|
|||||
|
|
| 基于卷积神经网络的手势识别初探 | |
| 引用本文： | 蔡娟,蔡坚勇,廖晓东,黄海涛,丁侨俊.基于卷积神经网络的手势识别初探[J].计算机系统应用,2015,24(4):113-117. |
| 作者姓名： | 蔡娟 蔡坚勇 廖晓东 黄海涛 丁侨俊 |
| 作者单位： | 1. 福建师范大学光电与信息工程学院,福州,350007 2. 福建师范大学光电与信息工程学院，福州 350007; 福建师范大学医学光电科学与技术教育部重点实验室，福州 350007; 福建师范大学福建省光子技术重点实验室，福州 350007; 福建师范大学智能光电系统工程研究中心，福州 350007 3. 福建师范大学光电与信息工程学院，福州 350007; 福建师范大学智能光电系统工程研究中心，福州 350007 |
| 摘 要： | 提出一种用于手势识别的新算法，使用卷积神经网络来进行手势的识别。该算法避免了手势复杂的前期预处理，可以直接输入原始的手势图像。卷积神经网络具有局部感知区域、层次结构化、特征抽取和分类过程等特点，在图像识别领域获得广泛的应用。试验结果表明，该方法能识别多种手势，精度较高且复杂度较小，具有很好的鲁棒性，也克服传统算法的诸多固有缺点。 |
| 关 键 词： | 手势识别 卷积神经网络 局部感知 特征抽取 鲁棒性 |
| 收稿时间： | 2014/7/28 0:00:00 |
| 修稿时间： | 2014/9/29 0:00:00 |
Preliminary Study on Hand Gesture Recognition Based on Convolutional Neural Network |
|
| CAI Juan,CAI Jian-Yong,LIAO Xiao-Dong,HUANG Hai-Tao and DING Qiao-Jun.Preliminary Study on Hand Gesture Recognition Based on Convolutional Neural Network[J].Computer Systems& Applications,2015,24(4):113-117. | |
| Authors: | CAI Juan CAI Jian-Yong LIAO Xiao-Dong HUANG Hai-Tao and DING Qiao-Jun |
| Affiliation: | School of Electronic College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, China;School of Electronic College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, China;Key Laboratory of Optoelectronic Science and Technology for Medicine Ministry of Education, Fujian Normal University, Fuzhou 350007, China;Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou 350007, China;Intelligent Optoelectronic Systems Research Centre, Fujian Normal University, Fuzhou 350007, China;School of Electronic College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, China;Intelligent Optoelectronic Systems Research Centre, Fujian Normal University, Fuzhou 350007, China;School of Electronic College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, China;School of Electronic College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, China |
| Abstract: | The paper proposed a new algorithm used for hand gesture recognition which based on the convolutional neural network. The method not only avoids the hand gesture in the early period of the complex pretreatment, but also can directly input the gesture of original image. The convolutional neural network is characterized by local receptive field, hierarchical structure, global learning for feature extraction and classical. It has been applied to many image recognition tasks. Experimental results showed that the multi-class hand gestures can be recognized with high accuracy, small complexity and good robustness, while the inherent shortcomings of the traditional algorithm are overcame. |
| Keywords: | hand gesture recognition convolutional neural network local receptive feature extraction good robustness |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《计算机系统应用》浏览原始摘要信息 | |
| 点击此处可从《计算机系统应用》下载全文 | |