查询结果:   薛俊韬,纵蕴瑞,杨正瓴.基于改进的YCbCr空间及多特征融合的手势识别[J].计算机应用与软件,2016,33(1):151 - 155.
中文标题
基于改进的YCbCr空间及多特征融合的手势识别
发表栏目
人工智能与识别
摘要点击数
1042
英文标题
GESTURE RECOGNITION BASED ON IMPROVED YCBCR SPACE AND MULTI-FEATURE INTEGRATION
作 者
薛俊韬 纵蕴瑞 杨正瓴 Xue Juntao Zong Yunrui Yang Zhengling
作者单位
天津大学电气与自动化工程学院 天津 300072     
英文单位
School of Electrical and Automation Engineering,Tianjin University,Tianjin 300072,China     
关键词
手势识别 YCbCr颜色空间 Hu矩 傅里叶描述子 BP神经网络
Keywords
Hand gesture recognition YCbCr colour space Hu moment Fourier descriptors BP neural network
基金项目
天津市科技支撑计划重点项目(10ZCKF SF01100);天津市科技型中小企业创新基金项目(13ZXCXGX40400)
作者资料
薛俊韬,副教授,主研领域:图像处理,智能信息处理,智能仪器,模式识别应用。纵蕴瑞,硕士生。杨正瓴,副教授。 。
文章摘要
针对基于视觉的手势识别的复杂性,提出一种基于改进的YCbCr空间及多特征融合的手势识别新方法。首先针对YCbCr颜色空间易受环境因素影响的特点,采用改进的YCbCr椭圆聚类肤色模型的手势分割方法提取手势区域;然后按手势图像外接矩形的宽高比和手指个数进行粗分类,再提取手势的Hu矩和傅里叶描述子构建融合特征,并将融合特征输入BP神经网络进行训练识别;最后综合粗分类和BP神经网络的结果进行手势判别。实验结果表明,该方法在保证实时性的同时具有较高的识别率。
Abstract
Because of the complexity of vision-based hand gesture recognition, we presented a novel hand gesture recognition algorithm which is based on improved YCbCr space and multi-feature integration. Firstly, considering the characteristic that YCbCr colour space is prone to the influence of environmental factors, the algorithm adopts the improved hand gesture segmentation method using YCbCr elliptic clustering skin colour model to extract hand gesture region. Then it makes initial classification according to the aspect ratio of envelop rectangle of hand gesture image and the number of fingers, and extracts Hu moment and Fourier descriptor of hand gesture to build integration features, which are put into BP neural network for training and recognition. Finally the results of the initial classification and BP neural network are combined for hand gesture recognition. Experimental results showed that the proposed method could ensure the real-time performances while getting a quite higher recognition rate.
下载PDF全文