|
課程名稱 |
圖形分析辨認
PATTEN ANALYSIS AND CLASSIFICATION |
|
開課學期 |
95-2 |
|
授課對象 |
電機資訊學院 資訊網路與多媒體研究所 |
|
授課教師 |
洪一平 |
|
課號 |
CSIE5079 |
|
課程識別碼 |
922 U3030 |
|
班次 |
|
|
學分 |
3 |
|
全/半年 |
半年 |
|
必/選修 |
選修 |
|
上課時間 |
星期三2,3,4(9:10~12:10) |
|
上課地點 |
資107 |
|
備註 |
總人數上限：60人 |
|
Ceiba 課程網頁 |
http://ceiba.ntu.edu.tw/952PR |
|
課程簡介影片 |
|
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
|
課程大綱
|
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
|
課程概述 |
The outline of this course is given below.
I. Pattern Recognition Overview
II. Bayesian Decision Theory
III. Supervised Learning Using Parametric Approaches
IV. Supervised Learning Using Non-parametric Approaches
V. Linear Discriminant Functions
VI. Unsupervised Learning and Clustering
VII. Special Topics in PR
|
|
課程目標 |
The goal of this course is to introduce the basic concepts and techniques used
in the field of pattern recognition (PR). Broadly speaking, PR is a science
that concerns the classification (or recognition) of measurements. It has many
important applications, for example, document analysis, face recognition,
fingerprint identification, speech recognition, medical diagnosis, data
mining, and information retrieval. |
|
課程要求 |
|
|
預期每週課後學習時數 |
|
|
Office Hours |
|
|
指定閱讀 |
|
|
參考書目 |
Textbook：R. Duda, P. Hart, D. Stork, `Pattern Classification and Scene Analysis,` second edition, John Wiley and Sons, 2000. |
|
評量方式
(僅供參考) |
|
No. |
項目 |
百分比 |
說明 |
|
1. |
Homeworks |
20% |
|
2. |
Two Exams |
40% |
|
3. |
Term Project |
35% |
|
4. |
In-class Performance |
5% |
|
|
|
週次 |
日期 |
單元主題 |
|
第1週 |
2/28 |
Holiday |
|
第2週 |
3/7 |
Introduction |
|
第3週 |
3/14 |
Chapter 1 Overview |
|
第4週 |
3/21 |
Chapter 2 Bayesian Decision Theory (Section 2.1) |
|
第5週 |
3/28 |
Chapter 2 Bayesian Decision Theory (Sections 2.2 - 2.6) |
|
第6週 |
4/4 |
Chapter 3 Supervised Learning Using Parametric Approach (Section 3.1) |
|
第7週 |
4/11 |
First Midterm |
|
第8週 |
4/18 |
Adaboost |
|
第8週 |
4/18 |
Chapter 3 Supervised Learning Using Parametric Approach (Section 3.2) |
|
第10週 |
4/25 |
Chapter 3 Supervised Learning Using Parametric Approach (Section 3.3.1) |
|
第11週 |
5/2 |
Chapter 3 Supervised Learning Using Parametric Approach (Section 3.3.2) |
|
第12週 |
5/9 |
Chapter 4 Supervised Learning Using Nonparametric Approach |
|
第13週 |
5/16 |
Second Midterm |
|
第14週 |
5/23 |
Chapter 10 Unsupervised Learning and Clustering |
|
第14週 |
5/23 |
Background Modeling |
|
第15週 |
5/30 |
Tracking: Particle Filtering |
|
第15週 |
5/30 |
Tracking: Mean Shift |
|
第15週 |
5/30 |
Chapter 10 Unsupervised Learning and Clustering |
|
第16週 |
6/6 |
Hidden Markov Models (Section 3.10) |
|
第16週 |
6/6 |
Feature Extraction |
|
第16週 |
6/6 |
Skin Color Detection |
|
第17週 |
6/13 |
Term Project Presentation |
|
第18週 |
6/20 |
Term Project Demo and Evaluation |
|