 二维码(扫一下试试看!) | 基于栈式稀疏自编码多特征融合的快速手势识别方法 | A Fast Gesture Recognition Method Based on Stacked Sparse Autoencoders Multi-Feature Fusion | 投稿时间:2018-01-21 | DOI:10.15918/j.tbit1001-0645.2019.06.014 | 中文关键词:YCbCr颜色空间模型手势分割栈式稀疏自编码多特征融合手势识别 | English Keywords:YCbCr color space modelgesture segmentationstacked sparse autoencodersmulti-feature fusiongesture recognition | 基金项目:国家自然科学基金资助项目(61572344);虚拟现实技术与系统国家重点实验室开放基金资助项目(BUAA-VR-17KF-15,BUAA-VR-17KF-14;BUAA-VR-16KF-13);山西省回国留学人员科研资助项目(2016-038) | | 摘要点击次数:788 | 全文下载次数:551 | 中文摘要: | 针对复杂背景下手势分割提取效果不佳、图像识别率不高、识别困难等问题,研究多特征融合的快速手势识别方法.利用YCbCr颜色空间模型,构建肤色分布模型,从复杂背景中去除大部分非肤色的干扰,从而实现手势分割;接着采用5层栈式稀疏自编码网络框架,分别提取手势感兴趣区域(region of interest,ROI)的纹理图像、形状图像和显著视觉图像作为自编码网络输入,将提取到的不同类型的特征进行线性融合;最后使用基于径向基核函数(radial basis function,RBF)的支持向量机(support vector machine,SVM)分类器进行融合特征数据分类,从而实现不同类型的手势识别.实验结果表明,相比其他手势识别方法,本文方法识别率较高,提取特征更具有代表性,平均识别率可达95.05%. | English Summary: | In order to solve the pro blem of poor gesture segmentation extraction, low image recognition rate and difficult recognition, a multi-feature fusion method was studied for fast gesture recognition. Firstly, a skin color distribution model was established based on the YCbCr color space model, removing the most of non-skin color interference from the complex background, so as to realize the gesture segmentation. And then, taking the texture image of the gesture ROI (region of interest), the shape image and the significant visual image as self-coding network input, the different types of features were linearly merged according as 5-layer stacked sparse autoencoders network framework. Finally, a SVM (support vector machine) classifier based on RBF (radial basis function) kernel function was used to classify the characteristic data, so as to realize the gesture recognition for different types of gestures. Experimental results show that, compared with other gesture recognition methods, the recognition rate is higher and the extraction characteristics are more representative. The average recognition rate can reach 95.05%. | 查看全文查看/发表评论下载PDF阅读器 | |
胡忠铠,高昆,豆泽阳,周颖婕,巩学美.基于全变分正则最大后验估计的高光谱图像亚像元快速定位方法[J].北京理工大学学报(自然科学版),2019,39(8):870~875.HUZhong-kai,GAOKun,DOUZe-yang,ZHOUYing-jie,GONGXue-mei.AFastMeth ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21韩先君,刘艳丽,杨红雨.基于生成对抗网络的人脸图像彩色化方法[J].北京理工大学学报(自然科学版),2019,39(12):1285~1291.HANXian-jun,LIUYan-li,YANGHong-yu.FaceImageColorizationBasedonGenerativeAdvers ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21张健源,朱星星,张旭明.基于统计形变模型的多模医学图像非刚性配准方法研究[J].北京理工大学学报(自然科学版),2019,39(S1):52~56.ZHANGJian-yuan,ZHUXing-xing,ZHANGXu-ming.StatisticalDeformationModelBasedNon ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21兰艳成,张旭明.基于电磁定位仪的超声图像中穿刺针实时跟踪软件开发[J].北京理工大学学报(自然科学版),2019,39(S1):48~51.LANYan-cheng,ZHANGXu-ming.DevelopmentofReal-TimeTrackingSoftwareforPunctureNeedl ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21丁明跃,冯瑞敏,黄晶,陈钊正,李晓庆.高频复合超声扫描探针显微镜声学图像融合研究[J].北京理工大学学报(自然科学版),2019,39(S1):57~61.DINGMing-yue,FENGRui-min,HUANGJing,CHENZhao-zheng,LIXiao-qing.Researchon ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21丛洋,梁洪,栾宽.空间点集配准算法研究[J].北京理工大学学报(自然科学版),2019,39(S1):77~82.CONGYang,LIANGHong,LUANKuan.StudyontheRegistrationAlgorithmofSpatialPointSets[J].Transactions ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21栾宽,王琭璐,刘小龙,袁浩,李金.基于三维图像的髓内针钉孔定位方法[J].北京理工大学学报(自然科学版),2019,39(S1):71~76.LUANKuan,WANGLu-lu,LIUXiao-long,YUANHao,LIJin.LocalizationofHolesonIntramedulla ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21程坤,时永刚,李依桐,刘志文.基于生成对抗网络的海马子区图像分割[J].北京理工大学学报(自然科学版),2019,39(S1):159~163.CHENGKun,SHIYong-gang,LIYi-tong,LIUZhi-wen.ImageSegmentationofHippocampalSubfi ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21秦明,陆耀.基于交叉协方差子空间估计的前景检测方法[J].北京理工大学学报(自然科学版),2018,38(1):91~95.QINMing,LUYao.AForegroundDetectionMethodBasedonCross-CovarianceSubspaceEstimation[J].Tra ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21麻振华,沈丛丛,张新.强C*-代数值度量空间及其不动点定理[J].北京理工大学学报(自然科学版),2018,38(1):108~110.MAZhen-hua,SHENCong-cong,ZHANGXin.StrongC*-Algebra-ValuedMetricSpaceandaFixedPoint ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21
| |