Computer Vision is the study of inferring properties of the world based on one or more digital images.
This course is intended for first year graduate students and advanced undergraduates. We assume students have a rudimentary understanding of linear algebra, calculus, and are able to program in some type of structured language. There will be five to six homework assignments, an exam, and a final project. Grading will be approximately 50% on the homework assignments, 25% on the exam, and 25% on the final project.
|E-mail:||hager at cs dot jhu dot edu|
|Office:||CSEB 121, Homewood Campus|
Grading will be approximately 50% on the homework assignments, 25% on the exam, and 25% on the final project.
Homeworks are due on by midnight on Wednesday, if submitted online and must be turned in by 5pm Wednesday afternoon, if submitted on paper. Late homework is frowned upon. 10% of the possible grade is deducted for each day late. If there is ever a situation which prohibits you from turning in your homework on time, you must alert the Office of Student Affairs because I will check with them to verify the claims.
Above all, you must not misrepresent someone else's work as your own. You can avoid this in two ways:
Naturally, even if you give appropriate credit, you will only receive credit
for your original work, so for this class you should stick with option #1.
All cases of confirmed cheating/plagiarism will be reported to the Student Ethics Board.
Please read the Computer Science Academic Integrity Code.
|One||Introduction||Cameras/Radiometry/Photometric Stereo||Course Syllabus, FP 1,5, 5.4, 6, TV Ch.1,2.1-2.2, SS 6||Notes1 Diary-2001 Diary-2003 Introscript|
|Two||Images and color images, cameras, etc.||Matlab.||TV Ch.3,4.1-4.2, FP 4,7||Notes Diary||hw1.txt matfiles.zip|
|Three||Filtering||Edge operators||TV Ch.4.3,5.1-5.2,5.5 FP 8||Prof. Hager Notes Diary||hw2.txt|
|Four||Edges||Edges||TV Ch.2, FP 8 FP 15.1, 15.5.2||M Dewan Notes M Lowe Paper M Sift Tutorial Extra||hw3.txt|
|Five||Grouping||Grouping/Segmentation||TV Ch.6, FP 2,3||Notes||hw4.txt|
|Seven||Exam 1||Calibration||TV Ch.7 (not 7.3.7,7.4.3), FP 11||Zhang Calibration Paper|
|Eight||Stereo||Stereo||TV 8-8.5.1, FP 10.1.3, 12.3, 12.4||Notes|
|Eleven||Object Recognition||Object Recognition||TV A.8, FP 21.4, 22.1-3, 18||Notes|
|Twelve||Object Recognition||Object Recognition||OR Paper|
|Thirteen||Exam 2||Face Finding||Pose Paper||Notes|
TV - Trucco and Verri, FP - Forsythe and Ponce (weblink), SS - Stockman and Shapiro (weblink)
A PNG is a Portable Network Graphics file. It has been developed, by and large, to replace the GIF format because of legal issues. However, while the GIF stores its data in an 8-bit lookup table, a PNG has the ability to maintain full color information. To save one in a matlab window, click the Export option in the File menu. Then choose Portable Network Graphics Format. Yes, it's that easy!
It is rather simple. First, load up Photoshop. Then ready the scanner: turn on the power, and place your paper inside. Select --> File --> Import --> Twain Acquire. If a dialog box appears indicating that no scanner can be found, and you have checked that the scannar power is on, then you must (1) leave the scanner power on, and (2) reboot the machine. When the machine reboots, launch Photoshop again, and select Twain Acquire. Now, the scanner will be there. Simply scan in the necessary region of your written work from the previewed image; you need not set any parameters, as the scanner is somewhat old and doesn't seem to let you indicate that it will be black and white, etc. Once the image has been scanner, BE SURE TO RESIZE it, down from its 8000x8000 resolution to something a little more usable, like 800x600, etc. Save it as a jpg and package it in with your homework, indicating, in the ASCII text file, what it is meant to accompany.
Do NOT forget to power off the scanner, but leave the computer on.