Air-writing Recognition of Farsi Digits based on Depth Image

Recognition of hand writing on paper, on display or on air is an important challenge in computer vision. Air-writing recocognition is especially difficult due to three dimentionality of space. In this research work the aim is recognizing persian digits which are written in air in front of a Kineckt sensor using a fingertip and the sensor can detect the digit using its depth image. For hand and fingertip segmentation we use K-means algorithm. To extract the features we use a novel method called slope variation detection, and to classify the features Hidden Markov Models (HMM) is used. Recognition rate of Persian digits using a local database with 10 times mutual validation is 96%. This novel method was compared with some other similar methods in the literature . The results confirm relative priority of the proposed method.