-1

I would like to know what algorithm is used to obtain an image and get the objects present in the image and process (give information about) it. And also, how is this done?

Zoltan Toth
  • 46,981
  • 12
  • 120
  • 134
Karthik.K
  • 9
  • 1
  • 2
  • 2
    You certainly need to specify your question. The common problem of finding objects in images is far from being solved. Some approaches have already been discussed on SO: http://stackoverflow.com/questions/2074956/logo-recognition-in-images http://stackoverflow.com/questions/2115364/detect-object-in-image-how-they-did-it-i-think-it-is-unbelieveable – Roman Shapovalov Jan 28 '10 at 17:02
  • https://github.com/Orpine/py-R-FCN https://arxiv.org/pdf/1605.06409.pdf – Bharat Dec 30 '16 at 19:22

3 Answers3

1

I agree with Sid Farkus, there is no simple answer to this question.

Maybe you can get started by checking out the Open Computer Vision Library. There is a Wiki page on object detection with links to a How-To and to papers.

You may find other examples and approaches (i.e. algorithms); it's likely that the algorithms differ by application (i.e. depending on what you actually want to detect).

Dieter
  • 1,154
  • 8
  • 7
1

There are many ways to do Object Detection and it still an open problem.

You can start with template matching, It is probably the simplest way to solve, which consists of making a convolution with the known image (IA) on the new image (IB). It is a fairly simple idea because it is like applying a filter on the signal, the filter will generate a maximum point in the image when it finds the object, as shown in the video. But that technique has several cons, does not handle variants in scale or rotation so it has no real application.

Also you can find another option more robust feature matching, which consist on create a dataset with features such as SIFT, SURF or ORB of different objects with this you can train a SVM to recognize objects

You can also check deformable part models. However, The state of the art object detection is based on deep-learning such as Faster R-CNN, Alexnet, which learn the features that will be used to detect/recognize the objects

Cristian Rodriguez
  • 793
  • 5
  • 16
-5

Well this is hardly an answerable question, but for most computer vision applications a good starting point is the Hough Transform

Ron Warholic
  • 9,994
  • 31
  • 47
  • 4
    -1: I disagree that the Hough transform is some kind of fundamental tool. If you are searching for lines or circles specifically, then yes. I would say that most tasks have little or no use of this though. None of the CV projects I've been involved in (or even heard about at the university) involve hough transforms. – Hannes Ovrén Jan 29 '10 at 11:11
  • Agreed with @HannesOvrén Hough transform is not related to object detection. – Cristian Rodriguez Dec 30 '16 at 07:17