Vision-Based Algorithm for Real-Time Hand Posture Recognition
نویسندگان
چکیده
Importance of human-computer interaction (HCI) systems is increasing since they revolutionized the way people interact with computers. Gesture and posture analysis, especially hand gesture and posture recognition, is one of the more recent areas in the HCI with ever widening field of applications. In this paper we propose an algorithm for hand posture recognition that is based on skin detection and Hu moments. Our algorithm is invariant to the hand position and experiments proved it to be robust with high percentage of posture recognition. Algorithm works in real-time and can successfully be used in variety of applications. Key-words: Hand posture recognition, Hand segmentation, Posture-based HCI, Image processing
منابع مشابه
A Real Time Traffic Sign Detection and Recognition Algorithm based on Super Fuzzy Set
Advanced Driver Assistance Systems (ADAS) benefit from current infrastructure to discern environmental information. Traffic signs are global guidelines which inform drivers from near characteristics of paths ahead. Traffic Sign Recognition (TSR) system is an ADAS that recognize traffic signs in images captured from road and show information as an adviser or transmit them to other ADASs. In this...
متن کاملA Tele-operated Gesture Recognition Mobile Robot using a Stereo Vision
In this paper, a tele-operated gesture recognition mobile robot using a stereo vision is represented. We propose a real-time face and hand classification and 3D position extraction using a stereo vision embedded system. To obtain the disparity image, we used the stereo vision process on FPGA and developed the embedded system to obtain the image sequence for basic image processing. Then we appli...
متن کاملFingertip Tracking and Hand Gesture Recognition by 3D Vision
This paper introduces an algorithm to track palm and fingertips based on images with depth data in real-time. Some meaningful hand gesture is then recognized by the detected palm and fingertips. The images with depth information are first captured by a Kinect camera. Then foreground and background are separated to pick up the potential hand. The fingertips are then detected by the curvature of ...
متن کاملControlling Computer Music Player Based On Human Hand Activity by Using CAMSHIFT Algorithm
The intent of the paper is to apply computer vision technique to control the music player by CAMSHIFT algorithm. Based on the human hand activity, gesture and posture recognition are used to communicate with computers. Gesture is the physical movement of a hand, expressive of an idea. Posture is the static morph of a hand. In this paper skin colour segmentation is used for hand detection, after...
متن کاملUsing A KNN and MOG Based Algorithm for Static Hand Posture Recognition
Several machine learning algorithms have been applied to the problem of static hand posture recognition. K-nearesr neighbor (KNN) performs very well in flexible posture recognition, but speed and memory requirements of the algorithm make it difficult to use in real time applications. In this paper we propose an approach to speed up the KNN without changing its behavior. We use the mixture of ga...
متن کامل