Suppose I have a set of images that I will use for training. Just as an example take that I have pics of the same car in many different camera angles. I am required to identify the important features like the mirrors, the logo, may be some body features like curves, dents etc. These features have to be extracted from each of the pics (say manually or please suggest a better way) as these will be used for training. The task is I am given an arbitrary image of the same car in some unknown angle and I am to identify as many of the above features as possible. (It feels like an unsupervised learning problem) What procedure/algorithm should I follow? PS: I am new to the field of computer vision.


closed as too broad by David Richerby, Evil, D.W. Oct 2 '16 at 0:02

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ Welcome to CS.SE! I'm afraid this question is too broad. I recommend you start by focusing on a single feature, and try to recognize just that one. Then, what have you tried? What approaches have you considered? What research have you done? There's lots written on object detection; you should start by reviewing the literature on that and see how much progress you can make, before asking here. Also, please see our guidance for the computer vision tag for other suggestions about how to improve your question: cs.stackexchange.com/tags/computer-vision/info. $\endgroup$ – D.W. Oct 2 '16 at 0:02

Browse other questions tagged or ask your own question.