Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
ÆÐÅÏÀνÄÀ» ÀÌ¿ëÇÑ ¼ö»ï µî±ÞÆÇÁ¤ ¾Ë°í¸®Áò¿¡ °üÇÑ ¿¬±¸ |
¿µ¹®Á¦¸ñ(English Title) |
A Study on a Ginseng Grade Decision Making Algorithm Using a Pattern Recognition Method |
ÀúÀÚ(Author) |
Seokhoon Jeong
Kuk Won Ko
Je-Yong Kang
Suwon Jang
Sangjoon Lee
Á¤¼®ÈÆ
°í±¹¿ø
°Á¦¿ë
Àå¼ö¿ø
ÀÌ»óÁØ
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 05 NO. 07 PP. 0327 ~ 0332 (2016. 07) |
Çѱ۳»¿ë (Korean Abstract) |
º» ¿¬±¸´Â ºñ Á¤Çü ³ó»ê¹° Áß 6³â±Ù ¼ö»ïÀÇ ÀÚµ¿ µî±Þ ºÐ·ùÇϱâ À§ÇÑ ¼±Ç࿬±¸·Î, À̸¦ À§ÇØ 4¹æ Çâ¿¡¼ À̹ÌÁö ÃëµæÀÌ °¡´ÉÇÑ ¼ö»ï ¿µ»ó ÃøÁ¤±â¸¦ Á¦ÀÛÇÏ¿´À¸¸ç ÃÑ 245 ¼ö»ï °³Ã¼¿¡ ´ëÇؼ ¿µ»óÀ» ÃëµæÇÏ¿´´Ù. ÃëµæµÈ ¿µ»óÀÇ °¢ ¼ö»ï °³Ã¼¸¶´Ù 12°³ÀÇ ÆĶó¹ÌÅ͸¦ ÃßÃâÇÏ¿´À¸¸ç KGC Àλï°ø»çÀÇ ¼ö»ï µî±Þ ºÐ·ù±âÁØ°ú °¢ µî±Þº° Æò±Õ ÆĶó¹ÌÅÍÀÇ ºÐÆ÷¸¦ Á¶»çÇÏ¿© ÃÖÁ¾ 4°³ ÆĶó¹ÌÅ͸¦ ¼±Á¤ÇÏ¿´´Ù. ÆÐÅÏ ÀÎ½Ä ºÐ·ù±â´Â Support Vector MachineÀ» »ç¿ëÇÏ¿´À¸¸ç °ø¿ë ¼ÒÇÁÆ®¿þ¾îÀÎ OpenCV Library¸¦ »ç¿ëÇÏ¿© k-Class ºÐ·ù±â¸¦ ¼³°èÇÏ¿´´Ù. °¢ µî±Þº° ÇнÀ µ¥ÀÌÅÍ ¼ö¸¦ 10, 15, 20À¸·Î Á¶Á¤ÇÏ¿© µî±Þº° Àνķü º»ÀÎ °ÅºÎÀ² ŸÀÎ ÀνÄÀ²À» Á¶»çÇÏ¿´À¸¸ç, ÇнÀ µ¥ÀÌÅÍ ¼ö°¡ 10°³ ÀÏ ¶§ 1µî±Þ Àνķü 94%, 2µî±Þ Àνķü 98%, 3µî±Þ Àνķü 90%·Î °¡Àå ³ôÀº Àνļº´ÉÀ» º¸¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
This study is a leading research project to develop an automatic grade decision making algorithm of a 6-years-old fresh ginseng. For this work, we developed a Ginseng image acquiring instrument which can take 4-direction¡¯s images of a Ginseng at the same time and obtained 245 jingen images using the instrument. The 12 parameters were extracted for each image by a manual way. Lastly, 4 parameters were selected depending on a Ginseng grade classification criteria of KGC Ginseng research institute and a survey result which a distribution of averaging 12 parameters. A pattern recognition classifier was used as a support vector machine, designed to ¡°k-class classifier¡± using the OpenCV library which is a open-source platform. We had been surveyed the algorithm performance(Correct
Matching Ratio, False Acceptance Ratio, False Reject Ratio) when the training data number was controlled 10 to 20. The result of the correct matching ratio is 94% of the 1st ginseng grade, 98% of the 2nd ginseng grade, 90% of the 3rd ginseng grade, overall, showed high recognition performance with all grades when the number of training data are 10. |
Å°¿öµå(Keyword) |
Pattern Recognition
Ginseng Grade Decision Making
Pattern Classifier
ÆÐÅÏÀνÄ
¼ö»ïµî±ÞÆÇÁ¤
ÆÐÅϺзù±â
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|