The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We consider the problem of depth-based robust 3D facial pose tracking under unconstrained scenarios with heavy occlusions and arbitrary facial expression variations. Unlike the previous depth-based discriminative or data-driven methods that require sophisticated training or manual intervention, we propose a generative framework that unifies pose tracking and face model adaptation on-the-fly. Particularly,...
Discovering the common (joint) and individual subspaces is crucial for analysis of multiple data sets, including multi-view and multi-modal data. Several statistical machine learning methods have been developed for discovering the common features across multiple data sets. The most well studied family of the methods is that of Canonical Correlation Analysis (CCA) and its variants. Even though the...
Regression based facial landmark detection methods usually learns a series of regression functions to update the landmark positions from an initial estimation. Most of existing approaches focus on learning effective mapping functions with robust image features to improve performance. The approach to dealing with the initialization issue, however, receives relatively fewer attentions. In this paper,...
In this paper, we propose a novel multi-center convolutional neural network for unconstrained face alignment. To utilize structural correlations among different facial landmarks, we determine several clusters based on their spatial position. We pre-train our network to learn generic feature representations. We further fine-tune the pre-trained model to emphasize on locating a certain cluster of landmarks...
In this paper, we propose a topology preserving graph matching (TPGM) method for partial face recognition. Most existing face recognition methods extract features from holistic face images, yet faces in real-world unconstrained environments are usually occluded by objects or other faces, which cannot provide the whole face images for recognition. Latest keypoint-based partial face recognition methods...
We present a framework for robust face detection and landmark localisation of faces in the wild, which has been evaluated as part of `the 2nd Facial Landmark Localisation Competition'. The framework has four stages: face detection, bounding box aggregation, pose estimation and landmark localisation. To achieve a high detection rate, we use two publicly available CNN-based face detectors and two proprietary...
Face hallucination, which refers to predicting a HighResolution (HR) face image from an observed Low-Resolution (LR) one, is a challenging problem. Most state-of-the-arts employ local face structure prior to estimate the optimal representations for each patch by the training patches of the same position, and achieve good reconstruction performance. However, they do not take into account the contextual...
Face alignment is a critical topic in the computer vision community. Numerous efforts have been made and various benchmark datasets have been released in recent decades. However, two significant issues remain in recent datasets, e.g., Intra-Dataset Variation and Inter-Dataset Variation. Inter-Dataset Variation refers to bias on expression, head pose, etc. inside one certain dataset, while Intra-Dataset...
With the increasing number of public available training data for face alignment, the regression-based methods attracted much attention and have become the dominant methods to solve this problem. There are two main factors, the variance of the regression target and the capacity of the regression model, affecting the performance of the regression task. In this paper, we present a Stacked Hourglass Network...
Convolutional neural networks have significantly boosted the performance of face recognition in recent years due to its high capacity in learning discriminative features. In order to enhance the discriminative power of the deeply learned features, we propose a new supervision signal named marginal loss for deep face recognition. Specifically, the marginal loss simultaneously minimises the intra-class...
Texture analysis is extensively used for extraction of facial features. In this paper, we investigate extraction of facial features related to attributes of gender, age, race and expression. We propose novel approaches for texture analysis to improve single-label classification of these facial attributes. The proposed methods are derived by applying Local Binary Pattern based approaches on polar raster...
We propose a novel 3D-assisted coarse-to-fine extreme-pose facial landmark detection system in this work. For a given face image, our system first refines the face bounding box with landmark locations inferred from a 3D face model generated by a Recurrent 3D Regressor at coarse level. Another R3R is then employed to fit a 3D face model onto the 2D face image cropped with the refined bounding box at...
Growing number of surveillance and biometric applications seek to recognize the face of individuals appearing in the viewpoint of video cameras. Systems for video-based FR can be subjected to challenging operational environments, where the appearance of faces captured with video cameras varies significantly due to changes in pose, illumination, scale, blur, expression, occlusion, etc. In particular,...
Digital cameras are widely used in desktop and notebook PCs. Taking self-portraits is one of the important function of such cameras, which allows users to capture memories, create art, and improve photography techniques. A desktop environment with a large display and a pan-and-tilt camera provides users with a good area for exploring more angles and postures while taking self-portraits. However, most...
Face recognition in real scenarios is mainly affected by illumination variation and occlusion, and therefore in order to develop a robust face recognition system these issues should be handled simultaneously. To this aim, the steps involved in the presented framework are (i) computationally simple and efficient preprocessing chain that eliminates major effects of illumination variation and noise while...
In the calculation of rank minimization, the non-negative sparse low-rank representation classification (NSLRRC) regularizes nuclear norm's each singular value equally, but this limits its flexibility and ability to solve many practical problems, where the singular values with clear physical meanings ought to be treated differently. In this paper, a weighted non-negative sparse low-rank representation...
Recognition of Face in a group of people is a bit of difficult in now days, in this paper, a new method called Fuzzy Logic Local Ternary Pattern has been introduced. This FLTP method is a commanding technique to identify the faces clearly and even their emotions too. Here, several videos are taken in to the database and compares with query image. Using FLTP, recognizes the person is present in those...
Feature refers to some relevant information which is present on images or faces. Feature extraction used to extract those features from the face. Among that bulk of keypoints, only robust features are detected by using feature descriptors. This paper analyzes 2 robust feature detector and descriptors are: Scale-Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF). These two robust...
This paper proposes a novel facial image representation Block-based Local Contrast Patterns (BLCP) for illumination-robust face recognition. This method is based on an effective texture descriptor local contrast patterns (LCP). We use the directed and undirected difference masks to calculate three types of local intensity contrasts: directed, undirected, and maximum difference responses. These response...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.