I've trained two classifiers for square and rectangular objects on the same scene.
Square obj: (4,100 pos; 10,000 neg)
Rectangular obj: (25,000 pos; 50,000 neg)
The problem is: they have similar features and I'm getting some square false positives from rectangular objects.
Like this case:
OpenCV 3 Blueprints (Howse, Puttemans, Hua, Sinha; 2015) says about training data for pedestrian and car detection:
The removal of all information that pollutes the training set, rather than helping it, such as color information, and simply using feature information that is more robust to all this intra-class variation such as edge information and pixel intensity differences.
I noticed that ~85% of my square positive samples were cut right by the edges, so, I got some approaches in mind:
- Training with a new square positive dataset where all edges are present, showing 5 to 10px of natural background. Like this:
- Add the false positives on rectangles to the square negative dataset.
- Add more square positive samples and repeat training.
Wich would be the best approach to get a lower square FP rate on rectangular objects? All, maybe?