基于视频图像的人脸检测与跟踪方法研究
|
摘要
人脸检测及跟踪属于模式识别与计算机视觉的研究领域,它作为人脸信息处理中的一项关键技术,在基于内容的图像与视频检索、视频监视与跟踪、视频会议以及智能人机交互等方面都有着重要的应用价值。
本文主要研究了视频中的人脸检测及跟踪技术。在总结现有算法的基础上,针对视频这一应用背景的实时性要求,选取人脸的小波特征作为视频中人脸的主要特征,通过Adaboost训练算法架构人脸检测器。本文研究了基于直方图统计学习的人脸检测方法与基于haar-like特征的人脸检测方法两种方法。前者通过使用5/3小波变换,能有效地提取出空域、频域和方向场上的信息进行建模,同时反映目标各部分之间的几何关系,从而提取出完备的特征,能有效地检测正面和侧面人脸;后者先利用“积分图”快速计算特征,构造弱分类器,然后通过Adaboost学习算法从得到的大量弱分类器中产生一个高效的强分类器,最后采用级联方式将单个的强分类器再合成为一个更加复杂的层叠分类器,使图像背景区域快速地丢弃,保证了检测速度,满足视频的实时性需要。
在人脸跟踪方法上,本文分别研究了两种侧重点不同的人脸跟踪方法。一种以基于直方图统计学习的人脸检测为基础,通过肤色预处理和视频中的运动信息获得人脸候选区域,再通过人脸检测算法精确定位人脸,实现了视频中基于人脸检测的人脸跟踪。另一种将Mean-Shift目标跟踪算法和Kalman滤波运用到人脸跟踪上,通过不断的进行均值偏移矢量的迭代和目标模版更新,可以快速有效的在视频中跟踪人脸。本文的创新点分别体现在以下3个方面:
(1)高效的肤色分割预处理算法;对已有的光照补偿算法做了改进;提出了针对于肤色二值图像的区域分割与合并算法;
(2)提出了求取小波系数量化参数的方法,并提出了分组量化的概念;改变了Adaboost训练过程中弱分类器的输出值,给出了弱分类器的阈值选取方法,减小了分类误差;提出了基于样本统计的最终人脸分类器阈值选取准则。
(3)在Mean-Shift目标跟踪算法和Kalmam滤波的基础上,提出了新的实时人脸跟踪算法。提出了把Adaboost人脸检测算法和Mean-Shift人脸跟踪算法相结合实现人脸的实时检测与跟踪,并对跟踪人脸实现姿态估计的新思路。
实验结果以及与其他算法的比较分析表明,本文算法在准确率、误检率和检测与跟踪速度等方面均可获得较理想的结果,是两个综合性能很强的完整、鲁棒、高效的人脸检测与跟踪算法。
Face detection and tracking is an important research aspect in artificial intelligence and computer vision. As a key technology of face information processing, it has a broad application values in many fields such as video surveillance, content-based image retrieval, videoconference, etc.
In this thesis, a study on face detection and tracking in video is presented. After a general review of existing schemes on this particular topic, we choose Wavelet feature as the main feature of human face and Adaboost training algorithm to construct the face detectore, due to the real-time requirement of video. We study two face detection approaches including histogram-based statistical learning approach and Haar-like feature-based face detection approach. By using 5/3 wavelet transformation, the former one could effectively decompose the image in frequency, orientation, space, and geometry, obtaining overcomplete feaure set and detecting frontal and profile faces effectively; While The latter utilize integral image to quickly calculate the feature, and construct weak classifier by the feature; then weak classifiers are combined to a strong classifier in a linear way.The final classifier is built in a cascade structure which could reject most non-face samples in the early layer.
Two face tracking methods with different emphasis are also studied in this thesis. The first one accomplish face tracking in viedo by utilizing histogram-based statistical learning approach to detect faces in face-candidate regions, which was obtained by using skin pre-process and motion information in video. The second one applies Mean-shift object tracking algorithm and Kalman filtering to face tracking. The central computational module is based on the mean shift iterations and target model updating and finds the most probable face target position in current frame.
The contributions of this paper could be expressed as the following 3 aspects:
(1) Efficient skin segmentation pre-processing algorithm; improve the current lighting compensation algorithm;propose a new region segmentation and combination algorithm especially for skin binary image;
(2) Present a method to quantize wavelet parameters and concept of quantization in different groups; change the output of weak classifier in Adaboost training and provide a method to set the threshold of the best weak classifier; propose a sample statistic-based criterion to set the threshold of face classifier;
(3) A novel real-time face tracking algorithm was presented based on Mean-Shift target tracking algorithm and Kalman filtering algorithm; propose a new thinking to detect and track face in real-time by combining Adaboost face detection algorithm and Mean-Shift algorithm with pose estimation implemented to the tracked face.
Experiment results and comparison with other published method show that algorithm in this thesis obtains almost ideal result in the field of detection accuracy rate, false alarm rate and detection and tracking speed, and both of these two algorithms are complete, robust and efficient face detection and tracking algorithms with great comprehensive performance.
本文主要研究了视频中的人脸检测及跟踪技术。在总结现有算法的基础上,针对视频这一应用背景的实时性要求,选取人脸的小波特征作为视频中人脸的主要特征,通过Adaboost训练算法架构人脸检测器。本文研究了基于直方图统计学习的人脸检测方法与基于haar-like特征的人脸检测方法两种方法。前者通过使用5/3小波变换,能有效地提取出空域、频域和方向场上的信息进行建模,同时反映目标各部分之间的几何关系,从而提取出完备的特征,能有效地检测正面和侧面人脸;后者先利用“积分图”快速计算特征,构造弱分类器,然后通过Adaboost学习算法从得到的大量弱分类器中产生一个高效的强分类器,最后采用级联方式将单个的强分类器再合成为一个更加复杂的层叠分类器,使图像背景区域快速地丢弃,保证了检测速度,满足视频的实时性需要。
在人脸跟踪方法上,本文分别研究了两种侧重点不同的人脸跟踪方法。一种以基于直方图统计学习的人脸检测为基础,通过肤色预处理和视频中的运动信息获得人脸候选区域,再通过人脸检测算法精确定位人脸,实现了视频中基于人脸检测的人脸跟踪。另一种将Mean-Shift目标跟踪算法和Kalman滤波运用到人脸跟踪上,通过不断的进行均值偏移矢量的迭代和目标模版更新,可以快速有效的在视频中跟踪人脸。本文的创新点分别体现在以下3个方面:
(1)高效的肤色分割预处理算法;对已有的光照补偿算法做了改进;提出了针对于肤色二值图像的区域分割与合并算法;
(2)提出了求取小波系数量化参数的方法,并提出了分组量化的概念;改变了Adaboost训练过程中弱分类器的输出值,给出了弱分类器的阈值选取方法,减小了分类误差;提出了基于样本统计的最终人脸分类器阈值选取准则。
(3)在Mean-Shift目标跟踪算法和Kalmam滤波的基础上,提出了新的实时人脸跟踪算法。提出了把Adaboost人脸检测算法和Mean-Shift人脸跟踪算法相结合实现人脸的实时检测与跟踪,并对跟踪人脸实现姿态估计的新思路。
实验结果以及与其他算法的比较分析表明,本文算法在准确率、误检率和检测与跟踪速度等方面均可获得较理想的结果,是两个综合性能很强的完整、鲁棒、高效的人脸检测与跟踪算法。
Face detection and tracking is an important research aspect in artificial intelligence and computer vision. As a key technology of face information processing, it has a broad application values in many fields such as video surveillance, content-based image retrieval, videoconference, etc.
In this thesis, a study on face detection and tracking in video is presented. After a general review of existing schemes on this particular topic, we choose Wavelet feature as the main feature of human face and Adaboost training algorithm to construct the face detectore, due to the real-time requirement of video. We study two face detection approaches including histogram-based statistical learning approach and Haar-like feature-based face detection approach. By using 5/3 wavelet transformation, the former one could effectively decompose the image in frequency, orientation, space, and geometry, obtaining overcomplete feaure set and detecting frontal and profile faces effectively; While The latter utilize integral image to quickly calculate the feature, and construct weak classifier by the feature; then weak classifiers are combined to a strong classifier in a linear way.The final classifier is built in a cascade structure which could reject most non-face samples in the early layer.
Two face tracking methods with different emphasis are also studied in this thesis. The first one accomplish face tracking in viedo by utilizing histogram-based statistical learning approach to detect faces in face-candidate regions, which was obtained by using skin pre-process and motion information in video. The second one applies Mean-shift object tracking algorithm and Kalman filtering to face tracking. The central computational module is based on the mean shift iterations and target model updating and finds the most probable face target position in current frame.
The contributions of this paper could be expressed as the following 3 aspects:
(1) Efficient skin segmentation pre-processing algorithm; improve the current lighting compensation algorithm;propose a new region segmentation and combination algorithm especially for skin binary image;
(2) Present a method to quantize wavelet parameters and concept of quantization in different groups; change the output of weak classifier in Adaboost training and provide a method to set the threshold of the best weak classifier; propose a sample statistic-based criterion to set the threshold of face classifier;
(3) A novel real-time face tracking algorithm was presented based on Mean-Shift target tracking algorithm and Kalman filtering algorithm; propose a new thinking to detect and track face in real-time by combining Adaboost face detection algorithm and Mean-Shift algorithm with pose estimation implemented to the tracked face.
Experiment results and comparison with other published method show that algorithm in this thesis obtains almost ideal result in the field of detection accuracy rate, false alarm rate and detection and tracking speed, and both of these two algorithms are complete, robust and efficient face detection and tracking algorithms with great comprehensive performance.
引文
1. Ming-Hsuan Yang, David Kriegman, and Narendra Ahuja. Detecting Faces in Images: A Survey. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002, 24(1):34-58.
2. Erik Hjelmas, Boon Kee Low. Face Detection: A Survey.Computer Vision and Image Understanding. 2001, 83(3):236-274.
3. 刘党辉,沈兰荪,Kin-Man Lam.人脸检测研究进展.计算机工程与应用.2003, 39(28):5-9.
4. 梁路宏,艾海舟,徐光裕等.人脸检测研究综述.计算机学报.2002, 25(5):449-458.
5. Kim H, Kang W, Shin J, Park S. Face Detection Using Template Matching and Ellipse Fitting. IEICE Trans. Inf. & Syst., Vol.E38-D, No.11, pp2008~2011, Nov 2000.
6. Wang J, Tan T. A new face detection method based on shape information. PRL, vol. 21, pp. 463~471, 00.
7. Paul Viola and Michael Jones. Rapid object detection using a boosted cascade of simple features. In: Proc. Conf. Computer Vision and Pattern Recognition. Kauai, HI, USA. 2001,1:511–518.
8. E. Osuna, R. Freund, and F. Girosi. Training support vector machines: An application to face detection. In: Proc. Conf. Computer Vision and Pattern Recognition, San Jaun, Puerto Rico, 1997:130–136.
9. M.-H. Yang, D. Roth, N. Ahuja. A SNoW-based face detector. In: Advances in Neural Information Processing Systems, Denver, CO, USA, 2000:855–861.
10. R. F′eraud, O.J. Bernier, J.-E. Viallet, and M. Collobert. A fast and accurate face detection based on neural network. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2001, 23(1):42–53.
11. Rowley HA. Neural Network-Based Face Detection. PhD thesis, Carnegie Mellon Univ., 1999.
12. Rowley H, Baluja S, Kanade T. Rotation Invariant Neural Network-Based Face Detection. Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 38~44, 1998.
13. Terrillon JC, Shirazi M N, Fukamachi H, and Akamatsu S. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images. Proc. IEEE Int'l Conf. on Face and Gesture Recognition, pp. 54-61, 2000.
14. Kim H, Kang W, Shin J, Park S. Face Detection Using Template Matching and Ellipse Fitting. IEICE Trans. Inf. & Syst., Vol.E38-D, No.11, pp2008~2011, Nov 2000.
15. M. Yang, N. Ahuja. Face Detection and Gesture Recognition for Human Computer Interaction. Kluwer Academic Publishers Group. 2001
16. B. Moghaddam, A. Pentland. Probabilistic visual learning for object recognition. IEEE Trans. PAMI. 1997, 19(7): 696-710.
17. 汪孔桥. 面向头肩序列图象的人脸检测、跟踪与编码技术的研究. 中国科技大学博士论文. 1999.
18. 毋立芳.基于人脸对象的图像检索关键技术研究.北京工业大学博士论文.2002.
19. 刘党辉.鲁棒的人脸识别技术研究.北京工业大学博士论文.2004.
20. I. A. Essa, A. Pentland.Facial expression recognition using a dynamic model and motion energy.Proc. of IEEE ICCV.1995:360-367.
21. G. Yang and T. S. Huang. Human Face Detection in Complex Background. Pattern Recognition. 1994 27(1):53-63.
22. Sinha P. Object recognition via image invariant: A case study. Investigative Ophthalmology and Visual Science, Florida, 1994, 1735-1740
23. Lam K M, et al. Locating and extracting the eye in human face images. Pattern Recognition, 1996, 29(5): 771-779.
24. Yuille A, et al. Feature extraction from faces using deformable templates. International Journal of Computer Vision, 1992. 8f21: 99-111.
25. Shen Lansun, Wang Kongqiao, Xing Xin. Automatic human face detection and tracking in a complex background. Chinese Journal of Electronics (CJE), 2000, 9(1): 65-69.
26. Govindaraj a V, et al. Locating human faces in photographs. Journal of Computer Vision, 1996, 19(2): 129-146.
27. Wang Jianguo, et al. Face detection using shape information--an effcient method for images with simple background. In: Proceeding of the second international conference on multimodal interfaces. Hong Kong, 1999, IV: 41-46.
28. M. C. Santana, M. H. Tejera, J. C. Gamez.Encara: real-time detection of frontal faces.IEEE ICIP.2003,(3): 881-884.
29. C.Lerdsudwichai, M. Abdel-Mottaleb.Algorithm for multiple faces tracking. IEEE ICME. 2003:777-780.
30. Yang J, Waibel A.Tracking human faces in real-time. Carnegie Mellon University, CA: Technical Report CMU-CS-95-210.1995.
31. 邢听,汪孔桥,沈兰荪. 基于器官跟踪的人脸实时跟踪方法.电子学报.2000, 28(6):29-31.
32. 艾海舟等. 基于差分图象的人脸检测. 中国图象图形报.1998, 3 (12) : 987-992.
33. 高峰等. 复杂背景人脸的定位与特征提取. 华东师范大学学报.1998, 2 : 44—50.
34. Samaria FS. Face Recognition Using Hidden Markov Models. PhD thesis, Univ. of Cambridge, 1994.
35. Charles Poynton. A technical introduction to digital video[M]. John Wiley & Sons, 1996.
36. Hsu Rein-Lien, Mohamed, Jain Anil K.. Face detection in color images[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, May 2002, 24(5):696-706.
37. Abdel-Mottaleb M., Elgammal A.. Face detection in complex environments from color images[A]. Proc. IEEE Int’l Conf. Image Processing[C], 1999:622–626.
38. Ming-Hsuan Yang, David Kriegman, and Narendra Ahuja. Detecting Faces in Images: A Survey. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002,24(1):34-58.
39. Fr?ba B, A. Ernst. Fast Frontal-View Face Detection Using a Multi-Path Decision Tree. In Proc. Audio- and Video-based Biometric Person Authentication (AVBPA ’2003), pp. 921~928, 2003.
40. Comaniciu D, Ramesh V. Meer P., Real-time tracking of non-rigid objects using mean shift [C]. IEEE Conf. on Computer Vision and Pattern Recognition, 2000, Vol.2:142-149.
41. Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. Pattern Recognition and intelligence,2001,Vol.24(5): 564-575
42. Jerome Friedman, Trevor Hastie, Robert Tibshirani. Additive Logistic Regression: a Statistical View of Boosting
43. X. He, S. Yan, Y. Hu, P. Niyogi. Face Recognition using Laplacian faces [J]. IEEE Trans, Pattern Recognition and intelligence. 2005, 27(3): 328-340
44. X. Ge, J. Yang, T. Zhang. Three-dimensional face pose estimation based on novel nonlineardiscriminant representation[J]. OE letters, 2006,45(9):1-3
45. Verma R C, Schmid C, Mikolajczyk K. Face detection and tracking in video by propagating detection probabilities[J]. Pattern Recognition and intelligence, 2003, 25(10):1215-1227
46. H. Schneiderman, T. Kanade. A Statistical Model for 3D Object Detection Applied to Faces and Cars. IEEE Conference on Computer Vision and Pattern Recognition, IEEE, June, 2000.
47. Viola P, Jones M. Robust real time object detection Technical Report. CRL 2001/01, Compaq Cambridge Research Laboratory, February 2001.
48. E. Shapire, Y. Singer. ―Improving Boosting Algorithms Using Confidence-rated Predictions.‖ Machine Learning 37:3, pp. 297-336. December, 1999.
49. Bauer, R. Kohavi. ―An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants.‖ Machine Learning. 36:1/2, pp. 105-139. July, 1999.
2. Erik Hjelmas, Boon Kee Low. Face Detection: A Survey.Computer Vision and Image Understanding. 2001, 83(3):236-274.
3. 刘党辉,沈兰荪,Kin-Man Lam.人脸检测研究进展.计算机工程与应用.2003, 39(28):5-9.
4. 梁路宏,艾海舟,徐光裕等.人脸检测研究综述.计算机学报.2002, 25(5):449-458.
5. Kim H, Kang W, Shin J, Park S. Face Detection Using Template Matching and Ellipse Fitting. IEICE Trans. Inf. & Syst., Vol.E38-D, No.11, pp2008~2011, Nov 2000.
6. Wang J, Tan T. A new face detection method based on shape information. PRL, vol. 21, pp. 463~471, 00.
7. Paul Viola and Michael Jones. Rapid object detection using a boosted cascade of simple features. In: Proc. Conf. Computer Vision and Pattern Recognition. Kauai, HI, USA. 2001,1:511–518.
8. E. Osuna, R. Freund, and F. Girosi. Training support vector machines: An application to face detection. In: Proc. Conf. Computer Vision and Pattern Recognition, San Jaun, Puerto Rico, 1997:130–136.
9. M.-H. Yang, D. Roth, N. Ahuja. A SNoW-based face detector. In: Advances in Neural Information Processing Systems, Denver, CO, USA, 2000:855–861.
10. R. F′eraud, O.J. Bernier, J.-E. Viallet, and M. Collobert. A fast and accurate face detection based on neural network. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2001, 23(1):42–53.
11. Rowley HA. Neural Network-Based Face Detection. PhD thesis, Carnegie Mellon Univ., 1999.
12. Rowley H, Baluja S, Kanade T. Rotation Invariant Neural Network-Based Face Detection. Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 38~44, 1998.
13. Terrillon JC, Shirazi M N, Fukamachi H, and Akamatsu S. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images. Proc. IEEE Int'l Conf. on Face and Gesture Recognition, pp. 54-61, 2000.
14. Kim H, Kang W, Shin J, Park S. Face Detection Using Template Matching and Ellipse Fitting. IEICE Trans. Inf. & Syst., Vol.E38-D, No.11, pp2008~2011, Nov 2000.
15. M. Yang, N. Ahuja. Face Detection and Gesture Recognition for Human Computer Interaction. Kluwer Academic Publishers Group. 2001
16. B. Moghaddam, A. Pentland. Probabilistic visual learning for object recognition. IEEE Trans. PAMI. 1997, 19(7): 696-710.
17. 汪孔桥. 面向头肩序列图象的人脸检测、跟踪与编码技术的研究. 中国科技大学博士论文. 1999.
18. 毋立芳.基于人脸对象的图像检索关键技术研究.北京工业大学博士论文.2002.
19. 刘党辉.鲁棒的人脸识别技术研究.北京工业大学博士论文.2004.
20. I. A. Essa, A. Pentland.Facial expression recognition using a dynamic model and motion energy.Proc. of IEEE ICCV.1995:360-367.
21. G. Yang and T. S. Huang. Human Face Detection in Complex Background. Pattern Recognition. 1994 27(1):53-63.
22. Sinha P. Object recognition via image invariant: A case study. Investigative Ophthalmology and Visual Science, Florida, 1994, 1735-1740
23. Lam K M, et al. Locating and extracting the eye in human face images. Pattern Recognition, 1996, 29(5): 771-779.
24. Yuille A, et al. Feature extraction from faces using deformable templates. International Journal of Computer Vision, 1992. 8f21: 99-111.
25. Shen Lansun, Wang Kongqiao, Xing Xin. Automatic human face detection and tracking in a complex background. Chinese Journal of Electronics (CJE), 2000, 9(1): 65-69.
26. Govindaraj a V, et al. Locating human faces in photographs. Journal of Computer Vision, 1996, 19(2): 129-146.
27. Wang Jianguo, et al. Face detection using shape information--an effcient method for images with simple background. In: Proceeding of the second international conference on multimodal interfaces. Hong Kong, 1999, IV: 41-46.
28. M. C. Santana, M. H. Tejera, J. C. Gamez.Encara: real-time detection of frontal faces.IEEE ICIP.2003,(3): 881-884.
29. C.Lerdsudwichai, M. Abdel-Mottaleb.Algorithm for multiple faces tracking. IEEE ICME. 2003:777-780.
30. Yang J, Waibel A.Tracking human faces in real-time. Carnegie Mellon University, CA: Technical Report CMU-CS-95-210.1995.
31. 邢听,汪孔桥,沈兰荪. 基于器官跟踪的人脸实时跟踪方法.电子学报.2000, 28(6):29-31.
32. 艾海舟等. 基于差分图象的人脸检测. 中国图象图形报.1998, 3 (12) : 987-992.
33. 高峰等. 复杂背景人脸的定位与特征提取. 华东师范大学学报.1998, 2 : 44—50.
34. Samaria FS. Face Recognition Using Hidden Markov Models. PhD thesis, Univ. of Cambridge, 1994.
35. Charles Poynton. A technical introduction to digital video[M]. John Wiley & Sons, 1996.
36. Hsu Rein-Lien, Mohamed, Jain Anil K.. Face detection in color images[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, May 2002, 24(5):696-706.
37. Abdel-Mottaleb M., Elgammal A.. Face detection in complex environments from color images[A]. Proc. IEEE Int’l Conf. Image Processing[C], 1999:622–626.
38. Ming-Hsuan Yang, David Kriegman, and Narendra Ahuja. Detecting Faces in Images: A Survey. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002,24(1):34-58.
39. Fr?ba B, A. Ernst. Fast Frontal-View Face Detection Using a Multi-Path Decision Tree. In Proc. Audio- and Video-based Biometric Person Authentication (AVBPA ’2003), pp. 921~928, 2003.
40. Comaniciu D, Ramesh V. Meer P., Real-time tracking of non-rigid objects using mean shift [C]. IEEE Conf. on Computer Vision and Pattern Recognition, 2000, Vol.2:142-149.
41. Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. Pattern Recognition and intelligence,2001,Vol.24(5): 564-575
42. Jerome Friedman, Trevor Hastie, Robert Tibshirani. Additive Logistic Regression: a Statistical View of Boosting
43. X. He, S. Yan, Y. Hu, P. Niyogi. Face Recognition using Laplacian faces [J]. IEEE Trans, Pattern Recognition and intelligence. 2005, 27(3): 328-340
44. X. Ge, J. Yang, T. Zhang. Three-dimensional face pose estimation based on novel nonlineardiscriminant representation[J]. OE letters, 2006,45(9):1-3
45. Verma R C, Schmid C, Mikolajczyk K. Face detection and tracking in video by propagating detection probabilities[J]. Pattern Recognition and intelligence, 2003, 25(10):1215-1227
46. H. Schneiderman, T. Kanade. A Statistical Model for 3D Object Detection Applied to Faces and Cars. IEEE Conference on Computer Vision and Pattern Recognition, IEEE, June, 2000.
47. Viola P, Jones M. Robust real time object detection Technical Report. CRL 2001/01, Compaq Cambridge Research Laboratory, February 2001.
48. E. Shapire, Y. Singer. ―Improving Boosting Algorithms Using Confidence-rated Predictions.‖ Machine Learning 37:3, pp. 297-336. December, 1999.
49. Bauer, R. Kohavi. ―An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants.‖ Machine Learning. 36:1/2, pp. 105-139. July, 1999.