• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¾îÁ¾ ºÐ·ù¸¦ À§ÇÑ CNNÀÇ Àû¿ë
¿µ¹®Á¦¸ñ(English Title) Application of CNN for Fish Species Classification
ÀúÀÚ(Author) ¹ÚÁøÇö   Ȳ±¤º¹   ¹ÚÈñ¹®   ÃÖ¿µ±Ô   Jin-Hyun Park   Kwang-Bok Hwang   Hee-Mun Park   Young-Kiu Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 01 PP. 0039 ~ 0046 (2019. 01)
Çѱ۳»¿ë
(Korean Abstract)
º» ¿¬±¸¿¡¼­ ¿Ü·¡¾îÁ¾ ÅðÄ¡¸¦ À§ÇÑ ½Ã½ºÅÛ °³¹ß¿¡ ¾Õ¼­ ¹° ¾ÈÀÇ ¾î·ù À̹ÌÁö¸¦ CNNÀ¸·Î ÇнÀÇÏ¿© ¾îÁ¾À» ºÐ·ùÇÏ´Â ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÏ°íÀÚ ÇÑ´Ù. CNN ÇнÀÀ» À§ÇÑ ¿øµ¥ÀÌÅÍ(raw data)´Â °¢ ¾îÁ¾¿¡ ´ëÇØ Á÷Á¢ ÃÔ¿µÇÑ ¿µ»óÀ» »ç¿ëÇÏ¿´À¸¸ç, ¾îÁ¾ ºÐ·ù¼º´ÉÀ» ³ôÀ̱â À§ÇØ ¿µ»ó À̹ÌÁöÀÇ °³¼ö¸¦ ´Ã¸° µ¥ÀÌÅͼ¼Æ® 1°ú ÃÖ´ëÇÑ ÀÚ¿¬È¯°æ°ú °¡±î¿î ¿µ»ó À̹ÌÁö¸¦ ±¸ÇöÇÑ µ¥ÀÌÅͼ¼Æ® 2¸¦ ±¸¼ºÇÏ¿© ÇнÀ ¹× Å×½ºÆ® µ¥ÀÌÅÍ·Î »ç¿ëÇÏ¿´´Ù. 4°¡Áö CNNÀÇ ºÐ·ù¼º´ÉÀº µ¥ÀÌÅͼ¼Æ® 1¿¡ ´ëÇØ 99.97%, µ¥ÀÌÅͼ¼Æ® 2¿¡ ´ëÇØ 99.5% ÀÌ»óÀ» ³ªÅ¸³»¾úÀ¸¸ç, ƯÈ÷ µ¥ÀÌÅͼ¼Æ® 2¸¦ »ç¿ëÇÏ¿© ÇнÀÇÑ CNNsÀÌ ÀÚ¿¬È¯°æ°ú À¯»çÇÑ ¾î·ù À̹ÌÁö¿¡ ´ëÇؼ­µµ ¸¸Á·ÇÒ ¸¸ÇÑ ¼º´ÉÀ» °¡ÁüÀ» È®ÀÎÇÏ¿´´Ù. ±×¸®°í 4°¡Áö CNN Áß AlexNetÀÌ ¼º´É¿¡¼­µµ ¸¸Á·½º·¯¿î °á°ú¸¦ µµÃâÇÏ¿´À¸¸ç, ¼öÇà½Ã°£°ú ÇнÀ½Ã°£ ¿ª½Ã °¡Àå ª¾Æ ¿Ü·¡¾îÁ¾ ÅðÄ¡¸¦ À§ÇÑ ½Ã½ºÅÛ °³¹ß¿¡ °¡Àå ÀûÇÕÇÑ ±¸Á¶ÀÓÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this study, before system development for the elimination of foreign fish species, we propose an algorithm to classify fish species by training fish images with CNN. The raw data for CNN learning were directly captured images for each species, Dataset 1 increases the number of images to improve the classification of fish species and Dataset 2 realizes images close to natural environment are constructed and used as training and test data. The classification performance of four CNNs are over 99.97% for dataset 1 and 99.5% for dataset 2, in particular, we confirm that the learned CNN using Data Set 2 has satisfactory performance for fish images similar to the natural environment. And among four CNNs, AlexNet achieves satisfactory performance, and this has also the shortest execution time and training time, we confirm that it is the most suitable structure to develop the system for the elimination of foreign fish species.
Å°¿öµå(Keyword) ÄÁº¼·ç¼Ç ½Å°æ¸Á   ¾î·ù À̹ÌÁö   ¾î·ù Á¾   ¾Ë·º½º³Ý   ºÐ·ù   CNN(Convolutional Neural Network)   Fish Image   Fish Species   AlexNet   Classification  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå