Added: 2 years ago
From: nakagawa53
Views: 10,148
Sort by time | Sort by thread (beta)

Link to this comment:

Share to:

All Comments (65)

Sign In or Sign Up now to post a comment!
  • Sir are u got ur answer , if yes plz share it i got the same problem

  • hello @nakagawa53.

    greet work, i downloaded code & libraries ( it's give a run time error on KNearest.cs

    "src_image = highgui.CvLoadImage(file, highgui.CV_LOAD_IMAGE_GRAYSCAL­E);"

    i think it's need a the training files.

    would you share them please, or tell me what to do?

    thank you so much

    i noticed that there was

    link for that but i missed now

  • Hey @nakagawa53. Have couple of questions. i) Does it detect hand when u bring the hand ahead of the face ? ii) Does using Haar clasifiers slow down the program ??

  • Thanks for the noob guide :D

  • Sorry about my (very) late reply. There are many people asking the same question.

    Please note that you cannot extract the program, compile it, and hoping that it would work right away =_=" there are several libraries that you need to install.

    I have updated the info section I hope it helps.

  • @nakagawa53 libraries such as? have you completed the 7 other signs left? thanks!

  • @nakagawa53 tried running your program but got this error --> src_image = highgui.CvLoadImage(file, highgui.CV_LOAD_IMAGE_GRAYSCAL­E);

  • How do you run this program? :)

  • @baamchika Info section updated.

  • waw... keren bgt... saya juga lagi berusaha untuk hand detection in c# juga ^^.. btw saya sudah kerem message ke @nakagawa53 .. mohon di baca ya ^^.. hope a great response

  • @MrSimplesify Info section barusan saya update boss

  • would u mind to post the link from where i can download your source code. the given link of 4shared is not working.

    plz give me the link. it will help me a lot to do something with that.

    thanks in advance.

  • plese put the link of soure code agine cos it not work to download

    thanks so mutch

  • Why is it necessary to train the system each time you run the code?

  • I'm sorry to bother you but can you elaborate more on how to use K-nn ? I read you codes and understand how you take your sampling, but how do you actually classify a new sign? Which part actually gets the user's input on what that is when training?

  • also, which haar classifiers did you use to detect the hand (ie object): horizontal or vertical etc?

  • Hey hi, I was just wondering, but what does the 'K' signify in the upper right corner???

  • Hey hi!

    First of all, great work. But when I tried running your source code the video input was not displayed in the window created. I've tried with different camera resolutions and different web cameras as well but to no avail. Also, it's unable to open a video file and work on it.

    Could you please guide me as to what to do?

  • hey...

    great work.

    i visited the link but was unable to run the code. it wasn't detecting my hand. can u give me some solution how i can go about doing it

  • @ank3201

    First of all make sure that the haar training detection works. If it doesn't maybe you should consider making your own haar training. The haar cascade I used works well in well-lighted roomt. If the haar detection works, then the hand shape classification should work as well.

    Please note that I used 640x480 resolution with Logitech Quickcam 9000.

  • Is it easy to add more signs?

  • @LittlePokeDigi hm...it's easy enough I guess...u just have to press A when the binary image shows up then it will add the captured binary image to the A training folder or press B to add the captured image to B training folder. If you want to add more signs that involve movement like J or Z you need to add finger tips tracking, optical flow etc. I haven't got enough free time to continue this project but feel free to modify my code.

  • Hi! i am Aminur from Bangladesh. I want to make a project to recognize Bengali Sign Language. So plz help me. Firstly i have run your code but i need Step by step instruction how the train menu will work.

    Best regards

    Aminur

  • Hello, for some reason the solution file seems to be missing. would be great if you can get back to me regarding this, thanks :)

  • @sanjeven sorry for the late reply I've been busy with my work lately, I've update the info section, there's new link to the complete source code and training files.

  • thanks for the source code. I would like to extend the project and make it better. In case i decide to, I will contact you.

  • I'am about to start project like this but the requirement PL is JAVA. I dobt have any idea how to start it. Do I need to use sensor to accomplish this?? or webcam could be enough???

  • @catubig3710 well I'm not much of a java person. I think for image processing it's best to do it in C++. Using webcam should be enough but u might also combine it with sensors to achieve better result.

  • @nakagawa53 base on what you do.. what kind of sensor do use? because there's a lot of sensor available I don't know what is going to be fitted on my study?? by the way thank you for answering my question.. the info that you have been given is very helpful..

  • @nakagawa53 Hello when I'm about trying to run your program and click training or Start Video I receive a message "NullReferenceException was unhandled" and pointed to this "src_image = highgui.CvLoadImage(file, highgui.CV_LOAD_IMAGE_GRAYSCAL­E);" To be honest JAVA pl is all I know so i dont familiar with this..

  • @catubig3710 sorry for the late reply I've been busy with my work lately, I've update the info section, there's new link to the complete source code and training files.

  • Comment removed

  • I haven't got much time to work on this project lately, so I decide to share the source code (download links added)

    feel free play around with it ^^

  • @nakagawa53 where are the download links...i cannot find them.. please help

  • ei how do u compare the hand sign from the database

  • what edge detection algo did you use?

  • @crsdaryl20 I'm just using thresholding to extract the shape. That's why the program hasn't been able to recognize similar signs to A (i.e S, E, M, N, and T) I tried to use canny...but the result is not very accurate.

  • Thanks for getting back with me, I am taking a class and in a group and we are trying to do this same thing or at least try to do what you have done.

  • I've updated the info section ^^

  • Great video! I was wondering what OpenCV functions you used to compare the life feed to the images in your MS Word document? Do you use a histogram comparison or some other form of comparison? Thanks, and keep up the good work!

  • nakagawa53,

    Hi, I was looking over your ASL video project that you have done. I was wondering what types of Opencv algorithm's you used?

    MrNkuhlenbeck

  • Hi!!

    This is a great video.. sent you a youtube mail... please check..thanks!

  • it seems the you have a predefined area to get the hand image. is it possible to show another video of another area where you get the hand signs? maybe lower or the other hand. thanks... very good still

  • I'm still working on 7 other hand signs and some minor improvements. I'll post another video when it's done ^^

  • badalah.... keren amat...

  • Comment removed

  • great man....

    The lecturers must be speechless...

    LOL

  • hah..presentasi bhasa inggris?...pie ceritane..

  • memperingati wisuda sing k 100 IT d kongkong boso inggrisan karo pak kholid ^^

  • sangar,.,.,.,.,.,TA opo TA iki,.,.ancen DEWA koncoq iki,.,.,

    tp sayang backgroundne nguilani jeh,.,.,

    kwkwkwkwkwkwk,.,.,hahahahahhah­a,.,.,:))

  • wkwkwk suwun2 mw sidang dosene ga ono sing teko macem2 ^_^ soale presentasi boso inggrisan

Loading...
Alert icon
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more