Palm veins images are taken by a near infrared camera and a common digital camera. It is possible to generate clear vein images using near-infrared rays, but this is not easy using a color image. A near infrared palm vein image for training data and a color image were arranged in a dataset pair; the datasets were learned using a deep learning method called pix2pix. Clear palm vein images close to the near infrared image were generated using our proposed method. Our experimental results showed that we can take a palm vein image using only a general digital camera without a near infrared camera. Realization of palm veins authentication on an inexpensive smartphone is expected.
We discuss material properties of different garment wrinkles. Subjects wear three kinds of different fabric garment: polyester, cotton, and linen. Scanning the subject's 3D body shape using a RGB-D camera and getting a 3DCG model of them. Generating a normal polygonal image applying a baking process. High-poly mesh is generated from low-poly mesh of the 3DCG model, and multiple high polygons are mapped into a low polygon. Computing the normal vectors of the high polygons on the low-poly mesh, generators our normal map image through this process. Garment wrinkles are detected by straight-line recognition on the normal map using Hough transform. Measuring the number of the garment wrinkles, the variation in the direction and position of garment wrinkles, and the length distribution . All properties of the garment wrinkle is necessary for an analysis in our experiment. But it is revealed that the dispersion in the wrinkle direction is important for distinguishing the fabrics.