计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2015年
17期
173-176
,共4页
多尺度分块二值模式%Fisherfaces%人脸识别%最近邻法
多呎度分塊二值模式%Fisherfaces%人臉識彆%最近鄰法
다척도분괴이치모식%Fisherfaces%인검식별%최근린법
Multi-scale Block Local Binary Patterns(MB-LBP)%Fisherfaces%face recognition%K-Nearest Neighbor(KNN)
针对不可控条件对人脸识别的影响,提出一种基于多尺度分块局部二值模式(Multi-scale Block Local Binary Patterns,MB-LBP)和Fisherfaces融合的人脸识别算法。采用适当模块大小的MB-LBP算子提取图像的纹理结构信息,得到相应的特征直方图;通过Fisherfaces方法对MB-LBP提取的特征进行降维和分类;经由最近邻方法进行匹配识别。在ORL和Yale人脸库上进行实验,分别与其他基于LBP和MB-LBP算法的识别效果进行比对。实验结果表明,识别效率显著提高,鲁棒性更好。
針對不可控條件對人臉識彆的影響,提齣一種基于多呎度分塊跼部二值模式(Multi-scale Block Local Binary Patterns,MB-LBP)和Fisherfaces融閤的人臉識彆算法。採用適噹模塊大小的MB-LBP算子提取圖像的紋理結構信息,得到相應的特徵直方圖;通過Fisherfaces方法對MB-LBP提取的特徵進行降維和分類;經由最近鄰方法進行匹配識彆。在ORL和Yale人臉庫上進行實驗,分彆與其他基于LBP和MB-LBP算法的識彆效果進行比對。實驗結果錶明,識彆效率顯著提高,魯棒性更好。
침대불가공조건대인검식별적영향,제출일충기우다척도분괴국부이치모식(Multi-scale Block Local Binary Patterns,MB-LBP)화Fisherfaces융합적인검식별산법。채용괄당모괴대소적MB-LBP산자제취도상적문리결구신식,득도상응적특정직방도;통과Fisherfaces방법대MB-LBP제취적특정진행강유화분류;경유최근린방법진행필배식별。재ORL화Yale인검고상진행실험,분별여기타기우LBP화MB-LBP산법적식별효과진행비대。실험결과표명,식별효솔현저제고,로봉성경호。
A hybrid approach combining Multi-scale Block Local Binary Patterns(MB-LBP)algorithm and Fisherfaces method is proposed for robust face recognition in the uncontrolled conditions. MB-LBP algorithm is utilized to describe and extract texture information of face images, and corresponding histogram vectors is obtained. Fisherfaces algorithm is employed to deal with the dimension and classifier problems. Experiments are conducted with the K-Nearest Neighbor algo-rithm(KNN)on the ORL and Yale face databases respectively, and the proposed approach yields impressive results com-pared to other LBP based and MB-LBP based approaches.