Course title
1M9932101
Advanced image sensing

 MAEDA Yoshihiro
Course content
Images are an essential medium utilized in daily life and various fields, containing a wealth of information. In this class, students will learn the fundamentals of image processing and pattern recognition, which serve as the foundation for image sensing—a technique for extracting useful information from images.
Purpose of class
The objective of this class is to acquire knowledge of image processing and pattern recognition, which form the foundation of image sensing. Additionally, students will aim to develop practical skills in image processing and pattern recognition techniques using Python.
Goals and objectives
  1. Students can explain the fundamental techniques of image processing.
  2. Students can explain the fundamental techniques of pattern recognition.
  3. Students can explain the fundamental techniques of deep learning.
Relationship between 'Goals and Objectives' and 'Course Outcomes'

 レポート1 レポート2 レポート3 Total.
1. 40% 40%
2. 30% 5% 35%
3. 25% 25%
Total. 40% 30% 30% -
Language
Japanese
Class schedule

 Class schedule HW assignments (Including preparation and review of the class.) Amount of Time Required
1． Image Processing (1)
Camera Models and Imaging, Image Formats 		Investigation of Camera Models, Imaging, and Image Formats. 60minutes
2． Image Processing (2)
Image Statistics, Color Spaces, Geometric Transformations 		Investigation of Image Statistics, Color Spaces, and Geometric Transformations. 60minutes
3． Image Processing (3)
Upsampling & Downsampling, Spatial Filtering 		Investigation of Upsampling & Downsampling, and Spatial Filtering. 180minutes
4． Image Processing (4)
Frequency Transformation and Frequency Filtering 		Investigation on Frequency Transformation and Frequency Filtering. 180minutes
5． Image Processing (5)
Edge-Preserving Smoothing Filters 		Investigation on Edge-Preserving Smoothing Filters 180minutes
6． Image Processing (6)
Exercise 1 (1): Upsampling, Downsampling, and Filtering Exercises 		Investigation on Upsampling, Downsampling, and Filtering. 60minutes
Preparing a Report 300minutes
7． Image Processing (7)
Exercise 1 (2): Upsampling, Downsampling, and Filtering Exercises 		Preparing a Report 300minutes
8． Pattern Recognition (1)
Feature Extraction, Clustering: Unsupervised Learning 		Investigation on Feature Extraction and K-Means Clustering. 60minutes
9． Pattern Recognition (2)
Clustering: Supervised Learning 		Investigation of Support Vector Machines (SVM) 180minutes
10． Pattern Recognition (3)
Exercise 2: Feature Extraction and Clustering 		Investigation on Feature Extraction and Clustering. 60minutes
Preparing a Report 300minutes
11． Pattern Recognition (4)
Deep Learning (1): Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN) 		Investigation on Multi-Layer Perceptron (MLP) and Convolutional Neural Network (CNN). 60minutes
12． Pattern Recognition (5)
Deep Learning (2): Deep Neural Networks(DNN) 		Investigation on Deep Neural Networks(DNN). 60minutes
13． Pattern Recognition (6)
Exercise 3 (1): Deep Learning Exercises 		Investigation on Deep Learning. 60minutes
Preparing a Report 300minutes
14． Pattern Recognition (7)
Exercise 3 (2): Deep Learning Exercises 		Preparing a Report 300minutes
Total. - - 2700minutes
Evaluation method and criteria
Evaluation Method
Evaluation will be based on reports from three exercises.
The distribution of scores and the passing criteria are as follows:
Report 1: 40 points, Report 2: 30 points, Report 3: 30 points
Total: 100 points (Passing score: 60 points or higher)

Evaluation Criteria
A score of 60 points will be given to students who demonstrate a basic ability to explain fundamental techniques in image processing and pattern recognition.
Feedback on exams, assignments, etc.
ways of feedback specific contents about "Other"
Feedback in the class
Textbooks and reference materials
Provide guidance as necessary.
Prerequisites
Possess basic knowledge of signal processing and be able to use Python.
Office hours and How to contact professors for questions
  • Questions will be accepted during the break after class and on Wednesdays from 14:00 to 15:00 in room 10M30. It is recommended to contact in advance.
Regionally-oriented
Non-regionally-oriented course
Development of social and professional independence
  • Course that cultivates an ability for utilizing knowledge
Active-learning course
More than one class is interactive
Course by professor with work experience
Work experience Work experience and relevance to the course content if applicable
N/A 該当しない
Education related SDGs:the Sustainable Development Goals
  • 9.INDUSTRY, INNOVATION AND INFRASTRUCTURE
Last modified : Wed Feb 26 18:15:47 JST 2025