06-25-2015 07:57 PM
Hi guys,
Could any body tell me how can i segment white area from red, black( background), and white parts of the image? I tried different color panel (Like blue channel, Green channel) as well, but the results is not really good.
Thanks
06-25-2015 10:39 PM
Take a look at the image after splitting it into HSL image (hue, saturation, intensity). I suspect the hue image will be almost all black, because white, black, and red all have a hue around 0 (some might be 255, though, or many different hues depending what color is dominant in the black and white areas). The saturation image will probably highlight the red areas, with the black and white areas both showing as black. The intensity will highlight the red and white areas, but not black.
You can do this as a two step process. Use the saturation image to make a mask for the red areas. Use the mask to remove the red areas from the intensity image, which gives you the white areas. Whatever is left is the black areas. Does that do what you need?
Bruce
06-26-2015 01:46 PM - edited 06-26-2015 01:48 PM
Ammons,
Thanks for the reply. The method you told me sounds interesting. But how can i do it in the labview NI VISION Assistant? I am sorry i just start learning the vision assistant.
I added one image i tried earily today and how can i write the loops here?
06-26-2015 02:13 PM
My approach works much better in LabVIEW. I'm not sure how it would be done in Vision Assistant. I find it difficult to work with multiple images with that.
Bruce
06-26-2015 02:51 PM
Can you post the original image?
06-26-2015 03:17 PM
Here i attached one original image. Please help me to segment the white and red part on this target. Vison bulider or vision assistant will be better.
Thanks!
06-26-2015 06:25 PM
06-27-2015 09:53 AM
Thanks!! This is really helpful. And i saw you guys doing machine vision system. Our research team want build a machine vision system, if you want communicate, Email?
ainirex@gmail.com
Once again, Thank you so much!
Sun
06-29-2015 05:01 AM
Just to add another method. Extract the particle and then threshold to get the red region as suggested. When you have extracted the particle you can inverse the binary image and get the white region.
06-29-2015 10:41 AM
Thanks for the reply.
When talking about particle extract, could you give me more detailsl. I tried in Vision Assistant, only works on thresholded image.