3

Good day! Just sorry for my English.

There are a few samples (etalons) stamps of various companies. And there are test images - photos of documents on which these stamps can occur. It is necessary to determine whether there is in the picture with the document or that stamp (reference). Stamps can be rotated.

Doing a similar task with the usual etalons (cartoon characters), finds good. But with stamps problem is probably due to the fact that they are very similar - all round. Use SurfFeatureDetector, SurfDescriptorExtractor

It might be worth other detector and a Descriptor? Thank you.

becks
  • 43
  • 4
  • It's difficult to tell exactly what your question is. Could you clarify? It is always worth trying other detectors and comparing their performance. OpenCV has implementations for SIFT, ORB, and FREAK. Also, posting an example of your stamps would be helpful. – Aurelius Jul 02 '13 at 15:21

1 Answers1

0

If stamp size is too small compared to the main image, using SURF descriptor alone may not be a feasible choice.

Since you have a finite number of stamp reference images, you can try template matching and after detecting the stamp region and calculating the orientation, you can just calculate the correlations with references and select the highest correlation as the detected object.

Template matching operation can be applied on each RGB channel (assuming color image) and matching scores can be summed as a final decision. However, the harder part is the detection of stamps and their orientations.

You can also use SURF keypoints on 3 RGB channels separately in order to utilize color information. After extracting keypoints for each channel, you can calculate matching scores separately and sum the three scores to obtain a final decision.

As another feature, you can use calculate color histograms of reference images and during testing, you can commpare these histograms to find a good match. THis feature is rotation independent and simple to calculate.

fatihk
  • 7,789
  • 1
  • 26
  • 48