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

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸Åë½ÅÇÐȸ Çмú´ëȸ > 2019³â Ãß°èÇмú´ëȸ

2019³â Ãß°èÇмú´ëȸ

Current Result Document : 5 / 22 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ĸÂ÷ À̹ÌÁö ÀνÄÀ» ÅëÇÑ °³¼±µÈ ĸÂ÷ À̹ÌÁö »ý¼º ¾Ë°í¸®Áò
¿µ¹®Á¦¸ñ(English Title) An Improved Captcha Image Generation Algorithm Using Captcha Image Recognition
ÀúÀÚ(Author) ±è¼ºÈ¯   ¹ÚÁöÈÆ   ¼­ÁöÈÆ   ¹èÁ¤¿ø   Sung Hwan Kim   Ji Hun Park   Ji Hun Seo   Jeong Won  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 02 PP. 0422 ~ 0424 (2019. 10)
Çѱ۳»¿ë
(Korean Abstract)
ÀÌ ³í¹®¿¡¼­´Â ĸÂ÷ À̹ÌÁöµéÀ» »ý¼ºÇÏ´Â »õ·Î¿î ±â¹ýÀ» ¿¬±¸ÇÏ¿´´Ù. ±âÁ¸¿¡ °ø°³µÇ¾î Àִ ĸÂ÷ À̹ÌÁö ¹®ÀÚ Á¦ÀÛ ¾Ë°í¸®Áò¿¡ 2°¡Áö »õ·Î¿î ±â¹ýÀ» Á¦¾ÈÇÏ¿´´Ù. Python ¾ð¾î¿Í À̹ÌÁö ÇÁ·Î¼¼½Ì¿¡ ÁßÁ¡À» µÐ ¿ÀǼҽº ¶óÀ̺귯¸®ÀÎ OpenCV¸¦ »ç¿ëÇÏ¿© Á¦¾ÈÇÑ ±â¹ýÀ» ±¸ÇöÇÏ¿´´Ù. °¢ ĸÂ÷ À̹ÌÁöµéÀ» CNN ¾Ë°í¸®ÁòÀ¸·Î ÀνķüÀ» È®ÀÎÇØ º» °á°ú, Ãʱâ À̹ÌÁöº¸´Ù ÀνķüÀÌ ¶³¾îÁ®¼­ Á¦¾ÈÇÑ ±â¹ýÀÌ Ä¸Â÷ÀÇ ¼º´ÉÀ» °­È­ÇÔÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù. ¶ÇÇÑ, Á¦¾ÈÇÑ 2°¡Áö ¾Ë°í¸®ÁòÀ» ÇÔ²² Àû¿ëÇÏ¿© ÀνķüÀ» Ãß°¡·Î Ç϶ô½ÃÄÑ Á¦¾ÈÇÑ ±â¹ýÀÇ È¿À²¼ºÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, new techniques for generating Captcha images were studied. Two new techniques are proposed for the existing Captcha image-making algorithm. The proposed technique is implemented using OpenCV, an open source library focused on the Python language and image processing. As a result of checking the recognition rate of each Captcha image by CNN algorithm, it was confirmed that the proposed method enhances the performance of the Captcha image, because the recognition rate is lower than the initial image. Also, by applying the two proposed algorithms together, the recognition rate can be further reduced to confirm the effectiveness of the proposed method.
Å°¿öµå(Keyword) Captcha   Convolutional Neural Network(CNN)   OpenCV   Pixel shift  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå