Global Journal of NeuroEngineering

Global Journal of NeuroEngineering - Volume 1

Color Detection Based Human – Computer Interface Design

Published on: 20 October 2015

Pages: 1-6

Ahmet Alkan, Mucahid Gunay and Sema Ergun

Department of Electrical and Electronics Engineering, KSU, Kahramanmaras, Turkey.

Abstract: Hand and fingers are one of the most important part of the human body. Hand gesture recognition system received great attention in the recent few years because of its various applications and the ability to interact with machine efficiently through human- computer interaction. Sign language is the basis for personal communication and it can also be used in human-computer/machine interaction. The aim of this study is to propose a human-computer interaction system that can be used for different applications to make life easier. Hand images with different colored fingertips were taken with a webcam and analyzed to extract the meaningful phrases. Each color of the related finger has a meaning, which can be converted to a character of the alphabet. Hand images with five fingers are taken as a five bits code and processed in Matlab. According to the hand finger movements/positions and color conditions occurred, a related character of the alphabet is assigned and printed on the monitor. To have accurate color recognition, several pixels that are selected from the same color on different images are used to train linear discriminant analysis for color classes. After training, system can distinguish/classify each color in the any test image. Then the assigned meanings (characters) related with the defined colors are printed on the monitor. Thus, a hand gesture recognition system was developed to recognize with colorful bands of fingertips and printing the meanings of them on the PC screen. Advantages and drawbacks of the proposed system are discussed. The experiments show that the proposed system can convert hand gestures to alphabetic characters with more than 90% accuracy depending on the stability of the webcam, environment and the user. This system can be thought as a generic applications software that can be used to any particular works on different human computer interactions. The extensive experiments demonstrated that the proposed system can be used for different human computer interface applications.

Keywords: Hand Gesture, Human Computer Interface, Segmentation, LDA.

copyrrightCreative Commons LicensePayza1cross