One of the major purposes of artificial intelligence and intellectual processing by a computer (machine) is an agency of the human function. As a result, the accuracy can be improved compared to the work done by human kind, and the processing time is expected to be shortened. Therefore, such technology has been applied in various fields. On the other hand, a lot of attempts to engineering investigated, simulated and application of human sensibility have been studied. Man and machine, should work together in responsible for the parts being good at in each. Therefore, the machine is expected to support the human ability for taking its full advantage. In addition, the machine is expected to have the effect of the stimulus even for unknown functions such as human sensibility and subjective functions, known as Kansei. In this paper, an attempt to support the intelligent processing ability possessed by human beings is picked up and studied. At first, we generally consider the stage of cognitive promotion in the visual world. Then, we will introduce Consecutive Fuzzy Reasoning with Preconception as a simulated example of recognition of the moving image. We also introduce the emotional contour extraction of graphic by inference as an application example of the sensibility in image processing. Moreover, we will introduce the emotional image classification as an example of the promotion of awareness by stimulating the human intellectual processing. Finally, we refer to the future prospects of these technologies.
Oracle bone inscriptions (OBIs) are one of the oldest characters which were inscribed on the bone of cattle or turtle shells in the period of Shang. Recognizing the OBI is important for understanding the origin of characters, history research, etc. However, aged caused OBI to be less legible. The OBI was inscribed by the sharp objects. Hence, the structure of OBI is simple and constructed mainly by lines. Our approach extracts the line features by Hough transform, and recognizes the OBI from templates. First, line candidates are estimated using voting scheme of the Hough transform. Second, the lines and the number of the lines are estimated by clustering neighbor of line candidates. The recognition of OBI is performed by minimizing the distance between the corresponding points on the Hough space of the target and template images. The experimental results show that about 87% OBIs are recognized in 7 kinds, 52 pieces of OBIs with 11 kinds of templates.
The automatic color feature extraction is one of the most important issues in a variety of research fields，such as image recognition，image analysis，color harmony，and so on．In this paper，we propose a method to extract a few dominant colors from images by using basic color categories，which are known as perceptual color categories of human．For that，we first extracted a number of dominant color candidates by image clustering．Next，we removed candidate colors which have low saturation or form small area in the image space．Finally，we merged perceptually similar candidate colors using the basic color categories．In this way，we can get the final dominant colors．We have compared our results with those of previous methods，and confirmed the validity of our method．
To create a DEM using satellite images, correspondence detection in a stereo pair is regained. For defining a stereo pair, two or more in-track images captured within short period are used in most cases. To use images from different orbits for a stereo pair, parallax, time difference, and environment should be considered. In this paper, we propose a selection method of stereo pairs for creating a precise DEM, in using parallax, time difference and similarity between satellite images. And our method selects stereo pairs for every point for calculating height. We evaluate our method using ALOS/PRISM images. The result shows that the DEM provided by our method using different track images has almost same precision in comparison with the computed one using in-track images.
Metamerism is a phenomenon where two objects recognized as having different colors under one light are also recognized as having the same color under another light. This short paper proposes a method that automatically calculates the blending ratios of oil paints satisfying the condition to occur metamerism under the specific light sources for actualizing artistic illusion. It entails metamerism occurring between four types of object colors under two types of light sources. This enables us to create false shading where the observer recognizes the 2D oil painting as if it is a 3D object with plausible shading.
For image recognition and understanding, it is one of the fundamental problems to binarize the gray-scaled image and divide the image into a target and a background. The threshold-based method is now used commonly in the image binarization. However, this method depends on the statistical condition of the image. There is a method to analyze geometrically in one of the methods not to depend on a statistical condition. We can consider the image to be a curved surface when the brightness of a pixel(x, y) is height. The surface generates a flow field based on the its gradient because of the differential geometric property. Therefore, in this article, we define the slope lines that describe the structures of surface very well. These lines emanate from the same maximum, and reach the same minimum. We call this lines dipole flow. We show that a set of the inflection point is classified based on its morphology. And we introduce a binarization method based on this classification.
This short paper proposes a non-photo realistic rendering method which generates images imitating the striped patterns that appear when natural rock like Malachite or Laguna Agate is cut. The proposed method generates stone-striped images by using bilateral minimum filter and bilateral maximum filter iteratively. In order to validate the effectiveness of the proposed method, the attractiveness of the images generated from several gray-scale images by the proposed method was evaluated visually. As a result of the experiments, we showed that the images generated by the proposed method are quite similar to the striped patterns that appear when natural rock is cut.
The non-photorealistic rendering method for generating islamic-pattern-like images from input color images by using weight-shifted color bilateral filter has been proposed. However, islamic pattern generated by the conventional method was constant in the size and interval. Therefor, we propose a method for generating islamic-pattern-like images that partially change the size and interval of islamic pattern by using quadtree segmentation. To validate the effectiveness of the proposed method, we conduct comparative experiments with the conventional method by using a questionnaire survey. As a result of the experiments, we showed that the proposed method can generate islamic-pattern-like images that looks impressive and beautiful than the conventional method.
This paper addresses a skill standard for standardization experts. The skill standard specifies the 36 tasks required for standardization and defines the skills required for those tasks. Categorization of the tasks is based on task phase and standard type. To evaluate the skills, we introduce skill evaluation criteria on performance (experience and achievement on carrying out a task) and capability (capability and knowledge required for the task). Skills and skill levels are specified in a skill card corresponding to a task. A skill card includes a set of data for the items of skill evaluation criteria on performance and capability. Then, the paper discusses the existing status of the skill standard and its extensions to an international standard.
International standards play very important roles not only in ensuring performance, compatibility and quality of products and services, but also in making business size bigger. In this paper, research results on collection and analysis of courses and programs about global standardization education in universities are described. As a result, 3 programs and 45 courses and of the education of global standardization were collected through crawling 132 Japanese universities. It is shown that two programs are offered as a master‘s degree program and one is offered as certificate program. Also, it is shown that 45 courses are offered in Japanese universities. It is concluded that the purposes, contents and offering methods of the education differ among universities.
In this paper, through my international standardization activities, some suggestions how to build a bridge between R&D and Standardizations and to make effective use of international standardization organizations are provided. I have been serving to ITU and IEC as four kinds of International Standardization experts / management members. In ITU, I was delegated to its Working Parties (WPs) by the Member State of Japan at first, then become a ITU-R WP 6M (interactivity and multimedia broadcasting) Vice Chairman. In IEC, I was the Secretary of Technical Committee 100 (TC 100: audio, video and multimedia systems and equipment) Secretary and finally to be the IEC Standardization Management Board (SMB) member representing Japanese National Committee. According to my experience, each stage assigns me its management powers and specific duties. How to use these functions are what I would like to provide in this paper, i.e., how to bring your R&D outputs to International Standardization activities.
Wireless cloud service is now inevitable and widely implemented to the global use. Increasing traffic demands of the smart phone and the tablet PC is the big problems due to the radio spectrum resource limitation. Key issues to be solved in near future are the bottleneck and the throughput improvement of the wireless cloud network. Video streaming service is included in the cloud service, and their information traffic volume has most important influence on the topics. In this paper, it is proposed that the Bigdata-based Social Level Agent (SoLA), which can effectively and seamlessly offload the video streaming traffic to the microcell networks to enhance the spectrum utilization efficiency. The system is also the one of the important items of the global standardization issues. The objectives, the configurations and functional operations, and the related standardization bodies and standards are investigated. And also the strategy of the proposed system standardization is mentioned..