Casio Computer Co., Ltd.

Eagle Industry Co., Ltd.

Shinshu University

Canon Machinery Inc.

Yoshihiro Teshima

Akira Hamada

Keiichi Sakurai

Tetsuji Makino

Naotomo Miyamoto

Akihiko Nagasaka

Masaru Nakamura

Hideyuki Inoue

Kouichi Nakagome

Masakuni Iwanaga

Shogo Hashimoto

Kouichi Nakagomi

Kazumasa Morichika

Hiroshi Sawada

Takuji Matsuki

Hiroshi Aoike

Akane Minagawa

Ryuhei Okuyama

Tasuku Sano

Hiroki Takeno

A training apparatus includes a processor which acquires an image to which identification information of a subject included in the image is attached as a first correct label the image being included in an image dataset for training and being an image for use in supervised training. The processor further attaches, to the acquired image, classification information based on a feature amount of the acquired image as a second correct label, trains a classifier using the acquired image and the second correct label attached thereto, and updates training content used in the training using the acquired image and the first correct label after training the classifier.

Image searching apparatus, classifier training method, and recording medium

An identification device includes an acquirer for acquiring a captured image obtained by imaging a predetermined target, a specifier for specifying a linear region extending in a plurality of mutually different directions, from a region of the captured image acquired by the acquirer, the region including the predetermined target, and an extractor for extracting a feature quantity based on the pixel value, from the linear region specified by the specifier.

Feature quantity extracting device, feature quantity extracting method, identification device, identification method, and program

An image searching apparatus includes: a processor; and a memory, wherein the processor is configured to attach, to an image with a first correct label attached thereto, a second correct label, the first correct label being a correct label attached to each image included in an image dataset for training for use in supervised training, the second correct label being a correct label based on a degree of similarity from a predetermined standpoint; execute main training processing to train a classifier by using the images and one of the first correct label and the second correct label, fine-tune a training state of the classifier; trained by the main training processing, by using the images and the other one of the first correct label and the second correct label; and search, by using the classifier that is fine-tuned, for images similar to a query image.

An object of the present invention is to obtain an image that is more similar to a real ink-wash painting. An ink-wash painting conversion unit converts data of an original image into data of a painterly image. A characteristic region detection unit detects a characteristic region of the original image from the data of the original image. A conversion unit executes gradation processing of gradating the characteristic region detected by the characteristic region detection unit, and margin setting processing of setting a margin region to be added to the painterly image, as image processing of further converting the data of the painterly image that was converted by the ink-wash painting conversion unit.

Image processing apparatus for converting image in characteristic region of original image into image of brushstroke patterns

A drawing apparatus includes a drawing unit that forms a nail design on a nail of an object by performing a plurality of processes and a processor that extracts a feature value of the object and controls the drawing unit. The processor acquires information on a performed process with respect to the nail of one object, whose nail is provided to be formed with the nail design, based on process management information in which the feature value with respect to each of a plurality of the objects and an information on the performed process with respect to the nail of each of the plurality of the objects are registered in association with each other and the feature value with respect to the one object, and determines a specific process to be performed to the nail of the one object, and causes the drawing unit to perform the specific process.

Drawing apparatus and drawing control method of drawing apparatus

A drawing apparatus is provided with a drawing unit which applies a drawing on a nail of a subject which is a finger or a toe; and a control unit which controls operation of the drawing unit. The control unit extracts a first feature part in a first area which is inside area of a first subject outline of the subject in a first subject image acquired by imaging the subject after a first drawing has been applied on the nail, acquires a position of the nail in the first subject image on the basis of the first feature part and a second feature part which is extracted in a second area which is inside area of a second subject outline of a second subject image except an area of the nail, the second subject image is acquired by imaging the subject which the drawing has not been applied; and controls a drawing position of the drawing unit when the drawing unit applies a second drawing on the nail after the first subject image is acquired, on the basis of the position of the nail in the first subject image.

Drawing apparatus and drawing method for drawing apparatus

Provided is a mechanical seal that ensures the flow rate of a cooling fluid, which is necessary to cool a slide seal surface, and that can prevent erosion from occurring. In the mechanical seal, the ratio between the depth and the width of each groove of a partial impeller is 2.0-5.0; the ratio of the distance between the grooves of the partial impeller to the width of a weir of a casing is 0.5-3.1; the ratio of the total length of the widths of the grooves of the partial impeller to the total length of the peripheral surface of the partial impeller, in which the grooves are formed, is 0.28-0.8; or the ratio of the length of the projected portion of the tip of each groove of the partial impeller to the width of a cooling liquid discharging groove of the casing is greater than 0 and less than or equal to 0.65.

Mechanical seal

A threshold setting device, an object detection device, a threshold setting method, and a computer readable storage medium are shown. According to one implementation, the threshold setting device includes, an image acquisition unit, a ratio acquisition unit, and a setting unit. The image acquisition unit acquires an image including a specific object. The ratio acquisition unit acquires ratio information related to a ratio of a plurality of colors present in the specific object. The setting unit sets, based on the ratio information acquired by the ratio acquisition unit, a threshold used in a binarization process performed on the image including the specific object acquired by the image acquisition unit.

Threshold setting device for setting threshold used in binarization process, object detection device, threshold setting method, and computer readable storage medium

An image processing apparatus acquires a photographed image of an object on which a plurality of indicators have been arranged, recognizes an indicator in the photographed image, detects a position of the indicator, judges a timing at which a state of the object is changed to a predetermined state based on a change in the detected position of the indicator with respect to respective sequentially acquired images, and judges a state of the photographed image based on detected positions of the plurality of indicators with respect to a photographed image acquired at the judged timing at which the state of the object is changed to the predetermined state.

Image processing apparatus for processing photographed images

The present invention improves the recognition rate of an augmented reality marker and the processing speed thereof, simultaneously. In the present invention, a CPU binarizes actual image captured in an image sensor in accordance with an adaptive thresholding, and detects an augmented reality marker from within the binarized image. Then, the CPU determines a binarization threshold based on the augmented reality marker, and after binarizing the actual image captured in the image sensor in accordance with a fixed threshold binarization method using the binarization threshold, recognizes the augmented reality marker based on the binarized image.

Image processing device, image processing method and computer-readable medium

An image processing apparatus of the present invention acquires a photographed image of an object on which indicators have been arranged, detects the indicators from the photographed image with use of a comparison reference image for pattern matching prepared in advance, and instructs to perform predetermined processing based on the detected indicators. The indicators each have a pattern where influence of geometrical image distortion generated corresponding to a photographing distance or a photographing angle with respect to the object is restrained by a central portion of the photographed image, and the comparison reference image is a partial image corresponding to a central portion of the indicator. The indicators are detected from the photographed image by comparing the comparison reference image with the acquired photographed image.

The importance detection unitdetects importance of each pixel composing the original image thus acquired. In addition, the importance map generation unitgenerates an importance map indicating distribution of the importance detected for each pixel. The characteristic region detection unitdetects a characteristic region of the original image, from the original image thus acquired. The determination unitdetermines a brushstroke pattern that should be applied to the characteristic region thus detected, from at least two types of brushstroke patterns stored in a storage unit. The brushstroke pattern conversion unitconverts an image in the characteristic region into an image, to which the brushstroke pattern is applied, based on the brushstroke pattern thus determined. The adjustment unitadjusts color of the image of the brushstroke pattern being the image in the characteristic region, based on the importance map thus generated.

A camera with a function of automatically setting shooting conditions, is provided with a memory storing plural pieces of feature information of an object corresponding to different positions, respectively, the feature information of an object representing features of the object, a judging unit for, when a shooting operation is performed with the camera at a position to obtain an image, obtaining from the memory feature information corresponding to the camera position and judging whether or not an object corresponding to the obtained feature information is found in the image obtained in the shooting operation, and a shooting-operation controller for changing shooting conditions depending on the judgment made by the judging unit.

Camera with a function of automatically setting shooting conditions and shooting method

The present invention provides a mechanical seal sliding member with high lubricating characteristics, in which the coefficient of friction and the temperature of sliding surfaces are lowered and stabilized without excessive leakage. In the mechanical seal sliding member of the present invention, on the sliding surface, a plurality of grating sectionsare formed separately in each of which a plurality of linear shape ridge portions parallel to each other are formed in a predetermined region with a predetermined pitch. The linear shape ridge portions of the plurality of grating sections are formed as inclined at a predetermined angle to a sliding direction of the sliding surfaces. Such periodic structure can improve the lubricating characteristics for lubrication. By irradiating a linearly polarized femtosecond laser with irradiating energy adjacent to a process threshold level to a material surface, a fine periodic structure with a cycle interval comparable with a laser wavelength and with a ridge depth half or less than the laser wavelength can be formed by a self-structuring manner.

Mechanical seal sliding member, and mechanical seal

An image-capturing apparatus includes an image-acquiring unit which acquires an image that is captured by photographing a photographic subject which is laid on an arbitrary place, a difference image producing unit which produces a difference image between the captured image that is acquired by the image-acquiring unit and an image which is captured before the photographic subject is laid, a contour extraction unit which extracts contour information of the photographic subject from the difference image that is produced by the difference image producing unit, and an image conversion unit which corrects a distortion of the captured image on the basis of the contour information that is extracted by the contour extraction unit.

Growing community of inventors

Higashimurayama, Japan

Yoshihiro Teshima