Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)
ÇѱÛÁ¦¸ñ(Korean Title) |
º´¸® Á¤º¸ ½Ã½ºÅÛÀ» À§ÇÑ À̹ÌÁö ¿Ü°û¼± ÃßÃâ ±â¹ý ¿¬±¸ |
¿µ¹®Á¦¸ñ(English Title) |
Image Edge Detection Technique for Pathological Information System |
ÀúÀÚ(Author) |
Xie Xiao
¡¡¿À»óÀ±
Xie Xiao
¡¡Sangyoon Oh
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 05 NO. 10 PP. 0489 ~ 0496 (2016. 10) |
Çѱ۳»¿ë (Korean Abstract) |
º´¸® Á¤º¸½Ã½ºÅÛ(Pathological Information System: PIS)Àº ¸ÅÀÏ ¼öõ À徿 »ý»êµÇ´Â ȯÀÚ º´¸® À̹ÌÁö¸¦ °ü¸®Çϴµ¥ È°¿ëµÇ°í ÀÖÀ¸¸ç, ÀÌ À̹ÌÁö Á¤º¸µéÀ» ¾î¶»°Ô È¿°úÀûÀ¸·Î ó¸®ÇÒ °ÍÀÎÁö´Â º´¸® Á¤º¸ 󸮿¡ ÀÖ¾î¼ Áß¿äÇÑ ¿¬±¸ °úÁ¦ Áß ÇϳªÀÌ´Ù. À̹ÌÁöÀÇ ¿Ü°û¼±À» ÃßÃâÇÏ´Â °ÍÀº º´¸® À̹ÌÁö 󸮿¡ ÀÖ¾î °¡Àå Áß¿äÇÑ ÀÛ¾÷ÀÌÁö¸¸ ÇöÀç »ç¿ëµÇ´Â ¾Ë°í¸®ÁòÀº Á¤È®µµ¿¡ ÀÖ¾î ¸¹Àº °³¼±Á¡À» °¡Áö¹Ç·Î, º» ³í¹®¿¡¼´Â À̹ÌÁöÀÇ ¿Ü°û¼± °ËÃø¿¡ ÀÖ¾î¼ ±âÁ¸ÀÇ Canny ¾Ë°í¸®ÁòÀÇ ¿ø¸®¸¦ ¹ÙÅÁÀ¸·Î ÀûÀÀÀû ÀÓ°è°ª ¼³Á¤ÀÌ °¡´ÉÇÏ¸ç ´«±ÝÀÚ¸¦ ÀÓ°è°ª ¼³Á¤ÀÇ ±âÁØÀ¸·Î »ï´Â¹æ½ÄÀ» Á¦¾ÈÇÏ¿© ±âÁ¸ ¿Ü°û¼± ÃßÃâ ¹æ½Äº¸´Ù Á¤È®ÇÑ ¹æ½ÄÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ¹æ½ÄÀº ±âÁ¸ ¹æ½Ä°úÀÇ ºñ±³½ÇÇèÀ» ÅëÇØ ¼º´ÉÀ» °ËÁõÇÏ¿´À¸¸ç, ÀÌ ½ÇÇè¿¡¼´Â ÀÓÀÇ·Î ¼±Á¤µÈ º´¸® À̹ÌÁö ±º, ±âÁ¸ ¹æ½ÄÀ¸·Î´Â ½Äº°ÀÌ Á¦ÇѵǾú´ø º´¸® À̹ÌÁö ±º ¹× ÀǵµÀûÀ¸·Î ³ëÀÌÁ Ãß°¡ÇÑ À̹ÌÁö ±ºÀ» ´ë»óÀ¸·Î ½ÇÇèÇÏ¿´°í, ½ÇÇè °á°ú¸¦ ºñ±³ÇÏ¿© Á¦¾ÈÇÏ´Â À̹ÌÁö ¿Ü°û¼± ½Äº° ¹æ½ÄÀÇ Çâ»óµÈ ¼º´ÉÀ» Áõ¸íÇß´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Thousands of pathological images are produced daily per hospital and they are stored and managed by a pathology information system (PIS). Since image edge detection is one of fundamental analysis tools for pathological images, many researches are targeted to improve accuracy and performance of image edge detection algorithm of HIS. In this paper, we propose a novel image edge detection method. It is based on Canny algorithm with adaptive threshold configuration. It also uses a dividing ruler to configure the two threshold instead of whole image to improve the detection ratio of ruler itself. To verify the effectiveness of our proposed method, we conducted empirical experiments with real pathological images(randomly selected image group, image group that was unable to detect by conventional methods, and added noise image group). The results shows that our proposed method outperforms and better detects compare to the conventional method.
|
Å°¿öµå(Keyword) |
º´¸® Á¤º¸ ½Ã½ºÅÛ
À̹ÌÁö ¿Ü°û¼± ÃßÃâ
À°¾È Á¶Á÷ ÃÔ¿µ ½Ã½ºÅÛ
Canny ¾Ë°í¸®Áò
Pathological Information System
Image Edge Detection
Digital Gross Photography System
Canny Algorithm
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|