ECE5470 Course Syllabus 2022 (tentative)
Location
Lectures: TBA, MW 9:40 am – 10:55 am
Instructor
A. P. Reeves, 392 Rhodes Hall, (255-2342) reeves@cornell.edu
Teaching Assistants
Not yet assigned for 2022
Prerequisite
New for 2022 The prerequisite for ECE5470 is ECE 2720, or permission of the instructor.
Reference Texts
[Recommended, Not Required] Sonka, Hlavac and Boyle, Image Processing, Analysis and Machine Vision, 4th Edition, Cengage Learning, 2014 or 3rd Edition, 2008. (for non-deep learning part of course)
Other on-line material is available for both image analysis and machine leaning
Exam Schedule
There will be 3 in class exams,and no Final exam
| Prelim 1 | Wednesday October 5 | 9:40 – 10:55 |
| Prelim 2 | Wednesday November 2 | 9:40 – 10:55 |
| Prelim 3 | Monday December 5 | 9:40 – 10:55 |
Information and Help
The primary information source for ECE5470 is Canvas. Notes, labs are on the on-line web at the following URL:
http://www.via.cornell.edu/ece5470
This will provide current information on reference materials, lecture contents, labs and homework assignments. Any corrections or changes will be posted on Canvas. Questions about the course may be sent to the instructor or the TA preferably by Piazza or also by email.
For help with the course material connect with the course TAs and instructor through the virtual office hours zoom link.
If you wish to have a homework or exam regraded then first connect with a TA to discuss the issue.
Course Requirements
The final grade for the course will be computed from the following weighted components. There are no absolute thresholds for grades; the grades for the course will be determined from the distribution of grades for the whole class. All work for this course is expected to be original.
| Prelim 1 | 18% |
| Prelim 2 | 18% |
| Prelim 3 | 18% |
| Quizzes | 16% |
| Labs | 30% |
Exams:
There are three in-class exams for this course. Exams cover the material given in both lectures and labs. The second exam will focus on material that is not covered in the first exam.
Homeworks:
Homeworks may be occasionally given based on the lecture material to reinforce the understanding of various course topics.
Labs and Project:
Computer labs assignments generally occur once a week are due after a week. The schedule for the labs is provided on the course website; this schedule may be revised during the semester. Lab assignments are conducted on-line using the ECE computer cloud. The main lab interfaces are jupyter lab and a special on-line viewer for detailed image inspection and annotation. Computer programming is in python although C may alternatively be used for labs involving image analysis.
Missed Deadlines:
Course assignments are due to be submitted to Canvas by 11:59 p.m. on the due date. Late assignments will receive a 10% grade penalty per day late. There are a total of three slip days allowed per semester for lab or homework assignments.
Class Handouts:
In general, slides presented in class will be made available on the course website; and a video recording of the class will be made available on canvas. These slides are not intended to be complete notes and students are responsible for taking notes on information presented in class that is not in the handouts.
Class Attendance:
Students are expected to attend class and to be there at the start of class. Pop-quizzes for credit may be given at any time.
Course Description:
Computer Vision is the construction of explicit meaningful descriptions of physical objects and other observable phenomena from images. Basic techniques for image processing and feature extraction are covered in lectures; topics include: image formation, edge detection, region growing, shape description, and machine learning for computer vision. Higher-level more experimental image analysis techniques, such as video image sequence analysis, are covered by selected presentations.
During the first part of the semester a sequence of computer labs will provide experience in the software tools that are important for computer vision applications and will include the basics of image processing, feature extraction and machine learning. In the last part of the semester, students will do additional labs on convolution neural networks and deep learning.
Essentially, ECE5470 is a first course on learning about how computers can see; that is, interpret the multidimensional signals provided by imaging sensors. Computer vision has a very wide range of applications from medical diagnosis to seeing robots, from particle physics to geological surveying. The objective of this course is to provide students with an understanding of the fundamental methods and an appreciation for the state of the art and the potential of computer vision.
Course Objectives
Students will gain an understanding of the fundamental issues and techniques for extracting information from digital imagery. They will have a good knowledge of well-established methods for decomposing an image into basic elements: edges, regions, and other features. They will also be introduced to convolution neural networks and deep learning higher-level image understanding methods.
Introductory labs provide the student with experience in using computer systems and the associated specialized software tools for processing and extracting information from digital images.
Caveat
The schedule and procedures in this course are subject to change as always.
Academic Integrity
Students expected to abide by the Cornell University Code of Academic Integrity with work submitted for credit representing the student’s own work. Discussion and collaboration on homework and laboratory assignments is permitted and encouraged, but final work should represent the student’s own understanding. Specific examples of this policy implementation will be discussed in class. Course materials posted on the computer vision website are for class use; students are not permitted to buy or sell any course materials without the express permission of the instructor. Such unauthorized behavior will constitute academic misconduct.