2D image processing
- Learning the main algorithms of traditional image processing.
- Thorough understanding of benefits and limitations of traditional image processing.
- Distinguish the main tasks of computer vision and 2d image processing.
- Set-up environment (OpenCV library) for C++/Python development on Windows and Linux/MacOS.
- Display video from web-camera and video files.
- Distinguish image color models.
- Apply point-wise operations for image contrast enhancements.
- Apply image binarization techniques.
- Apply local filters for image smoothing.
- Use FFT (Fast Fourier transform) for image filtering.
- Perform denoising in binary images with mathematical morphology.
- Find correspondent parts in different images.
- Create panoramas with image stitching.
- Detect objects with the Viola-Jones method.
- Solve content-based image retrieval tasks.
- Segment objects in binary images.
- Track object movements in videos.
- Perform image processing operations for video frames.
- Process grayscale and color images.
- Apply object detection, image retrieval and/or image segmentation in practice.
- 2D image processing overview
- Basic operations of 2D image processing
- Local (spatial) image filtering
- Image matching and local descriptors
- Image classification and object detection
- 2D image segmentation and object tracking. Final project
- Weekly Quizzes
- Programming Assignment 2 per course
- Final examTesting assignment Programming assignment
- Interim assessment (2 module)0.4 * Final exam + 0.4 * Programming Assignment 2 per course + 0.2 * Weekly Quizzes
- Prince, S. J. D. (2012). Computer Vision : Models, Learning, and Inference. New York: Cambridge eText. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=458656
- Richard Szeliski. (2010). Computer Vision: Algorithms and Applications. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.C0E46D49