Search

Automatic engagement recognition is a technique that is used to measure the engagement level of people in a specific task. Although previous research has utilized expensive and intrusive devices such as physiological sensors and pressure-sensing chairs, methods using RGB video cameras have become the most common because of the cost efficiency and noninvasiveness of video cameras. Automatic engagement recognition methods using video cameras are usually based on hand-crafted features and a statistical temporal dynamics modeling algorithm. This paper proposes a data-driven convolutional neural networks (CNNs)-based engagement recognition method that uses only facial images from input videos. As the amount of data in a dataset of children's engagement is insufficient for deep learning, pre-trained CNNs are utilized for low-level feature extraction from each video frame. In particular, a new layer combination for temporal dynamics modeling is employed to extract high-level features from low-level features. Experimental results on a database created using images of children from kindergarten demonstrate that the performance of the proposed method is superior to that of previous methods. The results indicate that the engagement level of children can be gauged automatically via deep learning even when the available database is deficient. [ABSTRACT FROM AUTHOR]

Accurate age estimation from a facial image is quite challenging, since physical age and apparent age can be quite different, and this difference is dependent on gender, ethnicity, and many other factors. Multitask deep learning is one of the approach to improve age estimation by employing auxiliary tasks, such as gender recognition, that are related to the primary task. However, in traditional multitask learning for age estimation, the relationship between the primary and auxiliary tasks is difficult to describe; how the auxiliary tasks enhance the model for the primary objective is ambiguous. In this letter, we propose a conditional multitask learning method that architecturally factorizes an age variable into gender-conditioned age probabilities in a deep neural network. The lack of accurate training labels with discrete age values is another critical limitation to training age estimation models. Therefore, we propose a label expansion method that increases the number of accurate labels from weakly supervised categorical labels. To verify the generality of the proposed method, we perform intensive experiments on the publicly available MORPH-II and FG-NET datasets. The proposed methods outperform state-of-the art methods in both age estimation and gender recognition accuracy. These performance gains are verified on well-known deep network architectures—VGG-16, CASIA-WebFace, and Alexnet—to confirm the proposed methods generality. [ABSTRACT FROM AUTHOR]

The authors present a robust face recognition system for large-scale data sets taken under uncontrolled illumination variations. The proposed face recognition system consists of a novel illumination-insensitive preprocessing method, a hybrid Fourier-based facial feature extraction, and a score fusion scheme. First, in the preprocessing stage, a face image is transformed into an illumination-insensitive image, called an “integral normalized gradient image,” by normalizing and integrating the smoothed gradients of a facial image. Then, for feature extraction of complementary classifiers, multiple face models based upon hybrid Fourier features are applied. The hybrid Fourier features are extracted from different Fourier domains in different frequency bandwidths, and then each feature is individually classified by linear discriminant analysis. In addition, multiple face models are generated by plural normalized face images that have different eye distances. Finally, to combine scores from multiple complementary classifiers, a log likelihood ratio-based score fusion scheme is applied. The proposed system using the face recognition grand challenge (FRGC) experimental protocols is evaluated; FRGC is a large available data set. Experimental results on the FRGC version 2.0 data sets have shown that the proposed method shows an average of 81.49% verification rate on 2-D face images under various environmental variations such as illumination changes, expression changes, and time elapses. [ABSTRACT FROM PUBLISHER]

A novel face recognition approach by the use of a bundle of example images is presented, in which a combination of useful examples for face recognition is selected, and multiple augmented example images are made using those images. For this purpose, first, example images are divided into multiple groups using unsupervised methods such as the K‐means method, and then clustering them into several groups according to their image variations. In each group, the most similar example images to an input image are found and they independently make an example average image from both the retrieved examples and their rank orders. When comparing similarities between two images, now local distance information can be utilised, which are calculated via corresponding average example images, as well as global distance information, the traditional direct comparison. The proposed approach is compared with the traditional direct comparison method on a multi‐PIE database, and the generalisation ability of the proposed method across different features, such as local binary pattern, histogram of oriented gradients and Gabor features, is demonstrated. [ABSTRACT FROM AUTHOR]

We describe a novel face recognition using the Extended Curvature Gabor (ECG) Classifier Bunch. First, we extend Gabor kernels into the ECG kernels by adding a spatial curvature term to the kernel and adjusting the width of the Gaussian at the kernel, which leads to numerous feature candidates being extracted from a single image. To handle large feature candidates efficiently, we divide them into multiple ECG coefficients according to different kernel parameters, and then we independently select the salient features from each ECG coefficient using the boosting method. A single ECG classifier is implemented by applying Linear Discriminant Analysis (LDA) to the selected feature vector. To overcome the accuracy limitation of a single classifier, we propose an ECG classifier bunch that combines multiple ECG classifiers with the fusion scheme. We confirm the generality of the performances of the proposed method using the FRGC version 2.0, XM2VTS, BANCA, and PIE databases. [ABSTRACT FROM AUTHOR]