Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

Train the neural network to detect object with different aspect ratio in pictures

I tried to detect object which could have different aspect ration in the positive photo.

I used the next params: opencv_traincascade -data haarcascade -vec samples.vec -bg negative.dat -numStages 15 -minhitrate 0.99 -maxFalseAlarmRate 0.4 -numPos 797 -numNeg 933 -w 15 -h 30 -mode ALL -precalcValBufSize 2048 -precalcIdxBufSize 2048

So, aspect ratio is 1:2 in the image pattern.

And when I use a generated cascade.xml I can detect an object in the pictures only with the similar aspect ratio. But some photos contains objects with 2:3 or even 1:1 ratio.

How can I detect these objects?

Train How to train the neural network to detect object with different aspect ratio in picturesratio?

I tried to detect object which could have different aspect ration in the positive photo.

I used the next params: opencv_traincascade -data haarcascade -vec samples.vec -bg negative.dat -numStages 15 -minhitrate 0.99 -maxFalseAlarmRate 0.4 -numPos 797 -numNeg 933 -w 15 -h 30 -mode ALL -precalcValBufSize 2048 -precalcIdxBufSize 2048

So, aspect ratio is 1:2 in the image pattern.

And when I use a generated cascade.xml I can detect an object in the pictures only with the similar aspect ratio. But some photos contains objects with 2:3 or even 1:1 ratio.

How can I detect these objects?

click to hide/show revision 3
No.3 Revision

How to train the neural network a CascadeClassifier to detect object with different aspect ratio?

I tried to detect object which could have different aspect ration in the positive photo.

I used the next params: opencv_traincascade -data haarcascade -vec samples.vec -bg negative.dat -numStages 15 -minhitrate 0.99 -maxFalseAlarmRate 0.4 -numPos 797 -numNeg 933 -w 15 -h 30 -mode ALL -precalcValBufSize 2048 -precalcIdxBufSize 2048

So, aspect ratio is 1:2 in the image pattern.

And when I use a generated cascade.xml I can detect an object in the pictures only with the similar aspect ratio. But some photos contains objects with 2:3 or even 1:1 ratio.

How can I detect these objects?

How to train a CascadeClassifier to detect object with different aspect ratio?

I tried to detect object which could have different aspect ration in the positive photo.

I used the next params: opencv_traincascade -data haarcascade -vec samples.vec -bg negative.dat -numStages 15 -minhitrate 0.99 -maxFalseAlarmRate 0.4 -numPos 797 -numNeg 933 -w 15 -h 30 -mode ALL -precalcValBufSize 2048 -precalcIdxBufSize 2048

So, aspect ratio is 1:2 in the image pattern.

And when I use a generated cascade.xml I can detect an object in the pictures only with the similar aspect ratio. But some photos contains objects with 2:3 or even 1:1 ratio.

How can I detect these objects?