In this paper, we present a novel open-source pipeline for face registration based on Gaussian processes as well as an application to face image analysis. Non-rigid registration of faces is significant for many applications in computer vision, such as the construction of 3D Morphable face models (3DMMs). Gaussian Process Morphable Models (GPMMs) unify a variety of non-rigid deformation models with B-splines and PCA models as examples. GPMM separate problem specific requirements from the registration algorithm by incorporating domain-specific adaptions as a prior model. The novelties of this paper are the following: (i) We present a strategy and modeling technique for face registration that considers symmetry, multiscale and spatially-varying details. The registration is applied to neutral faces and facial expressions. (ii) We release an open-source software framework for registration and modelbuilding, demonstrated on the publicly available BU3D-FE database. The released pipeline also contains an implementation of an Analysis-by-Synthesis model adaption of 2D face images, tested on the Multi-PIE and LFW database. This enables the community to reproduce, evaluate and compare the individual steps of registration to model-building and 3D/2D model fitting. (iii) Along with the framework release, we publish a new version of the Basel Face Model (BFM-2017) with an improved age distribution and an additional facial expression model.

Models of shape variations have become a central component for the automated analysis of images. An important class of shape models are point distribution models (PDMs). These models represent a class of shapes as a normal distribution of point variations, whose parameters are estimated from example shapes. Principal component analysis (PCA) is applied to obtain a low-dimensional representation of the shape variation in terms of the leading principal components. In this paper, we propose a generalization of PDMs, which we refer to as Gaussian Process Morphable Models (GPMMs). We model the shape variations with a Gaussian process, which we represent using the leading components of its Karhunen-Loève expansion. To compute the expansion, we make use of an approximation scheme based on the Nyström method. The resulting model can be seen as a continuous analog of a standard PDM. However, while for PDMs the shape variation is restricted to the linear span of the example data, with GPMMs we can define the shape variation using any Gaussian process. For example, we can build shape models that correspond to classical spline models and thus do not require any example data. Furthermore, Gaussian processes make it possible to combine different models. For example, a PDM can be extended with a spline model, to obtain a model that incorporates learned shape characteristics but is flexible enough to explain shapes that cannot be represented by the PDM. We introduce a simple algorithm for fitting a GPMM to a surface or image. This results in a non-rigid registration approach whose regularization properties are defined by a GPMM. We show how we can obtain different registration schemes, including methods for multi-scale or hybrid registration, by constructing an appropriate GPMM. As our approach strictly separates modeling from the fitting process, this is all achieved without changes to the fitting algorithm. To demonstrate the applicability and versatility of GPMMs, we perform a set of experiments in typical usage scenarios in medical image analysis and computer vision: The model-based segmentation of 3D forearm images and the building of a statistical model of the face. To complement the paper, we have made all our methods available as open source.

The genetic relatedness of North American soybean [Glycine max (L.) (Merr.)] may threaten long‐term breeding progress. To alleviate this problem, we propose that breeders diversify applied programs by capitalizing upon genetic patterns that may exist in cultivated germplasm. To date, only one diversity pattern, the well‐known North‐South distinction, is explained in applied breeding. Our objective was to identify and quantify additional factors influencing diversity in 258 cultivars released by public agencies during 1945 to 1988. We theorized that maturity group effects (MG, as a hybridization restriction factor), location of breeding programs (BP, as a selection factor), and breeder intuition and success factors beyond MG and BP may all influence the soybean cultivar diversity patterns. The patterns of diversity associated with the first two factors, MG and BP, were examined by quantifying average coefficient of parentage (r) within and between MG and BP. Multidimensional scaling (MDS) was applied to the r matrix to produce coordinates for pictorial depiction of MG and BP. To examine the third factor, breeder intuition and success, the MDS coordinates were also subjected to a nonhierarchical cluster analysis that revealed nine major clusters of soybean cultivars. A regression analysis was employed to determine the relative importance of North‐South, MG, BP, and cluster patterns in explaining variation in the r matrix. The South‐North distinction accounted for only 21% of variability in cultivar relations indicating the presence of other major patterns of diversity. The MG, BP, and clusters independently explained 32, 42, and 57% of the total variation in the cultivar pedigrees. Clusters most efficiently revealed patterns of diversity, and we propose the use of these clusters in the further study and management of soybean diversity. Multidimensional scaling coupled with nonhierarchical cluster analysis was a highly promising approach to the study of diversity.

It is well known that deep learning approaches to face recognition suffer from various biases in the available training data. In this work, we demonstrate the large potential of synthetic data for analyzing and reducing the negative effects of dataset bias on deep face recognition systems. In particular we explore two complementary application areas for synthetic face images: 1) Using fully annotated synthetic face images we can study the face recognition rate as a function of interpretable parameters such as face pose. This enables us to systematically analyze the effect of different types of dataset biases on the generalization ability of neural network architectures. Our analysis reveals that deeper neural network architectures can generalize better to unseen face poses. Furthermore, our study shows that current neural network architectures cannot disentangle face pose and facial identity, which limits their generalization ability. 2) We pre-train neural networks with large-scale synthetic data that is highly variable in face pose and the number of facial identities. After a subsequent fine-tuning with realworld data, we observe that the damage of dataset bias in the real-world data is largely reduced. Furthermore, we demonstrate that the size of real-world datasets can be reduced by 75% while maintaining competitive face recognition performance. The data and software used in this work are publicly available 1 .

No abstract