Abstract Modeling 3D origami pieces using conventional software is laborious due to the geometric constraints imposed by the complicated layered structure. Targeting origami models used in visual content such as CG illustrations and movies, we propose an interactive system that dramatically simplifies the modeling of 3D origami pieces with plausible outer shapes, while omitting accurate inner structures. By focusing on flat origami models with a front‐and‐back symmetry commonly found in traditional artworks, our system realizes easy and quick modeling via single‐view interface; given a reference image of the target origami piece, the user draws polygons of planar faces onto the image, and assigns annotations indicating the types of folding operations. Our system automatically rectifies the manually‐specified polygons, infers the folded structures that should yield the user‐specified polygons with reference to the depth order of layered polygons, and generates a plausible 3D model while accounting for gaps between layers. Our system is versatile enough for modeling pseudo‐origami models that are not realizable by folding a single sheet of paper. Our user study demonstrates that even novice users without the specialized knowledge and experience on origami and 3D modeling can create plausible origami models quickly.

Advanced robotic assistance in microsurgery, such as automation, requires an accurate estimation of the state of the robotic forceps. In this paper, we propose a robust and accurate forceps tracking method to estimate the full state of the forceps (i.e., the position, posture, and grip parameters) using visual information obtained from stereo microscopic images and kinematic information obtained from the robotic sensory information, forward kinematics, and hand-eye coordination. An online method for updating the hand-eye coordination was also developed using an extended Kalman filter to cancel the hand-eye coordination errors caused by the repositioning of the microscope. The experimental results showed that the proposed method could accurately and robustly estimate the state of the robotic forceps even after the repositioning of the microscope.

Forceps tracking is an important element of high-level surgical assistance such as visual servoing and surgical motion analysis. In many computer vision algorithms, artificial markers are used to enable robust tracking; however, markerless tracking methods are more appropriate in surgical applications due to their sterilizability. This paper describes a robust, efficient tracking algorithm capable of estimating the full state parameters of a robotic surgical instrument on the basis of projective contour modeling using a 3-D CAD model of the forceps. Thus, the proposed method does not require any artificial markers. The likelihood of the contour model was measured using edge distance transformation to evaluate the similarity of the projected CAD model to the microscopic image, followed by particle filtering to estimate the full state of the forceps. Experimental results in simulated surgical environments indicate that the proposed method is robust and time-efficient, and fulfills real-time processing requirements.

This paper describes a novel approach to duration information modeling for speech recognition. To eliminate the influence of speaking rate on the duration model, we propose a model utilizing the duration ratios of two successive syllables by log-normal distributions. We refer to this model as a syllable duration ratio model (SDRM), and compare it with a syllable duration model (SDM) that represents the duration of the syllable itself. These duration models are compared in isolated word and connected digit recognition tasks under noisy conditions. Experimental results show that the SDRM outperformed the SDM, and reduced the errors by approximately 30% compared to the baseline system without duration model at 15dB or higher SNR in 10 digits recognition tasks. In addition, we show that the SDRM is robust with respect to the difference in speaking rate between training and test data.