高阶NMI值的字母手势识别  

Recognition of Alphabet Gesture Based on Orientation and High Order NMI Feature

作　　者：戴俊[1] 葛元[1] 王林泉[1] 

机构地区：[1]上海海运学院计算机系,上海200135

出　　处：《计算机工程》2005年第14期164-166,共3页Computer Engineering

基　　金：上海市自然科学基金资助项目(02ZD14053)

摘　　要：提出了基于手势伸展方向以及手势图像高阶NMI值的特征向量进行识别分类的算法。首先,对采集到的手势图像进行预处理与二值化,然后按手势的伸展方向进行粗分类,之后,对每幅图像提取图像的1阶和4阶NMI值,这样将一幅图像表示成一个有17维分量的特征向量。识别时用k近邻原则进行判别,识别率达到86.6%。An alphabet gesture recognition algorithm based on orientation of gesture and high-order NMI feature of the image is presented. Firstly, the images are pre-processed to get the binary image. Then the system grossly classifies the alphabet gestures according to the gesture orientation and proceeds to calculate the high-order NMI feature of the gesture image. Lastly it recognizes the unknown samples by orientation and NMI feature. Experiments show that this method is efficacious and easy to operate.

关 键 词：手势识别 手势伸展方向 图像高阶NMI 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]