Introduction to Media Processing

Course title

33002200

	TAKAHASHI Masanobu
	TAKASHIMA Kazuki
	MANO Kazunori

Middle-level Diploma Policy (mDP)

Program / Major	mDP	Goals
IoT Course	DP-4a・2	キャリアを見据えた高度な専門知識情報処理やネットワーキングに関する技術を駆使し、情報社会の基盤となるIoTシステムを開発できる。
Software Course	DP-4b・2	キャリアを見据えた高度な専門知識ソフトウェア開発手法、情報ネットワーク、および機械学習に関する技術を駆使し、社会的ニーズに適切に対応したソフトウェアを開発できる。
Media Course	DP-4c・1	研究者・技術者としての基礎的素養プログラミング技術や機械・深層学習に関する専門知識を習得し、メディア技術の発展・拡張に寄与できる。
Data Science Course	DP-4d・1	研究者・技術者としての基礎的素養データ解析とそれに必要となる機械学習、プログラミング技術の専門知識を習得し、課題解決の鍵となる有効なエビデンスを見いだせる。
Mechatronics Course	DP-4・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Architecture and Architectural Engineering Course	DP-4a・2	キャリアを見据えた高度な専門知識国内外を問わず多様な人々と協働しながら、最新技術とシステム思考、柔軟な発想力でこれからの社会に必要とされる空間（建築）を創出できる。
Environmental Systems and Urban Planning Course	DP-4b・2	キャリアを見据えた高度な専門知識国内外を問わず多様な人々と協働しながら、持続可能なまちづくりに必要な環境システム、対策、政策、ビジネス等を提案し、社会実装に寄与できる。
Bioscience Course	DP-4a・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Biomedical Engineering Course	DP-4b・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Sports Engineering Course	DP-4c・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。
Mathematical Sciences Course	DP-4・2	キャリアを見据えた高度な専門知識現象の背後にある数理構造やデータのパターンを理論的に解析し、社会や自然科学、工学における複雑な課題に対して数理的視点から解決戦略を提案できる。
Mathematical Sciences Course	DP-4・3	専門分野と他分野を関連付ける素養主軸となる分野の専門知識を他分野と関連付ける分野横断型の知識と行動力を修得し、社会で活用できる。

Purpose of class

Students will understand the definitions of fundamental terms in image and speech/audio/acoustic processing, as well as gain a correct understanding of basic methodologies.

Course description

Media information, such as images and speech/audio/acoustics, serves as a vital source of information for humans, and the technologies used to handle them are essential for advancement in various fields. The goal of this course is to acquire fundamental knowledge, including basic methodologies and terminology, for processing these types of media.

For the image processing parts, lectures will cover digitization, color, grayscale transformation, filtering, image analysis, I/O devices, and file formats. Regarding speech, audio and acoustics, we will explore the nature of sound, its physical properties, the mechanism of hearing, recording and playback, speech production and recognition, and sound-based services.

As the textbook for the first half of the course is designed for certification exams, students are strongly encouraged to aim for "画像処理エンジニア検定".

Goals and objectives

Students will be able to correctly understand and explain the definitions of fundamental terms related to images.
Students will be able to correctly understand and explain the fundamental methodologies of image processing.
Students will be able to correctly understand and explain the definitions of fundamental terms related to speech, audio, and acoustics.
Students will be able to correctly understand and explain the fundamental methodologies of speech, audio, and acoustics processing.

Relationship between 'Goals and Objectives' and 'Course Outcomes'

	1st half review test	2nd half review test	Total.
1.	25%		25%
2.	25%		25%
3.		25%	25%
4.		25%	25%
Total.	50%	50%	-

Evaluation method and criteria

Evaluation of this class is based on the review tests and the quality of participation during Q&A sessions. Students who demonstrate a general understanding of fundamental terminologies and methodologies will receive a score of approximately 80%. Additionally, passing "画像処理エンジニア検定（CG-ARTS協会）" will be taken into account for the first-half grade. Further details will be provided during the first lecture.

Language

Japanese

Class schedule

	Class schedule	HW assignments (Including preparation and review of the class.)	Amount of Time Required
1.	Guidance, Perception and colors	Prepare for the text 1-4, 1-5.	90minutes
1.	Guidance, Perception and colors	Review of the class.	100minutes
2.	Digital camera model	Prepare for the text 1-3-2, 1-3-3, 1-6-1, 5-1, 5-2.	90minutes
2.	Digital camera model	Review of the class.	100minutes
3.	Grayscale transformation and filtering	Prepare for the text 5-3, 5-4, 6-1.	90minutes
3.	Grayscale transformation and filtering	Review of the class.	100minutes
4.	Image analysis	Prepare for the text 6-1, 6-2, 6-3, 7-3.	90minutes
4.	Image analysis	Review of the class.	100minutes
5.	Detection and recognition of patterns and features.	Prepare for the text 7-4, 7-5, 9-5.	90minutes
5.	Detection and recognition of patterns and features.	Review of the class.	100minutes
6.	Visual information processing systems	Prepare for the text 9-5, 9-6.	90minutes
6.	Visual information processing systems	Review of the class.	100minutes
7.	1st half review test and comments	Prepare for the test.	190minutes
8.	What is sound? Physical properties of sound (time and frequency)	Review of materials and assignments	190minutes
9.	Mechanisms of hearing	Review of materials and assignments	190minutes
10.	Sound recording and reproduction	Review of materials and assignments	190minutes
11.	Speech production and recognition	Review of materials and assignments	190minutes
12.	Audio and acoustics	Review of materials and assignments	190minutes
13.	Environmental sounds and audio-based applications	Review of materials and assignments	190minutes
14.	2nd half review test and comments	Prepare for the test.	190minutes
Total.	-	-	2660minutes

Feedback on exams, assignments, etc.

ways of feedback	specific contents about "Other"
Feedback in the class

Textbooks and reference materials

1st half classes: text "ビジュアル情報処理−ＣＧ・画像処理入門−（CG-ARTS協会）" is used.
2nd half classes: no texts. class materials are provided.

Prerequisites

None. Please study the introduction to C or Python programming languages.

Office hours and How to contact professors for questions

Friday lunch time. Other requests welcome, time permitting.

Regionally-oriented

Non-regionally-oriented course

Development of social and professional independence

Course that cultivates an ability for utilizing knowledge
Course that cultivates a basic problem-solving skills

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
Applicable	Leveraging Professors' experiences in the research and development of image and speech processing and recognition systems in companies, they will teach methodologies and terminology by linking them to systems and techniques currently used in industry.

Education related SDGs:the Sustainable Development Goals

4.QUALITY EDUCATION
8.DECENT WORK AND ECONOMIC GROWTH
9.INDUSTRY, INNOVATION AND INFRASTRUCTURE
12.RESPONSIBLE CONSUMPTION & PRODUCTION

Last modified : Mon Mar 16 04:02:30 JST 2026