The project aims to solve complex challenges in computer vision, using techniques such as image processing, segmentation, deep learning and transfer learning. The focus is on improving the accuracy and efficiency of image analysis, maximizing the use of limited resources and implementing advanced models efficiently.
APPLICATION EXAMPLES:
- In medicine: detecting cancer by analyzing images from medical examinations;
- In agriculture: counting fruit on trees to assess agricultural production;
- In banking institutions: Facial verification for identity authentication in financial transactions.
MANDATORY INFRASTRUCTURE RESOURCES:
- Python: Versatile, high-level programming language;
- TensorFlow: Open source deep learning framework;
- PyTorch: Deep learning framework with a focus on flexibility;
- OpenCV: Open source computer vision library;
- NumPy: Essential library for numerical computation in Python;
- Scikit-learn: Machine learning library in Python;
- GPUs: Graphics processing unit for computational acceleration;
- Clusters: Sets of interconnected computers for parallel processing;
- Cloud: Scalable computing platforms based in the cloud;
- Google Colab Pro Plus: cloud and collaborative development environment;
- Docker: Container technology for deploying applications;
- Git: Repository and version control tool.
