ÇѱÛÁ¦¸ñ(Korean Title) |
Á¶¸í º¯È¿¡ ¾ÈÁ¤ÀûÀÎ ¼Õ ÇüÅ ÀÎÁö ±â¼ú |
¿µ¹®Á¦¸ñ(English Title) |
A Robust Hand Recognition Method to Variations in Lighting |
ÀúÀÚ(Author) |
ÃÖÀ¯ÁÖ
ÀÌÁ¦¼º
À¯È¿¼±
ÀÌÁ¤¿ø
Á¶À§´ö
Yoo-Joo Choi
Je-Sung Lee
Hyo-Sun You
Jung-Won Lee
We-Duke Cho
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 15-B NO. 01 PP. 0025 ~ 0036 (2008. 02) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®Àº Á¶¸íÀÇ º¯È°¡ ½ÉÇÑ ¿µ»ó¿¡¼ ¼Õ ÇüŸ¦ ¾ÈÁ¤ÀûÀ¸·Î ÀÎÁöÇÏ´Â ±â¹ý¿¡ °üÇÑ °ÍÀÌ´Ù. Á¦¾ÈÇÑ ¹æ¹ýÀº HSI »ö»ó°ø°£¿¡¼ »ö»ó(Hue) ¹× »ö»ó ±â¿ï±â(Hue-Gradient)¸¦ ±â¹ÝÀ¸·Î Á¤ÀÇµÈ ¹è°æ¸ðµ¨À» ±¸ÃàÇÏ°í, ½Ç½Ã°£À¸·Î ÀԷµǴ ¿µ»ó°úÀÇ ¹è°æÂ÷ºÐ(background subtraction)±â¹ýÀ» ÀÌ¿ëÇÏ¿© ¹è°æ°ú ¼ÕÀ» ±¸ºÐÇÑ´Ù. ÃßÃâµÈ ¼ÕÀÇ ¿µ¿ªÀ¸·ÎºÎÅÍ 18°¡ÁöÀÇ Æ¯Â¡¿ä¼Ò¸¦ ÃßÃâÇÏ°í À̸¦ ±â¹ÝÀ¸·Î ´ÙÁßŬ·¡½º SVM(Support Vector Machine) ÇнÀ ±â¹ýÀ» »ç¿ëÇÏ¿© ¼ÕÀÇ ÇüŸ¦ ÀÎÁöÇÑ´Ù. Á¦¾È ±â¹ýÀº »ö»ó ±â¿ï±â¸¦ ¹è°æ Â÷ºÐ¿¡ Àû¿ëÇÔÀ¸·Î½á, Á¶¸í ȯ°æÀÌ ¹è°æ ¸ðµ¨ÀÇ Á¶¸í°ú ´Ù¸£°Ô ±Þ°ÝÇÑ º¯È°¡ ÀÌ·ç¾îÁ³À» ¶§µµ ¾ÈÁ¤ÀûÀ¸·Î ¼ÕÀÇ À±°ûÁ¤º¸¸¦ ÃßÃâÇÒ ¼ö ÀÖµµ·Ï ÇÏ¿´´Ù. ¶ÇÇÑ, ½Ç½Ã°£ 󸮸¦ ÀúÇØÇÏ´Â º¹ÀâÇÑ ¼ÕÀÇ Æ¯¼ºÁ¤º¸ ´ë½Å, OBBÀÇ Å©±â¿¡ ´ëÇÏ¿© Á¤±ÔÈµÈ µÎ °³ÀÇ °íÀ¯°ª°ú °´Ã¼ ±â¹Ý ¹Ù¿îµù ¹Ú½º(OBB)¸¦ ±¸¼ºÇÏ´Â 16°³ ¼¼ºÎ ¿µ¿ª¿¡¼ÀÇ ¼Õ À±°ûÇȼ¿ÀÇ °³¼ö¸¦ ¼ÕÀÇ Æ¯¼ºÁ¤º¸·Î »ç¿ëÇÏ¿´´Ù. º» ³í¹®¿¡¼´Â ±Þ°ÝÇÑ Á¶¸í º¯È »óȲ¿¡¼ ±âÁ¸ RGB »ö»ó¿ä¼Ò¸¦ ±â¹ÝÀ¸·Î ÇÏ´Â ¹è°æÂ÷ºÐ¹ý°ú »ö»óÀ» ±â¹ÝÀ¸·Î ÇÏ´Â ¹è°æÂ÷ºÐ¹ý, º» ³í¹®¿¡¼ Á¦¾ÈÇÏ´Â »ö»ó ±â¿ï±â ±â¹Ý ¹è°æ Â÷ºÐ¹ýÀÇ °á°ú¸¦ ºñ±³ÇÔÀ¸·Î½á Á¦¾È ±â¹ýÀÇ ¾ÈÁ¤¼ºÀ» ÀÔÁõÇÏ¿´´Ù. 6¸íÀÇ ½ÇÇè´ë»óÀÚÀÇ 1ºÎÅÍ 9±îÁöÀÇ ¼öÁöÈ 2700°³ÀÇ ¿µ»óÀ¸·ÎºÎÅÍ ¼Õ Ư¼º Á¤º¸¸¦ ÃßÃâÇÏ°í ÀÌ¿¡ ´ëÇÏ¿© ÈÆ·ÃÀ» ÅëÇÑ ÇнÀ ¸ðµ¨À» »ý¼ºÇÏ¿´´Ù. ÇнÀ¸ðµ¨À» ±â¹ÝÀ¸·Î ½ÇÇèÀÚ 6ÀÎÀÇ ¼Õ ÇüÅ 1620°³ÀÇ µ¥ÀÌÅÍ¿¡ ´ëÇÏ¿© ÀÎÁö ½ÇÇèÀ» ½Ç½ÃÇÏ¿© 92.6%¿¡ À̸£´Â ¼Õ ÇüÅ ÀÎ½Ä ¼º°ø·üÀ» ¾ò¾ú´Ù. |
¿µ¹®³»¿ë (English Abstract) |
In this paper, we present a robust hand recognition approach to sudden illumination changes. The proposed approach constructs a background model with respect to hue and hue gradient in HSI color space and extracts a foreground hand region from an input image using the background subtraction method. Eighteen features are defined for a hand pose and multi-class SVM(Support Vector Machine) approach is applied to learn and classify hand poses based on eighteen features. The proposed approach robustly extracts the contour of a hand with variations in illumination by applying the hue gradient into the background subtraction. A hand pose is defined by two Eigen values which are normalized by the size of OBB(Object-Oriented Bounding Box), and sixteen feature values which represent the number of hand contour points included in each subrange of OBB. We compared the RGB-based background subtraction, hue-based background subtraction and the proposed approach with sudden illumination changes and proved the robustness of the proposed approach. In the experiment, we built a hand pose training model from 2,700 sample hand images of six subjects which represent nine numerical numbers from one to nine. Our implementation result shows 92.6% of successful recognition rate for 1,620 hand images with various lighting condition using the training model. |
Å°¿öµå(Keyword) |
¹è°æÂ÷°¨
»ö»ó±â¿ï±â
SVM
¼ÕÀνÄ
Background Subtraction
Hue-Gradient
SVM
Hand Recognition
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|