Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
¸ð¹ÙÀÏ ºñµð¿À±â±â À§¿¡¼ÀÇ Áß¿äÇÑ °´Ã¼Å½»öÀ» À§ÇÑ ¹®¸ÆÀÎ½Ä Æ¯¼ºº¤ÅÍ ¼±Åà ¸ðµ¨ |
¿µ¹®Á¦¸ñ(English Title) |
Context Aware Feature Selection Model for Salient Feature Detection from Mobile Video Devices |
ÀúÀÚ(Author) |
ÀÌÀçÈ£
½ÅÇö°æ
Jaeho Lee
Hyunkyung Shin
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 15 NO. 06 PP. 0117 ~ 0124 (2014. 12) |
Çѱ۳»¿ë (Korean Abstract) |
¸ð¹ÙÀÏ ±â±â¸¦ »ç¿ëÇÑ ½Ç½Ã°£ ºñµð¿À ¿µ»ó󸮺оßÀÇ Áß¿ä °´Ã¼Å½»ö ¹× ÃßÀûÀÇ ¹®Á¦¿¡ ÀÖ¾î¼ ³Á¦´Â º¹ÀâÇÑ ¹è°æ¼Ó¿¡¼ Àü°æÀ» ±¸ºÐÇØ ³»´Â ÀÏÀÌ´Ù. º» ³í¹®¿¡¼´Â ±â°èÇнÀÀ» À§ÇÑ Æ¯¼ºº¤ÅÍ ¼±Á¤ÀÇ ¹®Á¦¸¦ À§ÇÑ ¹®¸ÆÀÎ½Ä ¸ðµ¨À» Á¦½ÃÇÏ¿© ÀâÀ½Á¦°Å¸¦ À§ÇÑ ±â°è ÇнÀ±â¹ÝÀÇ ±¸ºÐÀÚ¸¦ ±¸ÇöÇÏ¿´´Ù. ¼öÇÐÀûÀ¸·Î NP-hard·Î ¾Ë·ÁÁø °¡Àå °¡±î¿î ÀÌ¿ôÀ» »ç¿ëÇÑ ¹®¸ÆÀÎ½Ä Æ¯¼ºº¤ÅÍ ¼±Á¤ ¾Ë°í¸®ÁòÀÇ ±¸Çö¿¡ ÀÖ¾î¼, º» ³í¹®Àº ¿¬»êȽ¼ö¸¦ ÁÙÀÎ À¯»ç¹æ¹ý·Ð¿¡ ´ëÇØ ÀÚ¼¼È÷ °Å·ÐÇÏ¿´´Ù. ¶ÇÇÑ, ¹®¸ÆÀÎ½Ä ¼º°ÝÀ» °¡¹ÌÇÑ Æ¯¼ºº¤ÅÍ ¼±Á¤À» ÅëÇØ ¾ò¾îÁø Ư¼º °ø°£¿¡¼ÀÇ Çâ»óµÈ ºÐ¸®¼º¿¡ ´ëÇØ ÁÖ¼ººÐ ºÐ¼®À» ÅëÇØ ¾ö¹ÐÇÑ ºÐ¼®°á°ú¸¦ Á¦½ÃÇÏ¿´´Ù. Àü¹ÝÀûÀÎ ¼º´É Çâ»óÀÇ Á¤µµ¸¦ °èÃøÇϱâ À§ÇØ ´Ù¾çÇÑ ±â°èÇнÀ ¹æ¹ý·Ð, ¿¹¸¦ µé¾î, ´ÙÃþ½Å°æ¸Á, Áö¿øº¤Åͱâ°è, ³ªÀ̺꺣ÀÌÁö¾È, ȸ±ÍºÐ¼® µîÀ» »ç¿ëÇØ ºñ±³°á°ú¸¦ Á¦½ÃÇÏ¿´´Ù. º» ³í¹®¿¡¼ Á¦½ÃÇÑ ¹æ¹ý·ÐÀÇ ¼º´É°ú °è»ê»ó ÀÚ¿ø»ç¿ë¿¡ ´ëÇÑ ³»¿ëÀ» °á·ÐÀ¸·Î ¼¼úÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naive Bayesian, CART. Summary of computational costs and performance enhancement is also presented
|
Å°¿öµå(Keyword) |
Ư¡º¤Åͼ±ÅÃ
°¡Àå°¡±î¿î±Ù¹æŽ»ö
ÁÖ¼ººÐºÐ¼®
Á߿䰴üŽ»ö
±â°èÇнÀ
feature vector selection
nearest neighbor search
principal component analysis
salient feature detection
machine learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|