The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지

A Enhancement of the Face Recognition using PCA&LDA-SIFT Algorithm

PCA&LDA-SIFT 알고리즘을 이용한 얼굴인식 성능의 향상

  • Published : 2010.06.30
⟨ Previous Next ⟩

Abstract

Face recognition is actively being studied in image processing, pattern recognition, computer vision and neural network. It much developed through various studies in the past. Yet it is possible only in restricted environment because of changes in illumination or changes in image including facial size according to distance. This paper used among methods of recognizing face SIFT(Scale Invariant Feature Transform) algorithm which is characterized by being unyielding against illumination and invariant against the size and rotation of an image. However, the algorithm with the disadvantage of deteriorating keypoint matching performance becomes a factor of lowering recognition performance. To improve it, we proposed an algorithm of grafting a PCA&LDA fusion model into SIFT algorithm descriptor, and compared and analyzed it in performance with the existing recognition algorithms such as PCA(Principal Component Analysis), LDA(Linear Discirminant Analysis) and SIFT.

얼굴인식은 영상처리, 패턴인식, 컴퓨터 비젼, 그리고 신경망에서 활발하게 연구가 진행되고 있다. 과거 여러 연구를 통해 얼굴인식은 많은 발전이 있었다. 그러나 조명변화나 거리에 따른 얼굴의 크기 등의 영상의 변화 때문에 제약된 환경에서만 얼굴을 인식하는 수준에 머물러 있다. 본 논문은 인식 방법 중에 조명에 강인하고 영상의 크기와 회전에도 변하지 않는 특성을 가진 SIFT(Scale Invariant Feature Transform, 크기불변특징변환) 알고리즘을 이용한다. 그러나 SIFT 알고리즘은 특징점 정합 성능이 떨어지는 단점을 가지고 있어 인식 성능의 저하 요인이 되고 있다. 이를 개선하고자, SIFT 알고리즘의 기술자에 PCA&LDA 융합모델을 접목하는 알고리즘을 제안하고, 기존의 PCA(Principal Component Analysis, 주성분 분석법), LDA(Linear Discirminant Analysis, 선형판별분석법), SIFT등의 인식 알고리즘과 성능을 비교 분석한다.

Keywords

References

  1. R. Chellappa, Charles L. Wilson, and S. Sirohey,"Human and Machine Recognition of Faces : A Survey," Proc. IEEE, Vol. 83, No. 5, pp. 704-740, May, 1995.
  2. W. Zhao, R. Chellappa, A. Rosenfeld, and P.J. Phllips, "Facerecognition : A survey," CVL Technical Report, Center for Automation Research, University of Maryland at College Park, Oct., 2000.
  3. David G. Lowe, "Distinctive Image Features From Scale-Invariant Keypoints," Accepted for publication in the International Journal of Computer Vision, 2004.
  4. K. Mikolajczyk and C. Schmid, "An affine invariant interest point detector," Proc. of the 7th European conference on Computer Vision(ECCV), Copenhagen, Denmark, Vol. I, pp. 128-142, 2002.
  5. D. D. Zhang, "Automated Biometrics : Technologies and System," Kluwer Academic Publishers, Boston, May, 2000.
  6. A. S. Georghiades, P. N. Belhumeur, and D. J. Kriegman, "From Few to Many : Illumination Cone Models for Face Recognition under Variable Lighting and Pose," IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 23, No. 6, pp. 643-660, June, 2001. https://doi.org/10.1109/34.927464
  7. . Sirovich and M. Kirby, "Low-dimensional Procedure for the Characterization of Human Faces," J. Opt. Soc. Amer. 4, pp. 519-524, 1987. https://doi.org/10.1364/JOSAA.4.000519
  8. M. Turk and A. Pentland, "Eigenfaces for Recognition," Journal of Cognitive Neuroscience, Vol. 3, pp. 71-86, 1994.
  9. Erik. Hjelmas, "Face Detection : A Survey," Computer Vision and Image Understanding, Vol. 83, pp. 236-274, 2001. https://doi.org/10.1006/cviu.2001.0921
  10. K. K. Sung and T. Poggio, "Learning a Distribution-Based Face Model for Model Human Face Detection," CVPR'95, pp. 398-406, 1995.