Course Syllabus

Course Information：

Year-Semester Course Number Course Name Phase Credits Hours Required/Elective Instructor Class Student NO. Withdraw Note

Spring Semester
Year 2024 331831 Image & Signal Recognition 1 3.0 3 ★ Hong-Chuong Tran GME
GMT
IMMA
DME
機電外國學生專班 24 0 機電所、製科所、機械自動化專班和機電博(含外)合開,

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2024	331831	Image & Signal Recognition	1	3.0	3	★	Hong-Chuong Tran	GME GMT IMMA DME 機電外國學生專班	24	0	機電所、製科所、機械自動化專班和機電博(含外)合開,

Course Plan：

Instructor Hong-Chuong Tran　Office Hours

Email hctran@ntut.edu.tw

Last Updated 2023-12-17 13:46:35

Course Objective 本課程介紹當前針對訊號及影像常用之辨識演算法，包括支持向量機、支持向量描述、主成分分析、非線性主成分分析、線性鑑別分析、自回歸模型、共同空間圖形濾波。 Topics include support vector machine (SVM), support vector data description (SVDD), principal component analysis (PCA), nonlinear PCA, linear discriminant analysis (LDA), autoregressive model, and common spatial

Course Schedule Weeks 1-2: Introduction to Image and Signal Processing Overview of image and signal processing Basics of digital image representation Introduction to MATLAB or Python for image and signal processing Weeks 3-4: Image Enhancement Techniques Histogram equalization Spatial domain methods (smoothing, sharpening) Frequency domain methods (Fourier transform) Weeks 5-6: Image Filtering and Convolution Convolution operation Linear and nonlinear filtering Edge detection techniques Weeks 7-8: Image Transformations Image rotation, scaling, and translation Geometric transformations Introduction to wavelet transforms Weeks 9-10: Image Segmentation Thresholding methods Region-based segmentation Clustering algorithms for segmentation Weeks 11-12: Image Feature Extraction Feature extraction techniques Corner detection and Harris corner detector SIFT and SURF feature descriptors Weeks 13-14: Introduction to Signal Recognition Overview of signal recognition Signal processing techniques Feature extraction from signals Weeks 15-16: Pattern Recognition and Classification Introduction to pattern recognition Supervised and unsupervised learning Classification algorithms (e.g., SVM, k-NN) Weeks 17-18: Final Project and Review Application of image and signal recognition techniques in a final project Review of key concepts Preparation for final assessments

Evaluation and grading policy Homework 30% Midterm 30% Final Projects 40%

Materials All right reserved. Do not reproduce without permission.

Foreign-language textbooks:Yes
"Image Processing, Analysis, and Machine Vision" by Milan Sonka, Vaclav Hlavac, and Roger Boyle

The access to curricular consultation If students would like to consult about the course, please contact me via mail email address: hctran@ntut.edu.tw

The course corresponds to the SDGs

Note
　

Instructor	Hong-Chuong Tran　Office Hours
Email	hctran@ntut.edu.tw
Last Updated	2023-12-17 13:46:35
Course Objective	本課程介紹當前針對訊號及影像常用之辨識演算法，包括支持向量機、支持向量描述、主成分分析、非線性主成分分析、線性鑑別分析、自回歸模型、共同空間圖形濾波。 Topics include support vector machine (SVM), support vector data description (SVDD), principal component analysis (PCA), nonlinear PCA, linear discriminant analysis (LDA), autoregressive model, and common spatial
Course Schedule	Weeks 1-2: Introduction to Image and Signal Processing Overview of image and signal processing Basics of digital image representation Introduction to MATLAB or Python for image and signal processing Weeks 3-4: Image Enhancement Techniques Histogram equalization Spatial domain methods (smoothing, sharpening) Frequency domain methods (Fourier transform) Weeks 5-6: Image Filtering and Convolution Convolution operation Linear and nonlinear filtering Edge detection techniques Weeks 7-8: Image Transformations Image rotation, scaling, and translation Geometric transformations Introduction to wavelet transforms Weeks 9-10: Image Segmentation Thresholding methods Region-based segmentation Clustering algorithms for segmentation Weeks 11-12: Image Feature Extraction Feature extraction techniques Corner detection and Harris corner detector SIFT and SURF feature descriptors Weeks 13-14: Introduction to Signal Recognition Overview of signal recognition Signal processing techniques Feature extraction from signals Weeks 15-16: Pattern Recognition and Classification Introduction to pattern recognition Supervised and unsupervised learning Classification algorithms (e.g., SVM, k-NN) Weeks 17-18: Final Project and Review Application of image and signal recognition techniques in a final project Review of key concepts Preparation for final assessments
Evaluation and grading policy	Homework 30% Midterm 30% Final Projects 40%
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:Yes "Image Processing, Analysis, and Machine Vision" by Milan Sonka, Vaclav Hlavac, and Roger Boyle
The access to curricular consultation	If students would like to consult about the course, please contact me via mail email address: hctran@ntut.edu.tw
The course corresponds to the SDGs
Note