Review On Human Robot Communication By Using Hand Gesture
Volumn 3

Review On Human Robot Communication By Using Hand Gesture

Pawan Hood                                                                                                

Department of VLSI Engineering                                                                 

JIT College Lonara , Nagpur, India.                                                                                                                                                    


Prof. Nakul Nagpal

Department of VLSI Engineering

JIT College Lonara,  Nagpur, India



A Human robot Interaction (HRI)  between robots and human understands human language and develop a user friendly interface. Gestures a non-verbal form of communication provides the HRI interface. The Goal of gesture recognition is to create a system which can identify specific human gestures and use them to convey information or for device control. Real-time vision-based hand gesture recognition is considered to be more and more feasible for HRI with the help of latest advances in the field of computer vision and pattern recognition. This paper deals with discussion of  techniques  and algorithms related to the gesture recognition. The hand gesture is the most easy and natural way of communication. Hand gesture recognition has the various advantages of able to communicate with the Technology through basic sign language. The gesture will able to reduce the use of most prominent hardware devices which are used to control the activities of robot.

In this paper we present a new algorithm to track and recognize hand gestures for interacting with a robot. This algorithm is based on skin segmentation, feature extraction and matching.

Keywords- Hand gesture segmentation, HCI, ROI, RGB , HSV, YCbCr color space                       


Human gestures constitute a space of motion expressed by the body, face, and/or hands. Among a variety of gestures, hand gesture is the most expressive and the most frequently used. Gestures have been used as an alternative form to communicate with robot in an easy way. This kind of human-machine interfaces would allow a user to control a wide variety of devices through hand gestures. Most work in this research field tries to elude the problem by using markers, marked gloves or requiring a simple background . Glove-based gesture interfaces require the user to wear a cumbersome device, and generally carry a load of cables that connect the device to a computer. A real-time gesture recognition system which can recognize 46 ASL letter spelling alphabet and digits was proposed . This paper introduces a hand gesture recognition system to recognize ‘dynamic gestures’ of which a single gesture is performed in complex background. Unlike previous gesture recognition systems, our system neither uses instrumented glove nor any markers. The new barehanded proposed technique uses only 2D video input. This technique involves hand detection by using skin segmentation, morphological filtering, feature extraction and matching.

Hand Segmentation is the part of computer vision based Natural Human Computer Interaction. Hand tracking and segmentation are the primary steps for any hand gesture recognition system. The aim is to develop efficient and segmentation algorithm. Natural Human Computer Interaction (HCI) is the demand of today’s world. Survey and Sign Language study shows that from various gesture communications modality, the hand gesture is most easy and natural way of communication. Real-time vision-based hand gesture recognition is considered to be more and more feasible for Human-Computer Interaction with the help of latest advances in the field of computer vision and pattern recognition . The concept is to make computer understand human language to develop a user friendly human computer

interfaces (HCI). Making a computer understand human speech, face expressions and hand gestures are some steps towards it. Human Gestures are the non-verbal exchanged information. Since Human gestures are perceived through vision system, it is a subject of great interest for computer vision researchers. Coding of these gestures into machine language demands a complex programming algorithm


In any Hand Segmentation and Tracking system using color model, one of the most important problems in any color image analysis is that of segmentation process. Color resemblance as a relevant criterion an image into significant regions. The basic block diagram for the proposed Model is shown below: This is the model which is adapted in this research work for the purpose of Hand segmentation and Tracking using color model. Preprocessing is the steps in which we get the required output in form of an image. After the process of Hand Segmentation using YCbCr model, a Mix Model Approach is used for skin modeling of segmented Hand. Finally the result of Feature extraction using Region of Interest (ROI) properties is helpful for the purpose of tracking with color.


  1. Start Acquisition
  2. Input: Image using RGB
  3. Convert the RGB image into color space. (Eg. YCbCr, LAB, HSV)
  4. Extract the hand from an image using the color Models by   applying thresholding.
  5. Apply mix model approach for skin modeling (RGB +  HSV), (YCbCr + HSV).
  6. Color Based Segmentation using ROI properties.
  7. Real time color based Tracking.
Figure(1): Proposed Model For Hand Detection and Tracking


For computer images, there form different color spaces depending on different color expression ways . Hand skin has different color ranges in different color spaces. So selecting appropriate color space is the key stage for hand segmentation procedure. For now, most of researchers use RGB, HSV and YCbCr color spaces in the field of skin color detection of hand gesture.


RGB color space is a kind of mixed color space, describing color space through red green blue primary colors, and can represent most of colors. However, RGB color space is not used in most experiments. Because it is difficult to digitize the details and RGB color space mixes hue, luminance and saturation together. Each color channel is highly correlated and dependent, which means current methods can separate them hardly.

B. HSV Color Space

HSV color space is a kind of intensity/saturation/hue color space. HSV color space utilizes hue, saturation and value to express colors. Hue H[0°, 360°] is described by angle. Saturation S(color purity) means the distance to V axis. Value V is luminance. Convert RGB color space to HSV color space.

C. YCbCr Color Space

YCbCr color space is a kind of linear luminance/chromaticity color space. Moreover, it is one of the YUV color space family. In YCbCr color space, Y is luminance. Cb and Cr are chromaticity of blue and red colors. Cb and Cr are two-dimensional independent. Convert RGB color space to YCbCr color space.


Here we use different hand gestures for functioning of robot. In front of web camera we show different hand gestures like single finger, 2 finger, thumb, palm etc. camera will capture the image and process it. Database for this is already stored in computer.


In this paper we proposed a technique for hand gesture detection and robot functioning.  We have gone through various research papers in which various techniques of hand gesture recognition proposed. In all that we find this technique in which hand skin color segmentation is used. The efficiency of this technique is higher than any other techniques and also requires no external  hardware. It is possible to work on real time by continuously capturing images by simple webcam. After processing, feature extraction and hand gesture tracking are done. After that particular signal depends on particular hand gesture sends to robot through serial communication for functioning various tasks.


I would like to thanks all the researchers working on this field who in one way or another guided me , similarly I would also like to thanks  my guide Prof. Nakul Nagpal sir for his contribution and help in writing this paper.


  1. Madhurjya Kumar nayak,Anjan Kumar  Talukdar,”An Adaptive Algorithm for Hand Segmentation and Tracking for continuous Hand Posture Recognition”, IJCA, Mobile and Embedded Technology International Conference,ISSN-0957-8887,vo1-1,2013
  2. H. Duan and Y. Luo, “A Method of Gesture Segmentation Based on Skin Color and Background Difference Method”, Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering, (2013) March 22-23, Hangzhou, China
  3. Julio Cesar Silveira Jacques Junior, Soraia Ruppa Musse, “Crowd  Analysis Using Computer Vision Technique”, IEEE Signal Processing Magazine,ISSN- 10535888, doi:10.1109IMPS2010 9377394, September 2010
  4. Harshith.C, Karthik.R.Shastry, Manoj Ravindran, M.V.V.N.S Srikanth,” Survey on various Gesture Recognition Techniques for Interfacing Machine based on Ambient Intelligence”, (IJCSES) Vol.1,No.2,November 2010
  5. ]Asanterabi Malima, Erol Ozgur, Mujdat Cetin, “A Fast Algorithm for Vision Based Hand Gesture 895965, ISBN: 81381A , September 27,2011.
  6. Sunita Patidar, Dr. C.S.Satsangi,”  Hand Segmentation And Tracking Technique Using Color Models”.International Journal Of Software & Hardware Research In Engineering volume (1) Issue (2),October 2013
  7. Prof. S. M. Agrawal, Prof. Sagar P. More, Prof. M. A. Khan,” Hand Gesture Recognition System Using Image Processing”.Research Article Impact Factor: 0.621 ISSN: 2319-507x Sm Agrawal International Journal Of Pure And Applied Research In Engineering And Technology, 2014; Volume 2 (9): 290-298 IJPRET

Related posts

Asymmetric key based encryption and authentication for file sharing.






Leave a Comment