|
|
| BILL5040 | Computer Vision | 3+0+0 | ECTS:7.5 | | Year / Semester | Spring Semester | | Level of Course | Second Cycle | | Status | Elective | | Department | DEPARTMENT of COMPUTER ENGINEERING | | Prerequisites and co-requisites | None | | Mode of Delivery | Face to face | | Contact Hours | 14 weeks - 3 hours of lectures per week | | Lecturer | -- | | Co-Lecturer | | | Language of instruction | | | Professional practise ( internship ) | None | | | | The aim of the course: | | The principal objectives of this course continue to be to provide an introduction to basic concepts and methodologies for computer vision, and to develop a foundation that can be used as the basis for further study and research in this field. |
| Programme Outcomes | CTPO | TOA | | Upon successful completion of the course, the students will be able to : | | | | PO - 1 : | provide an introduction to basic concepts and methodologies for image processing and computer vision, | | | | PO - 2 : | develop a foundation that can be used as the basis for further study and research in this field. | | | | PO - 3 : | achieve simple algorithms for different pattern recognition research | | | | PO - 4 : | create computer vision based approach for different research in other disciplines | | | | CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), PO : Learning Outcome | | |
| Image Pre-processing; Image Segmentation : Clustering-based, Edge-based, Region Growing-Merging-Splitting; Mathematical morpholgy; Textures-Patterns feature extraction; Dimension Reduction (PCA, Kernel PCA, LDA, Kernel Fisher Discriminant Analysis), Image classification and understanding; Convolutional Neural Network for Computer Vision; Discrete Transforms; Vision Geometry and 3D Vision; Interest Points (Corner detection, SIFT); Motion analysis (Optical Flows, Background Estimation). |
| |
| Course Syllabus | | Week | Subject | Related Notes / Files | | Week 1 | Genereal Introduction: Image Pre-processing; | | | Week 2 | Clustering-based Segmentation | | | Week 3 | Edge-based Segmentation, Hough Tansform; | | | Week 4 | Region Growing-Merging-Splitting; Mathematical Morphology | | | Week 5 | Texture-Pattern Feature Extraction: Dimension Reduction: PCA | | | Week 6 | Dimension Reduction Kernel PCA, Kernel Fisher Discriminant Analysis, and Their applications | | | Week 7 | Image classification and understanding | | | Week 8 | Multi-layer Neural Network and Convolutional Neural Network
| | | Week 9 | Project-I Presentataion | | | Week 10 | Deep Learning based Image Segmentation, Object detection and classification | | | Week 11 | Discrete Transforms; DFT, FFT, DCT, Wavelet Transform, Gabor Transform | | | Week 12 | Vision Geometry and 3D Vision | | | Week 13 | Interest Points (Corner detection ? SIFT); Mosaic imaging | | | Week 14 | Motion analysis (Optical Flows, Background Estimation). | | | Week 15 | Project _II Presentation | | | Week 16 | Final Examination | | | |
| 1 | Milan Sonka, Vaclav Hlavac, Roger Boyle, 1999, Image Processing, Analysis, and Machine Vision, Second Edition, PWS Puıblishing, | | | |
| 1 | Rafael C. Gonzales, Richard E. Woods, 1998, Digital Image Processing, Addison-Wesley Publishing Company | | | 2 | Gerhard X. Ritter, Joseph N. Wilson, 2001, Handbook of Computer Vision Algorithms in Image Algebra, CRC Press | | | |
| Method of Assessment | | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | | Laboratory exam | 9
14 | | | | | End-of-term exam | 15 | | 2 | 50 | | |
| Student Work Load and its Distribution | | Type of work | Duration (hours pw) | No of weeks / Number of activity | Hours in total per term | | Yüz yüze eğitim | 3 | 14 | 42 | | Sınıf dışı çalışma | 2 | 14 | 28 | | Proje | 2 | 12 | 24 | | Dönem sonu sınavı için hazırlık | 1 | 14 | 14 | | Dönem sonu sınavı | 2 | 1 | 2 | | Total work load | | | 110 |
|