0

I am studying SIFT (Scale-invariant feature transform) and HOG (Histogram of Oriented Gradient). So I want to know the advantages of SIFT over HOG in case when we have to extract features from a sequence of frames of an activity (i.e. standing). Until now what i have understood:
1) In SIFT gaussian smoothing is applied in order to compute the DOG (difference of gaussian). Then performing Scale Extrema Detection you will detect the feature points. Once you have this feature points you will need to compute the HOG for each feature. Since it takes a 16x16 neighbourhood the result will be a 128 length descriptor. Whereas HOG compute edge gradient of a whole image and find orientation of each pixel so it can generate a histogram.
2) HOG is used to extract global feature whereas SIFT is used for extracting local features.
3) SIFT is also scale and rotation invariant whereas HOG is not scale and rotation invariant.

Please let me know if there is any other advantages of SIFT. Also correct me if i have wrong understanding. Thank you

Aadnan Farooq A
  • 626
  • 4
  • 8
  • 19
  • I don't think this is the right place to ask for such question. It's not programming one. You should check the publication concerning these features. e.g. Histograms of Oriented Gradients for Human Detection – Eypros Dec 16 '14 at 08:50
  • It depends on what you need the features for. Like you said, they are different kinds of features used for different purposes. – Don Reba Dec 16 '14 at 12:10
  • Don Reba, Thank you very for answering. For example, I want to take the features of a person who is doing some activities i.e. standing, sitting, jumping etc. Then, in that case SIFT is better than HOG theoretically? – Aadnan Farooq A Dec 17 '14 at 01:28

0 Answers0