Ask Your Question
0

Is it normal a HSV image looks like this?

asked 2014-02-13 16:11:33 -0600

Android65 gravatar image

Hello,

For a university project we have to navigate a drone through a building using a grid of symbols varying in color and shape. The drone takes pictures every second in JPEG format.

To recognize the shapes and colors in the picture I was thinking about using a color filter, thus eliminating noise and identifying the color of the symbols. I read through some opencv tutorials and documentation and the general consensus suggested to convert the image to HSV and then applying a mask.

To tweak the color masks I wrote a simple GUI to adjust the mask values. I do not know what color space JPEG uses so I tried both "RGB2HSV" and "BGR2HSV" but both images do not look like the original image at all

This is the result using RGB2HSV, and this is BGR2HSV. None of these images look like the original (that I cannot upload for some reason)

I was wondering if this is normal, and if so which conversion is the correct one?

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted
0

answered 2014-02-18 11:43:26 -0600

dma gravatar image

Bah..they do not look like the original picture because you display the HSV as if it was RGB that's all. But HSV is a better model to 'separate' perceptually the colors (then separate your objects). once your objects are separated, apply inverse color conversion to get the original color.

edit flag offensive delete link more

Question Tools

Stats

Asked: 2014-02-13 16:11:33 -0600

Seen: 767 times

Last updated: Feb 18 '14