Takayuki Shiose

A novel adaptive morphological approach for degraded character image segmentation

This work proposes a novel adaptive approach for character segmentation and feature vector extraction from seriously degraded images. An algorithm based on the histogram automatically detects fragments and merges these fragments before segmenting the fragmented characters. A morphological thickening algorithm automatically locates reference lines for separating the overlapped characters. A morphological thinning algorithm and the segmentation cost calculation automatically determine the baseline for segmenting the connected characters. Basically, our approach can detect fragmented, overlapped, or connected character and adaptively apply for one of three algorithms without manual fine-tuning. Seriously degraded images as license plate images taken from real world are used in the experiments to evaluate the robustness, the flexibility and the effectiveness of our approach. The system approach output data as feature vectors keep useful information more accurately to be used as input data in an automatic pattern recognition system.

Foundations for designing an ecological interface for mobile robot teleoperation

Abstract This paper presents foundations needed in designing an interface system for mobile robot teleoperation. For this purpose, Vicente’s idea of ecological interface design (EID) is firstly reviewed, and a preliminary design of our teleoperation system is presented. Our system enables the naturalistic collaboration between a human and a robot’s autonomy at the skill level by joining their respective perception–action cycles via virtually constructed visual 3D space, in which a human naturalistic reflex between stimulus and response is effectively utilized. Following the presentation of an overview of our system, discussions on the interface design for the teleoperation are done concentrating on its ecological aspects.

Morphological preprocessing method to thresholding degraded word images

This paper presents a novel preprocessing method based on mathematical morphology techniques to improve the subsequent thresholding quality of raw degraded word images. The raw degraded word images contain undesirable shapes called critical shadows on the background that cause noise in binary images. This noise constitutes obstacles to posterior segmentation of characters. Direct application of a thresholding method produces inadequate binary versions of these degraded word images. Our preprocessing method called Shadow Location and Lightening (SL*L) adaptively, accurately and without manual fine-tuning of parameters locates these critical shadows on grayscale degraded images using morphological operations, and lightens them before applying eventual thresholding process. In this way, enhanced binary images without unpredictable and inappropriate noise can be provided to subsequent segmentation of characters. Then, adequate binary characters can be segmented and extracted as input data to optical character recognition (OCR) applications saving computational effort and increasing recognition rate. The proposed method is experimentally tested with a set of several raw degraded images extracted from real photos acquired by unsophisticated imaging systems. A qualitative analysis of experimental results led to conclusions that the thresholding result quality was significantly improved with the proposed preprocessing method. Also, a quantitative evaluation using a testing data of 1194 degraded word images showed the essentiality and effectiveness of the proposed preprocessing method to increase segmentation and recognition rates of their characters. Furthermore, an advantage of the proposed method is that Otsus method as a simple and easily implementable global thresholding technique can be sufficient to reducing computational load.

A Study on Acquiring Underlying Behavioral Criteria for Manipulator Motion by Focusing on Learning Efficiency

Conventional humanoid robotic behaviors are directly programmed depending on the programmers personal experience. With this method, the behaviors usually appear unnatural. It is believed that a humanoid robot can acquire new adaptive behaviors from a human, if the robot has the criteria underlying such behaviors. The aim of this paper is to establish a method of acquiring human behavioral criteria. The advantage of acquiring behavioral criteria is that the humanoid robots can then autonomously produce behaviors for similar tasks with the same behavioral criteria but without transforming data obtained from morphologically different humans every time for every task. In this paper, a manipulator robot learns a model behavior, and another robot is created to perform the model behavior instead of being performed by a person. The model robot is presented some behavioral criteria, but the learning manipulator robot does not know them and tries to infer them. In addition, because of the difference between human and robot bodies, the body sizes of the learning robot and the model robot are also made different. The method of obtaining behavioral criteria is realized by comparing the efficiencies with which the learning robot learns the model behaviors. Results from the simulation have demonstrated that the proposed method is effective for obtaining behavioral criteria. The proposed method, the details regarding the simulation, and the results are presented in this paper.

System design of “Ba”-like stages for improvisational acts via Leibnizian space–time and Peirce’s existential graph concepts

A framework for “improvisational” social acts and communication is introduced by referring to the idea of “relationalism” such as natural farming, permaculture and deep ecology. Based on this conception, the notion of Existential Graph by C. S. Peirce is introduced. The notion of extended self in deep ecology is substantiated based on the Roy Adaptation Model in Nursing Theory and Narrative approaches. By focusing on Leibnizian notions of space and time and by introducing Petri net, a spatio-temporal model of improvisation is constructed. This model is expected to substantiate the interesting notion of “Ba” proposed by H. Shimizu reflecting Japanese culture.

The Development of Virtual 3D Acoustic Environment for Training ‘Perception of Crossability’

This study attempted to reveal the role of auditory information in the accurate “perception of crossability” for people with severe visual impairment (‘the blind’). We created a ‘virtual 3D acoustic environment’ in which listeners feel a car passing in front of them to help them cross the street safely. An idea of this acoustic system originated from a previous research that showed that the blind make good use of reflected sounds or reverberations in identifying sources and in specifying distances from objects. The system is useful not only for analyzing critical cues of perception of ‘crossability’ but also for training the blind how to cross a street. Such auditory information can provide the blind with a safe training system for acquiring such auditory information.

Exploiting interaction between sensory morphology and learning

This paper proposes a system that automatically designs the sensory morphology of an autonomous robot. This system uses two kinds of adaptation, ontogenetic adaptation and phylogenetic adaptation, to optimize the sensory morphology of the robot, in ontogenetic adaptation, individuals with many different sensory morphologies use reinforcement learning to adapt to a task. In phylogenetic adaptation, a genetic algorithm is used to select morphologies with which the robot can learn the task fasten We made the system design a line-following robot, and carried out experiments to compare the design solution with a hand-coded design. The results have shown that the designed robot outperforms the hand-coded design in terms of line-following accuracy and learning speed, although it has fewer sensors than hand-coded robots. The paper also shows the effective use of sensory morphology obtained by our system.

Design of Interactive Skill-Transfer Agent From a Viewpoint of Ecological Psychology

This article focuses on the design of an interactive skill-transfer agent for parameter tuning of an image sensor used to distinguish inferior goods from regular goods in a production line. The authors analyze the difficulty of transferring skills from a viewpoint of ecological psychology that takes into account the reciprocal relations between the participant and the environment. This article introduces an agent-based interactive skill-transferring system that stretches the meaning of this reciprocity as an interaction between an instructor and a successor. In concrete terms, an interactive agent system is proposed using an interactive learning classifier system with facial icons to enhance the human users trust in the agent. The experimental results demonstrate the effectiveness of this system in transferring a human experts skills.

Fuzzy Local Currency Based on Social Network Analysis for Promoting Community Businesses

This paper discusses the ability of local currencies (LCs) to exchange goods and/or services by introducing a method to analyze the reciprocity of communities based on fuzzy network analysis. LCs are expected to revitalize social communities that face difficulties due to the attenuation of human relations. Therefore, such currencies have drastically spread all over the world to resolve these difficulties. LCs circulate in particular areas or communities and enhance social capitals. The significance of reciprocity in a community is usually referred to in light of the non-additivity of evaluation measures that reflect the non-additivity of relationships among community members and/or their activities. To analyze such reciprocity, we employ a fuzzy measure based on fuzzy network analysis that provides certain guidelines for the emergence of interpersonal relationalities among community members.

Inclusive design workshop by regional cooperation between an NPO and a university

This is a case of running inclusive design workshops. Communication in an inclusive design workshop is not intercultural collaboration itself. However, as designers, engineers, and users who have individual needs, such as aged and disabled people, gather in the workshop, participants may become aware of differences in individual creation of meanings by communicating with other participants. Because as individuals our imaginative power is sometimes quite insufficient, it is not possible to sufficiently analyze such individual needs without communicating directly. In the inclusive design workshop, participants cooperate with each other during the design process, revealing differences in individual creation of meanings. In this paper, we describe some activities of social-academic cooperation, specifically cases of workshops that were run by an nonprofit organization (NPO) and a laboratory at Kyoto University. The former supports aged and disabled peoples participation in society and the latter researches communication by the system theory.