Datasets to train SVM classification
I tried to train my own SVM to detect people from video.
Here is how I did it: https://stackoverflow.com/questions/5...
I think the problem is with my dataset. I used INRIA dataset.
Here is how it looks like: https://drive.google.com/drive/folder...
There are about 200 positive samples and about 1400 negative.
I want ask you if you know any other datasets which I can download and use with my SVM?
Do you have also any advice on how a well-prepared database should look like?
i think i can help you. but could you explain what is your expected result
I want train my SVM to detect the silhouette of a specific person from video. But for now every dataset will be fine becasue I want just check if my code works. P.S. When I put data from INRIA it looks like my SVM doesn't learn anything.
could you expand "specific person"
what is your OpenCV version?
My OpenCV version is 3.4.1. Specific person = detect only one particular person like only detecting iron man from video :). But for now, dataset to detect all people from video will be just fine :)
do you have "INRIAPerson\Train\neg" images on your PC
please don't go away after answering. i try to explain what to do step by step.
Yes I have. I changed the format of all photos to png and their size on 64x128.
do you still have original pictures
resizing to 64x128 makes them useless