Á¤º¸°úÇÐȸ ³í¹®Áö D : µ¥ÀÌŸº£À̽º
Current Result Document : 6 / 7
ÇѱÛÁ¦¸ñ(Korean Title) |
À±°û¼± À̹ÌÁö ÇǶó¹Ìµå¿Í °ü½É¿µ¿ª°ËÃâÀ» ÀÌ¿ëÇÑ SIFT ±â¹Ý À̹ÌÁöÀ¯»ç¼º °Ë»ö |
¿µ¹®Á¦¸ñ(English Title) |
SIFT based Image Similarity Search using an Edge Image Pyramid and an Interesting Region Detection |
ÀúÀÚ(Author) |
À¯½ÂÈÆ
±è´öȯ
À̼®·æ
Á¤Áø¿Ï
±è»óÈñ
Seunghoon Yu
Deokhwan Kim
Seoklyong Lee
Chinwan Chung
Sanghee Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 35 NO. 04 PP. 0345 ~ 0355 (2008. 08) |
Çѱ۳»¿ë (Korean Abstract) |
´Ù¾çÇÑ ÇüÅ Ư¡ ÃßÃâ ¹æ¹ý ÁßÀÇ ÇϳªÀÎ SIFT´Â ¹°Ã¼ ÀνÄ, ¸ð¼Ç ÃßÀû, 3Â÷¿ø À̹ÌÁö À籸¼º°ú °°Àº ÄÄÇ»ÅÍ ºñÀü ÀÀ¿ë ºÐ¾ß¿¡¼ ¸¹ÀÌ »ç¿ëµÈ´Ù. ÇÏÁö¸¸ SIFT ¹æ¹ýÀº ¸¹Àº Ư¡Á¡µé°ú °íÂ÷¿øÀÇ Æ¯Â¡ º¤Å͸¦ »ç¿ëÇϱ⠶§¹®¿¡ À̹ÌÁö À¯»ç¼º °Ë»ö¿¡ ±×´ë·Î Àû¿ëÇϱ⿡´Â ¸¹Àº ¾î·Á¿òÀÌ ÀÖ´Ù. º» ³í¹®¿¡¼´Â À±°û¼± À̹ÌÁö ÇǶó¹Ìµå¿Í °ü½É¿µ¿ª °ËÃâÀ» ÀÌ¿ëÇÑ SIFT ±â¹Ý À̹ÌÁö À¯»ç¼º °Ë»ö ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÑ ¹æ¹ýÀº À±°û¼± À̹ÌÁö ÇǶó¹Ìµå¸¦ ÀÌ¿ëÇÏ¿© À̹ÌÁöÀÇ ¹à±â º¯È, Å©±â, ȸÀü µî¿¡ ºÒº¯ÇÑ Æ¯Â¡À» ÃßÃâÇÏ°í, Ÿ¿ø ÇüÅÂÀÇ ÇãÇÁº¯È¯À» ÀÌ¿ëÇÑ °ü½É¿µ¿ª °ËÃâÀ» ÅëÇØ ºÒÇÊ¿äÇÑ ¸¹Àº Ư¡Á¡µéÀ» Á¦°ÅÇÏ¿© °Ë»ö ¼º´ÉÀ» ³ôÀδÙ. ½ÇÇè °á°ú¿¡¼ Á¦¾ÈÇÑ ¹æ¹ýÀÇ À̹ÌÁö °Ë»ö ¼º´ÉÀÌ ±âÁ¸ÀÇ SIFTÀÇ ¹æ¹ý¿¡ ºñÇØ Æò±Õ ÀçÇöÀ²ÀÌ ¾à 20%Á¤µµ ÁÁÀº ¼º´ÉÀ» º¸ÀÌ°í ÀÖ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
SIFT is popularly used in computer vision application such as object recognition, motion tracking, and 3D reconstruction among various shape descriptors. However, it is not easy to apply SIFT into the image similarity search as it is since it uses many high dimensional keypoint vectors. In this paper, we present a SIFT based image similarity search method using an edge image pyramid and an interesting region detection. The proposed method extracts keypoints, which is invariant to contrast, scale, and rotation of image, by using the edge image pyramid and removes many unnecessary keypoints from the image by using the hough transform. The proposed hough transform can detect objects of ellipse type so that it can be used to find interesting regions. Experimental results demonstrate that the retrieval performance of the proposed method is about 20% better than that of traditional SIFT in average recall.
|
Å°¿öµå(Keyword) |
À̹ÌÁö À¯»ç¼º °Ë»ö
SIFT
ij´Ï ¿¡Áö ¾Ë°í¸®Áò
°ü½É ¿µ¿ª °ËÃâ
Image Similarity Search
SIFT
Canny Edge Algorithm
Interesting Region Detection
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|