• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ºÎºÐ°ø°£°ú LVQ ºÐ·ù±â¿¡ ±â¹ÝÇÑ ½Ç½Ã°£ ¾ó±¼ ÀνÄ
¿µ¹®Á¦¸ñ(English Title) Real-Time Face Recognition Based on Subspace and LVQ Classifier
ÀúÀÚ(Author) ±Ç¿À·û   ¹Î°æÇÊ   ÀüÁØö   Kwon Ohryun   Min Kyongpil   Chun Junchul  
¿ø¹®¼ö·Ïó(Citation) VOL 08 NO. 03 PP. 0019 ~ 0032 (2007. 06)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ½Ç½Ã°£ ¾ó±¼ÀÎÁõ ½Ã½ºÅÛÀÇ ±¸ÃàÀ» À§ÇÑ LVQ ½Å°æ¸Á ±â¹ÝÀÇ »õ·Î¿î ¾ó±¼ ÀÎ½Ä ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ±âÁ¸ÀÇ ¿¬±¸¿¡¼­ PCA, LDA º¯È¯ÀÌ ¸¹ÀÌ Àû¿ëµÇ¸ç ½Å°æ¸ÁÀ» °áÇÕÇÑ ÇüÅ°¡ Á¦¾ÈµÇ°í ÀÖÁö¸¸ ½Å°æ¸Á ÇнÀ ½Ã°£ÀÌ ¿À·¡ °É¸®´Â ´ÜÁ¡À» °¡Áö°í ÀÖ´Ù. LVQ ½Å°æ¸ÁÀº ÇнÀ ½Ã°£ÀÌ Âª°í Ŭ·¡½º°£ÀÇ ºÐ¸®µµ¸¦ ÃÖ´ëÈ­ÇÒ ¼ö ÀÖ´Â ±³»çÇнÀ¹æ¹ýÀÌ´Ù. µû¶ó¼­, º» ³í¹®¿¡¼­ Á¦¾ÈµÈ ¹æ¹ýÀº µ¿¿µ»óÀ¸·ÎºÎÅÍ ½Ç½Ã°£À¸·Î ÀԷµǴ ¾ó±¼¿µ»óÀ» PCA¿Í LDAº¯È¯À» ¼øÂ÷ÀûÀ¸·Î Àû¿ëÇÏ¿© ºÎºÐ°ø°£»óÀÇ º¯È¯µÈ Ư¡º¤ÅͷκÎÅÍ LVQ ½Å°æ¸ÁÀÇ ÇнÀÀ» ÅëÇÏ¿© ¾ó±¼À» ÀνÄÇÑ´Ù. ¿ÜºÎÁ¶¸íÀÇ ¿µÇâ¿¡ °­°ÇÇÑ ÀνĽýºÅÛÀ» ±¸ÃàÇϱâ À§ÇÏ¿© ¾ó±¼°ËÃâ ´Ü°è¿¡¼­ °ËÃâµÈ ¾ó±¼¿µ¿ªÀº ¹à±â°ªÀÇ ÃÖ´ë-ÃÖ¼Ò Á¤±ÔÈ­ ¹æ¹ý¿¡ ÀÇÇØ º¸Á¤µÈ Á¤±ÔÈ­ ¿µ»óÀ» »ý¼ºÇÑ´Ù. Á¤±ÔÈ­µÈ ¾ó±¼¿µ»óÀº PCA¿Í LDA º¯È¯À» ÅëÇØ ºÎºÐ°ø°£»óÀÇ Æ¯Â¡º¤ÅÍ·Î º¯È¯µÈ´Ù. º¯È¯µÈ ÈÆ·Ã µ¥ÀÌÅͷκÎÅÍ LVQ ½Å°æ¸ÁÀÇ Ãʱâ Á᫐ º¤Å͸¦ °áÁ¤ÇÏ°í ½Å°æ¸ÁÀÇ ÇнÀ·ü Çâ»óÀ» À§ÇØ K-Means Ŭ·¯½ºÅ͸µ ¾Ë°í¸®ÁòÀ» Àû¿ëÇϸç, Ãʱâ Á᫐ º¤Å͸¦ ÀÌ¿ëÇÏ¿© LVQ2 ÇнÀ ¹æ¹ý¿¡ ÀÇÇØ ÇнÀµÈ Á߽ɺ¤Åʹ Ŭ·¡½ºÀÇ ´ëÇ¥ º¤ÅÍ°¡ µÈ´Ù. °á±¹ °¢ Ŭ·¡½ºÀÇ ´ëÇ¥ º¤ÅͷκÎÅÍ ÀÔ·Â ¿µ»óÀÇ Æ¯Â¡º¤ÅÍ°£ÀÇ À¯Å¬¸®µð¾ð °Å¸® ºñ±³¹ýÀ» Àû¿ëÇÏ¿© ¾ó±¼ ÀνÄÀ» ¼öÇàÇÑ´Ù. ORL µ¥ÀÌÅͺ£À̽º¸¦ ÀÌ¿ëÇÑ Á¤Áö ¿µ»ó¿¡ ´ëÇÑ Àνİú ½Ç½Ã°£À¸·Î ÀԷµǴ ¿µ»ó¿¡ ´ëÇÑ ÀÎ½Ä µî µÎ °¡Áö ÇüÅÂÀÇ ¿µ»óÀ» ±â¹ÝÀ¸·Î ½ÇÇèÇÑ °á°ú µÎ °æ¿ì¿¡ ¸ðµÎ Á¦¾ÈµÈ ¹æ¹ýÀÌ ±âÁ¸ÀÇ ÀÎ½Ä ¹æ¹ýº¸´Ù Àνķü¿¡¼­ ¿ì¼öÇÔÀ» ÀÔÁõÇÒ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.
Å°¿öµå(Keyword) LVQ(Linear Vector Quantization) neural net   face recognition   LDA(Linear Discriminant Analysis   PCA(Principal Component Analysis  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå