Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

A Method for Determining Face Recognition Suitability of Face Image

얼굴영상의 얼굴인식 적합성 판정 방법

  • 이승호 (한국기술교육대학교 융합학과)
  • Received : 2018.07.09
  • Accepted : 2018.11.02
  • Published : 2018.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Face recognition (FR) has been widely used in various applications, such as smart surveillance systems, immigration control in airports, user authentication in smart devices, and so on. FR in well-controlled conditions has been extensively studied and is relatively mature. However, in unconstrained conditions, FR performance could degrade due to undesired characteristics of the input face image (such as irregular facial pose variations). To overcome this problem, this paper proposes a new method for determining if an input image is suitable for FR. In the proposed method, for an input face image, reconstruction error is computed by using a predefined set of reference face images. Then, suitability can be determined by comparing the reconstruction error with a threshold value. In order to reduce the effect of illumination changes on the determination of suitability, a preprocessing algorithm is applied to the input and reference face images before the reconstruction. Experimental results show that the proposed method is able to accurately discriminate non-frontal and/or incorrectly aligned face images from correctly aligned frontal face images. In addition, only 3 ms is required to process a face image of $64{\times}64$ pixels, which further demonstrates the efficiency of the proposed method.

얼굴인식(face recognition)은 스마트 감시 시스템, 공항 출입국관리, 스마트 기기의 사용자 인증 등 매우 다양한 용도로 활용되고 있다. 얼굴인식은 패턴인식(pattern recognition), 컴퓨터 비전(computer vision) 등에서 연구가 활발하게 진행되고 있으며 높은 인식 성능을 달성하였다. 하지만 입력된 얼굴영상의 특성(예 : 비 정면 얼굴)에 따라 동일한 얼굴인식 시스템의 성능이 크게 저하될 수 있는 문제점을 가지고 있다. 이러한 문제점을 극복하기 위해, 본 논문에서는 얼굴인식 시스템에 입력된 얼굴영상에 대하여 얼굴인식 측면에서의 사용 적합 여부를 판정하는 방법을 제안한다. 제안하는 방법은, 사전에 기준으로 정한 적합 얼굴영상들의 최적 조합으로 입력 얼굴영상을 복원하고, 복원 에러를 문턱값과 비교하여 사용 적합 여부를 결정한다. 얼굴영상에 포함된 조명변화가 사용 적합 여부를 판정하는데 미치는 영향을 감소시키기 위해, 기준 적합 얼굴영상들과 입력 얼굴영상들에 조명 보상을 위한 전처리(preprocessing) 과정을 수행한다. 실험결과, 제안하는 방법은 얼굴이 비 정면(non-frontal)인 경우나 얼굴정렬(face alignment)이 부정확한 경우 입력 얼굴영상을 얼굴인식에 부적합으로 판정할 수 있는 것으로 확인되었다. $64{\times}64$ 픽셀 크기의 얼굴영상 한 장을 판정하는데 불과 3ms의 처리시간을 가지므로 적합으로 판정된 입력 얼굴영상에 대해서만 얼굴인식을 수행함으로써 계산시간을 절약하고, 얼굴영상 특성에 따라 인식 성능이 급격히 저하되는 문제를 극복할 수 있을 것으로 기대한다.

Keywords

SHGSCZ_2018_v19n11_295_f0001.png 이미지

Fig. 1. Face image acquisition process in general FR framework(Images are from [7]). (a) Input image. (b) Detected face region. (c) Aligned face image.

SHGSCZ_2018_v19n11_295_f0002.png 이미지

Fig. 2. An overall framework of proposed determination method for an input face image.

SHGSCZ_2018_v19n11_295_f0003.png 이미지

Fig. 4. 50 reference face images(from [11]) used for determining an input face image.

SHGSCZ_2018_v19n11_295_f0004.png 이미지

Fig. 5. Reconstruction results for frontal face images without illumination change.

SHGSCZ_2018_v19n11_295_f0005.png 이미지

Fig. 6. Reconstruction results for frontal face images with illumination change.

SHGSCZ_2018_v19n11_295_f0006.png 이미지

Fig. 7. Reconstruction results for non-frontal face images.

SHGSCZ_2018_v19n11_295_f0007.png 이미지

Fig. 8. Reconstruction results for incorrectly aligned face images.

SHGSCZ_2018_v19n11_295_f0008.png 이미지

Fig. 3. (a)Input face image. (b)Blurred image of input face image in (a). (c)Preprocessed image.

References

  1. G. Hua, M. H. Yang, E. Learned-Miller, Y. Ma, M. Turk, D. J. Kriegman, T. S. Huang, "Introduction to the special section on real-world face recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.33, No.10, pp.1921-1924, 2011. DOI: https://dx.doi.org/10.1109/TPAMI.2011.182
  2. A. Eleyan, H. Ozkaramanli, H. Demirel, "Weighted majority voting for face recognition from low resolution video sequences", Proceedings of 2009 Fifth International Conference on Soft Computing, Computing with Words and Perceptions in System Analysis, Decision and Control, Sept., 2009. DOI: https://dx.doi.org/10.1109/ICSCCW.2009.5379496
  3. X. Gao, S. Z. Li, R. Liu, P. Zhang, "Standardization of Face Image Sample Quality", Proceedings of International Conference on Biometrics 2007: Advances in Biometrics, pp.242-251, 2007. DOI: https://dx.doi.org/10.1007/978-3-540-74549-5_26
  4. J. Sang, Z. Lei, and S. Z. Li, "Face Image Quality Evaluation for ISO/IEC Standards 19794-5 and 29794-5", Proceedings of International Conference on Biometrics 2009: Advances in Biometrics, pp.229-238, Springer, 2009. DOI: https://dx.doi.org/10.1007/978-3-642-01793-3_24
  5. J. Chen, Y. Deng, G. Bai, G. Su, "Face Image Quality Assessment Based on Learning to Rank", IEEE Signal Processing Letters, Vol.22, No.1, pp.90-94, 2015. DOI: https://dx.doi.org/10.1109/LSP.2014.2347419
  6. H. Wang, Y. Wang, Y. Cao, "Video-Based Face Recognition: A Survey", World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, Vol.3, No.12, pp.293-302, 2009.
  7. M. Krasser, "Deep face recognition with Keras, Dlib and OpenCV", Available From: http://krasserm.github.io/2018/02/07/deep-face-recognition/
  8. Wikipedia, "Nearest-Neighbor Interpolation", Available From: https://en.wikipedia.org/wiki/Nearest-neighbor_ interpolation
  9. Wikipedia, "Gaussian blur", Available From: https://en.wikipedia.org/wiki/Gaussian_blur
  10. L. Zhang, M. Yang, X. C. Feng, Y. Ma, D Zhang, "Collaborative Representation Based Classification for Face Recognition", arXiv:1204.2358, 2012.
  11. P. J. Phillips, H. Moon, S. A. Rizvi, P. J. Rauss, "The FERET Evaluation Methodology for Face Recognition Algorithms", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22, No.10, pp.1090-1104, 2000. DOI: https://dx.doi.org/10.1109/34.879790