How to determine which object is present in the image.?

Question

I gave the task to create an application in which the image was provided, and I have to determine which object (from the list of destination objects) is present in this image. In one image, only one object is present or the object is absent. the application should be able to identify the object if it is present (any of the listed objects) It would also be sufficient if the application (program) can calculate that the probability that a particular object is present in the image (from the list of objects).

Can anyone suggest how to approach this problem? opencv?

In fact, the task was to identify the logo (of any company, such as coke, pepsi, dell, etc.) from the image (if any of the list of logos is present (which, say, 100))

How can I do this project? please help. !!!!

Answer 1

There are many ways to do this, but the one that I like best is to create a set of functions for each object and then match it in the image.

You can use SIFT to create a vector of key points for each object. Approaching SIFT to each picture, yo will receive a set of descriptors for each image (say, an image, an object, ...).

When you get the image you want to process, use FAST to detect points and cvMatchTemplate () for each different set of descriptors. The one who is most likely to tell you who objected to you. If all the probabilities are too low, then you probably don't have an image in the image.

This is just one approach that I like, but it is quite modern, accurate, fast.

Answer 2

I recommend you googling and read on this subject before trying to do something. You want to perform object recognition or logo recognition. There are already SO questions about this .

Here is the starting point for Opencv

The whole process took me half a minute to search. Perhaps this is what you should start your search for.