2

I need to prepare training data which I will then use with OpenCV's cascaded classifier. I understand that for training data I'll need to provide rectangular images as samples with aspect ratios that correspond to the -w and -h parameters in OpenCV's training commands.

I was fine with this idea, but then I saw web-based annotation tool LabelMe. People have labelled in LabelMe using complex polygons!

Can these polygons be somehow used in cascaded training? Wouldn't using irregular polygons improve the classification results?

If not, then what is the use of the complex polygons that outline objects in LabelMe'd images?

user961627
  • 12,379
  • 42
  • 136
  • 210

1 Answers1

2

Data sets annotated with LabelMe are used for many different purposes. Some of them, like image segmentation, require tight boundaries, rather than bounding boxes.

On the other hand, the cascade classifier in OpenCV is designed to classify rectangular image regions. It is then used as part of a sliding-window object detector, which also works with bounding boxes.

Whether tight boundaries help improve object detection is an interesting question. There is evidence that the background pixels caught by the bounding box actually help the classification.

Dima
  • 38,860
  • 14
  • 75
  • 115
  • Thanks @Dima, I have a follow-up question if you don't mind: http://stackoverflow.com/questions/21310446/opencv-positive-samples-dimensions – user961627 Jan 23 '14 at 14:06