Image processing is crucial in advancing various fields, including industry, natural sciences, and entertainment. In the Digital
Media Processing class for second-year undergraduate students, the basics of image processing, such as image data structure,
image capturing methods, various filters, resizing, interpolation, and more, were introduced.
Building upon the Digital Media Processing class, this class will present methods for computers to recognize images. Specifically, this class introduces:
(1) Segmentation, which is a method to cut out regions of interest from an image
(2) Feature extraction, which is a method to convert a part of an image into a format that a computer can recognize
(3) Pattern recognition, which is a method to identify images (or image contents) using the extracted features.
In addition, we briefly introduce image processing using deep learning.
In the last half of this class, programming exercises using Python will be conducted for a deeper comprehension of the methods presented in the class.
Building upon the Digital Media Processing class, this class will present methods for computers to recognize images. Specifically, this class introduces:
(1) Segmentation, which is a method to cut out regions of interest from an image
(2) Feature extraction, which is a method to convert a part of an image into a format that a computer can recognize
(3) Pattern recognition, which is a method to identify images (or image contents) using the extracted features.
In addition, we briefly introduce image processing using deep learning.
In the last half of this class, programming exercises using Python will be conducted for a deeper comprehension of the methods presented in the class.
To learn various methods concerning image processing and image recognition.
To obtain deeper knowledge of the methods presented in the class and programming skills through Python programming exercises.
To obtain deeper knowledge of the methods presented in the class and programming skills through Python programming exercises.
- To be able to explain and implement representative algorithms for image segmentation
- To be able to explain and implement representative algorithms for image feature extraction
- To be able to explain and implement representative algorithms for pattern recognition
| mini exam | programming | Total. | |
|---|---|---|---|
| 1. | 17% | 17% | 34% |
| 2. | 17% | 17% | 34% |
| 3. | 16% | 16% | 32% |
| Total. | 50% | 50% | - |
By mini exams (50%) and assignments (50%).
-- The mini exam will contain basic questions (30~40%), developmental questions (20~30%), and calculation (30~40%) with respect to image processing.
-- Programming assignments contain basic assignments (60%) and developmental assignments (40%) with respect to image processing and image recognition.
If solving all basic questions and programming assignments, it will be evaluated as 60%.
-- The mini exam will contain basic questions (30~40%), developmental questions (20~30%), and calculation (30~40%) with respect to image processing.
-- Programming assignments contain basic assignments (60%) and developmental assignments (40%) with respect to image processing and image recognition.
If solving all basic questions and programming assignments, it will be evaluated as 60%.
| Class schedule | HW assignments (Including preparation and review of the class.) | Amount of Time Required | |
|---|---|---|---|
| 1. | Introduction # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 2. | Feature extraction 1 : template matching, corner detection, edge detection # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 3. | Feature extraction 2 :Difference of Gaussian. SIFT, Hough Transform. # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 4. | Segmentation 1: Introduction to image segmentation, thresholding, region growing, active contours # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 5. | Segmentation 2: graph cut segmentation, morphological operation, m arching cubes Optical flow # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 6. | Pattern recognition 1: Introduction to pattern recognition, support vector machine, random forest, k-nearest neighbors # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 7. | Pattern recognition 2: Neural network, deep learning # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 8. | Pattern recognition 3: PCA, auto encoder # mini exam |
Preparation and review the lecture by using online lecture notes. | 200minutes |
| 9. | Programming exercise (PC room): | solve assignments. | 200minutes |
| 10. | Programming exercise (PC room): | solve assignments. | 200minutes |
| 11. | Programming exercise (PC room): | solve assignments. | 200minutes |
| 12. | Programming exercise (PC room): | solve assignments. | 200minutes |
| 13. | Programming exercise (PC room): | solve assignments. | 200minutes |
| 14. | Programming exercise (PC room): | solve assignments. | 200minutes |
| Total. | - | - | 2800minutes |
| ways of feedback | specific contents about "Other" |
|---|---|
| Feedback in outside of the class (ScombZ, mail, etc.) |
Recommend to make a study plan based on this syllabus and online lecture notes (takashiijiri.com/classes/).
- Friday 10:40-12:30
- contact me with email or slack
- Course that cultivates a basic problem-solving skills
- Course that cultivates an ability for utilizing knowledge
- Course that cultivates a basic self-management skills
| Work experience | Work experience and relevance to the course content if applicable |
|---|---|
| N/A | N/A |
- 4.QUALITY EDUCATION
- 9.INDUSTRY, INNOVATION AND INFRASTRUCTURE
Last modified : Sat Mar 08 04:20:33 JST 2025