There have been some methods about applying coloration of painterly art to a photographic image. Most of the proposed method use some absolute criteria, e.g., by a certain mathematical formulas, for example the nearest distance in CIE L*a*b* color space, to convert a color to another uniquely. However, we want to develop a method that can convert color depending on the feelings and sensitivities of users themselves, like a painter makes a picture in the real world. Our algorithm can produce a color-transformed image resulting from two input images, which are a target photograph and a reference painting. Our method based. on interactive evolutionary computation (IEC) and can produce a variety of color-transformed images. The user interactively selects some candidates from those varieties to get the final result which looks similar to reference paintings. In this paper we exploit image-region matching for color transfer. Our experiments illustrate some color-transferred images and searching efficiency for our algorithm.

View full abstract

Applications of Kansei Engineering method can be found in many different companies, countries and cultures. Although new applications are increasingly being discovered, the relation of their core activities to Kansei Engineering can be readily identified. In this paper, a basic procedure is proposed which visualizes the way semantic descriptions are linked to product properties. From this model, a number of improvements can be derived, such as the need for a proper definition of the relative importance of product properties and the proximity of interaction. The aim of this paper is to propose a conceptual model for spanning the space of product properties, and to describe its testing in an application study. The space of product properties was spanned in three different steps. The first step was to collect potential properties from existing products, new product concepts and company image variables, followed by the second and third steps, selection and compilation. The application study, conducted on laminate flooring, revealed that laminate floors could be semantically described by four factors: reliable and practical, modern design, classic style, and finally nice and solid. From a physical perspective, eight different properties were chosen for evaluation according to the proposed model. It could be seen that the four previously mentioned factors were related to the properties. Moreover, it became clear that the two groups rating their impressions, craftsmen and architects, had different opinions. From this study, it was concluded that the proposed procedure and conceptual model for the space of product properties was useful when performing applications.

View full abstract

The main purpose of this research is to construct a learning environment utilizing 3-dimensional simulating contents based on the experience of which subjects are aquatic animals and their inhabiting environments in an aquarium. On producing the simulating model of a fish tank, the goal was set to provide a prepared environment that allows users to be involved independently in through their experience. This simulating model provides two kinds of points of view. One is “Outside view”and the other is “Diving view.”It is expected for users to recognize simulated experiences as learned one through the intuitive operation of interfaces provided to switch two points of view. After preparing 3-dimensional simulating content, the examination was held to confirm two points of view; one is the way of retrieval and the other is the way of providing information on each fish. Providing the points of view on the simulating contents that cannot be realized with the living fish in the actual ocean, users can realize a kind of experience through “discovery”and “awareness”with intuitive operation and action. In other words, simulating 3D environment can lead users to be involved in a self-directed learning through the comparison and trial.

View full abstract

The artifact is a complex element. Besides its elementary dimensions (material, functional and formal), the artifact is composed of much more dimensions: ergonomic, emotional, cultural, and even ethologic or theological. To take into account this great quantity and diversity of dimensions, the designer's work has to be widened out. Necessarily, this goes through ani nterdisciplinary approach, i.e. through an interdisciplinary workgroup activity. Nevertheless, this brings issues, notably concerning knowledge communication and sharing. For each variety of knowledge (tacit, prescriptive and descriptive), interdisciplinary activity provokes issues either because of disciplinary ontology differences, or because of human subjective understanding differences.I ntuition is a mental process which is able to minimize these issue effects. We then propose a methodology based on intuition, structured on the theory of Ba, on the SECI Model, which an evoked metaphor (EM) is added to. Through the EM, each member of the workgroup is able to participate to every steps of the design process and to communicate with other members, thanks to ani ntuitive understanding permanently validated by involved disciplines. This creates an efficient interdisciplinary dynamics and the realization of fully interdisciplinary projects. To illustrate this methodology, the design of MATiK is introduced as an example. MATiK is an original workgroup communication system based on a Kansei information approach. In order to understand the expected functionalities of MATiK and to design it, the EM is set up. Considering basic aspects of an extensive workgroup operative process, the Loft is defined as an EM. The Loft offers an opportunity to understand MATiK's original functionalities, MATiK'sd esign, and MATiK's functional and technical requirements intuitively. This methodology, based on the EM, asserts its relevancy for interdisciplinary design. Its strength comes from the fact that the EM links all the levels of the design process (the idea/concept level, the reality level, and the technical level) and makes their understanding accessible to all members thanks to intuition.

View full abstract

The acquisition of effective decision rules between design elements of products and human evaluations is significant, but difficult especially in the cases where we have to handle linearly inseparable and much ambiguous data. We have proposed the rough set method to handle these cases. In this paper, we also propose the utilization of gain chart that can visualize a relation between the effects of product attributes on decision and the number of evaluation events. Using the gain chart, we can set up a suitable parameter corresponding with gain property of each evaluation word. We show an application of our proposed rough set method to the extraction of decision rules between coffee flavor evaluations, i.e., taste and aroma, and the pattern of coffee manufacturing conditions. The results showed that our rough set method enabled more effectively to extract the combination rules of manufacturing conditions from much ambiguous data like sense and feeling. We also found out that it is easy to obtain more general rules by β-upper approximation as well as β-lower approximation.

View full abstract

This paper focuses on comparison of approximation methods in rough set method. It has been shown that rough set approach is more effective in extracting the design decision rules between human evaluation and product attributes. Since kansei evaluations to products include the ambiguity of decisions, we have proposed probabilistic rough set model based on upper approximation. In this paper, we propose β-method using dual β-lower and upper approximations to extract effective decision rules for kansei design of products. We compared the effectiveness of β-method with m-method as a lower approximation often used in Kansei Engineering applications and with 0.5-method as upper approximation in terms of the certainty, coverage and Michalski Q_M measures of decision rule through a practical application to the extraction of design decision rules for children shoes, so called toddler, Generally, the result showed that β-method using dual β-lower and upper approximations is more effective in extracting ‘interesting’ decision rules for product design as well as general ones compared with the other approximations.

View full abstract

The operability of a product, as evaluated from a user's viewpoint is useful in aiding manufacturers in product. Moreover, it is important to carry out good design and impression of a product in an operation part. In this study, we developed the product evaluation system for manufacturing. It was possible to evaluate exactly ‘intelligible operating method’ and ‘the exact operation of convenience’ by an amateur using behavior analysis about operability evaluation. In this study, we developed the evaluation system for operability according to behavior analysis, which requires three factors such as a simplicity, a precision, and an application field etc. As a result, it was possible to identify the foundation of the evaluation method, which includes simple behavior analysis, classifying of evaluators, regardless of finding improvement of simple nature and evaluation accuracy when in use compared with the conventional video appraisal method.

View full abstract