This course is designed to provide an in-depth study of selected areas in computer vision, leading to the ability to understand contemporary terminology, progress, issues, and trends. The interdisciplinary nature of computer vision is emphasized in the wide variety of examples and applications presented with both slide and video materials. We will cover computer vision topics in i) object detection and segmentation, ii) object tracking, iii) object recognition, iv) texture analysis v) scene analysis. Following this course, students will acquire: an understanding of some current research issues in computer vision; the skills and knowledge needed to appreciate papers in the area.
Lectures
1. Course Introduction (update part 1, part 2, part 3). Cameras and Lenses
2. Image Statistics
3. Object description
4. Content-Based Image Retrieval
5. Face Detection and Recognition
6. Texture
7. Medical Applications of Computer Vision
8. Applications in Microscopy
9. Stereo Matching
10. Motion Segmentation
11. How to Write Papers and Give Talks
Assignments
Students will be assigned a paper presentation and a project (implementing and extending the research described in one paper). If you have a proposal for a paper or a particular interest for the project, please discuss it with the professor. Presentations must be sent to remus.brad@ulbsibiu.ro.
Presentation Papers
Fast Automatic Detection of Calcified Coronary
Lesions in 3D Cardiac CT Images (.pdf) - Negrutiu Ana-Maria, Banu Mihai
An automated method for tracking clouds in planetary atmospheres (.pdf) - Cozma Alexandru
Establishing the correspondence between control points in pairs of mammographic images (.pdf) - Vinersar Denisa
Region Growing: A New Approach (.pdf) - Barbu Paul
Objective Grading of Fabric Pilling with Wavelet Texture Analysis (.pdf) - Mihalcea Cosmin-Gabriel
Color and Texture-Based Image Segmentation Using EM
and Its Application to Content-Based Image Retrieval (.pdf) - Modranga Cristina
A Novel Single Pass Thinning Algorithm (.pdf) - Calinescu Cozmin, Manescu Razvan
Snakes, Shapes, and Gradient Vector Flow (.pdf) - Orasan Vladut, Olescu Marco
Modified winner-update search algorithm
for fast block matching (link)
A simple and efficient blockmotion estimation algorithm
based on full-search array architecture (link) - Prundurel Ioan Flavius
Detection of Coronary Artery Stenosis from CT Imaging (link) - Ionescu Raluca
Real-time object detection for "smart" vehicles (.pdf) - Matei Alexandru
Histograms of Oriented Gradients for Human Detection (.pdf) - Fleaca Valentin
Robust Analysis of Feature Spaces: Color Image Segmentation (.pdf) - Bebeselea Nicoleta, Dobrila Petric Victor George
An extensive empirical evaluation of focus measures for digital photography (link) - Pamfiloiu Nicolae, Fleaca Dan-Traian
Active contours and Soft Plaque Detection in Coronary Arteries - Halati Daniel
A Target Model Construction Algorithm for Robust Real-Time Mean-Shift Tracking (link) - Tudorica Paul
Ultrasound Nerve Segmentation - Stoia Paul
History of Neutrosophic Theory and its Applications - Popa M
Pedestrian detection - Talpos Madalina
Fog detection with image processing - Morar Diana
Schedule
Starting from the 7th week, student presentations on assigned papers will take place. The presentations will last for about 30 minutes. The presentation will summarize the papers and include: - Introduction: introduce the problem, expain why it is important to solve it; indicate the method that is proposed to solve it. - Review of previous work; this is an important session; make sure that an appropriate background is given. Review previous/preliminary concepts that are critical for the undestanding of the presented work. If a good background is given, it is easier to explain the details of the method and technical solution later on. - Why the presented method is better than previous work; and/or explain the key contributions of this work; - Technical part: Summary of the technical solution, followed by the details of the technical solution; - Experiments: present here experimental results with plots, graphs, images and visualizations. - Conclusions.
Presentation schedule - each Wednesday from 17:00-20:00 , IE303
