Face Detection Based on Incremental Learning from Very Large Size Training Data

대용량 훈련 데이타의 점진적 학습에 기반한 얼굴 검출 방법

  • 박지영 (성균관대학교 정보통신공학부) ;
  • 이준호 (성균관대학교 정보통신공학부)
  • Published : 2004.07.01

Abstract

race detection using a boosting based algorithm requires a very large size of face and nonface data. In addition, the fact that there always occurs a need for adding additional training data for better detection rates demands an efficient incremental teaming algorithm. In the design of incremental teaming based classifiers, the final classifier should represent the characteristics of the entire training dataset. Conventional methods have a critical problem in combining intermediate classifiers that weight updates depend solely on the performance of individual dataset. In this paper, for the purpose of application to face detection, we present a new method to combine an intermediate classifier with previously acquired ones in an optimal manner. Our algorithm creates a validation set by incrementally adding sampled instances from each dataset to represent the entire training data. The weight of each classifier is determined based on its performance on the validation set. This approach guarantees that the resulting final classifier is teamed by the entire training dataset. Experimental results show that the classifier trained by the proposed algorithm performs better than by AdaBoost which operates in batch mode, as well as by ${Learn}^{++}$.

본 연구는 대용량 훈련 데이타를 사용하는 얼굴 검출 분류기의 학습과정에서 새로운 데이터의 추가 학습이 가능한 새로운 방법을 제안한다. 추가되는 데이타로부터 새로운 정보를 학습하여 이미 습득된 기존의 지식을 갱신하는 것이 점진적 학습의 목표이다. 이러한 학습 기법에 기반한 분류기의 설계에서는 최종 분류기가 전체 훈련 데이타 집합의 특성을 반영하는 것이 매우 중요한 문제이다. 제안하는 알고리즘은 최적화된 최종 분류기 획득을 위하여 훈련 집합의 전역적인 특성을 대표하는 검증집합을 생성하고, 이 집단 내에서의 분류성능을 기준으로 중간단계 분류기들의 가중치를 결정한다. 각 중간단계 분류기는 개변 데이타 집합의 학습 결과로써 가중치 기반 결합 방식에 의해 최종 분류기로 구성된다. 반복적인 실험을 통해, 제안한 알고리즘을 사용하여 학습한 얼굴 검출 분류기의 성능이 AdaBoost 및 Learn++기반의 분류기보다 우수한 검출 성능을 보임을 확인하였다.

Keywords

References

  1. Y. Freund and R. Schapire, 'A decision-theoretic generalization of on-line learning and an application to boosting,' Journal of Computer and System Sciences Vol. 55, pp. 119-139, 1997 https://doi.org/10.1006/jcss.1997.1504
  2. P. Viola and M. Jones, 'Robust real time object detection,' In: IEEE ICCV Workshop on Statistical and Computational Theories of Vision, 2001
  3. R. Polikar, L. Udpa, S. Udpa and V. Honavar, 'Learn++: An Incremental Learning Algorithm for Supervised Neural Networks,' IEEE Transactions on Systems, Man, and Cybernetics, Vol. 31, No. 4., pp. 497-508, 200l https://doi.org/10.1109/5326.983933
  4. T. Agui, Y. Kokubo, H., Nagashashi and T. Nagao, 'Extraction of Face Recognition from Mono-chromatic Photographs Using Neural Networks,' Proceedings of Second International Conference on Automation, Robotics, and Computer Vision, Vol. 1, pp. 18.8.1-18.8.5, 1992
  5. R. Feraud, O.J. Bernier, J.-E. Villet and M. Collobert, 'A Fast and Accurate Face Detector Based on Neural Networks,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No.1, pp. 42-53, 2001 https://doi.org/10.1109/34.899945
  6. S.-H. Lin, S.-Y., Kung and L.-J. Lin, 'Face Recognition/Detection by Probabilistic Decision-Based Neural Network,' IEEE Transactions on Neural Networks, Vol. 8, No. 1, pp. 114-132, 1997 https://doi.org/10.1109/72.554196
  7. H. Rowley, S. Baluja and T. Kanade, 'Neural Network-Based Face Detection,' IEEE Transactions onPattern Analysis and Machine Intelligence, Vol. 20, No. 1, pp. 23-38, 1998 https://doi.org/10.1109/34.655647
  8. H. Rowley, S. Baluja and T. Kanade, 'Human Face Detection in Visual Scenes,' Advances in Neural Information Processing Systems, pp. 875-881, 1996
  9. K.-K. Sung and T. Poggio, 'Example-Based Learning for View-Based Human Face Detection,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 1, pp. 39-51, 1998 https://doi.org/10.1109/34.655648
  10. R. Polikar, S. Krause and L. Burd, 'Ensemble of classifiers based incremental learning with dynamic voting weight update,' Proceedings of the International Joint Conference on Neural Networks, Vol. 4, pp. 2770-2775, 2003 https://doi.org/10.1109/IJCNN.2003.1224006
  11. H.P. Graf, T. Chen, E. Petajan and E. Cosatto, 'Locating Faces and Facial Parts,' Proceedings of First InternationalWorkshop Automatic Face and Gesture Recognition, pp. 41-46, 1995
  12. J. Cai and A. Goshtasby, 'Detecting human faces in color images,' Image and Vision Computing, Vol. 18, pp. 63-75, 1999 https://doi.org/10.1016/S0262-8856(99)00006-2
  13. I. Craw, H. Ellis and J. Lishman, 'Automatic Extraction of Face Features,' Pattern Recognition Letters, Vol. 5, pp. 183-187, 1987 https://doi.org/10.1016/0167-8655(87)90039-0
  14. R. Duda, P. Hart and D. Stork, 'Pattern Classification,' 2nd Ed., New York: Wiley, 2001
  15. N. Littlestone and M. Warmuth, 'Weighted majority algorithm,' Information and Computation, Vol. 108, pp. 212-261, 1994 https://doi.org/10.1006/inco.1994.1009
  16. R. Ziemer, 'Elements of engineering probability & statistics,' International Ed., Prentice Hall, 1997