Chenliang Xu


Spring 2018 - CSC 249/449: Machine Vision

Basic Information

Time/Place: TR 12:30-13:45 in 473 HUTCH B&L 106

Instructor: Prof. Chenliang Xu
Instructor's Office Hours: Tue 14:15-15:00, 3005 Wegmans

TAs and TAs' office hours:
Yapeng Tian (F 15:00-17:00, 3209 Wegmans),
Jie Chen (Tue 15:00-17:00, 3602 Wegmans).


Fundamentals of computer vision, including image formation, elements of human vision, low-level image processing, and pattern recognition techniques. Advanced topics include modern visual features, graphical models, model-based and data-driven approaches, and contextual inference, as well as illustrative examples of successes and challenges in applications.

Please check pre-requisites on the official course listing page. Some knowledge of linear algebra and basic statistics is helpful but we will review these subjects in the class. For assignments and projects, the most common programming languages are MATLAB and Python. Note that MATLAB provides an image processing toolbox and is available on most CS department undergraduate and research networks. CSC 449, a graduate-level course, has higher expectations / standards than CSC 249, an undergraduate-level course, for completing course project.


This is a tentative schedule of the course and will be populated over the semester.
Course materials will be posted on Blackboard.
Blue: lectures; Yellow: exams/presentations; Grey: no class or cancelled classes; Green: all others.

W Date Topic Supp. Reading Notes
1 1/18 Introduction
2 1/23,25 Camera Models FP 1
3 1/30,2/1 Color, Light and Shading FP 2, 3
4 2/6 MATLAB/Linear Algebra Review HW1 Out
4 2/8 Linear Filtering FP 4
5 2/13 Cancelled
5 2/15 Edges and Corners FP 5
6 2/20,22 SIFT, Segmentation I Lowe'04, FP 9
7 2/27,3/1 Segmentation II, Grouping and Fitting I FP 10, SZ 4.3, 6.1
8 3/6,8 Grouping and Fitting II, Linear Classifier I HW2 Out
9 3/13,15 Spring Recess HW1 Due (Extended)
10 3/20 Midterm Exam
10 3/22 Linear Classifier II GBC 4, 5
11 3/27,29 Convolutional Neural Network I GBC 6, 7 2-Page Proposal Due,
HW3 Out
12 4/3,5 Convolutional Neural Network II GBC 8, 9 HW2 Due
13 4/10 Guest Lec. by Prof. Zhiyao Duan on Audio-Visual
13 4/12 Recurrent Neural Network GBC 10
14 4/17,19 Deep Learning in Computer Vision
15 4/24 Guest Lec. by Prof. Guoyu Lu on 3D Vision
15 4/26 Project Presentation (Group 1)
16 5/1 Project Presentation (Group 2) HW3 Due

Slides for all groups are due by 4/26 10am on Blackboard.
Group 1: A General Intelligence, Treeconstruction, Vision Magicians, Reptile, noisiV enihcaM, Convoluted, Giza, #MeToo College, Cupid's Divination Class, Generative Strike Force, FCN, Object Just Becomes King, GFG, AID, LipsReading.
Group 2: NULL, Firefly, AAB, NB, AppleSlice, CSC449 Team, Terminator, Beauty Killers, Vision-aries, Riverview and Brooks Hall Council, 29-Characters, CV-Architect, On vacation, SBGAN, VisionTorch.

Information Flow

This course primarily uses Blackboard to manage information flow. The course ID is CSC249.2018SPRING.49702. It will be used for announcements, posting lecture notes and assignments, discussions and submitting work. The instructor's course website contains an outline of course schedule, which will be updated over the term, and also serves for the purpose of a syllabus.


Work and Grade

All assignments should be submitted on Blackboard and no late work will be accepted.

Textbook: Although we do not have a mandatory textbook, the following books are recommended.

Code of Conduct: Check here for classroom "etiquette" expectations.

Academic honesty: All assignments and activities associated with this course must be performed in accordance with the University of Rochester's Academic Honesty Policy. More information is available at here. You are expected to read, understand and follow the policy.

Disabilities: If you need an accommodation based on the impact of a disability, please contact me privately during the first two weeks to discuss your specific needs. Alternatively, contact Center for Excellence in Teaching and Learning at 585-275-9049 in room 1-154 Dewey Hall to coordinate reasonable accommodations.