Development of a New Arabic Sign Language Recognition Using K-Nearest Neighbor Algorithm
Hussein Hadi Owaied, Shaimaa Joudeh · 2012
This paper presents a new Arabic sign language recognition using K-nearest Neighbor algorithm. The algorithm is designed to work as a first level detection upon a series of steps to bring the captured character images into actual spelling. The algorithm acts in a high performance execution which is exactly needed for such type of systems. K-Nearest Neighbor Algorithm and feature extraction are the guidelines of the recognition system, because hand gestures is treated as a block of curves needed to be extracted in the best fit with a predefined character set in the knowledge base. The specific image preprocessing to form a new idea of histogram and a histogram transition table is formed as a hashed string of transformation of block histogram sequence using K-Nearest Neighbor Algorithm. Preparing the knowledge base as a sequence of characters for one time and will and fast easily compared to detecting the character input.