检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:王爱国[1]
出 处:《网络安全技术与应用》2014年第2期29-29,31,共2页Network Security Technology & Application
摘 要:在模式识别的众多领域中,针对于人脸识别的研究与应用逐渐成为重点和难点。尽管近些年众多学者不断钻研并改进人脸识别的算法,但是在复杂光照条件下和不同肤色的人脸识别中仍然存在着重重的不足。尤其是由于现阶段数据的计算速度和存储条件仍然不能很好地去适应优秀的算法对其的要求,因此如何改进算法,提高人脸识别的精度是本文主要研究的问题。本文结合Haar与Gabor特征提出了Adaboost人脸识别算法的改进方法,提高了人脸识别的速度和精度。in many fields of pattern recognition, according to the study and application in face recognition is becoming the focus and difficulty, although many scholars continue to study and improve the face recognition algorithms, but there are still many problems in the complex light conditions and different color face recognition. Especially due to the computational speed and storage conditions at the present stage of the data is still not very good to adapt to the requirements of good algorithm on it, so how to improve the algorithm enables the accuracy of face recognition to achieve maximum becomes the main research problems in the existing hardware condition. Combining the Haar and Gabor features of the improved method of Adaboost face recognition algorithm, improve the face recognition accuracy.
关 键 词:GA LLE Harr GABOR ADABOOST 人脸识别算法
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.117