Wednesday, August 22nd, 2012, 6 years ago

Collection of own hand gesture samples – the call for pictures, training method, tool and results


The call for hand gesture samples

Quite long time ago a call for hand gesture samples was made in here, unfortunately this call received few responses making contributions to the samples. Guess if I post free databases of hand gestures for high quality HAAR training then the situation would be quite different – kidding.

Read On…

Monday, August 20th, 2012, 6 years ago

Analysis of openCV’s face detection – the sample, method and performance

opencv face detection

From the picture of face detection in openCV website…

This post is the first of series articles discussing openCV HAAR classifier training and use, as it was implemented in GSoc 2012 project. Here in this post there is no complex algorithms presented, instead, this focuses on requirements and techniques for successful classifier training using openCV.

Read On…

Saturday, August 18th, 2012, 6 years ago

Coming soon – closed palm detection in openCV

binary hand gesturebinary hand gesture2

Coming soon…

Due to the end of this year’s Google Summer of Code 2012 is approaching soon, the development of hand gesture detection plugin for Gstreamer is also going to be packed. As one of important outputs of this project, herewith I forecast the good results of natural hand gesture detection using openCV HAAR training classifiers, mainly including the gestures of fist and closed palm.

Relevant posts regarding to this project, for example, how the call for hand gesture pictures was passively responded and how the classifier was going when insufficient samples were provided, will be published shortly in a series. Topics will cover:

1. Analysis of openCV’s face detection – the sample, method and performance
2. Collection of own hand gesture samples – the call for pictures, training method, tool and results
3. First trial of classifier training – the good and bad
4. Improved classifier training – the changes and lessens learned
5. Dead try – the keys to successful classifier training (samples and parameters)

Tuesday, July 10th, 2012, 6 years ago

Hand gesture detection and recognition using openCV 2

hand gesture detect using openCV - demo

Before the example – why haar classifiers for hand gesture detection

As mentioned in one of early articles such like hand gesture detection and recognition using openCV, there are two main ways to detect hand gestures, including skin colour segmentation and haar classifier training, although recently some feature-detecting algorithms are used to detect hand gestures such like swift. Skin colour segmentation is a dead end – hand colours can be white, or black, or any other colours – depends on the varieties of environmental light conditions. So using a skin colour model (as in The colour range for HSV skin extraction) with a specific colour range can do hand gesture recognition quite well in strict scenarios but this still faces tough challenges for other use.

Read On…

Sunday, May 20th, 2012, 6 years ago

The colour range for HSV skin extraction


The question raised about hsv colour values

Several days ago I got an email from a developer who asked why there were differences in the hsv threshold values between my example and the theoretical values from a paper. Well, my answer is that my example was designed to fit with the specific environment the application was implemented, which could be somehow smaller or larger than the theoretical range.

Read On…

Sunday, May 6th, 2012, 6 years ago

A failed example of hand gesture recognition using openCV haartraining classifiers

haartraining result

This example aimed to provide a good classifier that was able to recognise a flat contract palm in videos, but the results, as demonstrated in the haar performance evaluation, turned out quite disappointed. Here I list the details of this example, including the first stage of sampler extract, creating samples, training samples, and the final evaluation.

Read On…

Wednesday, May 2nd, 2012, 6 years ago

Writing a simple hand gesture picture sampler for classifier training

hand gestures

Progresses in training a classifier for hand gesture recognition is never an easy job, one of the difficulties that needs to overcome is the collection of sample images, both positive and negative. Collecting thousands of sample pictures for each hand gesture is a huge task that requires enormous time and energy on this. Also, inviting so many users to give hand gesture pictures seems a big challenge.

Read On…

Wednesday, April 25th, 2012, 6 years ago

Needed!!! High quality positive/negative hand pictures needed!!!


Give me your hands!!!

As a new hand gesture recognition project is launched recently, there is a strong need to collect a big number of good quality hand pictures – it is a pity I have only two hands. So I need your hands, do not worry, I am not using that for criminal purposes nor for dangerous operations, just need some pictures to train my programme to be capable to recognise beautiful hands like yours.

And the most important thing is, you will be paid to contributing your hand or other people’s high quality pictures of hand. The requirements are simple as follows.

Read On…

Tuesday, April 24th, 2012, 6 years ago

A new hand gesture recognition -related project launched


A new project launching of hand gesture recognition in gstreamer – as the proposal to developing a gstreamer plugin for accurate hand gesture recognition in multimedia streams has been accepted successfully, more practical activities are going to start soon. The expected results of this project is to develop a gstreamer plugin that is capable to support hand gesture index in video streams, also, recognising real time hand gestures in live video stream, thus enabling developers to build up advanced applications such like video playing control using fingers.

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