Atsuko Koizumi

A Vision-Based Method for Recognizing Non-manual Information in Japanese Sign Language

This paper describes a vision-based method for recognizing the nonmanual information in Japanese Sign Language (JSL). This new modality information provides grammatical constraints useful for JSL word segmentation and interpretation. Our attention is focused on head motion, the most dominant non-manual information in JSL. We designed an interactive color-modeling scheme for robust face detection. Two video cameras are vertically arranged to take the frontal and profile image of the JSL user, and head motions are classified into eleven patterns. Moment-based feature and statistical motion feature are adopted to represent these motion patterns. Classification of the motion features is performed with linear discrimant analysis method. Initial experimental results show that the method has good recognition rate and can be realized in real-time.

Vision sharing for new service development

The integration of technologies and customer value is a key issue for technology-based companies to achieve service innovation. We are developing a methodology for service concept creation focusing on customer value exploration to address this issue. Our primary goal is to deploy our methodology (process, methods, tools, and examples) to business planning sites in our company. By taking an action research approach consisting of four steps, observation (involved in pilot projects), conceptualization, modeling, and deployment, we have clarified the basic concept of our methodology and designed a process for service concept creation: (1) sharing a vision of new services, (2) exploring customer value, and (3) creating a service concept consisting of target users (Who), customer value (What), and key technologies (How). In this paper, we discuss the issues to solve in the early stage of developing new services and illustrate our vision sharing workshop, which is characterized by the following: (1) an interaction technique for empathetic understanding through storytelling and active listening, (2) a visualization technique for sharing clarified vision, (3) a feedback technique for deep understanding. By applying the workshop to our pilot projects, we demonstrated its feasibility and effectiveness.

Development of Methodology for Service Concept Creation

We are developing a methodology for service concept creation. Taking an approach consisting of four steps; observation (involvement in pilot projects), conceptualization, modeling, and deployment, we have clarified the basic concept of our methodology and designed a process for service concept creation. The process includes (1) sharing a vision of new services, (2) exploring customer values, and (3) creating a service concept consisting of target users (WHO), customer values (WHAT), and key technologies (HOW). In this paper we illustrate this process and propose methods designed to be used in the process by focusing on effective use of observation, story telling, and analogies for abductive reasoning in the step of searching for customer values.