A Bottom-Up Method for Facial Feature Extraction Using Active Shape Models

In the facial image, emotions are most widely represented with eye and mouth expressions. If we want to recognize the human's emotion via the facial image, we need to extract features of the facial image. Active Shape Model (ASM) is one of the most popular methods for facial feature extraction. Regarding the traditional ASM depends on the setting of the initial parameters of the model, in this paper we propose a facial emotion recognizing method based on ASM and Bayesian Network. Firstly, we obtain the reconstructive parameters of the new gray-scale image by sample-based learning and use them to reconstruct the shape of the new image and calculate the initial parameters of the ASM by the reconstructed facial shape. Then reduce the distance error between the model and the target contour by adjusting the parameters of the model. Finally get the model which is matched with the facial feature outline after several iterations and use them to recognize the facial emotion by using Bayesian Network.

A facial feature extraction method is proposed in this work, which uses location and texture information given a face image. Location and texture information can automatically be learnt by the system, from a training data. Best facial feature locations are found by maximizing the joint distribution of location and texture information of facial features. Performance of the method was found promising after it is tested using 100 test images. Also it is observed that this new method performs better than active appearance models for the same test data.

In this paper, we present an improved active shape model (ASM) for facial feature extraction. The original ASM method developed by Cootes et al. highly relies on the initialization and the representation of the local structure of the facial features in the image. We use color information to improve the ASM approach for facial feature extraction. The color information is used to localize the centers of the mouth and the eyes to assist the initialization step. Moreover, we model the local structure of the feature points in the RGB color space. Besides, we use 2D affine transformation to align facial features that are perturbed by head pose variations. In fact, the 2D affine transformation compensates for the effects of both head pose variations and the projection of 3D data to 2D. Experiments on a face database of 50 subjects show that our approach outperforms the standard ASM and is successful in facial feature extraction

Facial feature extraction using a probabilistic approach

Pose robust face tracking by combining view-based AAMs and temporal filters

Segmentation of diseased lungs in CT images is a nontrivial problem. As Active Appearance Model (AAM) has been applied effectively in this field, we propose a new approach for the construction of traditional AAM to segment the lung fields more accurately and efficiently: Matrixes based AAM (MatAAM). MatAAM is based on two-dimensional image matrixes rather one-dimensional vectors. Its appearance matrix does not need to be transformed into a vector prior to computing the appearance parameter. Instead, a covariance matrix is constructed directly using the normalized appearance matrixes and its eigenvectors are derived for the appearance parameter. The experiment results were compared to other landmark-based methods: Snake, Active Shape Model (ASM), AAM and several modified versions of them. For segmentation of lungs especially diseased lungs, MatAAM performed a superior result in both precision and efficiency.

Feature point detection is an important pre-processing step for quantitative evaluation of facial paralysis. Since the conventional methods such as active shape model (ASM) or active appearance model (AAM) are trained by using normal face and they are not possible to detect the feature points accurately for the face with paralysis. In this paper, we propose an automatic and accurate feature point detection method for quantitative evaluation of facial paralysis using deep convolutional neural networks (DCNN). The proposed method consists of two steps. We first use AAM for initial feature point detection. In the second step, a patch with the detected point at the center is used as an input of DCNN for refinement. Experiments demonstrated that the proposed method can significantly improve the detection accuracy of the conventional AAM.

PurposeRepresentation of anatomy appearance is one of the key problems in medical image analysis. An appearance model represents the anatomies with parametric forms, which are then vectorised for prior learning, segmentation and classification tasks.MethodsWe propose a part-based parametric appearance model we refer to as a deformable appearance pyramid (DAP). The parts are delineated by multi-scale local feature pyramids extracted from an image pyramid. Each anatomy is represented by an appearance pyramid, with the variability within a population approximated by local translations of the multi-scale parts and linear appearance variations in the assembly of the parts. We introduce DAPs built on two types of image pyramids, namely Gaussian and wavelet pyramids, and present two approaches to model the prior and fit the model, one explicitly using a subspace Lucas–Kanade algorithm and the other implicitly using the supervised descent method (SDM).ResultsWe validate the performance of the DAP instances with difference configurations on the problem of lumbar spinal stenosis for localising the landmarks and classifying the pathologies. We also compare them with classic methods such as active shape models, active appearance models and constrained local models. Experimental results show that the DAP built on wavelet pyramids and fitted with SDM gives the best results in both landmark localisation and classification.ConclusionA new appearance model is introduced with several configurations presented and evaluated. The DAPs can be readily applied for other clinical problems for the tasks of prior learning, landmark detection and pathology classification.

This paper obtains the contour map related to the facial features of the face by extracting important information such as facial features of the face, so as to complete the task of extracting the facial features of the face. With the rapid development of computer software and hardware technologies, facial feature extraction technology has become a research hotspot in computer image processing application scenarios such as face recognition and short video sketch filters. However, the current facial feature extraction technology based on deep learning still has problems such as insufficient contours of the extracted facial features and excessive noise. Therefore, aiming at the shortcomings of the original facial feature extraction methods, this paper proposes a facial feature extraction method based on semantic segmentation. The content of the Larticle is mainly expanded from the following main aspects: First, the development status of semantic segmentation is introduced. Then, an improvement to the semantic segmentation network model is proposed. Finally, the average intersection ratio is used as the evaluation index of the segmentation accuracy of the network model. By comparing the feature maps obtained by different methods, it is found that the improved semantic segmentation network model in this paper can realize the complete extraction of facial features.

In this talk, several feature extraction techniques will be introduced from two cues: algebraic feature extraction andgeometrical feature extraction methods. For algebraic feature extraction, Principal Component Analysis (PCA), LinearDiscriminant Analysis (LDA), Kernel Discriminant Analysis (KDA), Sparse representation and their variants will beintroduced. For geometrical feature extraction, Contour Points Distribution Histogram (CPDH), Active Shape Model (ASM),Active Appearance Model (AAM), ASM+AAM, and their variants will be presented. Typical applications of these featureextraction methods will be presented including face recognition, image fusion, image retrieval, and target tracking, etc. Themain aim of this talk is to introduce my main work in pattern recognition and computer vision, which hopefully ignitesdiscussions, and future development of feature extraction.

The use of appearance and shape priors in image segmentation is known to improve accuracy; however, existing techniques have several drawbacks. For instance, most active shape and appearance models require landmark points and assume unimodal shape and appearance distributions, and the level set representation does not support construction of local priors. In this paper, we present novel appearance and shape models for image segmentation based on a differentiable implicit parametric shape representation called a disjunctive normal shape model (DNSM). The DNSM is formed by the disjunction of polytopes, which themselves are formed by the conjunctions of half-spaces. The DNSM's parametric nature allows the use of powerful local prior statistics, and its implicit nature removes the need to use landmarks and easily handles topological changes. In a Bayesian inference framework, we model arbitrary shape and appearance distributions using nonparametric density estimations, at any local scale. The proposed local shape prior results in accurate segmentation even when very few training shapes are available, because the method generates a rich set of shape variations by locally combining training samples. We demonstrate the performance of the framework by applying it to both 2-D and 3-D data sets with emphasis on biomedical image segmentation applications.

Automatic segmentation of brain structures is a fundamental step for quantitative analysis of images in many brain’s pathologies such as Alzheimer’s, brain’s tumors or multiple sclerosis. The large variation of brain structures requires the development of efficient and specific methods, often by using Magnetic Resonance Imaging (MRI) modality. The goal of our work is to implement an automatic brain’s structures segmentation method that uses the active shape models (ASM) and active appearance models (AAM) techniques. Another goal of this work is to compare the performances of these segmentation approaches, and also to evaluate their use in a computer aided diagnosis tools and to compare their performances.

This paper presents an application of computer vision methods to dental age estimation based on the lower third right molar in panoramic X-ray images. For this purpose, two statistical computer vision models are adjusted and applied: Active Shape Model and Active Appearance Model. Both models use shape and appearance of the object to find the outer contour, with the only difference being in the way appearance is used. Statistical models are used to extract features describing the selected tooth, and neural network is used to provide dental age estimation using the features as input. Our own dataset was created, consisting of panoramic X-ray images with known age. A manual segmentation of the selected tooth has been performed for each image in the training set, and the obtained outer contours were used to train both models. Promising preliminary results are presented.

Heart disease is the leading cause of death in the modern world. Cardiac image processing is now routinely applied for detecting, classification and diagnosis of heart diseases. One of the most common uses of processing methods that are now widely applied are cardiac segmentation [1] and registration methods [2], that are used in order to extract the detailed anatomy and function of the heart. Automatic segmentation plays a central role when inspecting reconstructed 3D cardiac images from CT or MR scanners. An accurate classification of the different cardiac regions is usually the first step of tasks like: cardiac visualization, coronary artery inspection, measurement of the ejection fraction for the left and right ventricles and wall motion analysis. In a clinical context, physicians often mentally integrate image information from different modalities. Automatic registration, based on computer programs, might, however, offer better accuracy and repeatability and save time [3]. Cardiac image registration remains a challenge because of the numerous specific problems mainly related to the different motion sources (patient, respiration, heart) and to the specificity of each imaging modality. Up to now, no general method could automatically register any modality with any other modality so far. This paper presents a survey of shape modeling applications to cardiac image analysis from MRI, CT, echocardiography, PET, and SPECT and aims to introduce new methodologies in this field, classify major contributions in image-based cardiac modeling, provide a tutorial to beginners to initiate their own studies, and introduce the major challenges of registration and segmentation and provide practical examples. Image-driven processing methods, such as thresholding, region-based or edge-based techniques, or else pixel classification [4-6], provide a limited framework for further medical image analysis. They can include geometrical information, as well as high level information, in the so-called shape prior based segmentation framework, or through active shape models and active appearance models. At last, atlas guided segmentation also make use of a set of manually segmented images. By using different analysis software of cardiac images, CAD prototypes can be used in clinical routines in order to provide a computer output as a second reader to assist physicians in the detection of abnormalities, quantification of disease progression and differential diagnosis of lesions [7]. Computerized analysis of cardiac images in combination with artificial intelligence can be used in clinical practice and may contribute to more efficient diagnosis.

We investigated whether novel parameters derived from a Dual-energy X-ray absorptiometry (DXA) scan might improve fracture risk estimation. In this study, we analysed hip DXA scans from 29 older adults with a history of fragility fracture and 90 non-fractured controls. Active shape models and active appearance models were used to allow a quantitative characterisation of the shape and gross structure of the proximal femur. We also performed image texture analysis applied to various regions of interest. Feature selection was used to determine which method, or combination of methods, was best to discriminate between the fracture and control groups. Texture features derived from Gabor filters in combination with total T-score provided better estimates of risk (AUC = 0.787) than the standard measures of areal bone mineral density or total T-score alone (AUC = 0.699 and 0.692, respectively). Estimates of risk were more accurate when the texture was measured on the whole femoral neck compared to other regions. The features extracted from the active models were weaker with poor classification performance (AUC < 0.570). This study shows that image texture based on Gabor filters can complement the standard measures to improve fracture risk estimation.