LabVIEW

cancel
Showing results for 
Search instead for 
Did you mean: 

Object Classification in Image Processing

Hello,

 

Could please help me in Classification of objecets? My project to classify the objects in  ROI. For example in the below fig ROI contains 1 triangle, 2 Squares and 1 Circle. In the output it has to show TriangleClass Sample 1, SquareClass Sample 2 and CircleClass Sample 1.

Please help me.

 

Thanks in advance 

 

 

NeedThisClassification.png

 

 

 

0 Kudos
Message 1 of 15
(6,158 Views)

If you have Vision Development Module you could have a go with the geometrical pattern matching, I haven't used it myself, but there is an example that ships with LabVIEW (launch the example finder Help >> Find Example... and then search for "geometric", there should be one match called : Geometric Matching Example.vi)

 

Hope this helps


We have two ears and one mouth so that we can listen twice as much as we speak.

Epictetus

Antoine Chalons

0 Kudos
Message 2 of 15
(6,150 Views)

Thanks for the reply TiTou. I saw the example what you suggested but it is not related to my question.My project is classifying the objects in the given image with respect to shape, color and size etc.. 

0 Kudos
Message 3 of 15
(6,138 Views)

Please help me in doing Classification

Message 4 of 15
(6,109 Views)

Hey

 

For detecting shape you can use shape detection VI.

 

Please provide what you exactly want to do so that someone can help you

0 Kudos
Message 5 of 15
(6,100 Views)

My project is Pattern Recogonisation (Image Processing)

For this, I did Image Acquisition , Segmentation and Feature Extraction.. Now I have to do the final step clasification.

 

 

My original Image is TriangleCircleSquare.png

I need output asClassification.pngafter classification(with 3 diff classes ). I don know how to train the Image to get output as above.

0 Kudos
Message 6 of 15
(6,082 Views)

Search the examples for 'Classification'. There is one called 'Classification Example.vi' which looks just like what you are after.

 

p.s. The Vison examples always seem to use lots of stacked sequence structures. I often find them easier to read if you refactor the code to get rid of the stacked sequence structures.

0 Kudos
Message 7 of 15
(6,073 Views)

Thanks fot the reply Phil_. I saw that example.Ya it was related to my question. I am very new to Labview so not able to understand that code. Am attachting my code. If possible,please, can anyone add the classification part to this code.Image.png

Download All
Message 8 of 15
(6,063 Views)

Sorry, I am no more familliar with the classification VIs than you (neither am I in the business of doing peoples homework for them Smiley Wink .)

 

I would persevere with that example, use the help files to figure out how it all works and then try implementing it yourself.

(use the context help tool, then click 'more details' to dig deeper into the subject). 

 

Have a bit of a google, see if you can find a manual for it online. (I had a quick look, but didnt see anything)

 

Good Luck. Stick with it.

0 Kudos
Message 9 of 15
(6,057 Views)

A good place to start looking maybe: http://zone.ni.com/reference/en-XX/help/370281P-01/nivisionlvbasics/identify_parts_under_inspection/

 


Typical applications involving color classification include the following:

  • Sorting—Sorts objects of varied shapes. For example, sorting different mechanical parts on a conveyor belt into different bins.
  • Inspection—Inspects objects by assigning each object an identification score and then rejecting objects that do not closely match members of the training set.

Before you classify objects, you must create a classifier file with samples of the objects using the NI Particle Classification Training Interface. Go to Start»All Programs»National Instruments»Particle Classification Training to launch the NI Particle Classification Training Interface. Refer to the NI Particle Classification Training Interface Help for more information about the NI Particle Classification Training Interface.



0 Kudos
Message 10 of 15
(6,054 Views)