| Learning Outcomes |
Competences |
| Students are able to understand, apply, analyze, and assess conventional and AI methods that are needed to enhance images, automatically analyze image, compress images, and protect copyrights on digital images.
|
|
| Skills |
Knowledge |
Students are able to (all skills on K2 to K5):
- Improve image quality problems that are related to adverse image capture conditions
- Improve image quality using contrast enhancement, smoothing, and sharpening
- Extract relevant entities (edges, corners, regions) from images
- Represent regions using expressive features
- Classify regions in images
- Use suitable neural networks to master the tasks of image recognition, object detection, instance segmentation, and semantic segmentation
- Compress images using suitable JPEG standards
- Protect copyrights on images using digital watermarks
|
- Image restoration in image and frequency domain
- Image enhancement (contrast enhancement, image smoothing, image sharpening)
- Edge and corner detection
- Segmentation of images into regions
- Feature extraction for object representation
- Object classification
- Image recognition using CNNs (Convolutional Neural Networks)
- Object detection and segmentation using R-CNNs (Regions with CNN features)
- Semantic segmentation using FCNs (Fully Convolutional Networks)
- Image compression using JPEG standards
- Copyright protection for images with digital watermarks
|
|
