Jiunn-Lin Wu, PhD

1341 Probability (機率)

• Course Time: Mon 09:10-12:00

• Classroom: AT338

• Course Outlines: 

  • 1. Experiments, Models and Probabilities;

  • 2. Sequential Experiments;

  • 3. Discrete Random Variables;

  • 4. Continuous Random Variables.

  • 5. Multiple Random Variables;

  • 6. Probability Models of Derived Random Variables;

  • 7. Conditional Probability Models;

  • 8. Random Vectors;

  • 9. Sums of Random Variables;

  • 10. The Sample Mean;

  • 11. Hypothesis Testing;

  • 12. Estimation of a Random Variable;

  • 13. Stochastic Processes.

• Textbook: Probability and Stochastic Processes: A Friendly Introduction for Electrical and Computer Engineers ", the 3rd Edition, by Roy D. Yates and David J. Goodman   (John Wiley & Sons), 2015.

• Reference Books:  

  • Introduction to Statistical Pattern Recognition, by Keinosuke Fukunaga, 2nd Edition, Academic Press, 1990.

  • Introduction to Probability and Statistics:  for Engineering and the Computing Sciences,   by J. Susan Milton, Jesse C. Arnold, Liu Kwong Ip, the McGraw Hill  Companies.

  • R in ACTION: Data analysis and graphics with R, by  Kabacoff, Robert I., Manning Publications, 2015.

• Lecture Notes: Probability0 

• Grade:

• News:

  • ​9/14​因到台北參加國家新創獎複審停課一次。

  • HW1:  R Programming for Quiz 1.6. Due date: 10/19

  • HW2: Problems: 1.1.2, 1.3.1 and 1.5.7. Due date: 10/19

  • HW3:  R Programming for Quiz 2.4 Due date: 10/26

  • HW4: Problems: 2.1.10, 2.2.10 and 2.2.12 Due date: 10/26

  • ​下周二(10/20)補課，上課教室：應科338。 當天小考，範圍：Chapter 1 and Chapter2.

  • 11/2  0930-1130期中考，教室：應科336 and 338。範圍：Chapter 1, Chapter2 and Chapter3.

  • ​

​​6653&7766 Digital Image Processing (影像處理)

• Course Time: Tue 13:10-16:00 / Mon 18:20-21:00

• Classroom: AT336 / AT338 

• Course Outlines: This course covers fundamental concepts and methods in digital image processing and their applications. The course is outlined as:

  • 1 Introduction

  • 2 Digital Image Fundamentals

  • 3 Intensity Transformations and Spatial Filtering

  • 4 Filtering in the Frequency Domain

  • 5 Image Restoration and Reconstruction

  • 6 Wavelet and Other Image Transforms

  • 7 Color Image Processing

  • 8 Morphological Image Processing

  • 9 Image Segmentation

  • 10 Deep Learning

  • 11 Image Classification and Object Detection with Convolutional Neural Networks.

• Textbook: "Digital Image Processing", by R. C. Gonzalez and R. E. Woods, 4th Edition, Pearson (開發), 2017.

• Reference Books:  "

  • Digital Image Processing Using MATLAB", 2nd Edition, by Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins, 
    McGraw-Hill, 2009.

  • "Artificial Intelligence" by Leonardo Araujo dos Santos. 2018.

  •  "Hands-On Computer Vision with TensorFlow 2", by Benjamin Planche and Eliot Andres, Packt Publishing, 2019.

• Lecture Notes: Chapter0, 關於PPT授課著作權, 

• Grade:  

• News:​

  • ​9/14​影像處理碩專班課程正常上課。

  • HW1: Moiré Patterns and Image Interpolation: Develop a program to investigate Moiré patterns, nearest neighbor interpolation, and bilinear interpolation in digital images. First, generate a high-frequency periodic image, such as parallel lines, a checkerboard pattern, or a sinusoidal pattern. Then, resize the image to different resolutions using both nearest neighbor and bilinear interpolation. Both interpolation algorithms must be implemented entirely from scratch, including coordinate mapping, pixel selection, interpolation calculations, and boundary handling. The use of any built-in image resizing, resampling, or interpolation functions from OpenCV, PIL, SciPy, MATLAB, or any other library is strictly prohibited. Compare the Moiré patterns produced by the two interpolation methods at different image resolutions, and analyze their differences in terms of aliasing, image smoothness, and preservation of high-frequency details. Submit the source code, experimental results, and a brief discussion of your observations. Due date: 10/20.

  • HW2: Geometric Image Transformation and Perspective Correction: Write a program to implement geometric image transformations, including affine transformation or perspective transformation. For perspective correction, select an image containing a tilted rectangular object (e.g., a document, poster, building facade, or table tennis table), manually identify its four corner points, compute the 3 × 3 homography matrix, and rectify the selected region into a front-facing rectangular image. You must implement the transformation matrices, inverse mapping, and bilinear interpolation without using built-in image transformation or interpolation functions. Compare the original and transformed images, and provide a discussion of how different geometric transformations, interpolation, and perspective correction affect image quality, particularly in terms of geometric accuracy, distortion, and interpolation artifacts. Due date: 11/03.

  • Please combine your report (Word file) and source code into a single compressed archive in RAR, 7-Zip, or ZIP format. Name the archive using your student ID. You will submit the file via FTP, and the FTP address and other relevant information will be announced later.

  • FTP information: 主機:140.120.182.55, 連接阜: 1023. 使用者名稱: IP_student_2026, 密碼: student2026

  • 期末考筆試 12/1 for 碩博班, 11/30 for 碩專班。

  • ​期末報告：每人一組。報告時間(含QA 3分鐘)為15-20分鐘。報告論文須為近3年的JCR-SCIE期刊論文或頂級學術會議(CVPR、ICCV 與 ECCV)論文，論文題目與摘要請於11/24前交。