For years, computer vision and image processing have played a pivotal role in various aspects of Computer Science and Engineering,
driving advancements in areas such as object detection, recognition, 3D reconstruction, medical imaging, autonomous systems,
and augmented reality. Given the growing importance of these fields, acquiring a comprehensive understanding of image processing
and computer vision has become essential.
This course provides an in-depth exploration of key concepts and techniques, including image processing in both spatial and frequency domains, as well as computer vision methodologies such as feature extraction, detection, classification, tracking, and 3D scene reconstruction. Through hands-on exercises and theoretical insights, students will develop a strong foundation that prepares them for cutting-edge research in image and video analysis, computational photography, deep learning-based vision, and real-time image rendering.
This course provides an in-depth exploration of key concepts and techniques, including image processing in both spatial and frequency domains, as well as computer vision methodologies such as feature extraction, detection, classification, tracking, and 3D scene reconstruction. Through hands-on exercises and theoretical insights, students will develop a strong foundation that prepares them for cutting-edge research in image and video analysis, computational photography, deep learning-based vision, and real-time image rendering.
- Students are expected to develop a fundamental understanding of computer vision and image processing, along with their practical
applications in areas such as object recognition, 3D reconstruction, medical imaging, and real-time visual analysis.
- Students are also expected to enhance their ability to design, implement, and evaluate computer vision systems by applying advanced techniques and methodologies. They will develop problem-solving skills to tackle real-world challenges, engage in research and innovation, and effectively communicate their findings to both technical and non-technical audiences.
- Students are also expected to enhance their ability to design, implement, and evaluate computer vision systems by applying advanced techniques and methodologies. They will develop problem-solving skills to tackle real-world challenges, engage in research and innovation, and effectively communicate their findings to both technical and non-technical audiences.
| Goals and objectives | Course Outcomes | |
|---|---|---|
| 1. | The students can explain the fundamentals of image processing & computer vision |
A-1
|
| 2. | Students can explain concepts in image processing and computer vision through various applications, enabling both the development of assignments and the practical solving of real-life problems. |
A-1 ,
E
|
| 3. | Students can develop programming skills, teamwork, and critical thinking while also cultivating a positive attitude by proactively discussing with classmates and the lecturer, attending class on time, submitting assignments punctually, and maintaining academic integrity during exams. |
A-1 ,
E ,
D
|
| Mid-term | Final | Performance During Class | Total. | |
|---|---|---|---|---|
| 1. | 25% | 30% | 55% | |
| 2. | 10% | 10% | 20% | |
| 3. | 0% | 0% | 25% | 25% |
| Total. | 35% | 40% | 25% | - |
| Class schedule | HW assignments (Including preparation and review of the class.) | Amount of Time Required | |
|---|---|---|---|
| 1. | • Introduction to image processing & computer vision • Image Formation (I) - Fundamental of image formation - Geometric formation |
Review what you learnt and do the assignments | 380分 |
| 2. | Image Formation (II): Photometric Formation, Color | Review what you learnt and do the assignments | 380分 |
| 3. | • Early Vision (I): Linear Filters & features | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 4. | • Early Vision (II) : Linear Filters & features (continued) | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 5. | • Early Vision (III) : Processing in frequency domain | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 6. | • Early Vision (IV): Processing in frequency domain (continued) | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 7. | Mid-term examination and discussions on the solutions | Review all previous lessons as the preparation for a writing test (with 10 questions for 120 minutes) | 380分 |
| 8. | • Mid-level Vision (I) : Stereo Imaging (depth estimation, stereo matching, depth from stereo), Structure from Motion | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 9. | • Mid-level Vision (II): Segmentation, Tracking (optical flow, object tracking) | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 10. | • Mid-level Vision (III): Image stitching and mosaicking | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 11. | • High-level Vision (I): Object Detection, Object Recognition | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 12. | • High-level Vision (II): 3D reconstruction I | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 13. | • High-level Vision (II): 3D reconstruction II | In second half of class, student will practice with programming-based implementation so they are required to check the content of the class beforehand. | 380分 |
| 14. | Final exam and discussions on the solutions | Review all learnt lessons and practice for the final exam test (with 10 questions for 120 minutes) | 380分 |
| Total. | - | - | 5320分 |
| A:Fundamental Mechanical Engineering | B:Advanced Mechanical Engineering | C:Environment and Materials Engineering | D:Chemistry and Biotechnology | E:Electrical Engineering and Robotics | G:Advanced Electronic Engineering | F:Information and Communications Engineering | L:Computer Science and Engineering | H:Urban Infrastructure and Environment |
|---|
Grading Criteria:
- Midterm Exam: 35%
- Final Exam: 40%
- Performance during class: 25%
- A total score of more than 60% is required to earn course credit.
<Note>:
- Students will be marked absent if they arrive more than 5 minutes late to class.
- If students arrive late (by less than 5 minutes) twice, it will be counted as one absence
- If a student is absent for more than one-third of the total number of classes, they will not be eligible to receive course credit.
- Any absence will be counted as such unless valid evidence (e.g., a doctor’s note for illness or a similar justified reason) is provided.
- Midterm Exam: 35%
- Final Exam: 40%
- Performance during class: 25%
- A total score of more than 60% is required to earn course credit.
<Note>:
- Students will be marked absent if they arrive more than 5 minutes late to class.
- If students arrive late (by less than 5 minutes) twice, it will be counted as one absence
- If a student is absent for more than one-third of the total number of classes, they will not be eligible to receive course credit.
- Any absence will be counted as such unless valid evidence (e.g., a doctor’s note for illness or a similar justified reason) is provided.
| ways of feedback | specific contents about "Other" |
|---|---|
| Feedback in outside of the class (ScombZ, mail, etc.) | Feedbacks on exams, assignments, etc can be done either in class, via scomb or email. |
1. Digital Image processing 4e, Gonzalez Rafael 2017
2. Computer Vision: Algorithms and Applications 2nd Edition, Richard Szeliski, 2021
3. Multiple view geometry in Computer vision, 2nd edition, Richard Hartley, 2004
2. Computer Vision: Algorithms and Applications 2nd Edition, Richard Szeliski, 2021
3. Multiple view geometry in Computer vision, 2nd edition, Richard Hartley, 2004
- Contact based on the appointments by emailing to professor at: tanpx@shibaura-it.ac.jp
- Course that cultivates an ability for utilizing knowledge
| Work experience | Work experience and relevance to the course content if applicable |
|---|---|
| N/A | N/A |
Last modified : Thu Mar 06 10:07:16 JST 2025