移动终端手势交互中的图像特征识别技术仿真  

Image Feature Recognition Technology Simulation in Mobile Terminal Gesture Interaction

作　　者：郁涯[1] YU Ya(Baotou Teachers' College,Inner Mongolia University of Science and Technology,Baotou Inner Mongolia 014030,China)

机构地区：[1]内蒙古科技大学包头师范学院

出　　处：《计算机仿真》2019年第10期462-466,共5页Computer Simulation

基　　金：内蒙古自治区高校科学研究项目(NJSY17285)

摘　　要：针对传统的移动设备图像特征识别方法存在识别精度低、运行时间长的问题,提出一种新的移动终端手势交互中图像特征识别方法.将图像中含有特征的部分提取出来,并对其进行去噪处理和冗余消除处理;对提取出的特征区域边界进行腐蚀运算,以提取完整的边界特征信息;利用HMM模型对图像特征分类,完成不同特征的类型识别.分析仿真结果可知,所提方法不仅保证了图像特征的完整性和准确性,而且节约了识别时间,提升了图像特征识别效果,为移动通信以及图像处理技术的发展提供了有力的支持.Traditional recognition methods have low recognition accuracy and long running time. In this article, a method to recognize the image features in mobile terminal gesture interaction was proposed. First of all, we extracted the parts containing the features from the image. And then, we performed noise reduction and redundancy elimination on it. Moreover, we performed corrosion operation on the extracted feature region boundaries, so as to extract the complete boundary feature information. Finally, we used HMM model to classify image features, and thus to complete type identification of different features. Simulation results prove that the proposed method not only ensures the integrity and accuracy of image feature, but also saves the recognition time and improves the recognition effect of image feature, which provides powerful support for the development of mobile communication and image processing technology.

关 键 词：移动终端 手势交互 图像特征 特征识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]