Matlab Code for Simple Gesture Recognition
Hand gesture recognition possesses extensive applications in virtual reality, sign language recognition, and computer games. In this paper a novel and real-time approach for hand gesture recognition system is presented. In the suggested method, first, the hand gesture is extracted from the main image by the image segmentation and morphological operation and then is sent to feature extraction stage. In feature extraction stage the Cross-correlation coefficient is applied on the gesture to recognize it.
Platform : Matlab
Delivery : One Working Day
Support : Online Demo ( 2 Hours)
100 in stock
Introduction to Hand Gesture Recognition
Hand gesture recognition possesses extensive applications in virtual reality’ sign language recognition’ and computer games. The direct interface of hand gestures provides us a new way for communicating with the virtual environment. In this paper a novel and real-time approach for hand gesture recognition system is presented. In the suggested method’ first’ the hand gesture is extracted from the main image by the image segmentation and morphological operation and then is sent to feature extraction stage. In feature extraction stage the Cross-correlation coefficient is applied on the gesture to recognize it.
Our approach for hand gesture recognition is based on static mode so; our first problem is to gather a good quality of data since our classifier will classify characters according to it only.We had created our own database for each character of ASL’ which can includes 50 images ie. 10 images for each gestures. During creating a database images captured should have uniform white color background that can be a white color rubber glove on hand as in contrast. We had done this in order to minimize noise and unwanted data so that we can easily do segmentation process. The user has to wear a black color cloth around his arm till wrist from the shoulder so that black color cloth can easily match with the background. Covered arm and the background should be of similar color. for static gestures only. the below shows the sample of our database that are more like a databases.
Our approach for hand gesture recognition is consist ofthree step’
- Image segmentation
- Morphological Filtering;
- Cross-correlation based feature extraction
It is a process in which we convert a RGB image or gray scale image into binary (Black and White) image. This is to be done because we can get only two objects i.e. black and white only in our image. Black with the background and white represents our hand’ Qtsu algorithm is used to convert image into binary . A good segmentation process is that process in which background doesn’t denote any part of hand and hand shouldn’t have any part of background. To obtain best result we have to choose best possible threshold value and segmentation can be done according to that value. The selection of the segmentation technique mainly depends on the type of image on which we have to do processing and Qtsu algorithms  had been tested and work efficiently with our hand gestures data. It is an unsupervised and nonparametric method of segmentation which can select threshold automatically and do segmentation
The segmented images we get after applying the Otsu algorithm are not perfectly processed and further processing is needed in those images to remove unwanted data and errors. There are still some background parts which contain 1s and some hand parts which denote 0s. In order to remove that noise we have to apply morphological filtering techniques on those segmented images. It is necessary to remove these errors as they can create problem in recognition of hand gestures and reduce the system efficiency . So’ morphological filtering is necessary to applied on segmented images and then we get a better smooth’ closed and contour of a gesture. Dilation’ Erosion’ Opening’ and Closing is the basic operators that work in morphological filtering . Sample of pre-processing result is shown in Figure 3 and the experiments are performed in MATLAB. After the pre-processing we get a smooth and better hand gesture which can results a better efficiency .
Now we have to extract feature for gesture recognition. For feature extraction and matching we used Cross correlation Coefficient. In signal processing’ cross correlation is a measure of similarity of two waveforms as a function of a time-lag applied to one of them. In this part we used this function for matching of hand gesture. The cross correlation coefficient is defined as Equation
Our suggestive method have been done on Intel Core i3- 2330M CPU’ 2.20 GHz with 2 GB RAM under Matlab environment. the below shows the face of worked systems In our experiment (with the 98.80% accuracy)’ we observed confusion hand gesture in the recognition phase between some signs.
In this article we proposed a novel and real-time approach for hand gesture recognition system. In the mentioned method’ first’ the hand gesture is extracted from the main image by the image segmentation and morphological operation and then is sent to feature extraction stage. In feature extraction stage the Cross-correlation coefficient is applied on the gesture to recognize it. High recognition rate showed our proposed approach ability in hand gesture recognition.
. J. P. Wachs’ M. K olsch’ H. Stern’ and Y. Edan. Visionbased hand-gesture applications. Communications of the ACM’ 2011′ pp. 54-60.
. M. Heim. Metaphysics of virtual reality. Oxford University Press’ 1993.
. O. A. v. Nierop’ A. v. d. Helm’ K. J. Overbeeke’ and T. J. Djajadiningrat. A natural human hand model. The Visual Computer’ 24(Computer Science):14′ 2008.
. J. Steuer. Defining virtual reality: Dimensions determining telepresence. Journal of Communication’ 1992’pp 73–93
. Andrew Wilson and Aaron Bobick’ “Learning visual behavior for gesture analysis”‘ IEEE Symposium on Computer Vision’ 1995′ pp 1-10.
. A. Julka’ S. Bhargava“A Static Hand gesture recognition Based on Local Contour Sequence”‘ International Journal of Advanced Research in Computer Science and Software Engineerin’ vol. 3′ no 7′ 2013′ pp 918-924.
. M. Panwar and P. Mehra ‘ “Hand gesture recognition for Human Computer Interaction”‘ in Proceedings of IEEE International Conference on Image Information Processing(ICIIP 2011)’ Waknaghat’ India’ November 2011.’ pp 1-6.
. A. Jinda-apiraksa’ W. Pongstiensak’ and Toshiaki Kondo’ “A Simple Shape-Based Approach to Hand gesture recognition“‘ in Proceedings of IEEE International Conference on Electrical Engineering/Electronics Computer Telecommunications and Information Technology (ECTI-CON)’ Pathumthani’ Thailand ‘ 2010’ pp. 851-855.