Hand gesture detection and recognition using openCV

handrect1

handrect2

handrect3

Related Posts: Hand guesture recognition using openCV

Clicking the pictures and the detailed previews will display which show the hand contours extracting from video capture. These pictures illustrate the results of color based segmentation for hand gesture detection ( not recognition yet ). it is a  real time programme,  however, in this demonstration, the programme still depends on environments’ light , because of the color based segmentation method. If, combinned with motion detection and background substraction, it supposes to be robuster.

UPDATE[10, Jul, 2012]: a full example of hand gesture (fist in this instance) detection and recognition using openCV haar classifier training is updated in Hand gesture detection and recognition using openCV 2.

Author: Andol Li

A HCI researcher, a digital media lecturer, an information product designer, and a python/php/java coder.

156 Comments On “ Hand gesture detection and recognition using openCV”

  1. Hi andol. Great work! How did you finally manage to detect the contour of your hand with the noise and stuff? From an older post it reads “But the noise is easy to take off”… how did you do that?

    • Well, i used two steps to get the noises away which include using blur to smooth big contours and to melt numerous small contours, secondly, according to the hand characters, select largest contour as target.

  2. Hi. Will you be posting your code for this as you did for the circle detect? In the circle detect, there are two includes for math.h. Not being a C++ coder, I wonder what the differences in syntax between ” and < are for the math.h include files. Cheers.

    • Oh, the twice includes of math.h in circle detection codes was a mistake. You can delete one of them and debug it again, that would be fine, no different. About the code, yeah, i ll update it soon.

  3. Hi Andol! I’m new to opencv…lately i’ve been trying to do hand detection (detect hand and place a circle around it)…can you please help me? do i need to use haar classifier?
    Thank You

    • haar classifier is used to detect specified and predefined gestures, it is stable and effective once the training is finished. If you can get sufficient examples both positive and negative it would be very recommended to do so.

  4. I m doing the exact project in my engineering final year project but i have not used HAAR cascades but i have used skin segmentation to filter hand skin…. wud be glad if u can share ur email address so that i can clarify my doubts….. need some guidance in hand gesture recognition.

  5. Sir i have mailed u on ur hotmail account with some screenies and our exact problem…. we r anxiously waiting for ur reply…

  6. So far you have been very helpful with your recent articles and I would like you to know that I am grateful for your sharing.
    Hi! I was wondering if you might have any insight as to how I might go about identifying each finger and the thumb. Do you know what I could do next?

  7. @Dhruv it’d be wonderful if you could share it here! i’m pretty bad at programming but i need a finger/hand detection with tracking, any of u could help me out? my emails jona_lim87@hotmail.com any help is really really appreciated

      • hi,
        its very nice as i am able to see the boundary but it possible that if i open one figure its count 1 and if 2 then 2 if is there a way please tell me

        • @Yogendra
          if is possible to count the finger number based on the hsv skin colour segmentation – however, it is noted with not very high stability because the dynamic nature of colour range and backgrounds.

  8. Hi Andol, I couldn’t find the source code for the gestures !!! I found just a code for Hand Detection.
    Please I need a link for it.

1 2 3 5
Leave a comment
Due to technical adjustments, the comment function is shortly closed and will be re-openning soon. Thanks.


Copyrights 2006-2018 © All rights reserved
Theme Tree2, re-designed by Andol Li, powered by WordPress and Bootsrap
WWW.ANDOL.ME | 浙ICP备15040508号-1
公安备案图标 浙公网安备33010602004018号
Back to top