In a single photograph of fabric, it is difficult to observe the fine texture and material properties of the fabric. We propose to reveal the detail texture of fabric by using a sequence of photographs captured by changing the direction of light source. One problem encountered in implementing such approach is how to remove the shadows of the photographic equipment cast on the sequence of fabric images. In this paper, we propose a method to remove shadows on the images by applying Robust PCA to the image sequence with only diffuse reflection components. We compare original images with dimensionally reduced images and verify the effectiveness of our method.
In this paper, we propose a method to represent an overexposed area in an image by using an infrared image. In order to estimate an object shape in the overexposed area, thermal information in the infrared image is used. The infrared image is divided into some areas according to the thermal information, and the edge is detected in each region. Then, the image in the overexposed area becomes clear by adding the detected edges on the image. As the result of the comparison between the proposed method and a previous method, we have confirmed that the method can represent the overexposed area clearly without using multiple images.
We have proposed an artificial fiber pattern as a technique for embedding electrical information into fabric materials. In recent studies, we attempted to use a fiber pattern for embedding information into fabric materials without visual disturbance. In this paper, we examined different colors (cyan, magenta, and yellow) instead of the grayscale, and a specific pattern (a traditional Japanese katagami pattern for a kimono (i.e., Ise-katagami)) instead of a fiber pattern in order to adapting a variety of situations.
The invention of Jacquard loom in the early 19th century made a great influence for the birth of information science, and the image processing technology contributes to the development of jacquard textile in recent years. Since design process of jacquard weaving basically consists of editing binary data; over-under relationship of warp and weft yarns, image processing technology has a validity for upgrading them. This article describes an overview of the history of textile and information technology with examples of the study extending over both fields, and the possibility of image processing for future textile production and design.
250 million people in the world are suffering from Color Vision Deficiency(CVD). CVD causes troubles for job selection and communication in daily life. Most cases of CVD are caused by genetics, and currently no effective treatment has been established. In this study, we propose to support CVD people with See-Through Head-Mounted Display(OST-HMD). The images captured by an outward camera installed on the OST-HMD are processed to generate images for compensating the formation loss caused by CVD. CVD users can achieve better discrimination over scenes by superimposing the displayed compensation images over the real world scenes. In this paper, we introduce the implementation results using daltonization method for generating compensation images and discuss about the future challenges of the project.
Multispectral images (MSIs) enable more accurate color reproduction than RGB images. However, an MSI is difficult to transmit, display and store in the conventional RGB imaging systems because an MSI is not compatible with the conventional imaging system. We propose a method of embedding the spectral data into wavelet transform coefficients of chrominance channel. The watermarked RGB image obtained by this method can be utilized in the conventional RGB imaging system. Even if the watermarked image is compressed with a lossy compression method, the proposed method can reconstruct not only the visible components but also invisible components because our method uses robust watermarking.
Raccoons, that are alien species in Japan, are increasing significantly and recently cause serious damage to farm products and historical buildings. Our objective is to contribute the analysis of the behavior and distribution of raccoons and the prompt and effective reaction by developing more intelligent surveillance cameras. This manuscript reports trials of automated vermin detection for embedded systems including surveillance cameras. Following popular methods of image recognition, we adopt HOG (histograms of oriented gradients) as feature extraction scheme and SVM (support vector machine) or NN (Neural Network) as categorization scheme. We also adopt a variation of deep learning designated as CNN (convolutional neural network). We implement the image recognition methods of HOG+SVM, HOG+NN, and CNN as a software programs running on a PC and evaluated with training and test images of raccoons and raccoon dogs taken in a zoo. The experiment results in the recognition rates of 89.8%, 88.5%, and 94.5%, respectively, and the execution time of 111ms, 0.681ms, and 11.9ms, respectively.
Recently, a building made of a concrete are deteriorating. Therefore, maintenance and management of building made of the concrete is important. As a method of maintenance and management, there is the method to accurately detect cracks on the concrete. However, it is difficult to detect accurate the cracks, because it is based on the experience of a specialist. Therefore, in this paper, we are developing a system that anyone can easily perform inspect. Specifically, we propose the system that measures the crack width by processing the image got from the smartphone.
Individual opinion and living culture have not only been influenced by such image information as advertising papers and signboards but also recent advertisements through TV, Web and digital signage. Effectiveness of the image information above has been anlyzed by human information history, computer media history, language acquisition, and Maslow’s theory. Then image information effectiveness for cultural propagation has been discussed through the images of the Bible in the West, and figures of Confucianism filial piety in the East.