• 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) ½ÉÃþ ÇнÀ ±â¹ÝÀÇ ¼ö±â ÀÏȸ¼º ¾ÏÈ£ ÀÎÁõ ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) Handwritten One-time Password Authentication System Based On Deep Learning
ÀúÀÚ(Author) ¸®ÁØ   ÀÌÇý¿µ   ÀÌ¿µÁØ   À±¼öÁö   ¹èº´ÀÏ   ÃÖÈ£Áø   Zhun Li   HyeYoung Lee   Youngjun Lee   Sooji Yoon   Byeongil Bae   Ho-Jin Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 20 NO. 01 PP. 0025 ~ 0038 (2019. 02)
Çѱ۳»¿ë
(Korean Abstract)
½ÉÃþ ÇнÀ ¹× ¿Â¶óÀÎ »ýü ÀÎ½Ä ±â¹Ý ÀÎÁõÀÇ ±Þ¼ÓÇÑ °³¹ß¿¡ ¿µ°¨À» ¹Þ¾Æ, º» ³í¹®¿¡¼­´Â ½ÉÃþ ÇнÀÀ» ±â¹ÝÀ¸·Î ÇÊü ÀÎ½Ä ¹× ÀÛ¼ºÀÚ °ËÁõÀ» ¼öÇàÇÏ´Â ¼ö±â ÀÏȸ¼º ¾ÏÈ£ ÀÎÁõ ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. º» ³í¹®¿¡¼­´Â ¼ö±â·Î ÀÛ¼ºµÈ ¼ýÀÚ¸¦ ÀνÄÇÒ ¼ö ÀÖ´Â ÇÕ¼º°ö ½Å°æ¸Á°ú, ÀÔ·ÂµÈ ÇÊü¿Í ½ÇÁ¦ »ç¿ëÀÚÀÇ ÇÊü »çÀÌ À¯»ç¼ºÀ» °è»êÇÒ ¼ö ÀÖ´Â Siamese ½Å°æ¸ÁÀ» ¼³°èÇÑ´Ù. º» ³í¹®¿¡¼­´Â ÀÛ¼ºÀÚ °ËÁõÀ» À§ÇÑ NIST Speical Database 19 Á¦ 2ÆÇÀÇ Ã¹ ¹ø° ÀÀ¿ë »ç·Ê¸¦ Á¦½ÃÇÑ´Ù. º» ³í¹®ÀÌ Á¦¾ÈÇÏ´Â ½Ã½ºÅÛÀº ³× ÀåÀÇ ÀÔ·Â À̹ÌÁö¸¦ ±â¹ÝÀ¸·ÎÇÑ ¼ýÀÚ ÀÎ½Ä ÀÛ¾÷¿¡¼­ 98.58%, ÀÛ¼ºÀÚ °ËÁõ ÀÛ¾÷¿¡¼­ 93%ÀÇ Á¤È®µµ¸¦ ´Þ¼ºÇß´Ù. º» ³í¹®ÀÇ ÀúÀÚµéÀº Á¦¾ÈÇÑ ÇÊü ±â¹Ý »ýü Àνıâ¼úÀÌ FIDO ÇÁ·¹ÀÓ¿öÅ© ±â¹ÝÀÇ ´Ù¾çÇÑ ¿Â¶óÀÎ ÀÎÁõ ¼­ºñ½º¿¡ È°¿ëµÉ ¼ö ÀÖÀ» °ÍÀÌ¶ó ¿¹»óÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Inspired by the rapid development of deep learning and online biometrics-based authentication, we propose a handwritten one-time password authentication system which employs deep learning-based handwriting recognition and writer verification techniques. We design a convolutional neural network to recognize handwritten digits and a Siamese network to compute the similarity between the input handwriting and the genuine user¡¯s handwriting. We propose the first application of the second edition of NIST Special Database 19 for a writer verification task. Our system achieves 98.58% accuracy in the handwriting recognition task, and about 93% accuracy in the writer verification task based on four input images. We believe the proposed handwriting-based biometric technique has potential for use in a variety of online authentication services under the FIDO framework.
Å°¿öµå(Keyword) ½ÉÃþ ÇнÀ   ¼ö±â ÀνĠ  ÀÛ¼ºÀÚ °ËÁõ   ÀÎÁõ ½Ã½ºÅÛ   ÀÏȸ¼º ¾ÏÈ£   FIDO   Deep Learning   Handwriting Recognition   Writer Verification   Authentication System   One-time Password   FIDO  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå