1

Can I use cropped objects from full frames as training dataset for a cascade classifier (LBP or HAAR)?

I know that I have to use full frames with annotations when retraining a neural net (Tensorflow, YOLO and so on)

But do I need it for a cascade classifier? Or cropped images are ok?

It seems I can do it because we have positive and negative images

So it should be ok to crop objects from positive images

E.g.

enter image description here

or

enter image description here

user155
  • 775
  • 1
  • 7
  • 25

1 Answers1

0

The answer to this question Can I use cropped objects from full frames as a training dataset for a cascade classifier (LBP or HAAR) is yes. It depends on your model architecture, your aims and system compatibility. For training, we normally crop target objects from a whole image and feed into the model.

The answer to your this question I know that I have to use full frames with annotations when retraining a neural net (Tensorflow, YOLO and so on) It depends. What is your ROI size? You can resize your ROIs according to your architecture or, You can crop target objects from ROIs. It is completely up to you.

But do I need it for a cascade classifier? Or cropped images are ok?-Answer is both are okay. Choose based on your model architecture, training time, system configuration, and obviously training performance.

user1410665
  • 719
  • 7
  • 23