Boosting Pixel-based Classifiers for Face Verification

The performance of face verification systems has steadily improved over the last few years. State-of-the-art methods use the projection of the gray-scale face image into a Linear Discriminant subspace as input of a classifier such as Support Vector Machines or Multi-layer Perceptrons. Unfortunately, these classifiers involve thousands of parameters that are difficult to store on a smart-card for instance. Recently, boosting algorithms has emerged to boost the performance of simple (weak) classifiers by combining them iteratively. The famous AdaBoost algorithm have been proposed for object detection and applied successfully to face detection. In this paper, we investigate the use of AdaBoost for face verification to boost weak classifiers based simply on pixel values. The proposed approach is tested on a benchmark database, namely XM2VTS. Results show that boosting only hundreds of classifiers achieved near state-of-the-art results. Furthermore, the proposed approach outperforms similar work on face verification using boosting algorithms on the same database.

Sébastien Marcel, Yann Rodriguez

The performance of face authentication systems has steadily improved over the last few years. State-of-the-art methods use the projection of the gray-scale face image into a Linear Discriminant subspace as input of a classifier such as Support Vector Machines or Multi-layer Perceptrons. Unfortunately, these classifiers involve thousands of parameters that are difficult to store on a smart-card for instance. Recently, boosting algorithms has emerged to boost the performance of simple (weak) classifiers by combining them iteratively. The famous AdaBoost algorithm have been proposed for object detection and applied successfully to face detection. In this paper, we investigate the use of AdaBoost for face authentication to boost weak classifiers based simply on pixel values. The proposed approach is tested on a benchmark database, namely XM2VTS. Results show that boosting only hundreds of classifiers achieved near state-of-the-art results. Furthermore, the proposed approach outperforms similar work on face authentication using boosting algorithms on the same database.

Springer-Verlag2004

Multivariate Boosting with Look-Up Tables for Face Processing

Cosmin Atanasoaei

This thesis proposes a novel unified boosting framework. We apply this framework to the several face processing tasks, face detection, facial feature localisation, and pose classification, and use the same boosting algorithm and the same pool of features (local binary features). This is in contrast with the standard approaches that make use of a variety of features and models, for example AdaBoost, cascades of boosted classifiers and Active Appearance Models. The unified boosting framework covers multivariate classification and regression problems and it is achieved by interpreting boosting as optimization in the functional space of the weak learners. Thus a wide range of smooth loss functions can be optimized with the same algorithm. There are two general optimization strategies we propose that extend recent works on TaylorBoost and Variational AdaBoost. The first proposition is an empirical expectation formulation that minimizes the average loss and the second is a variational formulation that includes an additional penalty for large variations between predictions. These two boosting formulations are used to train real-time models using local binary features. This is achieved using look-up-tables as weak learners and multi-block Local Binary Patterns as features. The resulting boosting algorithms are simple, efficient and easily scalable with the available resources. Furthermore, we introduce a novel coarse-to-fine feature selection method to handle high resolution models and a bootstrapping algorithm to sample representative training data from very large pools of data. The proposed approach is evaluated for several face processing tasks. These tasks include frontal face detection (binary classification), facial feature localization (multivariate regression) and pose estimation (multivariate classification). Several studies are performed to assess different optimization algorithms, bootstrapping parametrizations and feature sharing methods (for the multivariate case). The results show good performance for all of these tasks. In addition to this, two other contributions are presented. First, we propose a context-based model for removing the false alarms generated by a given generic face detector. Second, we propose a new face detector that predicts the Jaccard distance between the current location and the ground truth. This allows us to formulate the face detection problem as a regression task.

EPFL2012

Comparison of MLP and GMM Classifiers for Face Verification on XM2VTS

Sébastien Marcel

We compare two classifier approaches, namely classifiers based on Multi Layer Perceptrons (MLPs) and Gaussian Mixture Models (GMMs), for use in a face verification system. The comparison is carried out in terms of performance, robustness and practicability. Apart from structural differences, the two approaches use different training criteria; the MLP approach uses a discriminative criterion, while the GMM approach uses a combination of Maximum Likelihood (ML) and Maximum a Posteriori (MAP) criteria. Experiments on the XM2VTS database show that for low resolution faces the MLP approach has slightly lower error rates than the GMM approach; however, the GMM approach easily outperforms the MLP approach for high resolution faces and is significantly more robust to imperfectly located faces. The experiments also show that the computational requirements of the GMM approach can be significantly smaller than the MLP approach at a cost of small loss of performance.

2003

Multivariate Boosting with Look-Up Tables for Face Processing

Cosmin Atanasoaei

EPFL2012