ecstatic_mortal | 21 Jun 01:12 2012

Wonder where my post is.

Hello programmers,

I spent nearly 20 minutes drafting a post yesterday and asking a query, but I am afraid the moderators have
deleted that post and not intimated me of that. I do not see the query post that I made yesterday.

Please let me know where my post is and why hasn't the query been allowed here?

Thank you.

EM

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com
vevin | 21 Jun 00:43 2012
Picon

Worked on ToF Camera PMD Cam Board

Has anyone worked on ToF camera before?
Thanks and Regards,
Vevin Moza

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com
jkitten33 | 20 Jun 22:28 2012
Picon

FaceRecognizer::predict - requirements & restrictions?

I haven't found much in the way of documentation for the FaceRecognizer, so I've been doing a lot of trial and
error.  It's slow going.  What I had intended to do was this:

1) Record User Images
Use the 960x720 camera and to record user images, cropping the faces to a 560x675 area.

2) Find Faces
Using real-time camera access, scan each frame capture for "faces" using CascadeClassifier.  (The
resulting Mat will be 960x720.)

3) Identify Faces
Create a ROI for each "face" found in #2, and pass the ROI to the FaceRecognizer for identification.  (The ROI
size will vary.)

The problem, I think, is that each step of this process seems to require the images (Mats) to all be the same
size.  Is this assumption true, or have I misinterpreted things?  If it is true, then what is my best course of
action for comparing the final found "faces" (which are arbitrary sizes) with the 560x675 sample images? 
(If you could reference specific library methods rather than arbitrary "just do this", I would be most
appreciative.  It will give me a good starting point when referencing the manuals.)

Thanks in advance.

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com
sblsbl2 | 20 Jun 23:32 2012
Picon

How to visualize descriptor matching using opencv module in python?

I am new to this group. If my question is not appropriate to be posted here, please let me know.

I am trying to use opencv with python. I wrote a descriptor (SIFT, SURF, or ORB) matching code in C++ version
of opencv 2.4. I want to convert this code to opencv with python. I found some documents about how to use
opencv functions in c++ but many of the opencv function in python I could not find how to use them. Here is my
python code, and my current problem is that I don't know how to use "drawMatches" of opencv c++ in python. I
found cv2.DRAW_MATCHES_FLAGS_DEFAULT but I have no idea how to use it. Here is my phthon code of matching
using ORB descriptors:

    im1 = cv2.imread(r'C:\boldt.jpg')
    im2 = cv2.cvtColor(im1, cv2.COLOR_BGR2GRAY)
    im3 = cv2.imread(r'C:\boldt_resize50.jpg')
    im4 = cv2.cvtColor(im3, cv2.COLOR_BGR2GRAY)

    orbDetector2 = cv2.FeatureDetector_create("ORB")
    orbDescriptorExtractor2 = cv2.DescriptorExtractor_create("ORB")
    orbDetector4 = cv2.FeatureDetector_create("ORB")
    orbDescriptorExtractor4 = cv2.DescriptorExtractor_create("ORB")

    keypoints2 = orbDetector2.detect(im2)
    (keypoints2, descriptors2) = orbDescriptorExtractor2.compute(im2,keypoints2)
    keypoints4 = orbDetector4.detect(im4)
    (keypoints4, descriptors4) = orbDescriptorExtractor4.compute(im4,keypoints4)
    matcher = cv2.DescriptorMatcher_create('BruteForce-Hamming')
    raw_matches = matcher.match(descriptors2, descriptors4)
    img_matches = cv2.DRAW_MATCHES_FLAGS_DEFAULT(im2, keypoints2, im4, keypoints4, raw_matches)
    cv2.namedWindow("Match")
    cv2.imshow( "Match", img_matches);

Error message of the line "img_matches = cv2.DRAW_MATCHES_FLAGS_DEFAULT(im2, keypoints2, im4,
(Continue reading)

vevin | 20 Jun 20:15 2012
Picon

PMD Camboard Nano

Hi Guys,
I am working on the newly released PMD camboard nano.Can anyone tell me whether OpenCV can read video data
from this camera.
Please help.
Thanks and Regards,
Vevin Moza

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com
kenny_zkit | 20 Jun 14:20 2012
Picon

Error building 2.4.1 with cuda on ubuntu 12.04

Hi all, 

Here is my problem when i build opencv : 

[  6%] Built target libjpeg
[ 10%] Built target libjasper
[ 12%] Built target libpng
[ 15%] Built target opencv_core
[ 16%] Built target opencv_ts
[ 21%] Built target opencv_imgproc
[ 24%] Built target opencv_highgui
Linking CXX executable ../../bin/opencv_perf_core
../../lib/libopencv_core.so.2.4.1: error: undefined reference to 'cuDeviceGetAttribute'
collect2: ld a retourné 1 code d'état d'exécution
make[2]: *** [bin/opencv_perf_core] Erreur 1
make[1]: *** [modules/core/CMakeFiles/opencv_perf_core.dir/all] Erreur 2
make: *** [all] Erreur 2

Is someone know something about that ? I'm really stuck here...

Thank you !

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com
ratnas | 20 Jun 19:16 2012
Picon

Haartraining question about crop images

Hi, 
I'm working on haartraining , I readed many tutorials
(http://se.cs.ait.ac.th/cvwiki/opencv:tutorial:haartraining etc  ) , but it not clear to me what to do
with the cropped images. I don't see any setting in the different .exe programs (createsamples.exe ,
haartraining.exe etc. ) that use the cropped images. Where Am I wrong? 
Hope to find a solution.
Thank You
M.R

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com
Mathieu Dubois | 20 Jun 17:20 2012
Picon

Strange results in LAB conversion [1 Attachment]

[Attachment(s) from Mathieu Dubois included below]

Hello,

I wanted to check some code that I wrote for Lab conversion by comparing the output to OpenCV but I'm facing some problems.
In order to check that, I wrote the attached program and tested it with attached image (use ./convert_lab test2.ppm).
The image is 1x4 matrix and consists in a white pixel, a red pixel, a green pixel, a blue pixel and soft green pixel.

The program loads an image, and convert it to Lab. Here are the values disaplyed by OpenCV:
(0,0): [100,-1.30398e-05,6.61304e-06]
(0,1): [53.2406,80.0942,67.2015]
(0,2): [72.5174,-1103.15,64.0418]
(0,3): [32.2957,79.187,-107.862]
(0,4): [55.2719,24.1407,62.3391]
Clearly the value of the (0,2) pixel (the green one) and the (0,4) pixel (which is also green) are strange (especially the one in bold).

In order to test I first converted the image to XYZ with OpenCV and then computed Lab with my own code (using the formulas found on OpenCV help). Here are the values:
(0,0): [100,0,-0.000248181]
(0,1): [53.2406,80.0942,67.2015]
(0,2): [87.7351,-86.1813,83.1774]
(0,3): [32.2957,79.187,-107.862]
(0,4): [63.3196,-65.8973,63.6004]
While I won't claim that my code is correct the values make more sense.  Note that they are very close to those computed by OpenCV except for the green pixels.

My question is then: is there something wrong in the way I convert to Lab with OpenCV? if no, why I don't get the same results than in OpenCV?

Thanks in advance,
Mathieu


Attachment(s) from Mathieu Dubois

1 of 1 File(s)


__._,_.___

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com




Your email settings: Individual Email|Traditional
Change settings via the Web (Yahoo! ID required)
Change settings via email: Switch delivery to Daily Digest | Switch to Fully Featured
Visit Your Group | Yahoo! Groups Terms of Use | Unsubscribe

__,_._,___
Vihari Piratla | 20 Jun 16:27 2012
Picon

Dense Feature extraction [1 Attachment]

[Attachment(s) from Vihari Piratla included below]

Hello, 
I am working on vision based obstacle avoidance and need to implement feature detection step in it.
This feature detection in the image should be well spread all through the image similar to the one shown in the attachment.
What I tried to do is divide the whole image in to grids and then detect features individually in each grid.
but then the features detected are not stable and hence when I tried to track them with pyramidal LK all of them have null status i.e. error.
So, I gave up doing it this way!
Is there a work around for this. How is this generally handled?
Thanks for the help. 

--
Vihari Piratla.
students.iitmandi.ac.in/~p_vihari

"If you can dream it, You can make it"




Attachment(s) from Vihari Piratla

1 of 1 Photo(s)


__._,_.___


Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com




Your email settings: Individual Email|Traditional
Change settings via the Web (Yahoo! ID required)
Change settings via email: Switch delivery to Daily Digest | Switch to Fully Featured
Visit Your Group | Yahoo! Groups Terms of Use | Unsubscribe

__,_._,___
ratulndciut | 20 Jun 14:53 2012
Picon

Descriptor for MSER

May I please ask which descriptor is recommended for maximally stable extremal regions (MSER) detector?
And why? A pointer to references or implementation is highly appreciated. 

Thanks in advance.

Cordially,
Hasan

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com
rambod | 20 Jun 13:14 2012
Picon

Errors while installing OpenCV 2.4.1

Hi everyone,
I have been trying to install OpenCV 2.4.1 following this install guide:

http://opencv.itseez.com/doc/tutorials/introduction/windows_install/wind\
ows_install.html#windows-installation

I didn't get any error untill I tried to compile the solution OpenCV.sln
createed by CMake 2.8.8 (which is the last step of the guide). I'm using
Visual Studio 2010 64x as compiler, and the output was:

========== Build: 15 succeeded, 155 failed, 0 up-to-date, 0 skipped
==========

You can find the whole output here:

http://www.beginninghtml.altervista.org/output.txt

Anyway, I'll try to sum up it: the compiler always gives this error when
it tries to build a part of the solution:

"LINK : fatal error LNK1104: cannot open file
'..\..\lib\Debug\opencv_highgui249d.lib'"
(the error is always the same but also with other files, such as
'..\..\lib\Debug\opencv_features2d249d.lib', ).

Therefore, is there anyone that can help me?

------------------------------------

Change settings: http://www.yahoogroups.com/mygroups, select
   Get Emails (get all posts)
   Daily Digest (one summary email per day)
   Read on the web (read posts on the web only)Or Unsubscribe by mailing OpenCV-unsubscribe <at> yahoogroups.com

Gmane