Personal Hello I'm in a visual computing project here from the company and wanted to know the most experienced in the subject if I'm doing the right thing to train an object.
I read a lot and I studied the subject about testing various frameworks and I came to the conclusion of using OpenCV. So the results of the training in my ShellPrompt are giving different from the examples I see in the tutorials and videos on the net.
I'm training 80 images of 80x54 (positive images) and 160 images (negative) following steps:
1-Create Samples
C:\OPENCV\v3.3.1\build\x64\vc14\bin\opencv_createsamples.exe -info C:\Trainner002\pos\pos.txt -vec C:\Trainner002\data\vector_rg.vec -bg C:\Trainner002\neg\infofile.txt -num 80 -w 80 -h 54
2-Train Cascade
C:\OPENCV\v3.3.1\build\x64\vc14\bin\opencv_traincascade.exe -data C:\Trainner002\cascade -vec C:\Trainner002\data\vector_rg.vec -bg C:\Trainner002\neg\infofile.txt -numPos 80 -numNeg 160 -mode ALL -numStages 25 -w 80 -h 54 -featureType LBP
3- Result of training in shellprompt
Myone-linetrainingisbystageandIhavealreadyseenmanytutorialsofpeopledoingobjectdetectiontrainingbutseverallinesperstage.
Herearesomeexamplesjustlikemine,infactI'mfollowingtheexampleIfoundandtheresultisdifferent.
link
look at the result of his training, the result is similar to mine but his table gives more results than mine and one row per table. But my training generates all the files correctly in this configuration.
I'm correct, will not it? Will it be a version of OpenCV? Sara the settings that are wrong in the traincascade?
I'm waiting!