Kenji Funahashi

User experiences with a virtual swimming interface exhibit

We created an exhibit based on a new locomotion interface for swimming in a virtual reality ocean environment as part of our Swimming Across the Pacific art project. In our exhibit we suspend the swimmer using a hand gliding and leg harness with pulleys and ropes in an 8ft-cubic swimming apparatus. The virtual reality ocean world has sky, sea waves, splashes, ocean floor and an avatar representing the swimmer who wears a tracked head-mounted display so he can watch himself swim. The audience sees the swimmer hanging in the apparatus overlaid on a video projection of his ocean swimming avatar. The avatar mimics the real swimmer’s movements sensed by eight magnetic position trackers attached to the swimmer. Over 500 people tried swimming and thousands watched during two exhibitions. We report our observations of swimmers and audiences engaged in and enjoying the experience leading us to identify design strategies for interactive exhibitions.

Obtaining Shape from Scanning Electron Microscope using Hopfield Neural Network

In the environment of the Scanning Electron Microscope (SEM), it is necessary to establish the technology of recovering the 3D shape of a target object from the observed 2D shading image. SEM has the function to rotate the object stand to some extent. This paper uses this principle and proposes a new method to recover the object shape using two shading images taken during the rotation. The proposed method uses the optimization of the energy function using Hopfield neural network, which is based on the standard regularization theory. It is also important to give the initial vector that is close to the true optimal solution vector. Computer simulation evaluates the essential ability of the proposed method. Further, the real experiments for the SEM images are also demonstrated and discussed.

Obtaining shape from Scanning Electron Microscope using Hopfield neural network

In the environment of the Scanning Electron Microscope (SEM), it is necessary to establish the technology of recovering the 3D shape of a target object from the observed 2D shading image. SEM has the function to rotate the object stand to some extent. This paper uses this principle and proposes a new method to recover the object shape using two shading images taken during the rotation. The proposed method uses the optimization of the energy function using Hopfield neural network, which is based on the standard regularization theory. It is also important to give the initial vector that is close to the true optimal solution vector. Computer simulation evaluates the essential ability of the proposed method. Further, the real experiments for the SEM images are also demonstrated and discussed.

Swimming across the Pacific: a virtual swimming interface

wimming Across the Pacific takes inspiration from the performance art piece Swimming Across the Atlantic. 1 Swimming Across the Atlantic was performed by the artist Alzek Misheff, who accomplished the endeavor by swimming in the pool of the Queen Elizabeth II ocean liner while it traveled from South Hampton to New York. More than 20 years later, we intend to accomplish the next stage of this performance piece by swimming across the Pacific Ocean, from Los Angeles to Tokyo, in an airplane. We have created a virtual swimming apparatus to fit inside a large passenger airplane. In our Swimming Across the Pacific artwork, we create a space for collaborative artwork in the airplane by having a swimmer swim while flying across the Pacific Ocean. The swimmer’s swimming represents a transformation of the airplane into an art gallery where the medium is the airplane, much as Misheff transformed the Queen Elizabeth II while he swam during her journey. By using elements such as the AV system, food, and clothing in the airplane for expression, fellow artists, scientists, engineers, musicians, media, and other passengers participate together to create artwork.

Shape from SEM Image Using Fast Marching Method and Intensity Modification by Neural Network

This chapter proposes a new approach to recover 3-D shape from a Scanning Electron Microscope (SEM) image. When an SEM image is used to recover 3-D shape, one can apply the algorithm based on the solving the Eikonal equation with Fast Marching Method (FMM). However, when the oblique light source image is observed, the correct shape cannot be obtained by the usual one-pass FMM. The approach proposes a method to modify the original SEM image with intensity modification by introducing a Neural Network (NN). Correct 3-D shape could be obtained using FMM and NN learning without iterations. The proposed approach is demonstrated through computer simulation and validate through experiment.

Forecasting Students’ Future Academic Records Using Past Attendance Recording Data and Grade Data☆

Abstract In this study, the authors forecast students’ future academic records using past attendance recording data and grade data. We use a Bayesian network as forecasting method. During construction of the Bayesian network forecasting model, unnecessary variables become noise and so lower the forecasting accuracy. Therefore, to improve the forecasting accuracy, we used information gain to reduce the number of variables in the model. As a result, accuracy improved.

Virtual liquid manipulation using general shape vessel

Describes a method to realize the interactive manipulation of a virtual liquid using virtual vessels which are expressed by a general convex-shape polyhedron. We propose a liquid manipulation model which has some functions to treat the relation between the volume of liquid in a vessel and the height level of the liquid surface in it while it is being tilted. For a general-shape vessel, a lookup table is implemented to calculate the above functions. Our system with this proposed model makes it possible to catch the liquid using the virtual vessel, to hold the liquid in it, then to spill the liquid by tilting it. Also, the system realizes a manipulation method to skim the liquid from another liquid vessel.

A Robust Method for Blood Vessel Extraction in Endoscopic Images with SVM-based Scene Classification.

This paper proposes a model for blood vessel detection in endoscopic images. A novel SVM-based scene classification of endoscopic images is used. This SVM-based model classifies images into four classes on the basis of dye content and blood vessel presence in the scene, using various colour, edge and texture based features. After classification, a vessel extraction method is proposed which is based on the Frangi vesselness approach. In original Frangi Vesselness results, it is observed that many non-blood vessel edges are inaccurately detected as blood vessels. So, two additions are proposed, background subtraction and a novel dissimilarity-detecting filtering procedure, which are able to discriminate between blood vessel and non-blood vessel edges by exploiting the symmetric nature property of blood vessels. It was found that the proposed approach gave better accuracy of blood vessel extraction when compared with the vanilla Frangi Vesselness approach and BCOSFIRE filter, another state-of-art vessel delineation approach.

Getting yourself superimposed on a presentation screen

When attending a conference some audiences lose attention following points on the screen. Although presenters usually use a pointer rod or a laser pointer, they are not convenient or easily visible on a large screen. A camera and another screen are also needed to show gestures. In this paper we propose using intuitive interface presentation support software. A presenter is superimposed onto a screen, and the person can draw there interactively. Realizing presenter movement on screen by recognizing natural and small actions, the person can move within a limited stage space. Presenters can point to any important areas and draw supplementary items with their own hand through our software, and of course show gestures on a large screen. It is expected that audiences will be better able to understand and focus.

Neural Network Based Image Modification for Shape from Observed SEM Images

A new approach to recover 3-D shape from a Scanning Electron Microscope (SEM) image is described. With an ideal SEM image, 3-D shape can be recovered using the Fast Marching Method (FMM) applied to the Eikonal equation. However, when the light source direction is oblique, the correct shape cannot be obtained by the usual one-pass FMM. The new approach modifies the intensities in the original SEM image using an additional SEM image of a sphere and Neural Network (NN) training. Image modification is a two degree-of-freedom (DOF) rotation. No assumption is made about the specific functional form for intensity in an SEM image. The correct 3-D shape can be obtained using the FMM and NN learning, without iteration. The approach is demonstrated through computer simulation and validated through real experiment.