摘要
提出了一种基于形状特征的字母手势的分类及识别算法。根据手势图像中手指的方向及数目进行粗分类,然后在边界图像及二值图像中提取手势的形状特征向量,进行基于类似度的模板匹配,实现对字母手势的细分类。实验证明,基于形状特征的粗分类能够排除完全不匹配的手势,减少了识别过程中的匹配搜索时间,提高了识别率。
This paper presents a classification and recognition algorithm based on shape feature. Gross classification is carried out according to the direction and number of the finger in the gesture. Sequentially, template matching is applied to implement the fine classification based on the similarity after the shape feature vectors of the gesture are extracted from the boundary image and binary image. The experiment result proves that the gross classification based on shape feature can remove the improper gestures, reduce the matching time and improve the recognition rate.
出处
《计算机工程》
CAS
CSCD
北大核心
2004年第18期130-132,186,共4页
Computer Engineering
基金
上海市自然科学基金资助项目(02ZD14053)
关键词
字母手势
手势识别
边界跟踪
模板匹配
Alphabet gesture
Gesture recognition
Boundary tracking
Template matching
