Vol.28 No.9 袁立等：基于核主元分析法和支持向量机的人耳识别 ·895。 [14 Gao G D.Li SZ,Chan K.Face recogrition by support vee- Recognit,2000:196 tor machines.Proc IEEE Int Conf Autom Face Gesture Ear recognition based on kernel principal component analysis and support vector machine YUAN Li,MU Zhichun,LIU Leiming Infomation Engineering School,University of Science and Technology Beijing.Beijng 100083.China ABSTRACT Some key issues in ear recognition were investigated.Two ear extraction and normalization methods,the mark line(long axis of the outer ear contour)based method and the mark points(the start and end points of the outer ear contour)based method,were proposed for recognizing ear images in the USTB ear database.Based on the analysis of the recent advances in ear recognition methods,the kemel principal component analysis(KPCA)was applied for ear feature extraction,and the support vector ma- chine(SVM)model was applied for ear recognition.The ear recognition rate on USTB ear database with pose variation and lighting variation was 98.7%.The experimental result indicates the effectiveness of this method and proves the feasibility of ear recognition to be used in the field of personal aut hentication. KEY WORDS ear recognition;ear image;image normalization;feature ex traction;kernel principal com- ponent analysis (KPCA);support vector machine(SVM) (上接第829页) Thermodynamic calculations of carbonitrides in V-Ti-N microalloyed steels for non-quenched/tempered seamless oil-well tubes WANG Andong LIU Guoquan,LIU Shengxin,YANG Caifu LI Changrong 1 XIANG Song",HAN Qingli) 1)Materiak Science and Ergineering School.University of Science and Technology Beijing.Beijing 100083.China 2)School of Materials Science and Engineering.Jiangsu Uriversity,Zhenjiang 212013.China 3)Institute for Structural Materials,Central Iron Sted Research Institute,Beijing 100081.China ABSTRACT The precipitation behaviors of carbonitrides in a V-Ti-N microalloyed steel for non- quenched/tempered seamless oil-well tubes were calculated by the equilibrium principle of a three-phase mis- cibility gap including the austenite and tw o carbonitrides.The thermodynamic calculations indicate that the precipitates formed first at 1473Care TiN particles,subsequently some of them formed at high tempera- tures maintain the chemical properties dow n to low temperatures,the others gradually transform to complex (TixVi-x)(CyNi-)carbonitrides.In addition,the precipitates formed at 846 C are V-and C-rich V(CxNI-x)carbonitrides.The formation sequence is verified by experimental data.These results are more consistent with the view point that,the precipitation behavior of vanadium in the austenite matrix below 800 C in medium-carbon V-bearing microalloyed steels plays a great role in controlling the decomposition of austenite. KEY WORDS microalloyed non-quenched/tempered steel;carbo nitrides;precipitation;themmody namic calculation[ 14] Gao G D, Li S Z, Chan K .Face recognition by support vec￾t or machines.Proc IEEE Int Conf Autom Face Gesture Recognit, 2000:196 Ear recognition based on kernel principal component analysis and support vector machine YUAN Li, MU Zhichun , LIU Leiming Inf ormation Engineering School, Universit y of Science and Technology Beijing, Beijing 100083, China ABSTRACT Some key issues in ear recognition w ere investigated .Tw o ear extraction and normalization methods, the mark line ( long axis of the outer ear contour) based method and the mark points ( the start and end points of the outer ear contour) based method, w ere proposed for recognizing ear images in the USTB ear database.Based on the analysis of the recent advances in ear recog nition methods, the kernel principal component analysis ( KPCA) w as applied for ear feature extraction, and the suppo rt vector ma￾chine ( SVM) model was applied for ear recognition .The ear recog nition rate on USTB ear database w ith pose variation and lighting variation was 98.7 %.The experimental result indicates the effectiveness of this method and proves the feasibility of ear recog nition to be used in the field of personal authentication . KEY WORDS ear recog nition ;ear image ;image normalization ;feature ex traction ;kernel principal com￾ponent analy sis ( KPCA) ;suppo rt vector machine ( SVM) ( 上接第 829 页) Thermodynamic calculations of carbonitrides in V-Ti-N microalloyed steels for non-quenched/ tempered seamless oil-well tubes WANG Andong 1, 2) , LIU Guoquan 1) , LIU Shengxin 1) , Y ANG Caifu 3) , LI Changrong 1) , X IANG Song 1) , HAN Qingli 1) 1) Materials Science and Engineering School, University of Science and Technology Beijing, Beijing 100083, China 2) School of Mat erials Science and Engineering, Jiangsu Uni versit y, Zhenjiang 212013, China 3) Institut e for Structural Materials, Cen tral Iron &St eel Research Institute, Beijing 100081, China ABSTRACT The precipitation behaviors of carbonitrides in a V -Ti -N microalloyed steel for non￾quenched/ tempered seamless oil-well tubes w ere calculated by the equilibrium principle of a three-phase mis￾cibility gap including the austenite and tw o carbonitrides .The thermodynamic calculations indicate that the precipitates formed first at 1 473 ℃are TiN particles, subsequently some of them formed at hig h tempera￾tures maintain the chemical properties dow n to low temperatures, the others g radually transform to complex ( Ti xV1 -x ) ( CyN1 -y ) carbonitrides .In addition, the precipitates formed at 846 ℃ are V -and C-rich V( C xN1 -x ) carbonitrides .The formation sequence is verified by experimental data .These results are more consistent w ith the view point that, the precipitation behavio r of vanadium in the austenite matrix below 800 ℃in medium-carbon V-bearing microalloyed steels plays a g reat role in controlling the decomposition of austenite. KEY WORDS microalloyed non-quenched/ tempered steel ;carbo nitrides ;precipitation ;thermody namic calculation Vol.28 No.9 袁 立等:基于核主元分析法和支持向量机的人耳识别 · 895 ·