0

I have searched a lot to know how can we test an object exist in an image. I am searching for the name of the scientific/ technology that can provide this. As an example I can mention Instagram where you upload an image and Instagram writes: This image may contain sea, people, car. Is this content based image retrieval? Do I need local feature extraction for it? Are they based on deep learning or do they work by something like SIFT?

Whatever I studied was just able to receive a query image and search a database to say that which image is "similar" to that, not which image contains it.

Cris Luengo
  • 55,762
  • 10
  • 62
  • 120
m123
  • 113
  • 6
  • Cross-posted: https://stackoverflow.com/q/62161538/781723, https://cs.stackexchange.com/q/126682/755. Please [do not post the same question on multiple sites](https://meta.stackexchange.com/q/64068). – D.W. Jun 04 '20 at 02:27

2 Answers2

0

Yeah it uses the technique of deep learning where they train their model to recognize number of objects in an image using either bounding box approach or multilabel classification. If a new image is passed to the model, it'll predict label of all the objects present in that image.

Aniket Thomas
  • 343
  • 2
  • 9
  • AHA, Thanks. Could you please tell me in which category of image processing and computer vision it lays? Object recognition? Classification? ...? I want to know the most specific category of it (the most inner subset) – m123 Jun 03 '20 at 17:59
  • @m123 it depends if you also want the location of the object then it lies in the object recognition task. If you only want the name of the objects then that falls under classification task specifically multilabel problem. – Aniket Thomas Jun 03 '20 at 18:10
0

This is known as object detection.

D.W.
  • 3,382
  • 7
  • 44
  • 110