欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
Mohammed等人提出了一种基于小波变换和极端学习机的人脸识别方法,该方法分为3步,首先对人脸图像做小波变换,然后用双向二维主成分分析进行特征提取,最后用极端学习机进行分类识别.但实验研究发现,用小波变换的低频子图直接作为极端学习机的输入,就可以达到非常好的识别效果,即第2步的特征提取是没有必要的.在3个人脸数据库上与Mohammed等人提出的方法进行了实验比较,实验结果显示本文提出的方法简单有效.
英文摘要：
Based on wavelet transform and extreme learning machine,Mohammed etc.proposed a face recognition method which consist of three steps,firstly the face images are transformed with wavelet, senondly the features are extracted with bidirectional two dimensional principal component analyses,final- ly face recognition is completed with extreme learning machine.We find with experiments that excellent recognition results can be obtained directly by inputting the wavelet sub-image of low frequency into ex- treme learning machine,in other words,the second step is unnecessary.Experimental comparisons with the method proposed by Mohammed etc.on 3face databases are conducted,the experimental results show that the proposed method is simple and efficient.
同期刊论文项目
同项目期刊论文
Local similarity and diversity preserving discriminant projection for face and handwriting digits re
A study on relationship between generalization abilities and fuzziness of base classifiers in ensemb
An improved differential evolution and its application to determining feature weights in similarity-
期刊信息
位置：