Institutional Repository of Coll Comp & Commun
Hand gesture modeling and high level feature extraction based on structure feature point | |
Zhang, Moyi![]() ![]() ![]() | |
2015-10-23 | |
发表期刊 | Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)
![]() |
ISSN | 16714512 |
卷号 | 43期号:10页码:87-91 |
摘要 | In monocular environment, a method to extract the structure feature points was proposed to improve the accuracy of gesture features detection, and then the extracted structure feature points was used to build and optimize the hand gesture model to extract the high level features. The gradient map was analyzed to give the definition of the smoothing points, no-smoothing points, as well as the conflict calculation method and the structure feature extraction method, to give the proper description of the local structure of the image. 2D (two dimension) gesture model was built to replace the 3D (three dimension) model. Based on the extracted structure feature point, combining the greedy algorithm and RANSAC algorithm, the optimized solution of the model was obtained to locate the palm, fingers and fingertip position. Experiments show that the method has good robustness even when the hand gesture processing result is rough, and it is not sensitive to the segmented edge, so it can effectively reduce the misjudgment caused by the interference point of traditional curvature algorithm. © 2015, Huazhong University of Science and Technology. All right reserved. |
关键词 | Extraction Image processing Conflict value Curvature algorithms Gesture features detections Hand gesture High-level feature extractions High-level features Optimized solutions Structure features |
DOI | 10.13245/j.hust.151017 |
收录类别 | EI |
语种 | 中文 |
出版者 | Huazhong University of Science and Technology |
EI入藏号 | 20155001654013 |
EI主题词 | Feature extraction |
EI分类号 | 802.3 Chemical Operations |
来源库 | Compendex |
分类代码 | 802.3 Chemical Operations |
引用统计 | 无
|
文献类型 | 期刊论文 |
条目标识符 | https://ir.lut.edu.cn/handle/2XXMBERH/112390 |
专题 | 计算机与通信学院 |
作者单位 | School of Computer and Communication, Lanzhou University of Technology, Lanzhou; 730050, China |
第一作者单位 | 兰州理工大学 |
第一作者的第一单位 | 兰州理工大学 |
推荐引用方式 GB/T 7714 | Zhang, Moyi,Zhang, Qiuyu,Lu, Junchi,et al. Hand gesture modeling and high level feature extraction based on structure feature point[J]. Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition),2015,43(10):87-91. |
APA | Zhang, Moyi,Zhang, Qiuyu,Lu, Junchi,&Duan, Hongxiang.(2015).Hand gesture modeling and high level feature extraction based on structure feature point.Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition),43(10),87-91. |
MLA | Zhang, Moyi,et al."Hand gesture modeling and high level feature extraction based on structure feature point".Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) 43.10(2015):87-91. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论