cardboard`, and `paper`.
- **Customized Training**: The model is trained with an image dataset split into training and testing sets.
- **DenseNet121 Architecture**: Utilizes the DenseNet121 architecture, optimized for image classification.
- **Automation**: Facilitates automatic waste classification, making it useful for recycling and waste management environments.
## Benefits
This software provides several key benefits:
- **Efficiency**: Enhances waste management efficiency by automating the classification process.
- **Accuracy**: Leverages a state-of-the-art neural network to improve the accuracy of waste type identification.
- **Scalability**: The model is adaptable and can be fine-tuned to include new waste categories or improve performance with additional data.
- **Environmental Impact**: By enabling better waste classification, this project can contribute to improved recycling processes and reduced environmental pollution.