Vegetable Classification & Detection, a web-based tool, leverages Streamlit, TensorFlow, and OpenCV. It employs CNN and YOLO models to classify and detect vegetables from images and live feeds, benefiting agriculture and food processing with accurate identification & detection tasks.
• TensorFlow:
A powerful open-source machine learning library used for building and training neural network models.
• Streamlit:
A Python library for creating web applications with interactive user interface.
• PIL (Pillow):
Python Imaging Library, used for opening, manipulating, and saving various image file formats.
• Matplotlib:
A plotting library for creating static data visualizations in Python.
• NumPy:
Essential for numerical operations, especially in handling image data arrays.
• TensorFlow Hub:
A repository of pre-trained machine learning models, providing modules and tools for building ML applications.
• YOLO (You Only Look Once)
Real-time object detection: The project utilizes YOLO, enabling the detection of vegetables in live webcam feeds. YOLO's efficient single-stage architecture allows for instant processing of the entire frame, facilitating real-time detection.
Concurrent prediction: YOLO predicts bounding boxes and class probabilities simultaneously across the image, enhancing the speed and accuracy of vegetable detection. This approach aligns with the project's goal of swiftly identifying vegetables for agricultural and food processing purposes.
-
Clone the repository to your local machine.
•
git clone <repository_url>•
cd Vegetable_Classification_And_Detection -
Install the required dependencies.
•
pip install -r requirements.txt -
Run the Streamlit application.
•
streamlit run app.py -
Visit http://localhost:8501 in your web browser to interact with the vegetable classification application.
👉 ©️ Credits goes to the owner of
all images. _Thank You_🤝...