what kind of approach can be used for recognize hand signs?

asked 2014-01-22 11:52:44 -0600

Parthi
1 ●2

updated 2014-01-22 22:12:18 -0600

what approach is used in the below video to recognition for hand signs?

why is he using cvblob? how did he separate his head from hand ( it has different colors) how to actually train the signs using the SVM ? how much time will it consume ?

Edit:My questions

how to recognize signs used in a sign language ? do we need store the signs as files in a Haar-like database? is it possible?
if we skin color recognition is used ? how to identify the signs?

edit retag flag offensive close merge delete

Comments

1

hi, parthi, your youtube link is no great help, most ppl won't even look at it.

chances for feedback / answers are much better, if you write down your problem.

berak ( 2014-01-22 13:09:34 -0600 )edit

add a comment

1

answered 2014-01-22 16:08:08 -0600

Vikas
11

Instead of cvblob, you can use findContours in opencv to find blobs of same color.

Use face detection to separate head from hands.

You will have to train one vs all SVM for this multiclass problem.

edit flag offensive delete link

Comments

1

true, cvblob is totally outdated / overrated nowadays

berak ( 2014-01-22 16:16:20 -0600 )edit

I do not agree on the one vs all SVM approach, you can perfectly run a single SVM with yes or no for each sign, then look at which positive responses show the highest confidence :)

StevenPuttemans ( 2014-01-23 03:56:10 -0600 )edit

add a comment

1

answered 2014-01-22 21:09:07 -0600

MRDaniel
489 ●3 ●9 ●25

Skin detection to create a mask. Use a classifier for pixels in hand such as EM() to create a cleaner map (optional). Find contour of hand.

1) Compare to known shapes using matchShapes().

2) Create a database of known shapes find some features to classify. Train classifier and then use for comparison on any new shapes found with this method.

edit flag offensive delete link

Comments

is there a link or a tutorial for step 2 . Exactly how to create that database and train the classifier

Parthi ( 2014-01-22 22:14:29 -0600 )edit

I suggest you go read some machine learning book about classifiers :) google or search this forum for SVM, cascade classification, Viola & Jones, naive bayes, regression trees, ... all possible approaches for your problem!

StevenPuttemans ( 2014-01-23 03:57:31 -0600 )edit

add a comment

what kind of approach can be used for recognize hand signs?

Comments

2 answers

Comments

Comments

Links

Question Tools

Stats

Related questions

what kind of approach can be used for recognize hand signs? edit

Comments

2 answers

Comments

Comments

Links

Question Tools

Stats

Related questions

what kind of approach can be used for recognize hand signs?