Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
ÀûÀÀ ÈÞ¸®½ºÆ½ ºÐÇÒ ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ ½Ç½Ã°£ Â÷·® ¹øÈ£ÆÇ ÀÎ½Ä ½Ã½ºÅÛ |
¿µ¹®Á¦¸ñ(English Title) |
Real-Time Vehicle License Plate Recognition System Using Adaptive Heuristic Segmentation Algorithm |
ÀúÀÚ(Author) |
Áø¹®¿ë
¹ÚÁ¾ºó
À̵¿¼®
¹Úµ¿¼±
Moon Yong Jin
Jong Bin Park
Dong Suk Lee
Dong Sun Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 03 NO. 09 PP. 0361 ~ 0368 (2014. 09) |
Çѱ۳»¿ë (Korean Abstract) |
Â÷·® ¹øÈ£ÆÇ ÀÎ½Ä ½Ã½ºÅÛÀº º¹ÀâÇÑ ±³Åëȯ°æÀÇ È¿À²Àû °ü¸®¸¦ À§ÇØ ¹ßÀüµÇ¾î ÇöÀç ¸¹Àº °÷¿¡ »ç¿ëµÇ°í ÀÖ´Ù. ±×·¯³ª Á¶¸í, ÀâÀ½, ¹è°æ º¯È, ¹øÈ£ÆÇ ÈÑ¼Õ µî ȯ°æº¯È¿¡ Å« ¿µÇâÀ» ¹Þ±â ¶§¹®¿¡ Á¦ÇÑµÈ È¯°æ¿¡¼¸¸ µ¿ÀÛÇϸç, ½Ç½Ã°£À¸·Î »ç¿ëÇϱ⠾î·Æ´Ù. º» ³í¹®¿¡¼´Â Á¶¸íº¯È¿Í ÀâÀ½¿¡ °°ÇÇÏ¸ç ºü¸¥ ¹øÈ£ÆÇ ÀνÄÀ» À§ÇÑ ÈÞ¸®½ºÆ½ ºÐÇÒ ¾Ë°í¸®Áò ¹× À̸¦ ÀÌ¿ëÇÑ ½Ç½Ã°£ ¹øÈ£ÆÇ ÀÎ½Ä ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. ù ¹ø° ´Ü°è´Â Haar-like Ư¡°ú Adaboost¸¦ ÀÌ¿ëÇÏ¿© ¹øÈ£ÆÇÀ» °ËÃâÇÑ´Ù. ÀÌ ¹æ¹ýÀº ÀûºÐ¿µ»óÀ» ÀÌ¿ëÇϸç ÄɽºÄÉÀÌµå ±¸Á¶·Î ±¸¼ºµÇ¾î ÀÖ¾î ºü¸¥ °ËÃâÀÌ °¡´ÉÇÏ´Ù. µÎ ¹ø° ´Ü°è¿¡¼ ÀûÀÀ È÷½ºÅä±×·¥ ÆòÈ°È ¹æ¹ý°ú ³ëÀÌÁ °æ°¨½ÃÅ°´Â ¹ÙÀÌ·¹ÅÍ·² ÇÊÅ͸¦ ÀÌ¿ëÇÏ¿© ¹øÈ£ÆÇÀÇ Á¾·ù¸¦ °áÁ¤ÇÑ ÈÄ, ¹øÈ£ÆÇ Á¾·ù¿¡ µû¶ó ÀûºÐ¿µ»óÀ» ÀÌ¿ëÇÑ ÀûÀÀ ÀÌÁøÈ, Çȼ¿ ÇÁ·ÎÁ§¼Ç, »çÀüÁö½Ä µîÀ» ±â¹ÝÀ¸·Î ºü¸£°í Á¤È®ÇÑ ¹®ÀÚ ºÐÇÒÀ» ÇÑ´Ù. ¼¼ ¹ø° ´Ü°è¿¡¼´Â HOG¿Í ½Å°æ¸Á ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÏ¿© ¼ýÀÚ¸¦ ÀνÄÇÏ°í, SVMÀ» ÀÌ¿ëÇØ ÇѱÛÀ» ÀνÄÇÑ´Ù. ½ÇÇè°á°ú´Â ¹øÈ£ÆÇ°ËÃâ¿¡ 94.29%ÀÇ °ËÃâ·ü, 2.94%ÀÇ ¿À°æº¸À²À» º¸À̸ç, ¹®ÀÚºÐÇÒ¿¡¼´Â °ËÃâ·ü 97.23%, 2.94%ÀÇ ¿À°æº¸À²À» º¸¿´´Ù. ¹®ÀÚÀνĿ¡¼ Æò±Õ ÀνķüÀº 98.38%ÀÌ´Ù. Æò±Õ ¿î¿ë½Ã°£Àº 140msÀ¸·Î ºü¸£°í °ÀÎÇÑ ½Ç½Ã°£ ½Ã½ºÅÛÀ» ¸¸µé ¼ö ÀÖ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.
|
Å°¿öµå(Keyword) |
¹øÈ£ÆÇÀÎ½Ä Heuristic Segmentation
AdaBoost
Histogram of Oriented Gradients(HOG)
Heuristic Segmentation
AdaBoost
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|