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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) »óó¿Í ÁÖ¸§ÀÌ ÀÖ´Â Áö¹® ÆǺ°¿¡ È¿À²ÀûÀÎ ½ÉÃþ ÇнÀ ºñ±³¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Comparative Study on the Effective Deep Learning for Fingerprint Recognition with Scar and Wrinkle
ÀúÀÚ(Author) ±èÁؼ·   ¸²ºó º¸´ÏÄ«   ¼º³«ÁØ   È«¹Î   JunSeob Kim   BeanBonyka Rim   Nak-Jun Sung   Min Hong  
¿ø¹®¼ö·Ïó(Citation) VOL 21 NO. 04 PP. 0017 ~ 0023 (2020. 08)
Çѱ۳»¿ë
(Korean Abstract)
Àΰ£ÀÇ Æ¯¼º°ú °ü·ÃµÈ ÃøÁ¤ Ç׸ñÀ» ³ªÅ¸³»´Â »ýüÁ¤º¸´Â µµ³­À̳ª ºÐ½ÇÀÇ ¿°·Á°¡ ¾øÀ¸¹Ç·Î ³ôÀº ½Å·Ú¼ºÀ» °¡Áø º¸¾È ±â¼ú·Î¼­ Å« ÁÖ¸ñÀ» ¹Þ°í ÀÖ´Ù. ÀÌ·¯ÇÑ »ýüÁ¤º¸ Áß Áö¹®Àº º»ÀÎ ÀÎÁõ, ½Å¿ø ÆÄ¾Ç µîÀÇ ºÐ¾ß¿¡ ÁÖ·Î »ç¿ëµÈ´Ù. ½Å¿øÀ» ÆľÇÇÒ ¶§ Áö¹® À̹ÌÁö¿¡ ÀÎÁõÀ» ¼öÇàÇϱ⠾î·Á¿î »óó, ÁÖ¸§, ½À±â µîÀÇ ¹®Á¦°¡ ÀÖÀ» °æ¿ì, Áö¹® Àü¹®°¡°¡ Àü󸮴ܰ踦 ÅëÇØ Á÷Á¢ Áö¹®¿¡ ¾î¶°ÇÑ ¹®Á¦°¡ ÀÖ´ÂÁö ÆľÇÇÏ°í ¹®Á¦¿¡ ¸Â´Â ¿µ»óó¸® ¾Ë°í¸®ÁòÀ» Àû¿ëÇØ ¹®Á¦¸¦ ÇØ°áÇÑ´Ù. À̶§ Áö¹®¿¡ »óó¿Í ÁÖ¸§ÀÌ ÀÖ´Â Áö¹® ¿µ»óÀ» ÆǺ°ÇØÁÖ´Â ÀΰøÁö´É ¼ÒÇÁÆ®¿þ¾î¸¦ ±¸ÇöÇÏ¸é ¼Õ½±°Ô »óó³ª ÁÖ¸§ÀÇ ¿©ºÎ¸¦ È®ÀÎÇÒ ¼ö ÀÖ°í, ¾Ë¸ÂÀº ¾Ë°í¸®ÁòÀ» ¼±Á¤ÇØ ½±°Ô Áö¹® À̹ÌÁö¸¦ °³¼±ÇÒ ¼ö ÀÖ´Ù. º» ¿¬±¸¿¡¼­´Â ÀÌ·¯ÇÑ ÀΰøÁö´É ¼ÒÇÁÆ®¿þ¾îÀÇ °³¹ßÀ» À§ÇØ Ä¯º¸µð¾Æ ¿Õ¸³´ëÇб³ÀÇ Çлý 1,010¸í, Sokoto ¿ÀÇ µ¥ÀÌÅͼ 600¸í, ±¹³» Çлý 98¸íÀÇ ¸ðµç ¼Õ°¡¶ô Áö¹®À» ÃëµæÇØ ÃÑ 17,080°³ÀÇ Áö¹® µ¥ÀÌÅͺ£À̽º¸¦ ±¸ÃàÇß´Ù. ±¸ÃàÇÑ µ¥ÀÌÅͺ£À̽º¿¡¼­ »óó³ª ÁÖ¸§ÀÌ ÀÖ´Â °æ¿ì¸¦ ÆǺ°Çϱâ À§ÇØ ±âÁØÀ» È®¸³ÇÏ°í Àü¹®°¡ÀÇ °ËÁõÀ» °ÅÃÄ µ¥ÀÌÅÍ ¾î³ëÅ×À̼ÇÀ» ÁøÇàÇß´Ù. Æ®·¹ÀÌ´× µ¥ÀÌÅͼ°ú Å×½ºÆ® µ¥ÀÌÅͼÂÀº įº¸µð¾ÆÀÇ µ¥ÀÌÅÍ, Sokoto µ¥ÀÌÅÍ·Î ±¸¼ºÇÏ¿´À¸¸ç ºñÀ²À» 8:2·Î ¼³Á¤Çß´Ù. ±×¸®°í ±¹³» Çлý 98¸íÀÇ µ¥ÀÌÅ͸¦ °ËÁõ µ¥ÀÌÅÍ ¼ÂÀ¸·Î ¼³Á¤Çß´Ù, ±¸¼ºµÈ µ¥ÀÌÅͼÂÀ» »ç¿ëÇØ Classic CNN, AlexNet, VGG-16, Resnet50, Yolo v3 µîÀÇ ´Ù¼¸ °¡Áö CNN ±â¹Ý ¾ÆÅ°ÅØó¸¦ ±¸ÇöÇØ ÇнÀÀ» ÁøÇàÇßÀ¸¸ç Áö¹®ÀÇ »óó¿Í ÁÖ¸§ Æǵ¶¿¡¼­ °¡Àå ÁÁÀº ¼º´ÉÀ» º¸ÀÌ´Â ¸ðµ¨À» ã´Â ¿¬±¸¸¦ ¼öÇàÇß´Ù. ´Ù¼¸°¡Áö ¾ÆÅ°ÅØó Áß Áö¹® ¿µ»ó¿¡¼­ »óó¿Í ÁÖ¸§ ¿©ºÎ¸¦ °¡Àå Àß ÆǺ°ÇÒ ¼ö ÀÖ´Â ¾ÆÅ°ÅØó´Â ResNet50À¸·Î °ËÁõ °á°ú 81.51%·Î °¡Àå ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Biometric information indicating measurement items related to human characteristics has attracted great attention as security technology with high reliability since there is no fear of theft or loss. Among these biometric information, fingerprints are mainly used in fields such as identity verification and identification. If there is a problem such as a wound, wrinkle, or moisture that is difficult to authenticate to the fingerprint image when identifying the identity, the fingerprint expert can identify the problem with the fingerprint directly through the preprocessing step, and apply the image processing algorithm appropriate to the problem. Solve the problem. In this case, by implementing artificial intelligence software that distinguishes fingerprint images with cuts and wrinkles on the fingerprint, it is easy to check whether there are cuts or wrinkles, and by selecting an appropriate algorithm, the fingerprint image can be easily improved. In this study, we developed a total of 17,080 fingerprint databases by acquiring all finger prints of 1,010 students from the Royal University of Cambodia, 600 Sokoto open data sets, and 98 Korean students. In order to determine if there are any injuries or wrinkles in the built database, criteria were established, and the data were validated by experts. The training and test datasets consisted of Cambodian data and Sokoto data, and the ratio was set to 8: 2. The data of 98 Korean students were set up as a validation data set. Using the constructed data set, five CNN-based architectures such as Classic CNN, AlexNet, VGG-16, Resnet50, and Yolo v3 were implemented. A study was conducted to find the model that performed best on the readings. Among the five architectures, ResNet50 showed the best performance with 81.51%.
Å°¿öµå(Keyword) µö·¯´×   Áö¹®   »ýüÁ¤º¸   2D ÇÕ¼º °ö ½Å°æ¸Á   »óó Áö¹® ÆǺ°   ÁÖ¸§ Áö¹® ÆǺ°   Deep learning   Biometric information   discriminating of scar fingerprint   discriminating of wrinkle fingerprint   2D Convolutional Neural Network  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå