This project aims to detect Parkinson's disease using a computer vision approach. It leverages transfer learning with a pre-trained Inception V4 model for feature extraction and employs K-Nearest Neighbors (KNN) for classification. The primary goal is to classify individuals as either healthy or affected by Parkinson's disease based on visual data.
Parkinson's disease affects millions worldwide. Early detection is crucial for effective management and treatment. This project applies advanced AI techniques to assist in accurate and early diagnosis.
- Transfer Learning: Utilized Inception V4 for efficient feature extraction.
- Classification: Implemented KNN to classify individuals into healthy or affected categories.
- Technologies: Python, TensorFlow, PyTorch.
- Programming Languages: Python
- Libraries/Frameworks: TensorFlow, PyTorch, NumPy, Scikit-learn
- Model: Inception V4 (pre-trained)
Accuracy: (to be updated with results).
- Explore alternative classification techniques.
- Expand the dataset for better generalization.
This project is licensed under the MIT License - see the LICENSE file for details.