西安邮电大学 机构 数字艺术学院,陕西,西安,710061
纸质出版:2016
移动端阅览
陶美平, 马力, 黄文静, 吴雨隆. 基于无监督特征学习的手势识别方法[J]. 微电子学与计算机, 2016, 33(1): 100-103.
TAO Mei-ping, MA Li, HUANG Wen-jing, et al. A Gesture Recognition Research Based on Unsupervised Feature Learning[J]. 2016, 33(1): 100-103.
针对静态手势图像的分类识别问题
提出了一种将无监督的特征学习和有监督的分类识别相结合的静态手势图像识别方法
通过无监督的稀疏自编码神经网络训练图像小块提取手势图像的边缘特征
并将此边缘特征作为训练分类器的输入
最后提出对训练好的分类器的参数进行调优从而提高准确率.
In order to solve static gesture image classification problems
the paper presents a unsupervised learning process combining the static supervised classification.According to the unsupervised sparse auto-encoder neural network
the image patches were trained to extract the edge feature of the image
and these edge features are the input of a classifier
and finally.And the classifier parameter was used to improve the classification accuracy.
Geetha M, Rohit Menon, Suranya Jayan, et al. Gesture recognition for american sign language with polygon approximation[C]// 2011 IEEE International Conference on Technology for Education. Chengal, Tamil Nadu: IEEE, 2011: 241-245.
Isaacs J, Foo S. Hand pose estimation for american sign language recognition[C]// InSystem Theory, 2004. Proceedings of the Thirty-Sixth Southeastern Symposium on. [s. l. ]: IEEE, 2004: 132-136.
Uebersax D, Gall J, Van den Bergh M, et al. Real-time sign language letter and word recognition from depth data132-1362011[C]// IEEE International Conference on Computer Vision Workshops (ICCV Workshops). Chennai, Tamil Nada: IEEE, 2011: 383-390.
敖道敢. 无监督特征学习结合神经网络应用于图像识别[D]. 广州: 华南理工大学, 2014.
Liwicki S, Everingham M. Automatic recognition of fingerspelled words in british sign language[C]// Computer Vision and Pattern Recognition Workshops, IEEE Compute Society Conference on IEEE. [s. l. ]: IEEE, 2009: 50-57.
王勇, 赵俭辉, 章登义, 等. 基于稀疏自编码深度神经网络的林火图像分类[J]. Computer Engineering and Applications, 2014, 50(24): 173-177. DOI: 173
张勤, 赵健, 孙道达, 等. 一种基于稀疏表示的手势识别算法[J]. 西北大学学报: 自然科学版, 2013, 43(6): 881-884. DOI: 881
0
浏览量
14
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号