English 中文(简体)
Resources for Image Recognition
原标题:

I am looking for a recommendation for an introduction to image processing algorithms (face and shape recognition, etc.) and wondered if anyone had an good recommendations, either for books, whitepapers or websites.

I am starting from knowing very little about image recognition and did some maths at University (a long time ago).

Any help or pointers would be greatly appreciated.

问题回答

I found this blog very helpful.

There are quite a lot of topics related to CV that you might want to read up on.

Some of the topics:

  1. Kernels
  2. Blurring
  3. Eigenfaces (face detection)
  4. Connected components
  5. Canny edge detection
  6. Gradients
  7. haar-like features
  8. Histogram Of Gradients
  9. Image segmentation

The two books that are pretty good on this subject are:

  1. Computer Vision: Shapiro
  2. Computer Vision A Modern Approach: Forsyth et al

I used the CV: A modern approach for a CV class I took a semester or two ago. It is fairly concise and includes explanations of how the techniques work. Its not for the faint of heart. Also: Forsyth is a well known author of many CV Papers.

Be aware that Computer Vision is in general very math heavy, so if you feel that your linear algebra skills are not up to date, then update them before attempting to read anything. Knowing your way around some basic signal processing will also be of great help.

For basic shape recognition like lines and circles an edge detector coupled with a simple(?) Hough transform could be enough to do the trick.

If you want to find other stuff that is not faces or basic shapes (cars, people, ...) then you are in for some really heavy reading as this is a quite large area of research with lots of different methods for feature extraction and classification.

If you want to look at faces only, then I suggest finding literature that deals with this specifically to not drown in a sea of math heavy information.

MIT OpenCourseWare has an image recognition course. Unfortunately, there are no video lectures for this course yet, but you ll find lecture notes and other materials.

http://ocw.mit.edu/OcwWeb/Electrical-Engineering-and-Computer-Science/6-801Fall-2004/CourseHome/index.htm

Here is a great book that you can download for free. http://szeliski.org/Book/





相关问题
How to add/merge several Big O s into one

If I have an algorithm which is comprised of (let s say) three sub-algorithms, all with different O() characteristics, e.g.: algorithm A: O(n) algorithm B: O(log(n)) algorithm C: O(n log(n)) How do ...

Grokking Timsort

There s a (relatively) new sort on the block called Timsort. It s been used as Python s list.sort, and is now going to be the new Array.sort in Java 7. There s some documentation and a tiny Wikipedia ...

Manually implementing high performance algorithms in .NET

As a learning experience I recently tried implementing Quicksort with 3 way partitioning in C#. Apart from needing to add an extra range check on the left/right variables before the recursive call, ...

Print possible strings created from a Number

Given a 10 digit Telephone Number, we have to print all possible strings created from that. The mapping of the numbers is the one as exactly on a phone s keypad. i.e. for 1,0-> No Letter for 2->...

Enumerating All Minimal Directed Cycles Of A Directed Graph

I have a directed graph and my problem is to enumerate all the minimal (cycles that cannot be constructed as the union of other cycles) directed cycles of this graph. This is different from what the ...

Quick padding of a string in Delphi

I was trying to speed up a certain routine in an application, and my profiler, AQTime, identified one method in particular as a bottleneck. The method has been with us for years, and is part of a "...

热门标签