电子与信息学报
電子與信息學報
전자여신식학보
JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY
2014年
6期
1327-1333
,共7页
人脸识别%纹理特征%局部二值模式%自适应阈值%自适应加权
人臉識彆%紋理特徵%跼部二值模式%自適應閾值%自適應加權
인검식별%문리특정%국부이치모식%자괄응역치%자괄응가권
Face recognition%Texture features%Local Binary Pattern (LBP)%Adaptive threshold%Adaptively weighted
针对局部二值模式(LBP)和中心对称局部二值模式(CS-LBP)方法描述图像纹理特征时,阈值不能自动选取并且图像中不同子块的贡献也没有进行区分的问题,该文提出一种自适应阈值及加权的局部二值模式方法。首先,将图像进行分块,采用设定的自适应阈值提取每个子块的LBP或CS-LBP纹理直方图;然后,将各子图像的信息熵作为直方图的加权依据,对每个子块对应的直方图进行自适应加权,并将所有子块的直方图连接成最终的纹理特征;最后,通过快速计算图像均值加快了算法的计算速度。在人脸数据库上进行的实验证明,利用该文提出的方法提取纹理特征,并结合最近邻分类法可以得到较高的正确识别率。
針對跼部二值模式(LBP)和中心對稱跼部二值模式(CS-LBP)方法描述圖像紋理特徵時,閾值不能自動選取併且圖像中不同子塊的貢獻也沒有進行區分的問題,該文提齣一種自適應閾值及加權的跼部二值模式方法。首先,將圖像進行分塊,採用設定的自適應閾值提取每箇子塊的LBP或CS-LBP紋理直方圖;然後,將各子圖像的信息熵作為直方圖的加權依據,對每箇子塊對應的直方圖進行自適應加權,併將所有子塊的直方圖連接成最終的紋理特徵;最後,通過快速計算圖像均值加快瞭算法的計算速度。在人臉數據庫上進行的實驗證明,利用該文提齣的方法提取紋理特徵,併結閤最近鄰分類法可以得到較高的正確識彆率。
침대국부이치모식(LBP)화중심대칭국부이치모식(CS-LBP)방법묘술도상문리특정시,역치불능자동선취병차도상중불동자괴적공헌야몰유진행구분적문제,해문제출일충자괄응역치급가권적국부이치모식방법。수선,장도상진행분괴,채용설정적자괄응역치제취매개자괴적LBP혹CS-LBP문리직방도;연후,장각자도상적신식적작위직방도적가권의거,대매개자괴대응적직방도진행자괄응가권,병장소유자괴적직방도련접성최종적문리특정;최후,통과쾌속계산도상균치가쾌료산법적계산속도。재인검수거고상진행적실험증명,이용해문제출적방법제취문리특정,병결합최근린분류법가이득도교고적정학식별솔。
A new method called weighted Local Binary Pattern (LBP) with adaptive threshold is proposed in this paper to address the shortcomings of LBP and Center Symmetric Local Binary Pattern (CS-LBP), using unflexible threshold and non-discriminating respective sub-patches based on different textures. Firstly, the image is divided into several sub-images and LBP or CS-LBP texture histograms are extracted respectively from each sub-image based on the adaptive threshold. Then, the proposed algorithm adaptively weighted the LBP or CS-LBP histograms of sub-patches with information entropy as their basis and connected all histograms serially to create a final texture descriptor. Finally, the improved efficiency of the proposed algorithm is achieved by speeding up the computation of the average of an image. The experimental results by face databases show that a higher recognition accuracy can be obtained by employing the proposed method with nearest neighbor classification.