计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2014年
23期
163-166,224
,共5页
人耳识别%局部线性嵌入%Gabor小波%特征提取
人耳識彆%跼部線性嵌入%Gabor小波%特徵提取
인이식별%국부선성감입%Gabor소파%특정제취
ear recognition%locally linear embedding%Gabor wavelets%features extraction
针对LLE算法对姿态变化和近邻点敏感的缺陷，提了一种融合Gabor小波和改进LLE算法的人耳识别算法（Gabor-ILLE）。该算法通过Gabor变换提取人耳特征，并对Gabor初始特征融合，采用改进LLE对特征进行降维，选择最有利于人耳识别的Gabor特征，采用K近邻算法建立人耳分类器实现人耳识别，并采用USTB3人耳图像库进行仿真实验。相对于参比人耳算法，Gabor-ILLE获得了更高的人耳识别率，实验结果验证了Gabor-ILLE算法的有效性。
針對LLE算法對姿態變化和近鄰點敏感的缺陷，提瞭一種融閤Gabor小波和改進LLE算法的人耳識彆算法（Gabor-ILLE）。該算法通過Gabor變換提取人耳特徵，併對Gabor初始特徵融閤，採用改進LLE對特徵進行降維，選擇最有利于人耳識彆的Gabor特徵，採用K近鄰算法建立人耳分類器實現人耳識彆，併採用USTB3人耳圖像庫進行倣真實驗。相對于參比人耳算法，Gabor-ILLE穫得瞭更高的人耳識彆率，實驗結果驗證瞭Gabor-ILLE算法的有效性。
침대LLE산법대자태변화화근린점민감적결함，제료일충융합Gabor소파화개진LLE산법적인이식별산법（Gabor-ILLE）。해산법통과Gabor변환제취인이특정，병대Gabor초시특정융합，채용개진LLE대특정진행강유，선택최유리우인이식별적Gabor특정，채용K근린산법건립인이분류기실현인이식별，병채용USTB3인이도상고진행방진실험。상대우삼비인이산법，Gabor-ILLE획득료경고적인이식별솔，실험결과험증료Gabor-ILLE산법적유효성。
LLE algorithm is very sensitive to the change of attitude and neighbor points, a novel ear recognition algorithm (Gabor-ILLE)based on Gabor wavelet and improved LLE algorithm is proposed in this paper. The ear features are ex-tracted by Gabor transform, and then the improved LLE is used to reduce dimensionality of features and select the optimal Gabor features of ear recognition, KNN is used to establish the classifier of human ear recognition, and the simulation ex-periment is carried out on USTB3 ear images. Compared with the reference methods, the proposed algorithm has obtained higher ear recognition rate, and the experimental results verify the effectiveness of the Gabor-ILLE algorithm.
