ECE5470 Course Syllabus 2019
Location
Lectures: Phillips 203 TR 10:10 am – 11:25 am
Instructor
A. P. Reeves, 392 Rhodes Hall, (255-2342) reeves@cornell.edu
Teaching Assistants
Office Hours: are posted on the course website home page Location: Phillips 314
Prerequisite
The prerequisite for ECE5470 is ECE 2200, or permission of the instructor.
Textbook
Sonka, Hlavac and Boyle, Image Processing, Analysis and Machine Vision, 4th Edition, Cengage Learning, 2014 or 3rd Edition, 2008
Exam Schedule
There will be 2 in class exams,and no Final exam
Prelim 1 | Thursday October 10 | 10:10am – 11:25am |
Prelim 2 | Tuesday December 10 | 10:10am – 11:25am |
Information and Help
The primary information source for ECE5470 is the on-line web at the following URL:
http://www.via.cornell.edu/ece5470
This will provide current information on handouts, reference materials, lecture contents, labs and homework assignments. Furthermore, any corrections or changes will be posted on the web pages. 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 see the instructor in his posted office hours or the TA in her office hours.
If you wish to have a homework or exam regraded then see the instructor, preferably during his office hour or at the end of a class. If you need to see the course instructor and are unable to come during scheduled office hours then request an appointment preferably by phone (255-2342) or by email.
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 | 25% |
Prelim 2 | 25% |
Labs, Homeworks & Projects | 50% |
Exams:
There are two 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 during the first part of the course and 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 may either be conducted on ECE computer facilities or on the student’s personal computer. The final lab may have a project component.
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 as handouts and on the course website. These handouts 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. In the last part of the semester, students will do additional labs on new and emerging ideas including 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 the more experimental 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. The student may gain in-depth understanding of a specific computer vision application through the course mini-project.
Caveat
The schedule and procedures in this course are subject to change as always. The labs in final part of the course are new to this year.
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.
Provisional Course Outline
Topic |
Pages in IPAMV 3rd Edition |
Pages in IPAWC 4th Edition |
1. Introduction | ||
1. Introduction
|
1-10 | 1-9 |
2. Image Sensors and Data Structures
|
11-15, 591-595, | 11-18, 627-631, |
3. Image Display and Digital Images
|
14-24, 41-44 | 14-25, 40-46 |
2. Binary Image Processing | ||
Lab 1. Introduction to VisionX (linux), and Images
|
|
|
4. Binary Image Processing and the VisionX system
|
351-357, 332-335 | 353-360, 333-336 |
5. Medial Axis Transform and Morphological Filtering
|
365-368, 657-666, 106-109 | 365-370, 684-692, 108-112 |
Lab 2. Binary Image Processing
|
|
|
3. Regions |
6. Thresholding and Region Growing
|
24-25, 175-183, 225-233 | 23-24, 179-186, 221-229 |
4. Image Filtering |
|
|
7. The Fourier Transform
|
49-66, 164-166 | 49-65 |
Lab 3. Segmentation: Automatic Image Thresholding
|
29-31 |   |
9. Contrast Enhancement
|
113-118 | 116-120 |
Lab 4. Image Filtering
|
||
10. Image Filtering
|
123-130, 148-152 | 125-132, 148,154 |
5. Edge Detection |
|
|
11. Edge Detection
| 132-142 | 133-146 |
Lab 5. Image Sequence Processing
| ||
12. Image Matching
| 237-240 | 232-237 |
6. Contours |
|
|
Lab 6. 3D Image Analysis
|
|
|
13 Machine Learning and Neural Networks
|
380-402, 404-407 | 385-407,407-412 |
7. Deep Learning |
|
|
14. Convolutional neural networks
|
|
|
Lab 7 Convolutional Neural Networks
|
|
|
8. Object Recognition | 328-332, 335 | 329-332 |
15. Curves, Splines and Polylines
|
341-347 | 343-348 |
16. The Hough Transform
|
212-221 | 210-217 |
17. Color
|
|
|
Lab 8 CNN Deep Learning
|
|
|
18. Segmentation with deep learning
|
|
|