Bo Wu

Fast rotation invariant multi-view face detection based on real Adaboost

In this paper, we propose a rotation invariant multi-view face detection method based on Real Adaboost algorithm. Human faces are divided into several categories according to the variant appearance from different viewpoints. For each view category, weak classifiers are configured as confidence-rated look-up-table (LUT) of Haar feature. Real Adaboost algorithm is used to boost these weak classifiers and construct a nesting-structured face detector. To make it rotation invariant, we divide the whole 360-degree range into 12 sub-ranges and construct their corresponding view based detectors separately. To improve performance, a pose estimation method is introduced and results in a processing speed of four frames per second on 320/spl times/240 sized image. Experiments on faces with 360-degree in-plane rotation and /spl mnplus/90-degree out-of-plane rotation are reported, of which the frontal face detector subsystem retrieves 94.5% of the faces with 57 false alarms on the CMU+MlT frontal face test set and the multi-view face detector subsystem retrieves 89.8% of the faces with 221 false alarms on the CMU profile face test set.

Boosting nested cascade detector for multi-view face detection

A novel nested cascade detector for multi-view face detection is presented. This nested cascade is learned by Schapire and Singers to improved boosting algorithms that use real-valued confidence-rated weak classifiers (Schapire, R. E. and Singer, Y, 1999), where we use confidence-rated look-up-table (LUT) weak classifiers based on Haar features. Experiments show the system performance is significantly improved compared with previous methods.

Real time facial expression recognition with AdaBoost

In this paper, we propose a novel method for facial expression recognition. The facial expression is extracted from human faces by an expression classifier that is learned from boosting Haar feature based look-up-table type weak classifiers. The expression recognition system consists of three modules, face detection, facial feature landmark extraction and facial expression recognition. The implemented system can automatically recognize seven expressions in real time that include anger, disgust, fear, happiness, neutral, sadness and surprise. Experimental results are reported to show its potential applications in human computer interaction.

LUT-based Adaboost for gender classification

There are two main approaches to the problem of gender classification, Support Vector Machines (SVMs) and Adaboost learning methods, of which SVMs are better in correct rate but are more computation intensive while Adaboost ones are much faster with slightly worse performance. For possible real-time applications the Adaboost method seems a better choice. However, the existing Adaboost algorithms take simple threshold weak classifiers, which are too weak to fit complex distributions, as the hypothesis space. Because of this limitation of the hypothesis model, the training procedure is hard to converge. This paper presents a novel Look Up Table (LUT) weak classifier based Adaboost approach to learn gender classifier. This algorithm converges quickly and results in efficient classifiers. The experiments and analysis show that the LUT weak classifiers are more suitable for boosting procedure than threshold ones.

Omni-directional face detection based on real AdaBoost

We propose an omni-directional face detection method based on the confidence-rated AdaBoost algorithm, called real AdaBoost, proposed by R.E. Schapire and Y. Singer (see Machine Learning, vol.37, p.297-336, 1999). To use real AdaBoost, we configure the confidence-rated look-up-table (LUT) weak classifiers based on Haar-type features. A nesting-structured framework is developed to combine a series of boosted classifiers into an efficient object detector. For omni-directional face detection, our method has achieved a rather high performance and the processing speed can reach 217 ms per 320/spl times/240 image. Experiment results on the CMU+MIT frontal and the CMU profile face test sets are reported to show its effectiveness.

Real-time gender classification

This paper introduces an automatic real-time gender classification system. The system consists of mainly three modules, face detection, normalization and gender classification. The LUT-type weak classifier based on Adaboost learning method is proposed for training both face detector and gender classifier, and a Simple Direct Appearance Model (SDAM) based method is developed to detect the facial landmark points for face normalization. This results in an integrated system with rather good performance. Experiment results on both pictures from World Wide Web and real-time video clips are reported to demonstrate its effectiveness and robustness.

Face pose estimation and its application in video shot selection

In this paper, a face pose estimation method and its application in video shot selection for face image preprocessing is introduced. The pose estimator is learned by a boosting regression algorithm called SquareLev.R that learns poses from simple Haar-type features. It consists of two tree structured subsystems for the left-right angle and up-down angle respectively. As a specific application in video based face recognition, the best shot selection problem is discussed, which results in a real-time system that can automatically select the most frontal face from a video sequence.

Glasses detection by boosting simple wavelet features

We propose a novel method for glasses detection. The glasses detectors are learned by using a variation of boosting algorithm, called real Adaboost, to boost simple wavelet feature based Look-Up-Table type weak classifiers. Two types of wavelet features, Haar and Gabor, have been investigated. Experiments results are reported to show that our method has very high correctness and extremely fast running speed. Based on this method we have developed a glasses detection system which can detect the glasses in facial images automatically.

Facial image retrieval based on demographic classification

In this paper, we propose a novel method for demographic classification and present an image retrieval system that can retrieve facial images by demographic information that includes gender, age and ethnicity. The demographic information is extracted from human faces by demographic classifiers that are learned from boosting Haar feature based look-up-table type weak classifiers. The image retrieval system consists of three modules, face detection, facial feature landmark extraction and demographic classification. Experimental results are reported to show its potential in the management of a large facial image database for online retrieval applications.