Small Particle Filtering From Image

[simply_me]

Hello,

I'm trying to build a vi that can count the number of certain particles, and I've followed both particle analysis example by NI. The problem is that the resolution isn't that good, and the particles that I'm trying to count are somewhere in the middle range (see particle I.vi). When I tried to incorporate more restrictive filters (see particle.vi) it doesn't find any particle. I would appreciate any suggestions you might have regarding counting this particles somewhat accurately/ consistently.

Thank you,

[simply_me]

Here attached the particles I'm trying to find and a sample image.

[KevinC]

1. It is not clear to me from your posted picture which particles are to be accepted and which are to be rejected. I would not be able to perform this task by hand, let

alone develop an automated algorithm. Could you explain in greater detail what it is that you are trying to do?

2. It would be helpful if you posted the actual image you are trying to process, in addition to your code.

3. From the screen shot you posted, it does not look like you have the best setting for a threshold value. Experimenting with that may be helpful, or you might want to try one of the automated threshold methods.

Kevin C.

[simply_me]

Hi Kevin,

Thanks for your reply.

1. I'm trying to get an estimate for the number of small brownish particles in the sample. It doesn't need to be a very restrictive code, just good enough to filter out the large particles.

2. Please see the attached file.

3. I've experimented a little with threshold values, and the best I've got was a range between 50-70. This range would still have some errors though, like accepting larger particles.

Any idea why the other vi (particle) doesn't work? That's where I've tried using area/bounding rectangle filtering, but I couldn't get it to run properly.

[simply_me · Accepted solution]

Hi Kevin,

I've worked it out. Thank you though.

[Aojha]

hi, simply_me

I am trying to do similar things for my project. I need to count multiple particles from noisy background and process them can you suggest me what approach you apllied.

I am using count objects in my program

[shreya111]

Hello, 

           I have to accept nut having diameter 1cm and reject other nuts , if I place them in front of my camera  using particle analysis.

I have Labview 2012 version and Camera used is Basler aca 2000-50gc .

I tried to make a VI by using concepts of " Particle analysis .vi " example, but it is not showing proper results. 

I am attaching my VI and  Image of nuts .

Please suggest me modifications as soon as possible.

Thanks.

[ChrisStrykesAgain]

shreya111,

Which measurement are you concerned with being 1cm? ID, flats, points or other?

[shreya111]

Hello,

          I made a VI , It sometimes show area(pixels) of 3 particles and sometimes more than 3 particles. I am attaching my vi and respected snapshots. Is I am going on right track ? Please suggest me modifications as soon as possible.

Thanks

[ChrisStrykesAgain]

I would try defining as small of an ROI as possible, and increasing the contrast between the nuts and the background. As it is, I believe you are picking up some of your vignetting as particles.

Additionally, if it's possible to change your actual acquisition environment, this is an application that screams for backlighting; it would make your image detection much easier. At the very least, a brighter light/more direct orientation would help eliminate the shadows.