Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
½ºÆÄÅ© ȯ°æ¿¡¼ ³»¿ë ±â¹Ý À̹ÌÁö °Ë»öÀ» À§ÇÑ È¿À²ÀûÀÎ ºÐ»ê ÀÎ-¸Þ¸ð¸® °íÂ÷¿ø »öÀÎ ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
An Efficient Distributed In-memory High-dimensional Indexing Scheme for Content-based Image Retrieval in Spark Environments |
ÀúÀÚ(Author) |
ÃÖµµÁø
¹Ú¼ÛÈñ
±è¿¬µ¿
À§Áö¿ø
Dojin Choi
Songhee Park
Yeondong Kim
Jiwon Wee
ÀÌÇöº´
ÀÓÁ¾ÅÂ
º¹°æ¼ö
À¯Àç¼ö
Hyeonbyeong Lee
Jongtae Lim
Kyoungsoo Bok
Jaesoo Yoo
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 47 NO. 01 PP. 0095 ~ 0108 (2020. 01) |
Çѱ۳»¿ë (Korean Abstract) |
¿µ»ó¿¡¼ ¹üÁË ÇàÀ§ ¸ð´ÏÅ͸µ ¹× ÃßÀûÀ» À§Çؼ À̹ÌÁö ³»¿¡ Æ÷ÇÔµÈ °´Ã¼¸¦ °Ë»öÇÏ´Â ³»¿ë ±â¹Ý °Ë»öÀÌ È°¿ëµÇ°í ÀÖ´Ù. º» ³í¹®¿¡¼´Â ³»¿ë ±â¹Ý À̹ÌÁö °Ë»öÀ» À§ÇØ À̹ÌÁö ¶Ç´Â °´Ã¼¿¡¼ ÃßÃâÇÑ ´ë¿ë·® Ư¡ º¤Å͸¦ ÀÌ¿ëÇÑ À¯»çµµ °Ë»öÀ» Áö¿øÇÏ´Â ºÐ»ê ÀÎ-¸Þ¸ð¸® ±â¹Ý °íÂ÷¿ø »öÀÎ ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ´ë¿ë·® ºÐ»ê 󸮸¦ À§ÇØ ºòµ¥ÀÌÅÍ Ç÷§ÆûÀÎ ½ºÆÄÅ©¸¦ È°¿ëÇÏ°í È¿À²ÀûÀÎ ºÐ»ê ÁúÀÇ Ã³¸® ÇÒ´çÀ» À§ÇØ ¸¶½ºÅÍ/½½·¹ÀÌºê ¸ðµ¨À» È°¿ëÇÑ´Ù. ¸¶½ºÅÍ¿¡¼´Â µ¥ÀÌÅÍ ¹× ÁúÀÇ ºÐ¹è¸¦ ¼öÇàÇÏ°í ½½·¹À̺꿡¼´Â µ¥ÀÌÅ͸¦ »öÀÎÇÑ´Ù. ´õºÒ¾î ±âÁ¸ ºÐ»ê °íÂ÷¿ø »öÀÎ ±â¹ý¿¡¼ k-ÃÖ±ÙÁ¢ ÁúÀÇ Ã³¸®ÀÇ ¼º´É ¹®Á¦¸¦ ÇØ°áÇϱâ À§Çؼ ¹ÐÁýµµ ¹× Ž»ö ºñ¿ëÀ» °í·ÁÇÑ k-ÃÖ±ÙÁ¢ ÁúÀÇ ÃÖÀûÈ ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ±â¹ýÀÇ ¿ì¼ö¼º ¹× Ÿ´ç¼º À» ÀÔÁõÇϱâ À§ÇØ ´Ù¾çÇÑ ¼º´É Æò°¡¸¦ ¼öÇàÇÑ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Content-based image retrieval that searches an object in images has been utilizing for criminal activity monitoring and object tracking in video. In this paper, we propose a high-dimensional indexing scheme based on distributed in-memory for the content-based image retrieval. It provides similarity search by using massive feature vectors extracted from images or objects. In order to process a large amount of data, we utilized a big data platform called Spark. Moreover, we employed a master/slave model for efficient distributed query processing allocation. The master distributes data and queries. and the slaves index and process them. To solve k-NN query processing performance problems in the existing distributed high-dimension indexing schemes, we propose optimization methods for the k-NN query processing considering density and search costs. We conduct various performance evaluations to demonstrate the superiority of the proposed scheme.
|
Å°¿öµå(Keyword) |
°Å¸® °ø°£
À̹ÌÁö À¯»çµµ °Ë»ö
°íÂ÷¿ø »öÀÎ
ºÐ»ê ó¸®
½ºÆÄÅ©
metric space
image similarity search
high dimensional indexing
distributed processing
spark
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|