Face Image Modeling by Multilinear Subspace Analysis With Missing Values

In this paper, we investigate facial age estimation with images in the wild. We aim to utilize images from the Internet to alleviate the problem of imbalance in age distribution. First, we crawl 14,283 images with their context from Wikipedia and infer age labels from the context for each image. After face detection, facial landmark detection and alignment, we build a set of images for facial age estimation, containing 9,456 faces with significant variations. Then, we exploit cost-sensitive learning algorithms including biased penalties SVM and Random forests for age estimation, using images in the wild as the training set. We propose to use the Gaussian function to determine varied misclassification costs. Conducted on two public aging datasets, the within-database experiments illustrate the performance improvement with the introduction of images in the wild. Furthermore, our cross-database experiments validate the generalization capability of proposed cost-sensitive age estimator.

The face recognition performance of linear discriminant analysis (LDA) is considerably reduced by illumination and scale changes. Actually, performance of LDA is significantly affected by the number of images of each individual in the training set. Hence, the idea presented in this paper is to generate new images with illumination and scale changes, from the available frontal images in the training set, and add to training set such that the recognition rate of LDA is maximised over both the training and test sets. A continuous genetic algorithm is used to find the optimal sets of illumination and scale change parameters that make the success of LDA invariant to these facial variations. Compared to the application of LDA over the initially given face database, experimental evaluations demonstrated that the performance of LDA is significantly enhanced over the test set for illumination and scale changes, without decreasing the success for other test cases.

Because face images are naturally two-dimensional data, there have been several 2D feature extraction methods to deal with facial images while there are few 2D effective classifiers. Meanwhile, there is an increasing interest in the multilinear subspace analysis and many methods have been proposed to operate directly on these tensorial data during the past several years. One of these popular unsupervised multilinear algorithms is Multilinear Principal Component Analysis (MPCA) while another of the supervised multilinear algorithm is Multilinear Discriminant Analysis (MDA). Then a MPCA+MDA method has been introduced to deal with the tensorial signal. However, due to the no convergence of MDA, it is difficult for MPCA+MDA to obtain a precise result. Hence, to overcome this limitation, a new MPCA plus General Tensor Discriminant Analysis (GTDA) solution with well convergence is presented for tensorial face images feature extraction in this paper. Several experiments are carried out to evaluate the performance of MPCA+GTDA on different databases and the results show that this method has the potential to achieve comparative effect as MPCA+MDA.

Facial age estimation has been widely adopted in the last decade, yet it presents critical privacy issues, such as susceptibility to unauthorized exposure. In contrast, tongue imagery has emerged as a promising alternative to traditional facial age estimation methods, offering improved privacy through reduced identifiability compared to facial imagery. This paper introduces a novel framework for age estimation using tongue imagery, addressing privacy concerns associated with facial recognition technologies. Our method takes advantage of a three-module approach: segmentation, quality control, and prediction, to estimate the age from tongue images. The segmentation module employs a zero-shot inference technique using the Large Language Instructed Segmentation Assistant (LISA) to accurately segment the tongue from its oral cavity images. Subsequent quality assessment of these segmentations is performed in the quality control module, ensuring only high-quality images proceed to the prediction stage. The age prediction module then employs an ensemble of EfficientNet B2 models, fine-tuned and optimized for age prediction from tongue imagery. Our experimental results derived from a newly collected dataset consisting of 9,767 tongue and facial images spanning diverse age groups demonstrate that the proposed method achieves an accuracy comparable to traditional facial age estimation techniques. This study not only provides an alternative approach to facial biometrics for age estimation but also enhances user privacy, making it particularly suitable for privacy-sensitive applications in healthcare and biometric monitoring.

An empirical study of the impact of masks on face recognition

Facial age estimation is of interest due to its potential to be applied in many real-life situations. However, recent age estimation efforts do not consider juveniles. Consequently, we introduce a juvenile age detection scheme called LaGMO, which focuses on the juvenile aging cues of facial shape and appearance. LaGMO is a combination of facial landmark points and Term Frequency Inverse Gravity Moment (TF-IGM). Inspired by the formation of words from morphemes, we obtained facial appearance features comprising facial shape and wrinkle texture and represented them as terms that described the age of the face. By leveraging the implicit ordinal relationship between the frequencies of the terms in the face, TF-IGM was used to compute the weights of the terms. From these weights, we built a matrix that corresponds to the possibilities of the face belonging to the age. Next, we reduced the reference matrix according to the juvenile age range (0–17 years) and avoided the exhaustive search through the entire training set. LaGMO detects the age by the projection of an unlabeled face image onto the reference matrix; the value of the projection depicts the higher probability of the image belonging to the age. With Mean Absolute Error (MAE) of 89% on the Face and Gesture Recognition Research Network (FG-NET) dataset, our proposal demonstrated superior performance in juvenile age estimation.

The minimum squared error (MSE) for classification is a linear discriminant function-based method that has been used in many applications such as face and handwritten character recognition. Nevertheless, MSE may not deal well with nonlinearly separable data sets. To address this problem, we improve the MSE and propose a new MSE-based algorithm, local MSE (LMSE), which is a local learning algorithm. For a test sample, we first determine its nearest neighbors from the training set. By using the determined neighbors, we construct a local MSE model to predict the class label of the test sample. LMSE can effectively capture the nonlinear structure of the data. It generally outperforms MSE, particularly when the data distribution is nonlinearly separable. Extensive experiments on many nonlinearly separable data sets show that LMSE achieves desirable recognition results.

In this work, we have proposed a self-adaptive radial basis function neural network (RBFNN)-based method for high-speed recognition of human faces. It has been seen that the variations between the images of a person, under varying pose, facial expressions, illumination, etc., are quite high. Therefore, in face recognition problem to achieve high recognition rate, it is necessary to consider the structural information lying within these images in the classification process. In the present study, it has been realized by modeling each of the training images as a hidden layer neuron in the proposed RBFNN. Now, to classify a facial image, a confidence measure has been imposed on the outputs of the hidden layer neurons to reduce the influences of the images belonging to other classes. This process makes the RBFNN as self-adaptive for choosing a subset of the hidden layer neurons, which are in close neighborhood of the input image, to be considered for classifying the input image. The process reduces the computation time at the output layer of the RBFNN by neglecting the ineffective radial basis functions and makes the proposed method to recognize face images in high speed and also in interframe period of video. The performance of the proposed method has been evaluated on the basis of sensitivity and specificity on two popular face recognition databases, the ORL and the UMIST face databases. On the ORL database, the best average sensitivity (recognition) and specificity rates are found to be 97.30 and 99.94%, respectively using five samples per person in the training set. Whereas, on the UMIST database, the above quantities are found to be 96.36 and 99.81%, respectively using eight samples per person in the training set. The experimental results indicate that the proposed method outperforms some of the face recognition approaches.

Face recognition technology has evolved as a popular identification technique to perform verification of human identity. By using the feature extraction methods and dimensionality reduction techniques in the pattern recognition applications, a number of facial recognition systems has been produced with distinct measure of success. Various face recognition algorithms and their extensions, have been proposed in the past three decades. However, face recognition faces challenging problems in real life applications because of the variation in the illumination of the face images. In the recent years, the research is focused towards Illumination-invariant face recognition system and many approaches have been proposed. But, there are several issues in face recognition across illumination variation which still remains unsolved. This paper provides a research on an efficient illumination-invariant face recognition system using Discrete Cosine Transform (DCT) and Principal Component Analysis (PCA). For processing the illumination invariant image, low frequency components of DCT are used to normalize the illuminated image, odd and even components of DCT is used for compensation in illumination variation and PCA is used for recognition of face images. The existing approaches in illumination Invariant face recognition are comprehensively reviewed and discussed. The proposed approach is validated with Yale Face Database B. Experimental results demonstrate the effectiveness of this approach in the performance of face recognition.

Our work is motivated by the problem of automatic face recognition, a difficult task, still missing a general solution. Its complexity lies in the wide range of variations presents in the input data, due to different lightings, background scenes and head positions. Moreover, the face appearance is affected by internal sources of variations: on a long temporal scale aging and weight gain, and on a short scale the action of the facial muscles. An effective recognition algorithm should be insensitive to all these sources of variations. During the last decade, good results to the recognition problem have been obtained using 3D Morphable Models (3DMMs). Their use allowed to separate the data variations due to the identity from the ones due to external sources like the lighting conditions. However, other internal sources were not considered. Our goal is to include expressions as an additional source of internal variation in 3DMMs, enabling us to recognize faces not only under different illuminations and pose conditions, but also with different expressions. In general, the construction of a 3DMM requires a corpus of training data; for our task we need a training set including examples of both identity and expression variations. Unfortunately, their acquisition alone is not sufficient, since they have to be previously registered with a reference 3D head model. The registration of 3D scans of expressions is a difficult problem, which could not be solved with the registration algorithm previously used. The main contribution of our work is a new registration algorithm which can cope with arbitrary expressions in the 3D data. Our algorithm is also capable of registering data with missing values, an important property since virtually no 3D acquisition devices is immune to holes and artifacts in the output. Given the training set of registered 3D examples, we construct a 3DMM where identity and expression variations are represented with two separate linear Gaussian models. The two models are then linearly combined, yielding an expression-identity 3DMM which we apply to the problem of 3D face recognition. Although this modeling approach does not take into account the interdependency between expressions and identity, the recognition performance is not negatively affected.

Multivariate time series anomaly detection has great potentials in many practical applications. Extreme unbalanced training set and noise interference make it challenging to accurately capture the distribution of normal data and then detect anomalies. Existing AutoEncoder(AE)-based approaches are lack of effective regularization method specially designed for anomaly detection tasks thus easily overfitting while Generative Adversarial Network(GAN)-based approaches are mostly trained under the hypothesis of pollution-free training set, which means the training set is all composed of normal samples and that is hard to satisfy in practice. To tackle these problems, in this paper we propose a GAN based anomaly detection method for multivariate time series named FGANomaly (letter F is for Filter). The core idea is to filter possible anomalous samples with pseudo-labels before training the discriminator thus to capture the distribution of normal data as precise as possible. In addition, we design a novel training objective for the generator, which leads the generator to concentrate more on plausible normal data and ignore anomalies. We conducted comprehensive experiments on four public datasets, and the experimental results show the superiority of our method over baselines in both performance and robustness.

Optimal descriptor as a translator of eclectic data into prediction of cytotoxicity for metal oxide nanoparticles under different conditions

Data augmentation has been utilized to improve the accuracy and robustness of face recognition algorithms. However, most of the previous studies focused on using the augmentation techniques to enlarge the feature set, while the diversity produced by the virtual samples lacked sufficient attention. In sparse dictionary learning-based face recognition, $$l_1$$ -based sparse representation (SR) and SVD-based dictionary learning (DL) both have shown promising performance. How to utilize both of them in an enhanced training process by data augmentation is still unclear. This paper proposes a novel method that utilizes the sample diversity generated by data augmentation and integrates sparse representation with dictionary learning, to learn dual sparse features for robust face recognition. An additional feature set is created by applying sample augmentation via simply horizontal flipping of face images. The two sparse models, $$l_1$$ -based SR and SVD-based DL, are integrated together using our new proposed objective function. Under two-level fusion of both data and classifiers, the diversity between two training sets is well learned and utilized, in three implementations, to obtain a robust face recognition. After conducting extensive experiments on some popular facial datasets, we demonstrate the proposed method can produce a higher classification accuracy than many state-of-the-art algorithms, and it can be considered as a promising option for image-based face recognition. Our code is released at GitHub.

A novel virtual samples-based sparse representation method for face recognition

Lack of training samples always affects the performance and robustness of face recognition. Generating virtual samples is one of effective methods to expand the training set. When the virtual samples are able to simulate the variations of facial images including variations of illuminations, facial postures and the facial expressions, the robustness will be enhanced and the accuracy will be improved obviously in the face recognition problem. In this paper, an improved linear representation-based classification combined virtual samples (ILRCVS) is proposed. First, we design a new objective function that simultaneously considers the information of the virtual training samples and the virtual test sample. Second, an alternating minimization algorithm is proposed to solve the optimization problem of the objective function. Finally, a new classification criterion combined with the virtual training and test sample is proposed. Experimental results on the Georgia Tech, FERET and Yale B face databases show that the proposed method is more robust than three state-of-the-art face recognition methods, LRC, SRC and CRC.