NCHU Course Outline

Course Name	(中) 影像處理與深度學習應用(7003)
	(Eng.) Image Processing and Deep Learning Applications
Offering Dept	Department of Management Information Systems
Course Type	Elective			Credits	3	Teacher	Chung-I Huang
Department	Department of Management Information Systems / Graduate			Language	Chinese	Semester	2026-FALL
Course Description	This course introduces image data representation, classical image processing, machine learning, neural networks, CNNs, RNN/LSTM models, and practical computer vision applications. Students will learn how to process visual data, train models, evaluate results, and present an applied deep learning topic.
Prerequisites

Relevance of Course Objectives and Core Learning Outcomes(%)			Teaching and Assessment Methods for Course Objectives
Course Objectives	Competency Indicators	Ratio(%)	Teaching Methods	Assessment Methods
Understand pixels, color channels, histograms, convolution, filtering, and feature extraction. Build machine learning pipelines for regression, classification, clustering, and decision trees. Implement ANN, CNN, and RNN/LSTM models. Evaluate visual AI systems using proper metrics and error analysis. Complete one topic report on an image processing or deep learning application.			topic Discussion / Production Lecturing	Written Presentation Attendance Oral Presentation Assignment Quiz Internship
Course Content and Homework/Schedule/Tests Schedule
Week Course Content Week 1 Course overview, learning outcomes, image representation, pixels, RGB/gray scale, histograms, convolution, common vision tasks, Python/Colab/OpenCV warm-up. Week 2 AI/ML/DL relationship, data-objective-model-metric-optimization pipeline, supervised learning, linear and nonlinear regression, loss functions, learning rate, gradient descent. Week 3 Underfitting/overfitting, entropy, information gain, regression trees, pruning, clustering vs. classification, density estimation, hierarchical clustering, k-means, PCA visualization. Week 4 Numeric representation, tensors, neural network architecture, hidden layers, activation functions, learning modes, GPU/TPU concepts, MNIST introduction. Week 5 Artificial neurons, bias, sigmoid, ReLU, perceptron, hidden layers, PyTorch/Keras MNIST implementation, epochs, layers, activation functions, dropout. Week 6 DNN depth, parameter explosion in images, CNN locality, weight sharing, convolution, stride, padding, pooling, flattening, LeNet, AlexNet, VGG, CIFAR-10. Week 7 Sequence data, hidden state, one-hot encoding, RNN limitations, vanishing gradient, LSTM gates, lookback windows, wind speed and traffic prediction examples. Week 8 Midterm Exam. Week 9 Bounding boxes, class labels, confidence scores, IoU, mAP, annotation quality, YOLO training workflow, dataset format. Week 10 Semantic segmentation, instance segmentation, masks, Dice score, mIoU, U-Net concept, medical/industrial/remote-sensing examples. Week 11 Pretrained models, feature extraction, fine-tuning, augmentation strategies, train/validation/test leakage, class imbalance. Week 12 Confusion matrix, precision, recall, F1, ROC/AUC, mAP review, overfitting diagnosis, failure-case visualization, reproducibility. Week 13 Frame-based processing, motion cues, object tracking, ID switches, MOTA/IDF1/HOTA concepts, traffic and surveillance applications. Week 14 Vision Transformers, multimodal vision-language models, image restoration, anomaly detection, generative AI applications, ethical and data-source issues. Week 15 Student presentations on selected image processing or deep learning applications, including problem definition, data, model, evaluation, and limitations. Week 16 Final Exam. self-directed learning    02.Viewing multimedia materials related to industry and academia.
Evaluation
Attendance, in-class practice, and homework: 20%; Midterm Exam: 25%; Topic Report: 25%; Final Exam: 30%.
Textbook & other References
Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, 4th ed.; Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning; Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd ed.; François Chollet, Deep Learning with Python, 2nd ed..
Teaching Aids & Teacher's Website
MaterialsInstructor slides, Python notebooks, OpenCV examples, scikit-learn examples, PyTorch/Keras practice code, Google Colab, Kaggle/Roboflow datasets, and selected technical documentation
Office Hours
Thursday, 08:00-11:00.

Please respect the intellectual property rights and use the materials and protected electronic files legally. Please respect gender equality.
Update Date, year/month/day：2026/07/04 16:12:28	Printed Date, year/month/day：2026 / 9 / 20
The second-hand book website：http://www.myub.com.tw/