Active Appearance Model Research Articles

Analysis of temporomandibular joint dysfunction in paediatric patients with unilateral crossbite using automatically generated finite element models

The evaluation of temporomandibular joint (TMJ) dysfunction using finite element models is a time consuming process that requires extensive technical knowledge. We combined a statistical active appearance model with automated modelling algorithms to biomechanically study the relationship between TMJ malformations and dysfunction in radiographs from 20 paediatric patients with unilateral crossbite. A fitting algorithm (fitting error < 4%) recognised the TMJ shape and adjusted the dimensions of each patient-specific 2D FE model, which was then used to compute 2 different joint movements. Significant functional differences were observed between the crossbite and non-cross bite sides, and the shape-function relation was verified.

Welding penetration monitoring for pulsed GTAW using visual sensor based on AAM and random forests

Abstract On-line welding penetration state monitoring based on passive visual sensing technology in pulsed gas tungsten arc welding (GTAW) has been a hot research topic in industry and academia. Passive vision sensing technology has some disadvantages. It is easy to be affected by some common disturbance during pulsed GTAW, like spattering, the change of arc intensity, the slightly change of focal length and viewing angle of visual sensor, etc. This paper proposed an intelligent penetration monitoring methodology for GTAW by combining pattern-based visual feature extraction method and supervised machine learning method. The proposed methodology mainly includes two parts: (a) visual features extraction for weld pool images based on active appearance model (AAM); (b) the implementation of penetration monitoring based on supervised machine learning method, random forests (RF). The extracted weld pool visual features include width, length and area size of weld pool. Then the extracted features are utilized to train RF model. Further, the trained RF model can implement the evaluation of penetration states and backside weld seam width. The experiments verify that the proposed method is effective with high accuracy and robustness, which also lays the foundation for online welding penetration control.

A comparison study on nonlinear dimension reduction methods with kernel variations: Visualization, optimization and classification

Because of high dimensionality, correlation among covariates, and noise contained in data, dimension reduction (DR) techniques are often employed to the application of machine learning algorithms. Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and their kernel variants (KPCA, KLDA) are among the most popular DR methods. Recently, Supervised Kernel Principal Component Analysis (SKPCA) has been shown as another successful alternative. In this paper, brief reviews of these popular techniques are presented first. We then conduct a comparative performance study based on three simulated datasets, after which the performance of the techniques are evaluated through application to a pattern recognition problem in face image analysis. The gender classification problem is considered on MORPH-II and FG-NET, two popular longitudinal face aging databases. Several feature extraction methods are used, including biologically-inspired features (BIF), local binary patterns (LBP), histogram of oriented gradients (HOG), and the Active Appearance Model (AAM). After applications of DR methods, a linear support vector machine (SVM) is deployed with gender classification accuracy rates exceeding 95% on MORPH-II, competitive with benchmark results. A parallel computational approach is also proposed, attaining faster processing speeds and similar recognition rates on MORPH-II. Our computational approach can be applied to practical gender classification systems and generalized to other face analysis tasks, such as race classification and age prediction.

Local transform directional pattern and optimization driven DBN for age estimation

Age estimation is an interesting and challenging research area, gaining significant importance in the recent era and is employed in various applications, such as intelligent surveillance, face recognition, biometrics, and so on. Various techniques are employed in the literature for age estimation from the face images. This paper introduces the age estimation scheme from the face image, and estimation is done by defining a novel feature extraction strategy, named Local Transform Directional Pattern (LTDP). The database containing the input images has many unwanted regions, and thus, the Viola Jones algorithm detects the required face region. After detecting the face regions, active appearance model extracts the active appearance features, and the proposed LTDP extracts the texture features. The proposed LTDP feature extraction model modifies the existing Local Directional Pattern (LDP) with several other texture feature extraction models. After the feature extraction, the Cuckoo search based Deep Belief Network (CDBN) classifier estimates the age of the person from the face image based on the extracted features. The simulation results reveal that the proposed LTDP with the CDBN classifier achieved high performance with the values of 2.3416, 0.9803, and 0.9724 for MAE, AEO, and AEM, respectively.

Pose and occlusion invariant face recognition system for video surveillance using extensive feature set

Face recognition presents a challenging problem in the field of image analysis and computer vision. Different video sequences of the same subject may contain variations in resolution, illumination, pose, and facial expressions. These variations contribute to the challenges in designing an effective video-based face-recognition algorithm. In this proposed method, we are presenting a face recognition method from video sequence with various pose and occlusion. Initially, shot segmentation process is done to separate the video sequence into frames. Then, face part is detected from each frame for further processing. Face detection is the first stage of a face recognition system. After detecting the face exactly the facial features are extracted. Here SURF features, appearance features, and holo-entropy is used to find out the uniqueness of the face image. The active appearance model (AAM) can be used to find out the appearance-based features in the face image. These features are used to select the optimal key frame in the video sequence which is based on the supervised learning method, modified artificial neural network (MANN) using bat algorithm. Here bat algorithm is used for optimising the weights of neurons. Finally, based on the feature library, the face image can be recognised.

Wrinkle detection system based on active appearance model

Wrinkle detection system based on active appearance model

Model-Based Active Appearance Model Approach For Face Recognition

Model-Based Active Appearance Model Approach For Face Recognition

Automatic prostate segmentation using multiobjective active appearance modelin MR images

Prostate cancer is the second largest cause of mortality among men. Prostate segmentation, i.e. the precise determination of the prostate region in magnetic resonance imaging (MRI), is generally used for prostate volume measurement, which can be used as a potential prostate cancer indicator. This paper presents a new fully automatic statistical model called the multiobjective active appearance model (MOAAM) for prostate segmentation in MR images. First, in the training stage, the appearance model, including the shape and texture model, is developed by applying principal component analysis to the training images, already outlined by a physician. Then noise and roughness are properly removed in the preprocessing step by Sticks filter and nonlinear filtering. This helps us provide the proper conditions for the prostate region detection. Finally, in order to detect the prostate region, a new multiobjective function is optimized using a suitable search algorithm. The proposed method has been applied to prostate images for segmenting the prostate boundaries. The evaluation results indicate that the presented method can yield a DSC value of \({87.4\pm5.00\%}\), is less sensitive to the edge information and initialization, and has a stronger capture range in comparison with existing methods.

Replicating Neuroscience Observations on ML/MF and AM Face Patches by Deep Generative Model.

A recent Cell paper (Chang & Tsao, 2017) reports an interesting discovery. For the face stimuli generated by a pretrained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit a strong linear relationship with the shape variables and appearance variables of the AAM that generates the face stimuli. In this letter, we show that this behavior can be replicated by a deep generative model, the generator network, that assumes that the observed signals are generated by latent random variables via a top-down convolutional neural network. Specifically, we learn the generator network from the face images generated by a pretrained AAM model using a variational autoencoder, and we show that the inferred latent variables of the learned generator network have a strong linear relationship with the shape and appearance variables of the AAM model that generates the face images. Unlike the AAM model, which has an explicit shape model where the shape variables generate the control points or landmarks, the generator network has no such shape model and shape variables. Yet it can learn the shape knowledge in the sense that some of the latent variables of the learned generator network capture the shape variations in the face images generated by AAM.

A Unified Tensor-based Active Appearance Model

Appearance variations result in many difficulties in face image analysis. To deal with this challenge, we present a Unified Tensor-based Active Appearance Model (UT-AAM) for jointly modelling the geometry and texture information of 2D faces. For each type of face information, namely shape and texture, we construct a unified tensor model capturing all relevant appearance variations. This contrasts with the variation-specific models of the classical tensor AAM. To achieve the unification across pose variations, a strategy for dealing with self-occluded faces is proposed to obtain consistent shape and texture representations of pose-varied faces. In addition, our UT-AAM is capable of constructing the model from an incomplete training dataset, using tensor completion methods. Last, we use an effective cascaded-regression-based method for UT-AAM fitting. With these advancements, the utility of UT-AAM in practice is considerably enhanced. As an example, we demonstrate the improvements in training facial landmark detectors through the use of UT-AAM to synthesise a large number of virtual samples. Experimental results obtained on a number of well-known face datasets demonstrate the merits of the proposed approach.

A Modular System for Detection, Tracking and Analysis of Human Faces in Thermal Infrared Recordings.

We present a system that utilizes a range of image processing algorithms to allow fully automated thermal face analysis under both laboratory and real-world conditions. We implement methods for face detection, facial landmark detection, face frontalization and analysis, combining all of these into a fully automated workflow. The system is fully modular and allows implementing own additional algorithms for improved performance or specialized tasks. Our suggested pipeline contains a histogtam of oriented gradients support vector machine (HOG-SVM) based face detector and different landmark detecion methods implemented using feature-based active appearance models, deep alignment networks and a deep shape regression network. Face frontalization is achieved by utilizing piecewise affine transformations. For the final analysis, we present an emotion recognition system that utilizes HOG features and a random forest classifier and a respiratory rate analysis module that computes average temperatures from an automatically detected region of interest. Results show that our combined system achieves a performance which is comparable to current stand-alone state-of-the-art methods for thermal face and landmark datection and a classification accuracy of 65.75% for four basic emotions.

Parametric face drawings: A demographically diverse and customizable face space model.

We introduce a novel face space model-parametric face drawings (or PFDs)-to generate schematic, though realistic, parameterized line drawings of faces based on the statistical distribution of human facial features. A review of existing face space models (including FaceGen Modeller, Synthetic Faces, MPI, and active appearance model) indicates that current models are constrained by their reliance on ethnically homogeneous face databases. This constraint has led to negative consequences for underrepresented populations, such as impairments in automatized identity recognition of certain demographic groups. Our model is based on a demographically diverse sample of 400 faces (200 female, 200 male; 100 East Asian/Pacific Islander, 100 Latinx/Hispanic, 100 black/African-American, and 100 white/Caucasian) compiled from several face databases (including FERET face recognition technology and the Chicago Face Database). Each front-view face image is manually coded with 85 landmark points that are then normalized and rendered with MATLAB (MathWorks, Natick, MA) tools to produce a smooth, parameterized face line drawing. We present data from two behavioral experiments to validate our model and demonstrate its applicability. In Experiment 1 we show that PFDs produce a reliable "inversion effect" in short-term recognition, a hallmark of holistic processing. In Experiment 2, we conduct a celebrity recognition task, comparing performance on PFDs to performance on untextured renderings from FaceGen Modeller. Participants successfully recognized approximately 50% of celebrity faces based on the PFD models, comparable to performance based on FaceGen Modeler (also 50% correct). We highlight a range of potential applications of our model, list some limitations, and provide MATLAB resources for researchers to utilize our face space, including the ability to customize the demographic makeup of the face space, add new faces, and produce morphs and caricatures.

Predicting Depression, Anxiety, and Stress Levels from Videos Using the Facial Action Coding System.

We present the first study in the literature that has aimed to determine Depression Anxiety Stress Scale (DASS) levels by analyzing facial expressions using Facial Action Coding System (FACS) by means of a unique noninvasive architecture on three layers designed to offer high accuracy and fast convergence: in the first layer, Active Appearance Models (AAM) and a set of multiclass Support Vector Machines (SVM) are used for Action Unit (AU) classification; in the second layer, a matrix is built containing the AUs’ intensity levels; and in the third layer, an optimal feedforward neural network (FFNN) analyzes the matrix from the second layer in a pattern recognition task, predicting the DASS levels. We obtained 87.2% accuracy for depression, 77.9% for anxiety, and 90.2% for stress. The average prediction time was 64 s, and the architecture could be used in real time, allowing health practitioners to evaluate the evolution of DASS levels over time. The architecture could discriminate with 93% accuracy between healthy subjects and those affected by Major Depressive Disorder (MDD) or Post-traumatic Stress Disorder (PTSD), and 85% for Generalized Anxiety Disorder (GAD). For the first time in the literature, we determined a set of correlations between DASS, induced emotions, and FACS, which led to an increase in accuracy of 5%. When tested on AVEC 2014 and ANUStressDB, the method offered 5% higher accuracy, sensitivity, and specificity compared to other state-of-the-art methods.

Multiple Classifiers for Age Prediction Against AAM and ASM

In recent years, the researchers on age prediction relied on face pictures to get more attention, due to their important applications in security control and human computer interaction. Age prediction incorporates two processes: traits elicitation and prediction of machine learning. In the aspect of face traits elicitation, accurate and robust location for the trait point is convoluted and becoming a challenging issue in age prediction. Active Shape Model (ASM) can elicit the facial shape effectively and correctly. Furthermore, as the improvement of ASM, Active Appearance Models (AAM) is proposed to elicit both shape and texture traits from facial images simultaneously. In this paper, the two models are tested and compared for their performance against 6 algorithms which are Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Support Vector Regression (SVR), Canonical Correlation Analysis (CCA), Linear Discriminant Analysis (LDA), and Projection Twin Support Vector Machine (PTSVM). The experiments show that ASM is faster and gains more precise result than the AAM

Cosmetic applied based face recognition for biometric passport

PurposeNowadays, the use of forged e-passport is increasing, which is threatening national security. It is important to improve the national security against international crime or terrorism. There is a weak verification process caused by lack of identification processes such as a physical check, biometric check and electronic check. The e-passport can prevent the passport cloning or forging resulting from the illegal immigration. The paper aims to discuss these issues.Design/methodology/approachThis paper focuses on face recognition to improve the biometric authentication for an e-passport, and it also introduces facial permanent mark detection from the makeup or cosmetic-applied faces, twins and similar faces. An algorithm is proposed to detect the cosmetic-applied facial permanent marks such as mole, freckle, birthmark and pockmark. Active Shape Model into Active Appearance Model using Principal Component Analysis is applied to detect the facial landmarks. Facial permanent marks are detected by applying the Canny edge detector and Gradient Field Histogram of Oriented Gradient.FindingsThis paper demonstrated an algorithm and proposed facial marks detection from cosmetic or makeup-applied faces for a secure biometric passport in the field of personal identification for national security. It also presented to detect and identify identical twins and similar faces. This paper presented facial marks detection from the cosmetic-applied face, which can be mixed with traditional methods. However, the use of the proposed technique faced some challenges due to the use of cosmetic. The combinations of the algorithm for facial mark recognition matching with classical methods were able to attain lower errors in this proposed experiment.Originality/valueThe proposed method will enhance the national security and it will improve the biometric authentication for the e-passport. The proposed algorithm is capable of identifying facial marks from cosmetic-applied faces accurately, with less false positives. The proposed technique shows the best results.

Locality-constrained framework for face alignment

Although the conventional active appearance model (AAM) has achieved some success for face alignment, it still suffers from the generalization problem when be applied to unseen subjects and images. To deal with the generalization problem of AAM, we first reformulate the original AAM as sparsity-regularized AAM, which can achieve more compact/better shape and appearance priors by selecting nearest neighbors as the bases of the shape and appearance model. To speed up the fitting procedure, the sparsity in sparsity-regularized AAM is approximated by using the locality (i.e., K-nearest neighbor), and thus inducing the locality-constrained active appearance-model (LC-AAM). The LC-AAM solves a constrained AAM-like fitting problem with the K-nearest neighbors as the bases of shape and appearance model. To alleviate the adverse influence of inaccurate K-nearest neighbor results, the locality constraint is further embedded in the discriminative fitting method denoted as LC-DFM, which can find better K-nearest neighbor results by employing shape-indexed feature, and can also tolerate some inaccurate neighbors benefited from the regression model rather than the generative model in AAM. Extensive experiments on several datasets demonstrate that our methods outperform the state-of-the-arts in both detection accuracy and generalization ability.

GHT based automatic kidney image segmentation using modified AAM and GBDT

These days age development to be more prominent in biometric angle. Particularly CAD machine is essentially renowned for ordering and division. In this theory Kidney issue and the division systems are examined. The kidney inconvenience recognizable proof and the finding in logical region are well focused on kidney’s external layer. Accordingly, the inward inconvenience isn’t yet considered in each case. This is mulled over and another time is produced in this examination for division of Kidney using GBDT (Gradient Boosting Decision Tree) thought. The exploration managed with a novel proficient componentThis research was handled with novel efficient mechanism named as GBDT. A systematic technique termed GBDT was utilized to enhance the predictive model. In the process of renal cortex phase localization, a technique which integrates Generalized Hough Transform (GHT) with Active Appearance Models (AAM) was enforced for kidney localization to appraise the renal cortex thickness. The AAM method always matches a new data to the appearance model by minimizing the intensity of root mean square (RMS) between the new data as well as appearance model instance. And finally, from the result of the localization phase, the proposed method GBDT was employed to segregate the kidney into various components. Then an accumulator matrix indicating the possible position of an object was constructed pursuant to the R-table, where the training set data is normally used in this form of table. The results were evaluated to reveal the higher achievement of the proposed system.

Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation

Facial Expression Recognition (FER) is an important subject of human–computer interaction and has long been a research area of great interest. Accurate Facial Expression Sequence Interception (FESI) and discriminative expression feature extraction are two enormous challenges for the video-based FER. This paper proposes a framework of FER for the intercepted video sequences by using feature point movement trend and feature block texture variation. Firstly, the feature points are marked by Active Appearance Model (AAM) and the most representative 24 of them are selected. Secondly, facial expression sequence is intercepted from the face video by determining two key frames whose emotional intensities are minimum and maximum, respectively. Thirdly, the trend curve which represents the Euclidean distance variations between any two selected feature points is fitted, and the slopes of specific points on the trend curve are calculated. Finally, combining Slope Set which is composed by the calculated slopes with the proposed Feature Block Texture Difference (FBTD) which refers to the texture variation of facial patch, the final expressional feature are formed and inputted to One-dimensional Convolution Neural Network (1DCNN) for FER. Five experiments are conducted in this research, and three average FER rates 95.2%, 96.5%, and 97% for Beihang University (BHU) facial expression database, MMI facial expression database, and the combination of two databases, respectively, have shown the significant advantages of the proposed method over the existing ones.

Facial expression recognition using distance and texture signature relevant features

Distance and texture characteristics among the landmark points reflected in human faces are important features in so far as the recognition of human faces is concerned. In this article we consider (i) normalized distance signature obtained from Active Appearance Model (AAM) based grid, (ii) normalized texture signature derived from salient landmarks within the grid, (iii) stability indices arising out of these signatures and (iv) relevant statistical measures as the set of features for training of artificial neural models such as Multilayer Perceptron (MLP), Radial Basis Function Network (RBF), Nonlinear AutoRegressive with eXogenous input (NARX) and Convolutional Neural Network (CNN) to achieve the task of recognition of facial expressions. The Cohn-Kanade (CK+), Japanese Female Facial Expression (JAFFE), MMI and MUG benchmark databases are used to conduct the experiments and the results obtained justify the effectiveness of the proposed procedure. The combined distance-texture (D-T) signature is found to perform convincingly better than the distance signature and texture signature individually. The effectiveness of the proposed technique based on combined D-T signature is substantiated by its extremely encouraging performance compared to other existing arts.

Active Appearance Model Induced Generative Adversarial Network for Controlled Data Augmentation.

Data augmentation is an important strategy for enlarging training datasets in deep learning-based medical image analysis. This is because large, annotated medical datasets are not only difficult and costly to generate, but also quickly become obsolete due to rapid advances in imaging technology. Image-to-image conditional generative adversarial networks (C-GAN) provide a potential solution for data augmentation. However, annotations used as inputs to C-GAN are typically based only on shape information, which can result in undesirable intensity distributions in the resulting artificially-created images. In this paper, we introduce an active cell appearance model (ACAM) that can measure statistical distributions of shape and intensity and use this ACAM model to guide C-GAN to generate more realistic images, which we call A-GAN. A-GAN provides an effective means for conveying anisotropic intensity information to C-GAN. A-GAN incorporates a statistical model (ACAM) to determine how transformations are applied for data augmentation. Traditional approaches for data augmentation that are based on arbitrary transformations might lead to unrealistic shape variations in an augmented dataset that are not representative of real data. A-GAN is designed to ameliorate this. To validate the effectiveness of using A-GAN for data augmentation, we assessed its performance on cell analysis in adaptive optics retinal imaging, which is a rapidly-changing medical imaging modality. Compared to C-GAN, A-GAN achieved stability in fewer iterations. The cell detection and segmentation accuracy when assisted by A-GAN augmentation was higher than that achieved with C-GAN. These findings demonstrate the potential for A-GAN to substantially improve existing data augmentation methods in medical image analysis.