Tantárgy adatlapja
The Image Processing and Deep Learning course provides comprehensive knowledge on fundamental image processing techniques combined with modern deep learning methods for visual data analysis. The course covers the theoretical background of image processing, classical computer vision algorithms, and the latest advancements in convolutional neural networks (CNNs), generative models, and robust neural network architectures.
Introduction to Image Processing and Deep Learning
- Image Representation and Basic Transformations
- Filtering and Edge Detection Techniques
- Image Segmentation Methods
- Feature Extraction and Object Detection
- Introduction to Neural Networks for Image Processing
- Convolutional Neural Networks (CNNs)
- Image Classification with CNNs
- Object Detection and Segmentation with Deep Learning
- Generative Models and Image Synthesis
- Robustness and Adversarial Attacks in Image Processing
- Explainability and Interpretability of Deep Learning Models
List of selected literature:
Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1, No. 2). Cambridge: MIT press.
Castleman, K. R. (1979). Digital image processing. Prentice Hall Professional Technical Reference.
Solomon, C., & Breckon, T. (2011). Fundamentals of Digital Image Processing: A practical approach with examples in Matlab. John Wiley & Sons.
List of required and recommended skills:
Algorithm Design and Implementation
- Critical Evaluation of Deep Learning Models
- Data Preprocessing and Augmentation
- Robustness and Ethical Considerations in AI Systems
