Take the 2-minute tour ×
Computer Science Stack Exchange is a question and answer site for students, researchers and practitioners of computer science. It's 100% free, no registration required.

I am basically an Electronics and Communication Engineering student. My relevant coursework include Probability Theory and Stochastic Processes, Engineering Mathematics, Signals and Systems, Digital Signal Processing (this semester).

Now, this area Computer Vision - Image Processing - Object recognition - etc caught my eye and I am thinking to study this subject and write a nice research paper in one of the areas later on.

So, could anyone tell me what the differences between Computer Vision and Image Processing are? Say, we consider Object recognition - what are the roles of vision and image processing?

share|improve this question
    
In order to get an answer you should rephrase your question. Nobody can decide for you if you should study vision or image processing. But you could ask for books or introductory material. Or you could ask for differences and similarities on both subjects. –  A.Schulz Nov 30 '12 at 16:33
    
@A.Schulz did that. check now –  gena Nov 30 '12 at 17:02
    
There is a lot of stuff available online ... did you check it? In particular some of the lectures explain that computer vision is a broad area that have many relations with other fields (and Image processing is one of them). See also the two Wikipedia articles. –  Vor Nov 30 '12 at 17:32
    
@Vor I did go through them.. what's interesting is.. Image processing even explains them.. I just don't know where to start –  gena Nov 30 '12 at 17:39
    
@gena: ok, my small suggestion is: start reading a "computer vision" book. It has an extensive introduction that is freely available online. The book has 14 chapters and chapter 3 is "Image processing". –  Vor Nov 30 '12 at 18:06
show 2 more comments

2 Answers

up vote 9 down vote accepted

you can find answer of these in title itself.

image processing- title says that it processes image, means does some transformations on image. that means may be it does some smoothing,sharpening, contrasting,stretching.. on the image for making image more enhancive & readable that is input and output of a process are images.

computer vision -> the ultimate goal is to use computers to emulate human vision, including learning and being able to make inferences and take actions based on visual inputs.

image processing is one part of computer vision.computer vision system uses the image processing algorithms.

the main difference is in goals, not in methods. For example, if the goal is to enhance image for later use , then this may be called image processing. And if the goal is to emulate human vision like object recognition, defect detection or automatic driving, then it is closer to computer vision.

share|improve this answer
add comment

The terms may change from university to university. fe. i had at the uni as computer vision topics both of what Ravindra described as IP and CV.

I would look at the contents/fields rather get stuck at formal definitions. There are 3 main fields in Image Blabla:

- 3d programming (fe. you want the write a program like AutoCad, requirement: strong Linear Algebra and Numerical Analysis knowledge)
- 2d programming (fe. you want to write a program like Photoshop, Unless you want to write a dissertation or fully understand what goes on behind the scenes, you only need basic school math for it. For example i never calculated a Forier Transformation on paper, but i know how to manipulate an image using discrete Fourier Transformation. So here is the keyword for every formulation DISCRETE.)
- Artificial Intelligence (fe. you want to write a software which makes pattern matching between cancer cells and healthy cells. Requirements: strong statistics skills.)

Choose whatever you want.

share|improve this answer
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.