Gosuke Ohashi

Exploiting Depth Discontinuities for Vision-Based Fingerspelling Recognition

We present a novel method for automatic fingerspelling recognition which is able to discriminate complex hand configurations with high amounts of finger occlusions. Such a scenario, while common in most fingerspelling alphabets, presents a challenge for vision methods due to the low intensity variation along important shape edges in the hand image. Our approach is based on a simple and cheap modification of the capture setup: a multi-flash camera is used with flashes strategically positioned to cast shadows along depth discontinuities in the scene, allowing efficient and accurate hand shape extraction. We then use a shift and scale invariant shape descriptor for fingerspelling recognition, demonstrating great improvement over methods that rely on features acquired by traditional edge detection and segmentation algorithms.

Development of a camera system for the acquisition of high-fidelity colors

A set of three optical filters was designed and a camera system was developed using these filters in order to capture high-fidelity colors within the gamut of vision. Photographs of a number of highly saturated colors and a combination of the Macbeth chart and 18 pieces of clothing samples of various colors were taken. A 3 x 9 matrix was used to convert the camera output signals into XYZ tristimulus data. The tristimulus values of the colors were compared with those of the images captured by the camera. The average color difference, ΔE, for these samples were found to be 2.16 and 1.18, respectively.

Vehicles detection based on extremas in nighttime driving scene

The purpose of this study is to identify vehicles by detecting lights based on extremas in nighttime. This method has focused on headlights of vehicle that are high brightness and taillights of vehicle that are red in nighttime. Headlights are detected by grayscale images, and taillights are detected by red extracted images. In fact, The usefulness of this method is confirmed by using in-vehicle camera images.

Vision-Based Nighttime Vehicle Detection Using CenSurE and SVM

In this paper, we propose a method for detecting vehicles from a nighttime driving scene taken by an in-vehicle monocular camera. Since it is difficult to recognize the shape of the vehicles during nighttime, vehicle detection is based on the headlights and the taillights, which are bright areas of pixels called blobs. Many research studies using automatic multilevel thresholding are being conducted, but these methods are prone to get affected by the ambient light because it uses the luminance of the whole image to derive the thresholds. Owing to such reasons, we focused on the Laplacian of Gaussian operator, which derives the response of luminance difference between the blob and its surroundings. Compared with automatic multilevel thresholding, Laplacian of Gaussian operator is more robust to the ambient light. However, the computational cost to derive the response of this operator is large. Therefore, we used a method called Center Surround Extremas to detect the blobs in high speed. Since the detected blobs include nuisance lights, we had to determine whether the blob is a light of a vehicle or not. Thus, we classified them according to the features of the blob using support vector machines. Then, we detected vehicle traffic lane and specified the region where the vehicle may exist. Finally, we classified the blobs based on the movements across the frames. We applied the proposed method to nighttime driving sequences and confirmed the effectiveness of the classification process used in this method and that it could process within frame rate.

Recognition of Isolated Fingerspelling Gestures Using Depth Edges

Although steady progress has been made on developing vision-based gesture recognition systems, state-of-the-art approaches are still limited to discriminate hand configurations with high amounts of finger occlusions, a common scenario in most fingerspelling alphabets. In this article, we propose a novel method for recognition of isolated fingerspelling gestures based on depth edge features. Our approach is based on a simple and inexpensive modification of the capture setup: a multi-flash camera is used with flashes strategically positioned to cast shadows along depth discontinuities in the scene, allowing efficient and accurate extraction of depth edges. We then use a shift and scale invariant shape descriptor for fingerspelling recognition, demonstrating great improvement over methods that rely on features acquired by traditional edge detection and segmentation algorithms.

Color-conversion method for a multi-primary display to reduce power consumption and conversion time

— A color-conversion method for a light-emitting multi-primary-color display is proposed. While amulti-primary-color display uses four or more primary colors to reproduce a wide color gamut, multiple sets of primary-color signals are needed to reproduce one color. Therefore, linear programming, which results in low power consumption, was adopted to uniquely determine the set of primary-color signals. Although a highly accurate color conversion was achieved by using linear programming with low power consumption, it requires a very long time to convert colors of high-resolution images. Therefore, by categorizing the color conversion of linear programming as a classification problem, colors are converted by using the decision-tree method, which is a classification method. As a result, color conversion with high accuracy, low power consumption, and short conversion time was achieved.

Speckle Reduction by Summation of Higher Order Harmonic Images

Granular patterns called speckles appearing in ultrasonic echo images have become a contributing factor to deteriorated picture quality. Speckle is a kind of statistical noise that does not depend on histological distribution but it’s average size is dependent on duration and beam width of ultrasonic pulses.

Image quality enhancement support system by gamma correction using interactive evolutionary computation

By noting gamma correction as one of the image quality adjustment parameters, the authors create an image quality enhancement support system capable of reflecting user subjectivity. In this study, the derivation of an optimum gamma value is formulated as an optimization problem. To reflect user subjectivity, an image quality enhancement support system is realized by interactive evolutionary computation. This technique is verified by comparing it with a manually derived gamma value, image quality, and derivation time.

X-ray, gamma-ray detector/imager by CdTe semiconductor and its applications

Photon counting type X-ray, gamma-ray detector and imager were developed by using CdTe compound semiconductor. The detector / imager could be applied for practical application and we tried to apply material identificated X-ray CT. The imager has photon energy discriminate function and high linearity between number of incident photons and output counts. It make high contrast image for X-ray penetration image and material identification in X-ray computed tomography (CT) measurement.

Development of an image capturing system for the reproduction of high-fidelity color

An image capturing system for the reproduction of high-fidelity color color was developed and a set of three optical filters were designed for this purpose. Simulation was performed on the SOCS database containing the spectral reflectance data of various objects in the range of wavelength of 400nm ~ 700nm in order to calculate the CIELAB color difference ΔEab. The average color difference was found to be 1.049. The camera was mounted with the filters and color photographs of all the 24 color patches of the Macbeth chart were taken. The measured tristimulus values of the patches were compared with those of the digital images captured by the camera. The average ΔEab was found to be 5.916.