MRF-based texture segmentation using wavelet decomposed images

In recent textured image segmentation, Bayesian approaches capitalizing on computational efficiency of multiresolution representations have received much attention. Most of the previous researches have been based on multiresolution stochastic models which use the Gaussian pyramid image decomposition. In this paper, motivated by nonredundant directional selectivity and highly discriminative nature of the wavelet representation, we present an unsupervised textured image segmentation algorithm based on a multiscale stochastic modeling over the wavelet decomposition of image. The model, using doubly stochastic Markov random fields, captures intrascale statistical dependencies over the wavelet decomposed image and intrascale and interscale dependencies over the corresponding multiresolution region image.     

Fault tolerant approach for biosignal-based robot control

This paper proposes a fault tolerant framework for biosignal-based robot control with multiple sensor electrodes. In this approach, to cope with sensor faults, a reliable joint torque estimation model is selected from a group of estimation models based on sensor failure classifiers. The correlation among the electromyography (EMG) signal streams is used as input feature vectors for fault detection. To validate our proposed method, we artificially disconnect an EMG electrode or detach one side of an EMG probe from the skin surface during elbow-joint torque estimation experiments with five participants. When one EMG sensor electrode experiences one of the problems, the experimental results show that the joint torque can be estimated with significantly fewer errors using our proposed approach than a joint torque estimation method without sensor fault detection or than a method with a conventional sensor fault detection algorithm. Furthermore, we controlled a mannequin-arm-attached one-DOF exoskeleton based on the estimated torque profiles by generating movements with the estimated torque derived from the selected model.     

Curvature continuous path generation for autonomous vehicle using B-spline curves

In this paper we introduce a roadmap algorithm for generating collision-free paths in terms of cubic B-spline curves for unmanned vehicles used in mining operations. The algorithm automatically generates collision-free paths that are curvature continuous with an upper bounded curvature and a small slope discontinuity of curvature at knots, when we are given the locations of the obstacles, the boundary geometry of the working area, positions and directions of the vehicle at the start, loading, and the goal points. Our algorithm also allows us to find a switch back point where the vehicle reverses its direction to enter the loading area. Examples are provided to demonstrate the effectiveness of the proposed algorithms.     

Cylindrical coils created with 3D X-ray lithography and metallization

The demand for microactuators is increasing recently. The key technology to realizing practical microactuators is microfabrication process. In the production of microminiature components, the technologies for processing high-aspect-ratio structures are essential. As one of these technologies, the LIGA process is widely known. Our laboratory researches the LIGA process to three-dimensional microfabrication and established the cylindrical-microcoil production process. In this paper, we have fabricated the cylindrical-microcoil for the solenoidal electromagnetic type microactuator. We designed and analyzed microactuators, and fabricated and evaluated microactuator coils produced by the combination of three-dimensional X-ray lithography and level copper plating. We succeeded in creating threaded groove-shaped structures with 10 μm line width, 20 μm pitch, and aspect ratio of 5 on the surface of an acrylic pipe by means of three-dimensional X-ray lithography. As a measure to suppress void generation, which is one of the shortcomings of electrolytic plating processes, the sputtering apparatus and plating equipment were improved, a pretreatment process was additionally provided, and the actual electrolytic plating method was improved. As a result, a void-free metallic deposit could be formed on a thin coil line. The processing technology enables the formation of thin-wire coil lines whose current paths feature a large allowable current-carrying capacity, enabling the production of miniature, high-output microactuators.     

Fabrication of X-rays mask with carbon membrane for diffraction gratings

We have produced diffraction gratings for obtaining high resolution X-ray phase imaging, such as X-ray Talbot interferometer. These diffraction gratings were required to have a fine, high accuracy, high aspect ratio structure. Therefore, we decided to use the X-rays lithography technique that used synchrotron radiation of the directivity for a manufacture process. The accuracy of the completed structure depends largely on the accuracy of the X-ray mask. In our group, a resin material is conventionally used for the membrane of large X-ray masks. However, X-ray masks comprising a resin membrane have the disadvantage that, after several cycles of X-ray exposure, they crease and sag due to X-ray-derived heat. As a substitute for the conventional resin membrane, we experimentally fabricated a new X-ray mask using a carbon wafer membrane. The newly fabricated X-ray mask was subjected to X-ray exposure experiment. We succeeded in making the structure body which was almost shape. And the experimental results verified that the new mask did not deteriorate even when used repeatedly, demonstrating that it was highly durable.     

Speech recognition in living rooms: Integrated speech enhancement and recognition system based on spatial,spectral and temporal modeling of sounds

Research on noise robust speech recognition has mainly focused on dealing with relatively stationary noise that may differ from the noise conditions in most living environments. In this paper, we introduce a recognition system that can recognize speech in the presence of multiple rapidly time-varying noise sources as found in a typical family living room. To deal with such severe noise conditions, our recognition system exploits all available information about speech and noise; that is spatial (directional), spectral and temporal information. This is realized with a model-based speech enhancement pre-processor, which consists of two complementary elements, a multi-channel speech–noise separation method that exploits spatial and spectral information, followed by a single channel enhancement algorithm that uses the long-term temporal characteristics of speech obtained from clean speech examples. Moreover, to compensate for any mismatch that may remain between the enhanced speech and the acoustic model, our system employs an adaptation technique that combines conventional maximum likelihood linear regression with the dynamic adaptive compensation of the variance of the Gaussians of the acoustic model. Our proposed system approaches human performance levels by greatly improving the audible quality of speech and substantially improving the keyword recognition accuracy.     

Self-organizing maps with asymmetric neighborhood function

The self-organizing map (SOM) is an unsupervised learning method as well as a type of nonlinear principal component analysis that forms a topologically ordered mapping from the high-dimensional data space to a low-dimensional representation space. It has recently found wide applications in such areas as visualization, classification, and mining of various data. However, when the data sets to be processed are very large, a copious amount of time is often required to train the map, which seems to restrict the range of putative applications. One of the major culprits for this slow ordering time is that a kind of topological defect (e.g., a kink in one dimension or a twist in two dimensions) gets created in the map during training. Once such a defect appears in the map during training, the ordered map cannot be obtained until the defect is eliminated, for which the number of iterations required is typically several times larger than in the absence of the defect. In order to overcome this weakness, we propose that an asymmetric neighborhood function be used for the SOM algorithm. Compared with the commonly used symmetric neighborhood function, we found that an asymmetric neighborhood function accelerates the ordering process of the SOM algorithm, though this asymmetry tends to distort the generated ordered map. We demonstrate that the distortion of the map can be suppressed by improving the asymmetric neighborhood function SOM algorithm. The number of learning steps required for perfect ordering in the case of the one-dimensional SOM is numerically shown to be reduced from O(N(3)) to O(N(2)) with an asymmetric neighborhood function, even when the improved algorithm is used to get the final map without distortion.