Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Improved Facial Component Detection Using Variable Parameter and Verification

가변 변수와 검증을 이용한 개선된 얼굴 요소 검출

  • Oh, Jeong-su (Department of Display Engineering, Pukyong National University)
  • Received : 2019.12.05
  • Accepted : 2019.12.12
  • Published : 2020.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Viola & Jones' object detection algorithm is a very good algorithm for the face component(FC) detection, but there are still problems such as duplicate detection, false detection and non-detection due to parameter setting. This paper proposes an improved FC detection algorithm that applies the variable parameter to reduce non-detection and the verification to reduce duplicate detection and false detection to the Viola & Jones' algorithm. The proposed algorithm reduces the non-detection by changing the parameter value of the Viola & Jones' algorithm until the potential valid FCs are detected, and eliminates the duplicate detection and the false detection by using the verification that evaluates size, position, and uniqueness of the detected FCs. Simulation results show that the proposed algorithm includes valid FCs in the detected objects and then detects only the valid FCs by removing invalid FCs from them.

Viola & Jones의 객체 검출 알고리즘은 얼굴 요소 검출을 위한 매우 우수한 알고리즘이지만 변수 설정에 따른 중복 검출, 오 검출, 미 검출 같은 문제들이 여전히 존재한다. 본 논문은 Viola & Jones의 객체 검출 알고리즘에 미 검출을 줄이기 위한 가변 변수와 중복 검출과 오 검출을 줄이기 위한 검증을 적용한 개선된 얼굴 요소 검출 알고리즘을 제안한다. 제안된 알고리즘은 잠재적 유효 얼굴 요소들을 검출할 때까지 Viola & Jones의 객체 검출의 변수 값을 변화시켜 미 검출을 줄이고, 검출된 얼굴 요소의 크기, 위치, 유일성을 평가하는 검증을 이용해 중복 검출과 오 검출들을 제거시켜 준다. 시뮬레이션 결과들은 제안된 알고리즘이 검출된 객체들에 유효 얼굴 요소들을 포함시키고 나서 무효 얼굴 요소들을 제거하여 유효 얼굴 요소들만을 검출하는 것을 보여준다.

Keywords

References

  1. X. Sun, P. Wu, and S.C.H. Hoi, "Face Detection Using Deep Learning: An Improved Faster RCNN Approach," Neurocomputing, vol. 299, no. 19, pp. 42-50, Jul. 2018. https://doi.org/10.1016/j.neucom.2018.03.030
  2. M. Castrillon, O. Deniz, D. Hernandez, and J. Lorenzo, "A Comparison of Face and Facial Feature Detectors Based on the Viola-Jones General Object Detection Framework," Machine Vision and Applications, vol. 22, no. 3, pp. 481-494, Mar. 2011. https://doi.org/10.1007/s00138-010-0250-7
  3. P. Viola, and M. J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Kauai, pp. 511-518, 2001.
  4. J. S. Oh, "Improved Face Detection Algorithm Using Face Verification," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 10, pp. 1334-1339, Oct. 2018. https://doi.org/10.6109/JKIICE.2018.22.10.1334
  5. J. S. Oh, and H. Hoon, "Performance Analysis of Viola & Jones Facial Component Detection Algorithm," Proceedings of Conference on Korea Information and Communication Engineering, vol. 23, no. 2, Busan, pp. 603-606, 2019.
  6. H. Y. Han, Introduction to Pattern Recognition, Hanbit Academy, Inc., Seoul, 2015.
  7. A. Kaehler, and G. Bradski, Learning OpenCV3, Wikibooks, Paju, 2018.
  8. MathWorks, vision.CascadeObjectDetector System object : Properties [internet]. Available https://kr.mathworks.com/help/vision/ref/vision.cascadeobjectdetector-system-object.html.