Jump to content

Doing PHD in computer vision, with electrical engineering background, advice


mish4

Recommended Posts

Background:

I did my undergrad at a public university in electrical engineering, and at the end of my senior year i took computer vision as an elective. I thought it was a pretty fun area and decided to stay for a masters (in ee department) at the same school (focus on computer vision). Since then i am on my third semester as a grad student finishing up course work and focusing on research next semester. Thus far i have taken all the computer vision courses that were offered and i began doing research this last summer (in computer vision / image processing), although i still haven't done anything too substantial as course work has been a priority.

Desire:

Since i like computer vision and it turns out computer vision is generally in the computer science departments, i am planning to apply to compsci programs for a phd.

Some schools say they recommend the cs gre subject test. I have not taken this, and at the moment my background in areas like operating systems, computer architecture, and advanced programming are lacking or non existent. I am currently taking an algorithms course which has forced me to learn some additional programming and discrete math on my own. Currently i am reading a c++ book on the side, but i dont have a ton of experience with the advanced programming concepts. Thus if i did take the gre cs exam i would probably do poorly. Irregardless i think i could handle computer science topics without too much trouble provided i took a few introductory courses (hopefully these would be sufficient for any candidacy exams i would need to take.)

*note from my experiences so far in computer vision courses i have used a ton of matlab. also i have informally seen stuff like dynamic programming and graph algorithms in the vision courses.

Questions:

a.) How badly will not having cs gre hurt my chances, will the fact that i did ee as undergrad/ms help or hurt my chances?

b.) Should i focus on applying to schools that have at least several people doing research in computer vision?

c.) With all the different labs and professors who do research, how do i go about finding the one i want to work with. Or in particular the one i will mention in the application / statement of purpose. My interests in the area are still somewhat broad (tracking,registration,reconstruction,segmentation..) So choosing person / lab a over person / lab b is hard. Its not like one particular research topic stands out a lot more than others. Should i start reading research papers and seeing if i find that particular problem cool? Is there any reason to send emails to professors, ie asking if they will be looking for phd students?

d.) What are my chances for schools like, cmu, ucla, mit, umaryland, hopkins, usc.

had about a 3.6 for undergrad gpa, about a 3.85 for masters. about 760 math gre, 580 verbal, 4.5 writing.

should have 2 really solid letters (one may have a bigger presence in the computer vision field) Third letter should be good.

Research, i did research this past summer, and have slowly been working on it since (taking courses has slowed me down.) I plan to do most of my research next semester. Sadly this isn't so great for admissions. I haven't published anything most likely because i haven't done anything great yet. Mostly simulations, collecting data, still in progress.

Ive also had several internships, but i dont think admissions would care much.

lastly any general advice would be appreciated, especially from others pursuing computer vision.

Thanks

Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
×
×
  • Create New...

Important Information

This website uses cookies to ensure you get the best experience on our website. See our Privacy Policy and Terms of Use