Large size variations with IMAQ Pattern matching?

Does the pattern matching functions work for only +-5% size variations? Which means that the pattern matching is made for static situations only? (With static I mean a static camera watching e.g. a moving assemblyline)
I have a scenario where the camera is moving in 6DOF, giving my fiducials very much slant and very large size variations.
Is it then not possible to use the pattern matching of IMAQ?
The "IMAQ Vision Concepts Manual" says:
"Because pattern matching is the first step in many machine vision
applications, it should work reliably under various conditions.
In automated machine vision applications, the visual appearance of
materials or components under inspection can change due to factors such
as ori
entation of the part, scale changes, and lighting changes. The pattern
matching tool maintains its ability to locate the reference patterns despite
these changes."
-But with my experience, this is not correct in my scenario. Actually, the pattern matching tool was not able to find a match in any of my tested images. My size variations were large in these images (probably 50-200%).
Thanks!

Unfortunately the pattern matching algorithm NI currently uses is not a geometric (scaleable) pattern matching algorithm. The current algorithm works despite orientation, and some lighting changes, but not scale changes.

Similar Messages

How do I find out how IMAQ pattern match works inside?

I need detailed info on the internal workings of the IMAQ pattern match vis (L7.1).
I don't need source code as such (although that would be cool). I just
need a desription of the algortihm. The manual is not detailed enough.
I need to be able to explain my program rigourously for a scientific
paper so I have to find this out. Any help much appreciated..

Hello
If you want more information about the pattern matching algorithms, look at the IMAQ Vision Concepts Manual which can be found at the link below.
http://digital.ni.com/manuals.nsf/websearch/49110D7DB7FD282E86256EE70014816F
If you look at Chapter 12 this discusses the way in which the pattern matching is performed. This is probably the most detailed information we will be able to give out to you. Let me know if this isn't what you need and I'll see what I can find.
Regards
Hannah
NIUK & Ireland

IMAQ Pattern Match Score

I am working on an application that uses the IMAQ Match Pattern VI. The matches that are returned have a score assigned to them. The help documentation for this reads:
Score ranks the match results on a scale of 0 to 1,000, where 0 equals no match and 1,000 equals a perfect match.
Likewise, there is a VI input called "Minimum Match Score", which is the smallest score a match can have to be considered valid. The data range for a match is between 0 and 1000.
Can anyone point me to a resource that might better explain how this score is derived or at least defined?

Hi,
The NI Vision Concepts Manual provides ancillary information; I've linked that below. The In-Depth Discussion for both Pattern Matching and Geometric Matching may prove helpful in providing the detail you're wanting.
Machine Vision:
http://zone.ni.com/reference/en-XX/help/372916P-01/TOC15.htm
I hope you find this information helpful. Have a great day!
- Kale

Help with regex pattern matching.

Hi everyone
I am trying to write a regex that will extract each of the links from a piece of HTML code. The sample piece of HTML is as follows:
<td class="content" valign="top">
     
<script language="JavaScript"
src="http://chat.livechatinc.net/licence/1023687/script.cgi?lang=en&groups=0"></script>
<a href="makeReservation.html">Making a reservation</a><br/>
<a href="changeAccount.html">Changing my account</a><br/>
<a href="viewBooking.html">Viewing my bookings</a><br/>I am interested in extracting each link and the corrresponding text for that link into groups.
So far I have the following regex <td class="content" valign="top">.*?<a href="(.*?)">(.*?)</a><br>However this regex only matches the first line in the block of links, but I need to match each line in the block of links.
Any ideas? Any suggestions are appeciated as always.
Thanks.

Hi sabre,
thanks for the reply.
I am already using a while loop with matcher.find(), but it still only returns the first link based on my regex.
the code is as follows.
private static final Pattern MENU_ITEM_PATTERN = compilePattern("<td class=\"content\" valign=\"top\">.*?<a href=\"(.*?)\">(.*?)</a><br>");
private LinkedHashMap<String,String> findHelpLinks(String body) {
    LinkedHashMap<String, String> helpLinks = new LinkedHashMap<String,String>();
    String link;
    String linkText;
      Matcher matcher = MENU_ITEM_PATTERN.matcher(body);
      while(matcher.find()){
        link = matcher.group(1);
        linkText = matcher.group(2);
        if(link != null && linkText != null){
          helpLinks.put(link,linkText);
    return helpLinks;
private static Pattern compilePattern(String pattern) {
    return Pattern.compile(pattern, Pattern.DOTALL + Pattern.MULTILINE
        + Pattern.CASE_INSENSITIVE);
}Any ideas?

Using lat long with imaq axis matching

I am having trouble associating the lat long values with the imaq image extent, firstly the imaq has an indirect coordinate reference with y axis icreasing top to bottom which is reverse to latitude values. Secoundly, I am unable to change the value of origion to any value other then (0,0). Can anybody help me or provide any guidence in this reard...
Solved!
Go to Solution.

Hi Amir13,
I would suggest you post this to the machine vision forum, http://forums.ni.com/t5/Machine-Vision/bd-p/200 , I think you'll get a better response there. After you do that, could you please post a link to the new post here so user Sets can find it?
Also, when you make your new post, please attach an example VI and/or picture of what you're trying to accomplish. Sometimes this can help describe the issue in more detail than text can.
Thanks,
Bobby Breyer
Applications Engineer
National Instruments

Problem while using color pattern matching

Currently we are doing projects on real time object tracking where we found one doubt that irrespective of the object size whether this color pattern match works or not . My questions are as follows:
1. Whether it is applicable for objects moving far . Because as it moves far, the size of the object decreases such that the color pattern matching is not working what will be solution since we must use color image
2. What is the difference in using scale and rotate invarient in color pattern matching
3. How we can effectively decrease the ROI depending upon the object position as per below attached screen shots .
we have removed boundary box values of X and Y coordinates at the four corner but we can't track as the object moves far away or we can't decrease the ROI as the object moves far.
4. whether it is possible to see the value of particular pixel in LABVIEW vision development module as we seen only the coordinate position . whether it is applicable to see particular pixel value. Guide us
please, see the below screen shots and provide the solution how effectively decrease or increase the ROI depending on objects position using color pattern match
Attachments:
problem in matching while object moves far.png ‏515 KB

Hello,
I have not been using the color pattern matching a lot (especially not in real-time). But since the pattern matching considers only small scale changes, you could try updating the color template every n-th iteration (depending on your setup and requirements). The major problem is the template size, since the color pattern matching tends to take quite a lot of time in learning the template. You would of course need to come up with some idea on how to change the subimage size, where the new template will be learned.
This is the part of coarse (rough) object detection as was suggested by MoviJOHN. For example, if your object is distinctly red, you can extract the green channel from your rgb image and use threshold to roughly find the object and apply the new ROI - template.
So:
1. learn the template,
2. use pattern matching with bounding rectangle (ROI) for the next couple of frames (you would need to experiment here where the detection fails -> how fast can you move the object away so that the detection fails),
3. Before the detection fails -> rough object detection with some padded bounding rectangle (new ROI),
4. Re-learn te template of new ROI and go back to 2.
Again, the biggest issue is the template learning time - if you have a high resolution camera and the template is large, this won't satisfy your real-time application.
You should set up the appropriate illumination first. The resolution is also important, since your object is moved back and forth (but the resolution will have a direct impact on the template learning time).
Best regards,
K
https://decibel.ni.com/content/blogs/kl3m3n
"Kudos: Users may give one another Kudos on the forums for posts that they found particularly helpful or insightful."

How to use Labview to output the coordinates from Pattern Matching result

I tried to add some labview commands into the vi program created by IMAQ Pattern Matching scrip to output the coordinates of a target point found in Pattern Matching because i need to do some calculations for the point coordinates and I don't want just to read the values from the IMAQ results on the monitor. Does anyone can help me? Thank you.
Attachments:
PatternMatching1.vi ‏84 KB

I have posted replies to your other postings with your same question, and continue to recomend that you look at some of the LabVIEW tutorials.
I modified the attched program such that it would index the arrays of match information returned and then unbundle the X and Y features of the match and add them to gether as an example of how to access the data programatically.
I hope this helps.
Regards,
Amaury Rolin
NI Applications Engineer
Attachments:
PatternMatching_mod.vi ‏88 KB

USB SNAP + colour pattern matching ( IMAQ)

I am new to LAbView and currently I am working on colour pattern matching with USB snap. My problem is this program keep prompt me on the IMAQ Learn Colour Pattern. I need someone to help me solve that problem.
Another question is 'Are colour pattern matching require us to save and load file before learn a template?'
I am using LabView 7.1 and I would appreciate anyone who help me. Thanks
Message Edited by Chee Hou on 09-16-2009 03:46 AM
Attachments:
Untitled.vi ‏189 KB

Hello Chee Hou,
Have you tried to run the example to do color pattern matching?
From the example, you do need to have a template picture ready when you are using the colour pattern matching.
You need to Learn Colour Pattern and then load the pattern to do color pattern matching.
Hope this helps.
James
- Meadow -
LabVIEW 7.0 - 2011, Vision, RT, FPGA
TestStand 3.0 - 4.5

Error-1074396120 Not an image, problem with IMAQ Learn multiple geometric patterns

Error-1074396120 Not an image, problem with IMAQ Learn multiple geometric patterns
Hi!
I've tried to modify the example of "multiple geometric patterns matching" , and just use two patterns, but when I run the VI this error appear and I doon't know how to solve it! , the error appears in the "IMAQ Learn multiple geometric patterns" block.
Running on:
- labview 32 bits
- windows 7 64 bits
- usb camera 2.0
Any sugestion would be helpful..... ! Regards
Attachments:
template_12.png ‏150 KB
template_11.png ‏123 KB
vision_multiple_pattern_matching.vi ‏127 KB

thanks all for your replies, the problem was on my template images, I had to give them information about the pattern matching, and I did it with NI Vision Template Editor, within Vision utilities, and I chose template with Feature Based.
Thank you again and Regards!

How to use Colour pattern matching with a webcam

Hi,
I have a web cam which I am able to use successfully in labview (i.e.. Get images)
I have looked at the colour pattern matching examples and tried to modify them, so that I can detect a red spot, that can be seen through the webcam, but have been unsuccessful.
In essence I'm trying to do real time colour pattern matching
Can anyone steer me in the right direction? Or help me out?
Thanks
Solved!
Go to Solution.

Hi kr121,
I'm trying to work on color myself right now.
What have you tried so far? What type of web camera are you using? I'm using a Microsoft Life Camera with LV 2011 on Windows 7.
I started here: http://zone.ni.com/devzone/cda/epd/p/id/5030
If you are not using an NI camera I was able to get this to work using the cmd prompt and extracting the files manually to at least run the NI-IMAQ for USB: Snap and Save Image with USB Camera and NI-IMAQ for USB: Grab and Save Image with USB Camera examples.
The command prompt command is:
ni_imaq_usb_installer_86.exe /x
Don't know if this is 100% correct but it at least allowed me to capture images and avi's.
Regards,
-SS

Undertake Vision pattern matching with a mask

I am trying to undertake a pattern match, with a irregular shape, and also with a masked area inside the shape, e.g. I have an object (rectangle in shape), with different colours, shapes on top of it. None of the objects break the outline shape. I want to be able to determine if the outline shape is present regardless of the objects within the border of the shape. Taking this one step further I also want to be able to do this when the outside shape is irregular. Any tips would be appreciated.

I don't think this is possible with any of the existing IMAQ tools. It sounds like a geometric pattern matching.
Bruce
Bruce Ammons
Ammons Engineering

Trouble using a pattern match in the GO URL when the value starts with %

Hi guys,
We are trying to use a Go URL as follows:
[http://hostname.com:9704/analytics/saw.dll?Go&Path=/users/administrator/Test/TestReport&Action=Navigate&col1=TestReport.SUBJECT&op1=like&val1="%25D8D8%25"|http://hostname.com:9704/analytics/saw.dll?Go&Path=/users/administrator/Test/TestReport&Action=Navigate&col1=TestReport.SUBJECT&op1=like&val1="%25D8D8%25"]
Basically, we want to send the filter : SUBJECT like '%D8D8%' in the GoURL. However, the report that opens up does not fetch any rows because BI somehow messes up the clause by not recognizing the leading %25 (which is an escaped % character). Instead it resolves the %25D8D8%25 into something like �D8% .
As you can see, the %25 at the end however gets resolved correctly but somehow the one at the beginning gets clubbed with the leading D8 to give �.
Any idea, how to get BI to accept a leading escaped % character when doing a pattern match in the Go URL?

I'm heading to the Apple Store in Danbury CT tomorrow to test out a MacBook Pro. I'll happily post what I like and dislike here.
Waiting for a MacBook Pro... Other OS

Is there a way to make the view window on mail display messages with a larger size ?

I would like to set it up as a default, and not have to zoom in or make larger (cmd +) each individual message.
I have tried the font setup, but it does not work. It works for my own messages only.
I guess what I'm asking is if the font-setup of the sender of the mail can be overidden.

~Bee: I think you meant to say Mail's preferences.
I tried to do the same myself with the Fonts in Mail. Problem is it only enlarges part of messages for the most part. I could not get a good balance that way with some text enlarging while some stays small.
Using the cmd+ keys to zoom brings everything in the message to a larger size which is much better. Yes it's a pain, but I haven't found a better alternative yet.
Also, ctrl-mouse zoom works also, but not as crisp text. Wish the mouse tap zoom would work in mail, but it doesn't.
It would be a nice addition if apple would just include a zoom setting for all screens including Safari.
But as Bee suggested, increasing the font size does help depending on what is sent to you.

In IE if I set the zoom at lets say 150% it will stay that way even if I shut down. But with firefox, it goes back to small print every time I view a new page. Is there a way to set the zoom to stay at a larger size? Thanks, EH

# Question
In IE if I set the zoom at lets say 150% it will stay that way even if I shut down. But with firefox, it goes back to small print every time I view a new page. Is there a way to set the zoom to stay at a larger size? Thanks, EH

If you need to adjust the font size on websites then look at:
* Default FullZoom Level - https://addons.mozilla.org/firefox/addon/6965
* NoSquint - https://addons.mozilla.org/firefox/addon/2592
Your above posted system details show outdated plugin(s) with known security and stability risks.
*Shockwave Flash 10.0 r45
Update the [[Managing the Flash plugin|Flash]] plugin to the latest version.
*http://www.adobe.com/software/flash/about/

Mod_security: Access denied with code 405. Pattern match "!(GET|HEAD|POST)

Hi all,
After Cloning facing an issue
mod_security: Access denied with code 405. Pattern match "!(GET|HEAD|POST)"
and not able to get the login prompt
EBS: 12.1.3
DB:11G
Please help as this is urgent.
Regards,
Raj.

Hi Hussein/Srini,
My OS details are as follows
Source OS : OE Linux 5X
Target : REHL
DB : 11.2.0.3
In my previous cloning the R12 login URL was not getting redirected to https from http. This backup was given by client last week and I completed the cloning and post cloning procedures without any error, but unable to login as the page is redirecting to https:/hostname:port/OA_HTML/AppsLogin.
I have done the following so far, but the issue is not getting resolved.
1) Generated JAR files using ADADMIN (Force)
2) Compiled JSP
3) Ran autoconfig multiple times without any error in both db and application tiers.
4) DB alert log did not have any error.
5) Executed relink all from APPL_TOP
6) Able to launch http://XXXXXXXXX:XXXX/forms/frmservlet?
Kindly help me out on this
Regards

Large size variations with IMAQ Pattern matching?

Similar Messages

Maybe you are looking for