1 / 19

Train a Classifier Based on the Huge Face Database

Train a Classifier Based on the Huge Face Database. Jie Chen, Ruiping Wang, Shengye Yan, Shiguang Shan, Xilin Chen, Wen Gao. Presented by: Jie Chen. Motivation. Data collection is tedious but essential for learning based algorithms In Viola CVPR 2001, bootstrap for negative ;

keita
Download Presentation

Train a Classifier Based on the Huge Face Database

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Train a Classifier Based on the Huge Face Database Jie Chen, Ruiping Wang, Shengye Yan, Shiguang Shan, Xilin Chen, Wen Gao Presented by: Jie Chen

  2. Motivation • Data collection is tedious but essential for learning based algorithms • In Viola CVPR 2001, bootstrap for negative; • Ours: Resampling the positive set, besides the bootstrap for negative. • Why? • Collected face samples randomly; • Result in the bias of the trained detector. • How? • Fill in the face example space by GA; • Subsample it by manifold; • Mend by SVM. The collected face and nonface set Resulting distribution.

  3. Contribution of this Paper • Subsample a small but efficient and representative subset based on the manifold: • Discuss the effects of outliers; • The performance is instable to train a detector based on the random subsampling. However, a detector trained on the subsampled face set by manifold is not only stable but also performance improved; • When we prepare the training set, we should collect more samples along those dimensionalities with larger variances to get a nearly uniformed distribution in the manifold, for example, left-right pose of faces more than up-down pose.

  4. Manifold • A typical manifold –Swiss Roll (B. J. Tenenbaum, V. Silva, and J. Langford ) from http://www.cs.toronto.edu/~roweis/lle/

  5. Face Sample Manifold Too sparse! Too dense! An individual with varying pose and expression from http://www.cs.toronto.edu/~roweis/lle/

  6. Dimensionalities of Isomap • The residual variance of Isomap embedding on the 698 face database left-right pose up-down pose lighting direction

  7. Dimensionalities • Each coordinate axis of the embedding correlates highly with one degree of freedom underlying the original data: • left-right pose corresponding to the first degree of freedom; • up-down pose corresponding to the second one ; • lighting direction to the third one. • That is to say the scatter of face images in left-right pose is the biggest while the scatter in lighting is the smallest among these three factors. • We conclude that, in order to select representative example set, we should pay more attention to the left-right pose variations than the up-down pose.

  8. Subsampling by manifold (a) (b) (c) (a) illustration of subsampling based on the estimated geodesic distance; (b) manifold of 698 faces; (c) subsampled results.

  9. Experiments:Subsampling by manifold • training set -- 6,977 images (2,429 faces and 4,548 non-faces) • testing set -- 24,045 images (472 faces and 23,573 non-faces). • All of these images are grayscale and they are available on the CBCL webpage. • let K=6 for the manifold learning. • Trained on the AdaBoost based classifier

  10. Subsampling based on manifold • Some possible reasons: • Examples subsampled based on the manifold distributereasonable in the example space and have no example congregating compared with the whole set; • Outliers in the whole set deteriorate its performance

  11. Subsampling based on the manifold and random • Results based on random subsampling is much instable

  12. Outliers effects • Outliers deteriorate its performance

  13. Large scale of database • The face-image database consists of 100,000 faces (collected form web, video and digital camera); • Randomly rotate , translate and scale; • After these preprocessing, we get 1,200,000 face images which constitute the whole set; • The first group is composed of 15,000 face images which are subsampled by the manifold (ISO15000) ; • The second or third group is also composed of 15,000 face images which are random subsampling (Rand1-15000 and Rand2-15000).

  14. Test on MIT+CMU set • Sampled training set by the manifold and the random subsampled set • Trained on the AdaBoost based classifier

  15. The ROC curves comparison • Compared with other published algorithms on the MIT+CMU face test set

  16. Conclusion • Present a manifold-based method to subsample. • Compared with the detector by random subsampling, the detector trained by manifold is more stable and achieve better performance. • Improved performance results from: • Reasonable-distributed examples, subsampled based on manifold, • Nooutliers, discarded during the manifold learning

  17. Some outputs of our detector

  18. Thank you very much!

  19. By the way… • 1. Demo outside • Face Recognition against a large scale face database from our lab. • 2. BJUT-3D face database available • 500 3D faces! Free! • Assign a release agreement • For research purpose only • Get it now outside beside the demo desk.

More Related