Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Improved Skin Color Extraction Based on Flood Fill for Face Detection

얼굴 검출을 위한 Flood Fill 기반의 개선된 피부색 추출기법

  • Lee, Dong Woo (Dept of Plasma Bio Display, KwangWoon University) ;
  • Lee, Sang Hun (Ingenium College of Liberal Arts, KwangWoon University) ;
  • Han, Hyun Ho (Institute of Information Technology, KwangWoon University) ;
  • Chae, Gyoo Soo (Division of Information Communication Eng., Baekseok University)
  • 이동우 (광운대학교 플라즈마바이오디스플레이학부) ;
  • 이상훈 (광운대학교 인제니움학부) ;
  • 한현호 (광운대학교 정보과학교육원) ;
  • 채규수 (백석대학교 정보통신학부)
  • Received : 2019.03.15
  • Accepted : 2019.06.20
  • Published : 2019.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a Cascade Classifier face detection method using the Haar-like feature, which is complemented by the Flood Fill algorithm for lossy areas due to illumination and shadow in YCbCr color space extraction. The Cascade Classifier using Haar-like features can generate noise and loss regions due to lighting, shadow, etc. because skin color extraction using existing YCbCr color space in image only uses threshold value. In order to solve this problem, noise is removed by erosion and expansion calculation, and the loss region is estimated by using the Flood Fill algorithm to estimate the loss region. A threshold value of the YCbCr color space was further allowed for the estimated area. For the remaining loss area, the color was filled in as the average value of the additional allowed areas among the areas estimated above. We extracted faces using Haar-like Cascade Classifier. The accuracy of the proposed method is improved by about 4% and the detection rate of the proposed method is improved by about 2% than that of the Haar-like Cascade Classifier by using only the YCbCr color space.

본 논문에서는 YCbCr 색공간을 이용한 피부색 추출에서 조명과 그림자에 의한 손실 영역을 Flood Fill 알고리즘을 이용하여 보완하고 Haar-like 특징을 이용한 Cascade Classifier 얼굴 검출 방법을 제안하였다. Haar-like 특징을 이용한 Cascade Classifier는 이미지에서 기존의 YCbCr 색공간을 이용한 피부색 추출은 단순히 임계값만 사용하기 때문에 조명, 그림자 등에 의해 잡음과 손실 영역이 발생할 수 있다. 이러한 문제를 해결하기 위해 침식, 팽창 연산을 사용하여 잡음을 제거하였고 손실 영역을 추정하기 위해 Flood Fill 알고리즘을 사용하여 손실 영역을 추정하였다. 추정한 영역에 대하여 YCbCr 색공간의 임계값을 추가로 허용하였다. 나머지 손실영역에 대하여 위에서 추정한 영역중 추가로 허용한 영역의 평균값으로 색을 채워 넣었다. 추출한 이미지에 Haar-like Cascade Classifier를 사용하여 얼굴을 검출하였다. 기존의 Haar-like Cascade Classifier의 방법보다 제안하는 방법이 정확도가 약 4% 향상되었으며 YCbCr 색공간만을 이용한 피부색 추출보다 제안하는 방법의 검출률이 약 2% 향상되었다.

Keywords

OHHGBW_2019_v10n6_7_f0001.png 이미지

Fig. 1. Haar-like elementary feature

OHHGBW_2019_v10n6_7_f0002.png 이미지

Fig. 2. Feature Detection using Haar-like

OHHGBW_2019_v10n6_7_f0003.png 이미지

Fig. 3. Cascade Classifier

OHHGBW_2019_v10n6_7_f0004.png 이미지

Fig. 4. 4-way Flood Fill

OHHGBW_2019_v10n6_7_f0005.png 이미지

Fig. 5. Flow Chart of Proposed Method

OHHGBW_2019_v10n6_7_f0006.png 이미지

Fig. 6. Skin Detection using YCbCr

OHHGBW_2019_v10n6_7_f0007.png 이미지

Fig. 7. Noise Removal Image

OHHGBW_2019_v10n6_7_f0008.png 이미지

Fig. 8. Flood Fill Result

OHHGBW_2019_v10n6_7_f0009.png 이미지

Fig. 9. Flood Fill Result(a) Original Image

OHHGBW_2019_v10n6_7_f0010.png 이미지

Fig. 10. Flood Fill Result

OHHGBW_2019_v10n6_7_f0011.png 이미지

Fig. 11. Correction using Flood Fill

OHHGBW_2019_v10n6_7_f0012.png 이미지

Fig. 12. Haar-like Cascade Classifier

OHHGBW_2019_v10n6_7_f0013.png 이미지

Fig. 13. Compared in people image

OHHGBW_2019_v10n6_7_f0014.png 이미지

Fig. 14. Comparing images of objects with human figures

OHHGBW_2019_v10n6_7_f0015.png 이미지

Fig. 15. Comparing Image of Gray Image

Table 1. Comparison with other algorithms

OHHGBW_2019_v10n6_7_t0001.png 이미지

Table 2. Comparison with other Skin Color Extraction

OHHGBW_2019_v10n6_7_t0002.png 이미지

References

  1. H. J. Kim, Y. S. Park, K. B. Kim & S. H. Lee. (2019). Modified HOG Feature Extraction for Pedestrian Tracking. Journal of the Korea Convergence Society, 10(3), 39-47. https://doi.org/10.15207/JKCS.2019.10.3.039
  2. S. K. Pyo, Y. S. Park, G. S. Lee & S. H. Lee. (2019). Hangeul detection method based on histogram and character structure in natural image. Journal of the Korea Convergence Society, 10(3), 15-22. https://doi.org/10.15207/JKCS.2019.10.3.015
  3. T. H. Yoo, G. S. Lee & S. H. Lee. (2012). Window Production Method based on Low-Frequency Detection for Automatic Object Extraction of GrabCut. Journal of Digital Convergence, 10(8), 211-217 https://doi.org/10.14400/JDPM.2012.10.8.211
  4. H. H. Han, G. S. Lee, J. Y. Lee & S. H. Lee. (2012). Region Segmentation Technique Based on Active Contour for Object Segmentation, Journal of Digital Convergence, 10(3), 167-172. https://doi.org/10.14400/JDPM.2012.10.3.167
  5. J. H. Park. (2016). Improved Face Detection Algorithm Using Color Distribution and Shape Characteristics, Graduate dissertation. Kwangwoon University, Seoul
  6. J. S Oh (2018). Improved Face Detection Algorithm Using Face Verification. Journal of the Korea Institute of Information and Communication Engineering, 22(10), 1334-1339 https://doi.org/10.6109/JKIICE.2018.22.10.1334
  7. M. A. Turk & A. P. Pentland. (1991). Face recognition using eigenfaces. In Proceedings, 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 586-591). IEEE.
  8. S. F, Hafez, M. M. Selim & H. H. Zayed. (2015). 2d face recognition system based on selected gabor filters and linear discriminant analysis lda. Conference on Computer Vision and Pattern Recognition. Boston: IEEE
  9. S. Chang & S. Yoo. (2000). Face Detection Using Color Information,. The Journal of Korean Institute of Communications and Information Sciences, 25(6), 1012-1020.
  10. R. L. Hsu, M. Abdel-Mottaleb & A. K. Jain. (2002). Face detection in color images. IEEE transactions on pattern analysis and machine intelligence, 24(4), 696-706 https://doi.org/10.1109/34.1000242
  11. D. N. Chandrappa, M. Ravishankar & D. R. RameshBabu. (2011, April). Face detection in color images using skin color model algorithm based on skin color information. In 2011 3rd International Conference on Electronics Computer Technology. (1, pp. 1988-2018) Kanyakumari : IEEE.
  12. C. M. Kim & K. W. Lee. (2014). Face Region Detection of a Pedestrian Using Ω-Feature in Video Surveillance System, Journal of KIIT. 14(9), 27-36
  13. C. A. Perez, V. A. Lazcano & P. A. Estevez. (2007). Real-time iris detection on coronal-axis-rotated faces. IEEE Transactions on Systems, Man, and Cybernetics, Part C(Applications and Reviews), 37(5), 971-978. https://doi.org/10.1109/TSMCC.2007.900647
  14. W. Chen, T. Sun, X. Yang & L. Wang. (2009, August). Face detection based on half face-template. In 2009 9th International Conference on Electronic Measurement & Instruments. (pp. 4-54). Beijing : IEEE.
  15. W. Wang & H. Niu. (2012). Face detection based on improved AdaBoost algorithm in E-Learning. In Cloud Computing and Intelligent Systems.2012 IEEE 2nd International Conference on (pp. 924-927). Hangzhou : IEEE.
  16. D. C. Kim, C. H. Lee, M. H. Choi & Y. H. Haa. (2012). Skin Detection Method using Color Space based Methods and Focus Region. Journal of Korean Society for Imaging Science and Technology, 18(4), 16-22.
  17. P. Viola & M. J. Lee.(2004). Robust real-time face detection, Proceedings Eighth IEEE International Conference on Computer Vision. (pp. 137-154) Vancouver : IEEE
  18. I. Kallenbach, R. Schweiger, G. Palm & O. Lohlein. (2006, September). Multi-class object detection in vision systems using a hierarchy of cascaded classifiers. In Intelligent Vehicles Symposium, (pp. 383-387). Tokyo : IEEE.
  19. E. M. Nosal. (2008, October). Flood-fill algorithms used for passive acoustic detection and tracking. In New Trends for Environmental Monitoring Using Passive Systems, (pp. 1-5). Hyeres : IEEE.