Gesture recognition is an image sensing technology that allows people to operate devices with natural movements. Gesture recognition applications include patient monitoring, surveillance, robotics, sign language recognition, and more. However, there are many places where gesture recognition using normal cameras cannot be used from a privacy consideration. For example, personal spaces such as toilets and bathrooms, public spaces, and more. We have proposed a method of capturing shadow pictures using single-pixel-imaging to realize privacy-conscious gesture recognition. Single-pixel-imaging is a method of image reconstruction using random mask patterns and a single point detector. As an implementation method of single-pixel imaging in public spaces, we have studied using a high-frame-rate LED display as a light source. By using a high-frame-rate LED display, random patterns can be latent while the observer perceives an apparent image. However, the image reconstructed by single-pixel-imaging using a high-frame-rate LED display is influenced by the apparent image, making gesture recognition difficult. In this study, we show that the influence of the apparent image can be removed by restoring the restored image using deep learning with a convolutional network called U-Net.
The material of parts produced by laser stereolithography is a photopolymer. The photopolymer parts must be reinforced by particles or short fibers to increase the mechanical strength of the parts. The purpose of this research work is to reinforce the photopolymer part along thickness direction. Carbon fiber was selected as the fiber because the carbon fiber has high tensile strength. Static electricity was used for orientation of the carbon fiber along thickness direction. The orientation conditions for example, applying voltage between electrode plates, length of carbon fiber and orientation repetition time were examined. Orientation of carbon fiber was possible under a wide range of conditions.