KSC 2018
Current Result Document : 1 / 1
ÇѱÛÁ¦¸ñ(Korean Title) |
ºê·¹ÀÌÅ© Æ÷ÀÎÆ® °ª ±â¹Ý ¾ó±¼ °ËÃâ ¾Ë°í¸®ÁòÀÇ ¼º´É ºÐ¼® |
¿µ¹®Á¦¸ñ(English Title) |
Performance Analysis of Break Point Value Based Face Detection Algorithm |
ÀúÀÚ(Author) |
źÁö³ª ¼úź
µ¨ ·Î¾î È£»çÀÎ
¾ÆÁî ÇÏ ·çµò
±¸¿£ ¾È È
ÀÌ¿µ±¸
Tangina Sultana
Md Delowar Hossain
Md. Azher Udd
Nguyen Anh Tu Young-Koo Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 45 NO. 02 PP. 0821 ~ 0823 (2018. 12) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Face detection determines the presence and location of a face in an image to localize and excavate faces from the background. One of the most efficient face detection algorithms is Viola Jones algorithm, but the major limitations of this algorithm is the redundant pixel value of the integral image. This is because the integral image integrates both face and non-face pixel values and it reduces the accuracy. To overcome this issue a new method is proposed in this paper. A mathematical model is derived of our proposed method to analyze the performance with the existing system. By using the proposed method, the more relevant frame can be easily found. From the mathematical analysis, it can be seen that our proposed method has achieved higher efficiency than the Viola Jones algorithm. Therefore, our proposed method is more efficient face detection process as compared to the previous processes. |
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|