基本素養 Basic Literacy

畢業生應具備科技人文素養、資訊工程倫理與終身學習的態度
graduates should equip with the attitude of technological/cultural literacy, information engineering ethics, and life-long learning
畢業生應具備專業外語能力及良好國際觀
graduates should equip with both the professional foreign language proficiency and excellent global view

核心能力 Competence

畢業生應具備資訊專業理論知識
graduates should equip with professional theoretical knowledge in informatics
畢業生應具備資訊專業理論推導、分析、歸納之能力
graduates should equip with the capability of professional theory derivation, analysis, and induction in informatics
畢業生應具備資訊領域獨立發掘問題、策劃實驗、解決問題之能力
graduates should equip with the informatics ability to identify problems independently, to implement experiments, and to solve problems
畢業生應具備資訊領域設計、驗證及實作整合之能力
graduates should equip with the informatics ability in designing, verification, and integrating engineering practices
畢業生應具備資訊領域創新思考之能力
graduates should equip with the informatics capability in innovative planning
畢業生應具備專業簡報及論文撰寫之能力
graduates should equip with the ability in professional presentation and thesis writing
畢業生應具備良好溝通協調與團隊合作之能力
graduates should equip with fair ability in communication, coordination, and team-work collaboration

課程概述 Course Description

這門課除了讓學生能深入了解電腦視覺、機器學習及人工智慧-深度學習的理論知識,與分析深度學習的原理是如何結合人工智慧及電腦視覺發展而來的相互關係外,技術功能面會以授課老師20幾年的產學合作經驗(臉部偵測、辨識及表情分析、雲端智慧型監控服務、自動光學檢測、智慧製造、智慧型機器手臂控制、自走車)及近年來在臨床醫學影像與精準運動分析合作經驗來舉實際的範例解釋。 課程會先教攝影機及鏡頭產生的2D影像與3D物體及增擬實境之間關係的基本電腦視覺原理及技術開始,包括攝影機的校正方法及3D物體重建原理,接著就會傳授電腦視覺基本但實用的技術,包括即時偵測、追蹤及辨識系統的設計。再來藉由機器學習的連接帶入深度學習領域,教授如何藉由深度學習的原理來開發更好的即時偵測、追蹤及辨識技術以解決實際的產業界、臨床醫學影像及精準運動分析上的問題。 本課程期待培養學生於電腦視覺、機器學習及深度學習領域技術設計及整合實作的能力,透過務實的作業實例來培育學生具備研發思考、程式設計及解決現存問題的能力,藉由分組計劃的實作來培養學生具備發現問題、解決問題及團隊分工合作的能力與精神,並可把所學的理論基礎應用到工業界、臨床醫學影像處理及精準運動的實務面。
"Apart from providing students with a deeper understanding of the theoretical knowledge of computer vision, machine learning and artificial intelligence - depth learning, and analyzing how the principles of depth learning combine with the development of artificial neural networks (ANNs) and computer vision, the functional aspects of this course will be explained by teacher’s more than 20 years of experience in industrial cooperation (face detection, recognition and expression analysis, intelligent video surveillance as a service, automated optical inspection (AOI), intelligent manufacturing, visual-guided robot arm control, and automatic guided vehicle (AGV)). The course will teach the basic computer vision principles and techniques for the relationship between 2D images and 3D objects with augmented reality (AR), including the calibration method of the camera and the reconstruction principle of 3D objects. Then I will teach the basic but practical techniques of computer vision, including the design of real-time detection, tracking and recognition systems. We will bring machine learning connections to the field of deep learning. Based on deep learning technology, I will teach you how to develop better real-time detection, tracking and recognition techniques to solve practical problems in the fields of industry, clinical imaging and AI sports. This course aims to develop students' ability to design and integrate skills in computer vision, machine learning and depth learning. Through practical practice, students' ability to think, program design and solve existing problems can be nurtured. Students' ability and spirit of team work can be nurtured through group work. They can also apply the theoretical foundation to industry, clinical imaging and precision sports analytics. "

課程學習目標 Course Objectives

  • 具備基本的電腦視覺、機器學習及深度學習理論基礎;
  • 融匯貫通深度學習的原理是如何結合人工智慧及電腦視覺發展而來的;
  • 具備以電腦視覺及深度學習的技術來解決即時偵測、追蹤、辨識及增擬實境的實際問題。
  • 課程進度 Progress Description

    進度說明 Progress Description
    1Sensor - Camera model: Geometric transformations between 2D and 3D.
    2Sensor - Camera calibration: Optimization process and AR (Augmented reality).
    3Sensor - 3D: 1) Stereo, 2) ToF (Time-Of-Flight, Kinect 2, SoftKinetic), and 12.1, 12.2 3) Structured light (Kinect 1, DLP projector).
    4From AI (artificial intelligence) to ML (machine learning), to DP (deep learning): -From Bayes’ Rule (posterior probability) to Gaussian model, to similarity measure (likelihood probability: Mahalanobis distance, SSD (sum of squared differences) and correlation (or pattern matching)), to PCA (linear combination). -From supervised ˴ unsupervised ˴ semi-supervised learning, to DP - Reinforcement
    5SIFT (and brief HOG): Feature extraction.
    6Background subtraction/modeling: Real-time motion detection using GMM.
    7Optical flow: Real-time motion estimation (or feature tracking) for facial expression extraction.
    8PCA (principal component analysis, dimensionality reduction, domain knowledge): Real-time face detection (eigenfeature), face recognition (eigenface) and facial expression recognition (eigenflow). And LDA (linear discriminant analysis): Linear classification for face recognition.
    9Buffer/Break
    10AdaBoost: Face detection.
    11SVM (support vector machines): Non-linear classification.VQ (vector quantization): Clustering and K-means. And HMM:
    12Deep learning: LeNet and AlexNet
    13Deep learning: VGG16 and GoogLeNet
    14Deep learning: ResNet and RetinaNet
    15Exam
    16Deep learning: Faster R-CNN and Mask R-CNN
    17Deep learning: Generative Adversarial Network
    18Final Project (Group Project) – Deep Learning
     以上每週進度教師可依上課情況做適度調整。The schedule may be subject to change.

    課程是否與永續發展目標相關調查
    Survey of the conntent relevant to SDGs

    本課程與SDGs相關項目如下:
    This course is relevant to these items of SDGs as following:
    • 教育品質 (Quality Education)
    • 就業與經濟成長 (Decent work and Economic growth)
    • 工業、創新與基礎建設 (Industry Innovation and infrastructure)

    有關課程其他調查 Other Surveys of Courses

    1.本課程是否規劃業界教師參與教學或演講? 否
    Is there any industry specialist invited in this course? How many times? No
    2.本課程是否規劃含校外實習(並非參訪)? 否
    Are there any internships involved in the course? How many hours? No
    3.本課程是否可歸認為學術倫理課程? 否
    Is this course recognized as an academic ethics course? In the course how many hours are regarding academic ethics topics? No
    4.本課程是否屬進入社區實踐課程? 否
    Is this course recognized as a Community engagement and Service learning course? Which community will be engaged? No