Sparsity has played a key role in compression of signals such as speech, electrocardiogram signals, images, video, etc. The recent thrust in the field has been to solve various inverse problems within the framework of sparsity. The sparsity constraint enables one to find unique solutions even in the case of underdetermined system of equations. The field has strong links to convex optimization, machine learning, linear algebra, Bayesian estimation, dictionary learning, etc. In the first workshop of its kind in the area in India, we shall expose the audience to some basic concepts in sparse signal processing to some state-of-the-art developments in the area including important applications in image processing.

Gesture recognition enables humans to communicate with the machine (HMI) and interact naturally without any mechanical devices. Using the concept of gesture recognition, it is possible to point a finger at the computer screen so that the cursor will move accordingly. This could potentially make conventional input devices such as mouse, keyboards and even touch-screens redundant.

Gesture recognition can be conducted with techniques from computer vision and image processing.

The literature includes ongoing work in the computer vision field on capturing gestures or more general human pose and movements by cameras connected to a computer.

go through this link for how the working of recognize hand gestures

http://www.intorobotics.com/9-opencv-tutorials-hand-gesture-detection-recognition/

go through this link to understand sparse representation

http://www.eecs.berkeley.edu/~yang/courses/ECCV2012/

Hand gesture recognition is one of the applications where Sparse Representation can be applied.

Dear Shangaranarayanee

Thanks for your very nice answer. Is there any sample project in areas that you mentioned?

Dear Shangaranarayanee

I checked the link that explained it with openCV, do you know any matlab sample tutorial? Or it's better if I do it with openCV? What's your opinion?

Dear Dr Selva,

Yes, there are some applications, but how sparse representation can be applied on hand gesture recognition? I want to see some applicable examples.

All the best

A recognition system consists of five parts: image acquisition -> preprocessing > feature extraction -> classification -> post processing.

An image is high dimensional. For example, a 200x200 image contains 40000 pixels! Training a model with such high dimensional data would be very difficult. 

Instead, you may use sparse representation to represent an image, by extracting useful, relevant information from the image. This significantly reduces the dimension but yet most informative information of the image. 

Dear Martin,

Thanks, for your explanation. Then sparse representation is used in feature extraction part, so it is a subset of feature extraction methods, isn't it? If the image is not high dimensional, then sparse representation cannot be used? 

Usually you can think sparse representation is kind of data representation. There are lot of ways or formats to represent data. By considering your application, you may think of a suitable data representation method.

Besides, for computer vision problem like hand gesture recognition, you may consider using deep learning methods. Deep learning are the hottest and the most promising technique for image classification nowadays. 

Dear Giovanni

Do you have any related practical example or project, that has used sparse representation?