Revision history [back]

So I'm not sure exactly how much time and effort I should be spending on preparing my negative picture sets.

I usually just choose backgrounds that I think I'll encounter, which don't contain the entity I'm searching for. Also, I don't have a general rule of what the general dimensions should be, relative to the positive sample sizes.

See my images below:

Now my question is, how much does your negative set impact the overall quality of your detector? And does the traincascade utility scale the negative samples during training? If it doesn't, then it would seem crucial to choose negatives with lots of different dimensions.

And thank you for spending your time on my question!

So I'm not sure exactly how much time and effort I should be spending on preparing my negative picture sets.

I usually just choose backgrounds that I think I'll encounter, which don't contain the entity I'm searching for. Also, I don't have a general rule of what the general dimensions should be, relative to the positive sample sizes.

See my images below:

Now my question is, how much does your negative set impact the overall quality of your detector? And does Does the traincascade utility scale trainer slice up the negative samples during training? If images into sub-windows, and then walk across it? Is it doesn't, then worth the time customizing the negative set? Not much is said in the Viola Jones paper, but from what I can surmise, it would seem crucial to choose negatives with lots of different dimensions.seems like they used random regions from random photos.

And thank you for spending your time on my question!

So I'm not sure exactly how much time and effort I should be spending on preparing my negative picture sets.

I usually just choose backgrounds that I think I'll encounter, which don't contain the entity I'm searching for. Also, I don't have a general rule of what the general dimensions should be, relative to the positive sample sizes.

See my images below:

Now my question is, how much does your negative set impact the overall quality of your detector? Does the trainer slice up the negative images into sub-windows, and then walk across it? it in some order, or is it random? Does the trainer scale or crop the negative images? Is it worth the time customizing the negative set? Not much is said in the Viola Jones paper, but from what I can surmise, it seems like they used random regions from random photos.

And thank you for spending your time on my question!