Hand pose recognition has received increasing attention in an area of human–computer interaction. With the recent spread of many low‐cost three‐dimensional (3D) cameras, research into understanding more natural gestures has increased. In this study, the authors present a method for hand part classification and joint estimation from a single depth image. They apply random decision forests (RDFs) for hand part classification. Foreground pixels in the hand image are estimated by RDF. Then hand joints are estimated based on the classified hand parts. They suggest a robust feature extraction method for per‐pixel classification, which enhances the accuracy of hand part classification. They also propose a tree selection algorithm using legacy trained RDF to classify unseen test data. Selecting trees using the proposed method show better performance than using all the trees as in conventional method. Depth images and label images synthesised by 3D hand mesh model were used for training forests and algorithm verification. The authors’ experiments show that the enhanced algorithm outperforms the state‐of‐the‐art method in accuracy.
Gradient descent method is an essential algorithm for learning of neural networks. Among diverse variations of gradient descent method that have been developed for accelerating learning speed, the natural gradient learning is based on the theory of information geometry on stochastic neuromanifold, and is known to have ideal convergence properties. Despite its theoretical advantages, the pure natural gradient has some limitations that prevent its practical usage. In order to get the explicit value of the natural gradient, it is required to know true probability distribution of input variables, and to calculate inverse of a matrix with the square size of the number of parameters. Though an adaptive estimation of the natural gradient has been proposed as a solution, it was originally developed for online learning mode, which is computationally inefficient for the learning of large data set. In this paper, we propose a novel adaptive natural gradient estimation for mini-batch learning mode, which is commonly adopted for big data analysis. For two representative stochastic neural network models, we present explicit rules of parameter updates and learning algorithm. Through experiments on three benchmark problems, we confirm that the proposed method has superior convergence properties to the conventional methods.
As a novel approach to perform user authentication, we propose a multimodal biometric system that uses faces and gestures obtained from a single vision sensor. Unlike typical multimodal biometric systems using physical information, the proposed system utilizes gesture video signals combined with facial images. Whereas physical information such as face, fingerprints, and iris is fixed and not changeable, behavioral information such as gestures and signatures can be freely changed by the user, similar to a password. Therefore, it can be a countermeasure when the physical information is exposed. We aim to investigate the potential possibility of using gestures as a signal for biometric system and the robustness of the proposed multimodal user authentication system. Through computational experiments on a public database, we confirm that gesture information can help to improve the authentication performance.
Multi-attribute recognition is one of the main topics attaining much attention in the pattern recognition field these days. The conventional approaches to multi-attribute recognition has mainly focused on developing an individual classifier for each attribute. However, due to rapid growth of deep learning techniques, multi-attribute recognition using multi-task learning enables the simultaneous recognition of more than two relevant recognition tasks through a single network. A number of studies on multi-task learning have shown that it is effective in improving recognition performance for all tasks when related tasks are learned together. However, since there are no specific criteria for determining the relationship among attributes, it is difficult and confusing to choose a good combination of tasks that have a positive impact on recognition performance. As one way to solve this problem, we propose a multi-attribute recognition method based on the novel output representations of a deep learning network which automatically learns the exclusive and joint relationship among attribute recognition tasks. We apply our proposed method to multi-attribute recognition of facial images, and confirm the effectiveness through experiments on a benchmark database.