CENG 483 Introduction to Computer Vision (Spring 2019)

Instructor:	Gokberk Cinbis
TA:	Ezgi Ekiz
Syllabus:	Please read the syllabus for course details.
Important note:	Monday lecture starts at 9am by default (not 8:40), unless otherwise announced.

Weekly schedule (tenative)

Week	Lectures	Optional readings
	Lecture: Introduction, course logistics
	Lecture: Linear algebra review	NumPy tutorial by Ranjay Krishna.
	Lecture: Color Image formation	Paper is white because it reflects all light, and mirrors reflect all light, so why don't they look the same?
	Lecture: Filtering Edge detection
	Lecture: Interest point detection, corner detection
	Lecture: Scale selection, local descriptors, SIFT
	Lecture: Clustering
	Lecture: Bag of visual words
	Lecture: Introduction to learning-based vision	ML Basics (Deep Learning book by Goodfellow et al.)
	Lecture: Loss functions Midterm: 17 April 2019, 18:00, BMB1.	Linear classification (from CS231n)
	Lecture: Optimization	Optimization-1 (from CS231n) Optimization-2 (from CS231n)
	Lecture: Back-propagation (very briefly) Deep network basics	Neural networks-1 (from CS231n) Neural networks-2 (from CS231n) Neural networks-3 (from CS231n)
	Lecture: Deep network training fundamentals	Case study (from CS231n)
	Lecture: Convolutional neural networks Example ConvNet architectures	ConvNets (from CS231n)
	Monday class only. No class on Friday due to academic calendar. Lecture: Sensing depth: stereo vision, monocular depth cues, structure from motion	Implementing Lucas-Kanade Optical Flow algorithm in Python.

All assignments are announced on ODTUClass.