The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Face Recognition System Using LDA and SVM

LDA와 SVM을 이용한 얼굴 인식 시스템에 관한 연구

  • Lee, Jung-Jai (Dept. of Computer Information Science, Songwon University)
  • 이정재 (송원대학교 컴퓨터정보학과)
  • Received : 2015.10.15
  • Accepted : 2015.11.23
  • Published : 2015.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study proposed a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. The algorithm proposed detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). Also, by applying the feature vector obtained for SVM, face areas can be tested. After the testing, the feature vector is applied to LDA and using Euclidean distance in the 2nd dimension, the final analysis and matching is performed. The algorithm proposed in this study could increase the stability and accuracy of recognition rates and as a large amount of calculation was not necessary due to the use of two dimensions, real-time recognition was possible.

본 논문에서는 얼굴 인식을 위한 보다 안정적이며 조명 변화와 회전에 강인하게 얼굴 영역을 검출하며, 계산의 효율성과 검출 성능을 동시에 만족시키는 강인한 인식 알고리즘에 대해 제안한다. 제안하는 알고리즘은 전처리 과정을 거쳐 정규화한 후 얼굴 영역만을 분할 검출한 후 주성분분석(PCA)을 이용하여 특징벡터를 구한다. 또한 구해진 특징벡터를 SVM에 적용하여 최적의 이진분류를 진행함으로써 얼굴 영역에 대한 검증을 수행한다. 검증 후 특징벡터를 다시 LDA에 적용하여 2차원 공간상에서 유클리디안 거리 이용하여 최종 얼굴을 인식하게 된다. 본 논문에서 제안하는 방법으로 인식률의 안전성과 정확성을 향상시킬 수 있었으며, 차원 축소로 인해 많은 계산 량이 요구되지 않기 때문에 실시간 인식도 가능하다.

Keywords

References

  1. R. C. Gonzalez and R. E. Woods, Digital Image Processing. Upper Saddle River. New Jersey 07458: Prentice Hall, 2002.
  2. M. O. Faruqe and M. A. M. Hasan, "Face Recognition Using PCA and SVM", Anti-counterfeiting, Security, and Identification in Communication, 2009. ASID 2009. 3rd Int. Conf. on, Hong Kong, 20-22 Aug 2009, pp. 97-101.
  3. J. Yang and J. Yang, "Why can LDA be performed in PCA transformed space?," Pattern Recognition vol. 36, no. 2 Feb 2003, pp. 563-566. https://doi.org/10.1016/S0031-3203(02)00048-1
  4. V. N. Vapnik, The Natue of Statistical Learning Theory. New York: Springer-verlag, 1995.
  5. P. Liao, J. Liu, M. Wang, J. Ma, and W. Zhang, "Ensemble local fractional LDA for Face Recognition," Computer Science and Automation Engineering(CSAE), 2012 IEEE Int. Conf. on, Zhangjiajie, China vol. 3, 25-27 May 2012, pp. 586-590.
  6. C. Liu and H. Wechsler, "Independent component analysis of Gabor feature for face recognition," IEEE Trans. Neural Networks, vol. 14, no. 4, July 2003, pp. 919-928. https://doi.org/10.1109/TNN.2003.813829
  7. S. E. El-Khamy, O. Abdel-Alim, and M. M. Saii, "Neural Network Face Recognition Using Statistical Feature Extraction," Radio Science Conf., 2000. 17th NRSC '2000. Seventeenth National, Minufiya, 22-24 Feb 2000, pp. C31/1-C31/8.
  8. E. Osuna, R. Freund, and F. Girosi, "Training Support Vector Machines: An application ot face detection." Proc. IEEE. Computer Society Conference on. Computer Vision and Pattern Recognition(CVPR), San Juan, Puerto Reco. 17-19 Jun 1997, pp. 130-136.
  9. J. C. Platt, "Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines," Microsoft Research Technical Report MSR-TR-98-14, Microsoft, Redmond Wash., January, 1998.
  10. M.-H. Yang."Kernel Eigenfaces vs, Kernal Fisherfaces: Face Recognition Using kernal Methods, Automatrix Face and Gesture Recognition," 202, Proc. Fourth IEEE Int. Conf., Washinton D.C., U.S.A, 20-21 May 2002, pp. 0215.
  11. H. Kim,"Vocal Separation in Music Using SVM and Selective Frequency Subtraction," J. of the Korea Institute of Electronic Communication Sciences, vol. 10, no. 1, 2015, pp. 1-6. https://doi.org/10.13067/JKIECS.2015.10.1.1
  12. J. Jo, "A Car License Plate Recognition Using Colors Information, Morphological Characteristic and Neural Network," J. of the Korea Institute of Electronic Communication Sciences, vol. 5, no. 3, 2010, pp. 304-308.
  13. H. Park, A User Adaptation Method for Hand Shape Recognition Using Wrist-Mounted Camera," J. of the Korea Institute of Electronic Communication Sciences, vol. 8, no. 6, 2013, pp. 805-814. https://doi.org/10.13067/JKIECS.2013.8.6.805