0

Could you please help understand several points related to Haar Classifier training:

1) Should positive image contain only the training object or they can contain some other objects in it? Like I want to recognize some traffic sign, should the positive image contain only traffic sign or it can contain highway also?
2) There are 2 ways of creating samples vector file, one is using info file, which contains the detected object coordinates in positive image, another just giving the list of positives and negatives. Which one is better?
3) How usually you create info file, which contains the detected object coordinates in positive image? Can image clipper generate object cordinates?

And does dlib histogram of adaptive gradient provides better results than Haar classifier?
My target is traffic sign detection in raspberry pi.

Thanks

haykp
  • 435
  • 12
  • 29
  • The button you clicked is labeled "Ask Question", not "Ask multiple Questions". Your questions also do not meet the requirements that are listed here [ask]. There are also plenty of papers and tutorials available online. Please do some own research. – Piglet Aug 30 '17 at 08:48
  • noted for future cases! thanks – haykp Aug 30 '17 at 09:59

1 Answers1

2

the positive sample (not necessarily the image) should contain only the object. Sometimes it is not possible to get the right aspect ratio for each positive sample, then you would either add some background or crop some of the object boundary. The final detector will detect regions of your positive sample aspect ratio, so if you use a lot of background around all of your positive samples, your final detector will probably not detect a region of your traffix sign, but a region with a lot of background around your traffic sign.

Afaik, the positive samples must be provided by a .vec file which is created with opencv_createsamples.exe and you'll need a file with the description (where in the images are your positive samples?). I typically go the way that I preprocess my labeled training samples, crop away all the background, so that there are only intermediate images where the positive sample fills the whole image and the image is already the right aspect ratio. I fill a text file with basically "folder/filename.png 0 0 width height" for each of those intermediate images and then create a .vec file from that intermediate images. But the other way, using a real roi information out of full-size images should be of same quality.

Be aware that if you don't fix the same aspect ratio for each positive sample, you'll stretch your objects, which might or might not be a problem in your task.

And keep in mind, that you can create additional positive samples from warping/transforming your images. opencv_createsamples can do that for you, but I never really used it, so I'm not sure whether training will benefit from using such samples.

Micka
  • 19,585
  • 4
  • 56
  • 74
  • Thank you soo much!! so I need to keep the same aspect ratio both for positive and negative images, got it! last quesiton: what about colors of images? should all they be gray-style? – haykp Aug 30 '17 at 09:57
  • negative images should be provided in full-size, because opencv will automatically choose each (correct aspect ratio) sub-window of each negtive image as negative sample. Only if you want to add additional hard-negative-samples, you might want to fix the aspect ratio. Afaik, cascade training only works on grayscale, but probably will convert automatically. – Micka Aug 30 '17 at 10:03