U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process.

Colored product textures correspond to particle size distributions. The microscopic images of colorants must be divided into regions to determine the particle size distribution. The conventional method used for this process involves manually dividing images into areas, which may be inefficient. In this paper, we have overcome this issue by developing two different modified architectures of U-Net convolution neural networks to automatically determine the particle sizes. To develop these modified architectures, a significant amount of ground truth data must be prepared to train the U-Net, which is difficult for big data as the labeling is performed manually. Therefore, we also aim to reduce this process by using incomplete labeling data. The first objective of this study is to determine the accuracy of our modified U-Net architectures for this type of image. The second objective is to reduce the difficulty of preparing the ground truth data by testing the accuracy of training on incomplete labeling data. The results indicate that efficient segmentation can be realized using our modified U-Net architectures, and the generation of ground truth data can be simplified. This paper presents a preliminary study to improve the efficiency of determining particle size distributions with incomplete labeling data.

Bismuth electrochromic device with high paper-like quality and high performances.

An electrochromic-type electronic paper was prepared using nanocomposites that consisted of silica nanoparticles (silica 60 wt %) and polyamide pulp. Its light scattering, ion transport, and aqueous electrolyte retention characteristics were examined. As a result, the shape of the nanocomposites was completely self-standing, though it could be impregnated with about nine times as much water on a weight basis. Moreover, its light scattering property was extremely similar to paper. Because of the impregnation of a large amount of water, the ion transport property of the nanocomposites was the same as that of the electrolyte solution without the nanocomposites. The nanocomposites was impregnated using an aqueous solution in which bismuthyl perchlorate (redox species), copper perchlorate, perchloric acid, sodium perchlorate, hydroquinone (electron mediator) and 2-buthyne-1,4-diol (leveling agent) were dissolved. The electronic paper was then prepared by sandwiching the nanocomposites between an indium-tin-oxide transparent electrode and a copper sheet. This electronic paper utilizes the reversible codeposition reaction of black Bi-Cu from bismuthyl perchlorate and copper(II) ions. The characteristics of this electronic paper were examined, and excellent characteristics with a white reflectivity of 65%, black reflectivity of 6.4%, contrast ratio of 10:1, operating life of over 1 x 10(6) cycles and open-circuit memory of at least 1 month were obtained. In addition, its driving voltage was 1.2 V, and the write time was 500 ms.