佳木斯大学学报(自然科学版)
佳木斯大學學報(自然科學版)
가목사대학학보(자연과학판)
JOURNAL OF JIAMUSI UNIVERSITY (NATURAL SCIENCE EDITION)
2015年
1期
109-112
,共4页
小波树%二维主元分析%人脸识别%小波变换
小波樹%二維主元分析%人臉識彆%小波變換
소파수%이유주원분석%인검식별%소파변환
wavelet tree%two -dimensional principal component analysis%face recognition%wavelet transform
为提高人脸识别率,结合小波树和子空间分析中的二维主元分析,提出基于小波树和二维主元分析的人脸识别算法( WTMPCA ).该算法先利用小波变换公式,在人脸图像上计算出一个小波近似分量和三个细节分量;分层次重组小波近似分量,得到新样本集;最后在此样本集上使用二维主元分析进行人脸识别.ORL和CAS-PEAL-R1人脸库的实验结果表明,与基于图像矩阵的二维主元分析(2D-PCA)相比较,WTMPCA方法的人脸识别率为96%,对光照条件、脸部表情变化有良好的鲁棒性.
為提高人臉識彆率,結閤小波樹和子空間分析中的二維主元分析,提齣基于小波樹和二維主元分析的人臉識彆算法( WTMPCA ).該算法先利用小波變換公式,在人臉圖像上計算齣一箇小波近似分量和三箇細節分量;分層次重組小波近似分量,得到新樣本集;最後在此樣本集上使用二維主元分析進行人臉識彆.ORL和CAS-PEAL-R1人臉庫的實驗結果錶明,與基于圖像矩陣的二維主元分析(2D-PCA)相比較,WTMPCA方法的人臉識彆率為96%,對光照條件、臉部錶情變化有良好的魯棒性.
위제고인검식별솔,결합소파수화자공간분석중적이유주원분석,제출기우소파수화이유주원분석적인검식별산법( WTMPCA ).해산법선이용소파변환공식,재인검도상상계산출일개소파근사분량화삼개세절분량;분층차중조소파근사분량,득도신양본집;최후재차양본집상사용이유주원분석진행인검식별.ORL화CAS-PEAL-R1인검고적실험결과표명,여기우도상구진적이유주원분석(2D-PCA)상비교,WTMPCA방법적인검식별솔위96%,대광조조건、검부표정변화유량호적로봉성.
In order to improve the face recognition rate , this paper proposed face recognition based on wavelet tree and two -dimensional principal component analysis (WTMPCA).The algorithm calculated a wave-let approximation coefficient and three detail components in face images with the help of the wavelet transform formula.Then, the wavelet approximation coefficients were recombine hierarchically .In the end, a new sample set and complete face recognition was gotten using two -dimensional principal component analysis .The simula-tion results of experiments on the ORL and CAS -PEAL-R1 face database show that compared with two -di-mensional principal component analysis (2D-PCA) based on image matrix , the new algorithm has a high recog-nition rate of 96%and better robustness to illumination condition and face expression change .