Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Improvement of Skin Loss Area in Skin Color Extraction for Face Detection

얼굴 검출을 위한 피부색 추출 과정에서 피부색 손실 영역 개선에 관한 연구

  • Kim, Dong In (Dept of Plasma Bio Display, KwangWoon University) ;
  • Lee, Gang Seong (Ingenium College of Liberal Arts, KwangWoon University) ;
  • Han, Kun Hee (Division of Information & Communication Engineering, Baekseok University) ;
  • Lee, Sang Hun (Ingenium College of Liberal Arts, KwangWoon University)
  • 김동인 (광운대학교 플라즈마바이오디스플레이학과) ;
  • 이강성 (광운대학교 인제니움학부대학) ;
  • 한군희 (백석대학교 정보통신학부대학) ;
  • 이상훈 (광운대학교 인제니움학부대학)
  • Received : 2019.03.15
  • Accepted : 2019.05.20
  • Published : 2019.05.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an improved facial skin color extraction method to solve the problem that facial surface is lost due to shadow or illumination in skin color extraction process and skin color extraction is not possible. In the conventional HSV method, when facial surface is brightly illuminated by light, the skin color component is lost in the skin color extraction process, so that a loss area appears on the face surface. In order to solve these problems, we extract the skin color, determine the elements in the H channel value range of the skin color in the HSV color space among the lost skin elements, and combine the coordinates of the lost part with the coordinates of the original image, To minimize the number of In the face detection process, the face was detected using the LBP Cascade Classifier, which represents texture feature information in the extracted skin color image. Experimental results show that the proposed method improves the detection rate and accuracy by 5.8% and 9.6%, respectively, compared with conventional RGB and HSV skin color extraction and face detection using the LBP cascade classifier method.

본 논문에서는 피부색 추출과정에서 그림자나 조명에 의해 얼굴 표면이 손실되어 피부색 추출이 되지 않는 문제점을 해결하기 위하여 개선된 얼굴 피부색 추출 방법을 제안하였다. 기존의 HSV를 이용한 방법은 조명에 의해 얼굴표면이 밝게 비춰지는 경우에 피부색 추출과정에서 피부색 요소가 손실되기 때문에 얼굴표면에 손실 영역이 나타나게 된다. 이러한 문제점을 해결하기 위해 피부색을 추출한 뒤 손실된 피부 요소 중 HSV 색공간에서 피부색의 H 채널 값 범위에 있는 요소들을 판단하여 손실된 부분의 좌표와 원본 이미지 좌표의 결합을 통해 피부색이 손실되는 부분을 최소화 하는 방법을 제안하였다. 얼굴 검출 과정으로는 추출한 피부색 이미지에서 질감 특징정보를 나타내는 LBP Cascade Classifier를 이용하여 얼굴을 검출하였다. 실험결과 제안하는 방법이 기존의 RGB와 HSV 피부색 추출과 LBP Cascade Classifier 방법을 이용한 얼굴검출보다 검출률과 정확도는 각각 5.8%, 9.6% 향상된 결과를 보였다.

Keywords

OHHGBW_2019_v10n5_1_f0001.png 이미지

Fig. 1. Face Skin Color Extraction (a) Original Image (b) RGB Skin Color Extraction (c) YCbCr Skin Color Extraction (d) HSV Skin Color Extraction

OHHGBW_2019_v10n5_1_f0002.png 이미지

Fig. 2. 19stage facial features (a) Original Image (b) stage1 ⋯ stage19 (c) LBP face feature

OHHGBW_2019_v10n5_1_f0003.png 이미지

Fig. 3. Face LBP feature

OHHGBW_2019_v10n5_1_f0004.png 이미지

Fig. 4. Flowchart of proposed method

OHHGBW_2019_v10n5_1_f0005.png 이미지

Fig. 5. Skin Color Extraction (a) Original Image (b) RGB skin extraction image (c) HSV skin extraction image

OHHGBW_2019_v10n5_1_f0006.png 이미지

Fig. 6. Skin Color Extraction (a) Original Image (b) HSV skin extraction image

OHHGBW_2019_v10n5_1_f0007.png 이미지

Fig. 8. Comparison Skin Color Extraction (a) HSV Skin Color Extraction (b) Proposed method result

OHHGBW_2019_v10n5_1_f0008.png 이미지

Fig. 9. FDDB 2002 Dataset

OHHGBW_2019_v10n5_1_f0009.png 이미지

Fig. 10. Experimental results (a) Original Image (b) HSV skin extraction face detection (c) Proposed method

OHHGBW_2019_v10n5_1_f0010.png 이미지

Fig. 11. Face detection comparison ① (a) Original Image (b) LBP cascade face detection (c) proposed method

OHHGBW_2019_v10n5_1_f0011.png 이미지

Fig. 12. Face detection comparison ② (a) Original Image (b) LBP cascade face detection (c) proposed method

Fig. 7. Combine Skin Extraction image (a) Skin Color Extraction Image (b) Original Image (c) Improved Skin Color Extraction

OHHGBW_2019_v10n5_1_t0001.png 이미지

Table 1. Comparison table of other algorithms

OHHGBW_2019_v10n5_1_t0002.png 이미지

References

  1. J. H. Park. (2017). Improved face detection algorithm using color distribution and shape characteristics. Master dissertation. Kwangwoon University, seoul.
  2. K. H. Kong. (2017). A Study of Face Detection Algorithm Using CNN Based on Symmetry-LGP & Uniform-LGP and the Skin Color. JKIIT, .15(.1), 107-113. DOI : 10.14801/jkiit.2017.15.1.107
  3. Zhang, J. & Xiao, X. (2015). Face Recognition Algorithm Based on Multi-layer Weighted LBP. In 2015 8th International Symposium on Computational Intelligence and Design(ISCID), (Vol. 1, pp. 196-199). IEEE.
  4. D. S. Pamungkas & S. Al-Aidid. (2018). Detection, Recognition, and Tracking Face Using 2 DoF Robot with Haar LBP Histogram. In 2018 International Conference on Applied Engineering (ICAE). (pp. 1-5). IEEE.
  5. Y. S. Ryu. (2018). A study on object tracking method using particle filter based on uniform CB-LBP. Master dissertation. Kwangwoon University, seoul.
  6. J. H. Kim. (2015). A Study on Tracking in Video Using Modified Particle Filter. Master dissertation. Kwangwoon University, Seoul.
  7. 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
  8. 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
  9. H. H. Han, J. Y. Lee, K. D. Jung & S. H. Lee. (2018). Patch Information based Linear Interpolation for Generating Super-Resolution Images in a Single Image. Journal of the Korea Convergence Society, 9(6), 45-52. https://doi.org/10.15207/JKCS.2018.9.6.045
  10. 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
  11. 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
  12. H. B. Kwon, D. J. Kwon, U. D. Chang, Y. B. Yun ,& J. H. Ahn. (2004, Jun). A Facial Region Detection using the Skin Color and Edge Information at YCbCr, Journal of Korea Multimedia Society, 7(1), 27-34.
  13. J. J. De Dios & N. Garcia. (2003, Sep.). Face detection based on a new color space YCgCr, Image Processing 2003 International Conference on Image Processing (Cat. No. 03CH37429) (3, pp. III-909). IEEE.
  14. Oliveira, V. A., & A. Conci. (2009). Skin Detection using HSV color space. H. Pedrini, & J. Marques de Carvalho, Workshops of Sibgrapi.
  15. H. J. Lee, H. Y. Kim, D. Lee & S. G. Lee. (2017). Face Detection using Orientation(In-Plane Rotation) Invariant Facial Region Segmentation and Local Binary Patterns(LBP), Journal of KIISE, 44(7), 692-702. DOI :10.5626/JOK.2017.44.7.692
  16. C. Y., Jo. (2008). Face Detection using LBP features. Final Project Report 77
  17. P. Viola & J. Michael. (2001). Rapid object detection using a boosted cascade of simple features." Computer Vision and Pattern Recognition(1), 1, 511-518
  18. D. N. Chandrappa, M. Ravishankar & D. R. RameshBabu. (2011). In 2011 3rd International Conference on Electronics Computer Technology, (1, pp. 254-258). IEEE.
  19. 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 DOI : 10.6109/jkiice.2018.22.10.1334
  20. FDDB: Face Detection Data Set and Benchmark. http://vis-www.cs.umass.edu/fdd