Frontal Face Test Set Research Articles

A novel two-stage weak classifier selection approach for adaptive boosting for cascade face detector

It is well-known for AdaBoost to select out the optimal weak classifier with the least sample-weighted error rate, which might be suboptimal for minimizing the naïve error rate. In this paper, a novel variant of AdaBoost named OtBoost is proposed to learn optimal thresholded node classifiers for cascade face detector. In OtBoost, a two-stage weak classifier selection approach based on adaptive boosting framework is applied to minimize both the sample-weighted error rate and the optimal-thresholded multi-set class-weighted error rate. Besides, a new sample set called selection set is also applied to prevent overfitting on the training set. Several upright frontal cascade face detectors are learned, which shows that the OtBoost strong classifiers have much better convergence ability than the AdaBoost ones with the cost of slightly worse generalization ability. Some OtBoost based cascade face detectors have acceptable performance on the CMU+MIT upright frontal face test set.

WLD: A Robust Local Image Descriptor

Inspired by Weber's Law, this paper proposes a simple, yet very powerful and robust local descriptor, called the Weber Local Descriptor (WLD). It is based on the fact that human perception of a pattern depends not only on the change of a stimulus (such as sound, lighting) but also on the original intensity of the stimulus. Specifically, WLD consists of two components: differential excitation and orientation. The differential excitation component is a function of the ratio between two terms: One is the relative intensity differences of a current pixel against its neighbors, the other is the intensity of the current pixel. The orientation component is the gradient orientation of the current pixel. For a given image, we use the two components to construct a concatenated WLD histogram. Experimental results on the Brodatz and KTH-TIPS2-a texture databases show that WLD impressively outperforms the other widely used descriptors (e.g., Gabor and SIFT). In addition, experimental results on human face detection also show a promising performance comparable to the best known results on the MIT+CMU frontal face test set, the AR face data set, and the CMU profile test set.

Optimization of a training set for more robust face detection

The performance of a learning-based method highly depends on the quality of a training set. However, it is very challenging to collect an efficient and effective training set for training a good classifier, because of the high dimensionality of the feature space and the complexity of decision boundaries. In this research, we study the methodology of automatically obtaining an optimal training set for robust face detection by resampling the collected training set. We propose a genetic algorithm (GA) and manifold-based method to resample a given training set for more robust face detection. The motivations behind lie in two folds: (1) dynamic optimization, diversity, and consistency of the training samples are cultivated by the evolutionary nature of GA and (2) the desirable non-linearity of the training set is preserved by using the manifold-based resampling. We demonstrate the effectiveness of the proposed method through experiments and comparisons to other existing face detectors. The system trained from the training set by the proposed method has achieved 90.73% accuracy with no false alarm on MIT+CMU frontal face test set—the best result reported so far to our knowledge. Moreover, as a fully automatic technology, the proposed method can significantly facilitate the preparation of training sets for obtaining well-performed object detection systems in different applications.

Enhancing Human Face Detection by Resampling Examples Through Manifolds

As a large-scale database of hundreds of thousands of face images collected from the Internet and digital cameras becomes available, how to utilize it to train a well-performed face detector is a quite challenging problem. In this paper, we propose a method to resample a representative training set from a collected large-scale database to train a robust human face detector. First, in a high-dimensional space, we estimate geodesic distances between pairs of face samples/examples inside the collected face set by isometric feature mapping (Isomap) and then subsample the face set. After that, we embed the face set to a low-dimensional manifold space and obtain the low-dimensional embedding. Subsequently, in the embedding, we interweave the face set based on the weights computed by locally linear embedding (LLE). Furthermore, we resample nonfaces by Isomap and LLE likewise. Using the resulting face and nonface samples, we train an AdaBoost-based face detector and run it on a large database to collect false alarms. We then use the false detections to train a one-class support vector machine (SVM). Combining the AdaBoost and one-class SVM-based face detector, we obtain a stronger detector. The experimental results on the MIT + CMU frontal face test set demonstrated that the proposed method significantly outperforms the other state-of-the-art methods.

Real-Time Face Detection and Motion Analysis With Application in “Liveness” Assessment

A robust face detection technique along with mouth localization, processing every frame in real time (video rate), is presented. Moreover, it is exploited for motion analysis onsite to verify "liveness" as well as to achieve lip reading of digits. A methodological novelty is the suggested quantized angle features ("quangles") being designed for illumination invariance without the need for preprocessing (e.g., histogram equalization). This is achieved by using both the gradient direction and the double angle direction (the structure tensor angle), and by ignoring the magnitude of the gradient. Boosting techniques are applied in a quantized feature space. A major benefit is reduced processing time (i.e., that the training of effective cascaded classifiers is feasible in very short time, less than 1 h for data sets of order 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> ). Scale invariance is implemented through the use of an image scale pyramid. We propose "liveness" verification barriers as applications for which a significant amount of computation is avoided when estimating motion. Novel strategies to avert advanced spoofing attempts (e.g., replayed videos which include person utterances) are demonstrated. We present favorable results on face detection for the YALE face test set and competitive results for the CMU-MIT frontal face test set as well as on "liveness" verification barriers.

Robust Face Detection for Low-Resolution Images

Face detection, one of the most actively researched and progressive computer vision fields, has been little studied in low-resolution images. Using the AdaBoost-based face detector and MIT+CMU frontal face test set – the standard detector and images for evaluation in face detection – we found that face detection rate falls to 39% from 88% as face resolution decreases from 24×24 pixels to 6×6 pixels. We discuss a proposal using “portrait images,” “image expansion,” “frequency-band limitation of features” and “two-detector integration” and show that 71% of face detection rate is obtained for 6×6 pixel faces of MIT+CMU frontal face test set. Note that each of the above detections involves 100 false positives for 112 evaluation images.

Face Samples Expanding Based on the GA Re-Sampling

Data collection for both training and testing a classifier is a tedious but essential step towards face detection and recognition. All of the statistical methods suffer from this problem. In this paper, a genetic algorithm (GA) based method to swell face database through re-sampling from existing faces is presented. The basic idea is that a face is composed of a limited components set, and the GA can simulate the procedure of heredity. This simulation can also cover the variations of faces in different lighting conditions, poses, accessories, and quality conditions. To verify the generalization capability of the proposed method, the expanded database is used to train an AdaBoost-based face detector and test it on the MIT+CMU frontal face test set. The experimental results show that the data collection can be speeded up efficiently by the proposed methods.