HAAR Cascade Trainning recognizing few features [closed]

asked 2018-02-09 12:01:06 -0600

Commands used:

opencv_createsamples -info annotations.txt -bg bg.txt -num 107 -w 80 -h 45 -vec samples.vec

opencv_traincascade -data /home/USER/test/classifier -vec samples.vec -bg bg.txt -numStages 12 -minHitRate 0.999 -maxFalseAlarmRate 0.5 -numPos 107 -numNeg 292 -w 80 -h 45 -mode ALL -precalcValBufSize 1024 -precalcIdxBufSize 1024

Cascade Config

I got this so far

Stage 0-2

Stage 3

edit retag flag offensive reopen merge delete

Closed for the following reason question is not relevant or outdated by sturkmen
close date 2020-11-05 12:34:46.864079

Comments

And what is your question exactly?

StevenPuttemans gravatar imageStevenPuttemans ( 2018-02-12 09:23:52 -0600 )edit

I read somewhere that It should recognize more than 1 feature in the first epoc/stage

PabloOyarzo gravatar imagePabloOyarzo ( 2018-02-12 10:25:10 -0600 )edit

Well it finds 3! Get yourself a copy of OpenCV3 Blueprints. It discusses all parameters in quite the detail!

StevenPuttemans gravatar imageStevenPuttemans ( 2018-02-13 01:02:18 -0600 )edit
1

Thanks I'll give it a look

PabloOyarzo gravatar imagePabloOyarzo ( 2018-02-14 12:51:52 -0600 )edit