We propose a novel geometric framework for analyzing 3D faces, with the specific goals of comparing, matching, and averaging their shapes. Here we represent facial surfaces by radial curves emanating from the nose tips and use elastic shape analysis of these curves to develop a Riemannian framework for analyzing shapes of full facial surfaces. This representation, along with the elastic Riemannian metric, seems natural for measuring facial deformations and is robust to challenges such as large facial expressions (especially those with open mouths), large pose variations, missing parts, and partial occlusions due to glasses, hair, and so on. This framework is shown to be promising from both-empirical and theoretical-perspectives. In terms of the empirical evaluation, our results match or improve upon the state-of-the-art methods on three prominent databases: FRGCv2, GavabDB, and Bosphorus, each posing a different type of challenge. From a theoretical perspective, this framework allows for formal statistical inferences, such as the estimation of missing facial parts using PCA on tangent spaces and computing average shapes.

/pdf/3d-face-recognition-under-expressions-occlusions-and-pose-26qgp6f3vp.pdf

3D Face Recognition under Expressions, Occlusions, and Pose Variations

A novel unsupervised deep learning model for global and local health condition assessment of structures

In this paper, we present a novel approach to 3D face matching that shows high effectiveness in distinguishing facial differences between distinct individuals from differences induced by nonneutral expressions within the same individual. The approach takes into account geometrical information of the 3D face and encodes the relevant information into a compact representation in the form of a graph. Nodes of the graph represent equal width isogeodesic facial stripes. Arcs between pairs of nodes are labeled with descriptors, referred to as 3D Weighted Walkthroughs (3DWWs), that capture the mutual relative spatial displacement between all the pairs of points of the corresponding stripes. Face partitioning into isogeodesic stripes and 3DWWs together provide an approximate representation of local morphology of faces that exhibits smooth variations for changes induced by facial expressions. The graph-based representation permits very efficient matching for face recognition and is also suited to being employed for face identification in very large data sets with the support of appropriate index structures. The method obtained the best ranking at the SHREC 2008 contest for 3D face recognition. We present an extensive comparative evaluation of the performance with the FRGC v2.0 data set and the SHREC08 data set.

3D Face Recognition Using Isogeodesic Stripes

We describe an expression-invariant method for face recognition by fitting an identity/expression separated 3D Morphable Model to shape data. The expression model greatly improves recognition and retrieval rates in the uncooperative setting, while achieving recognition rates on par with the best recognition algorithms in the face recognition great vendor test. The fitting is performed with a robust nonrigid ICP algorithm. It is able to perform face recognition in a fully automated scenario and on noisy data. The system was evaluated on two datasets, one with a high noise level and strong expressions, and the standard UND range scan database, showing that while expression invariance increases recognition and retrieval performance for the expression dataset, it does not decrease performance on the neutral dataset. The high recognition rates are achieved even with a purely shape based method, without taking image data into account.

/pdf/expression-invariant-3d-face-recognition-with-a-morphable-2hov6m1nh1.pdf

Expression invariant 3D face recognition with a Morphable Model

This paper proposes a new 3D face recognition approach, Collective Shape Difference Classifier (CSDC), to meet practical application requirements, i.e., high recognition performance, high computational efficiency, and easy implementation. We first present a fast posture alignment method which is self-dependent and avoids the registration between an input face against every face in the gallery. Then, a Signed Shape Difference Map (SSDM) is computed between two aligned 3D faces as a mediate representation for the shape comparison. Based on the SSDMs, three kinds of features are used to encode both the local similarity and the change characteristics between facial shapes. The most discriminative local features are selected optimally by boosting and trained as weak classifiers for assembling three collective strong classifiers, namely, CSDCs with respect to the three kinds of features. Different schemes are designed for verification and identification to pursue high performance in both recognition and computation. The experiments, carried out on FRGC v2 with the standard protocol, yield three verification rates all better than 97.9 percent with the FAR of 0.1 percent and rank-1 recognition rates above 98 percent. Each recognition against a gallery with 1,000 faces only takes about 3.6 seconds. These experimental results demonstrate that our algorithm is not only effective but also time efficient.

/pdf/robust-3d-face-recognition-by-local-shape-difference-14gp6f9bnd.pdf

Robust 3D Face Recognition by Local Shape Difference Boosting

Thirty local geometrical features extracted from 3D hitman face surfaces have been used to model the face for face recognition. They are the most discriminating ones selected from a set of 86. We have experimented with 420 3D-facial meshes (without texture) of 60 individuals. There are 7 images per subject including views presenting fight rotations and facial expressions. The HK algorithm, based in the signs of the mean and Gaussian curvatures, has been used for region segmentation. Experiments under controlled and non-controlled acquisition conditions, considering pose variations and facial expressions, have been achieved to analyze the robustness of the selected characteristics. Success recognition results of 82.0% and 90.16% were obtained when the images are frontal views with neutral expression using PCA and SVM, respectively. The recognition rates only decrease to 76.2% and 77.9% using PCA and SVM matching schemes respectively, under gesture and light face rotation.

Face recognition using 3D local geometrical features: PCA vs. SVM

Differential optical flow applied to automatic facial expression recognition

Preprocessing stage for denoising is a crucial task in image analysis in general, and in computer-aided diagnosis using medical images in particular. Standard acquisition of Magnetic Resonance Images MRI presents statistical Rician noise which degrades the performance of the image analysis. This paper presents a new technique to reduce Rician noise of brain MRI. The new method for noise filtering is achieved in the discrete Wavelet Packets Transform WPT domain. Four methodologies for thresholding the detail coefficients in the same 2D WPT domain have been experimented considering two scenarios with and without a previous adaptive Wiener filtering in the spatial domain. Best quantitative and qualitative results have been obtained by the new method presented in this work specifically tailored for brain MRI, which is adaptive to each subband and dependent on the data. It has been compared with other traditional methods considering the Signal to Noise Ratio SNR, Normalized Cross Correlation NCC and execution time ∼ 0.1 s/slice. A complete dataset of structural T1-w brain MRI of the BrainWeb database has been used for experiments. An important aspect is that these experiments with synthetic images proved that the common prior adaptive Wiener filtering often used by many authors is a dispensable procedure.

Rician noise attenuation in the wavelet packet transformed domain for brain MRI

A novel robust technique for the off-line signature verification problem in practical real conditions is presented. The technique is based on the use of compression neural networks, and in the automatic generation of the training set from only one signature for each writer. Our proposal incorporates a new kind of acceptance/rejection rule, which is based on the similarity between subimages or positional cuttings of a test signature and the corresponding representation stored in the class compression network. Experimental results show that the proposed technique reduces significantly the false acceptation rate (FAR).

Robust off-line signature verification using compression networks and positional cuttings

Demographic handwriting-based classification problems, such as gender and handedness categorizations, present interesting applications in disciplines like Forensic Biometrics. This work describes an experimental study on the suitability of deep neural networks to three automatic demographic problems: gender, handedness, and combined gender-and-handedness classifications, respectively. Our research was carried out on two public handwriting databases: the IAM dataset containing English texts and the KHATT one with Arabic texts. The considered problems present a high intrinsic difficulty when extracting specific relevant features for discriminating the involved subclasses. Our solution is based on convolutional neural networks since these models had proven better capabilities to extract good features when compared to hand-crafted ones. Our work also describes the first approach to the combined gender-and-handedness prediction, which has not been addressed before by other researchers. Moreover, the proposed solutions have been designed using a unique network configuration for the three considered demographic problems, which has the advantage of simplifying the design complexity and debugging of these deep architectures when handling related handwriting problems. Finally, the comparison of achieved results to those presented in related works revealed the best average accuracy in the gender classification problem for the considered datasets.

/pdf/gender-and-handedness-prediction-from-offline-handwriting-13xh1d049p.pdf

A. B. Moreno

Papers

Face recognition using 3D local geometrical features: PCA vs. SVM

Differential optical flow applied to automatic facial expression recognition

Rician noise attenuation in the wavelet packet transformed domain for brain MRI

Robust off-line signature verification using compression networks and positional cuttings

Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks