It is a challenging task to identify a person based on her/his gait patterns. State-of-the-art approaches rely on the analysis of temporal or spatial characteristics of gait, and gait recognition is usually performed on single modality data (such as images, skeleton joint coordinates, or force signals). Evidence has shown that using multi-modality data is more conducive to gait research. Therefore, we here establish an automated learning system, with an associated spatio-temporal capsule network (ASTCapsNet) trained on multi-sensor datasets, to analyze multimodal information for gait recognition. Specifically, we first design a low-level feature extractor and a high-level feature extractor for spatio-temporal feature extraction of gait with a novel recurrent memory unit and a relationship layer. Subsequently, a Bayesian model is employed for the decision-making of class labels. Extensive experiments on several public datasets (normal and abnormal gait) validate the effectiveness of the proposed ASTCapsNet, compared against several state-of-the-art methods.

The majority of work on the perception of gloss has been performed using smooth surfaces (e.g., spheres). Previous studies that have employed more complex surfaces reported that increasing mesoscale roughness increases perceived gloss [Psychol. Sci. 19, 196 (2008), J. Vis. 10(9), 13 (2010), Curr. Biol. 22, 1909 (2012)]. We show that the use of realistic rendering conditions is important and that, in contrast to [Psychol. Sci. 19, 196 (2008), J. Vis. 10(9), 13 (2010)], after a certain point increasing roughness further actually reduces glossiness. We investigate five image statistics of estimated highlights and show that for our stimuli, one in particular, which we term “percentage of highlight area,” is highly correlated with perceived gloss. We investigate a simple model that explains the unimodal, nonmonotonic relationship between mesoscale roughness and percentage highlight area.

Textures are the most important element for simulating real-world scenes and providing realistic and immersive sensations in many applications. Procedural textures can simulate a broad variety of surface textures, which is helpful for the design and development of new sensors. Procedural texture generation is the process of creating textures using mathematical models. The input to these models can be a set of parameters, random values generated by noise functions, or existing texture images, which may be further processed or combined to generate new textures. Many methods for procedural texture generation have been proposed, but there has been no comprehensive survey or comparison of them yet. In this paper, we present a review of different procedural texture generation methods, according to the characteristics of the generated textures. We divide the different generation methods into two categories: structured texture and unstructured texture generation methods. Example textures are generated using these methods with varying parameter values. Furthermore, we survey post-processing methods based on the filtering and combination of different generation models. We also present a taxonomy of different models, according to the mathematical functions and texture samples they can produce. Finally, a psychophysical experiment is designed to identify the perceptual features of the example textures. Finally, an analysis of the results illustrates the strengths and weaknesses of these methods.

Texture synthesis methods based on patch sampling and pasting can generate realistic textures with a similar appearance to a small sample. However, the sample usually has to be used throughout the synthesis stage. In contrast, the learned representation of the textures is more compact and discriminative, and can also yield good synthesis results. In this paper, we introduce a learned approach for texture synthesis based on support vector machines (SVM). This approach benefits from the merit of SVM that the sample texture pattern is learned using a model, and the sample itself can be discarded during the synthesis stage; the approach is also used to synthesize three-dimensional surface textures. Experimental results show that our approach is particularly effective in modeling and synthesizing near-regular or regular textures, which are difficult to achieve using traditional parametric texture synthesis methods. We further apply the proposed approach to constrained texture synthesis, image extrapolation, and texture inpainting. For texture inpainting, we develop a new method for automatically detecting holes in textures without the requirement of human intervention. Our approach yields promising results for the three tasks.