Hitachi, Ltd.

Hitachi High-tech Corporation

Hitachi-high-technologies Corporation

Hitachi-kokusai Electric Inc.

Hideharu Hattori

Yasuki Kakishita

Kenko Uchida

Sadamitsu Aso

Yoshifumi Izumi

Toshinari Sakurai

Taku Sakazume

Anirban Ray

Koichi Hamada

Hiroshi Mitsumaki

Muneaki Yamaguchi

Yasuhiro Akiyama

Masanori Takeuchi

Yuichiro Komiya

Tatsuhiko Kagehiro

Yoichiro Suzuki

Ok-Kyung Cho

Yoon-Ok Kim

Fumiaki Hamazato

An apparatus for generating models for identifying objects of interest from images is disclosed. The apparatus includes an input unit that receives input images, an object segmentation unit that receives the input images from the input unit and separates regions of objects of interest from a background region, and a learning unit that learns models used by the object segmentation unit. The learning unit trains new models using training data and outputs of existing models in relation to the training data, adds the trained new models to the existing model, and repeats the training of the new models and the adding of the trained new models to the existing models.

Apparatus, method and system for generating models for identifying objects of interest from images

In order to perform quantitative analysis on an object in an image, it is important to accurately identify the object, but when plural objects are in contact with each other, it is potential that a target portion cannot be accurately identified. An image is segmented into a foreground region and a background region, the foreground region being a region in which an object for which quantitative information is to be calculated is shown, and the background region being a region other than the foreground region. With respect to a first object and a second object in contact with each other in the image, a contact point between the first object and the second object is detected based on a region segmentation result output by a segmentation unit. The first object and the second object can be separated by connecting two boundary reference pixels including a first boundary reference pixel that is a pixel in a background region closest to the contact point, and a second boundary reference pixel that is a pixel in a background region in a direction opposite to the first boundary reference pixel across the contact point.

Image processing method, image processing apparatus, and image processing system

A machine learning device with a processor and a memory, in which the processor receives an image and calculates a feature amount of an object included in the image, the processor identifies a local part from the feature amount and calculates a local identification value, the processor calculates an overall identification value using the local identification value, and the processor generates a classifier using the local identification value and the overall identification value and stores it in the memory.

Machine learning device, image diagnosis support device, machine learning method and image diagnosis support method

An image diagnosis assisting apparatus according to the present invention executes: processing of inputting an image of a tissue or cell; processing of extracting a feature amount of a tissue or cell from a processing target image; processing of extracting a feature amount of a tissue or cell from an image having a component different from that of the target image; and processing of determining presence or absence of a lesion and lesion probability for each of the target images by using a plurality of the feature amounts.

Image diagnosis assisting apparatus, image diagnosis assisting system and image diagnosis assisting method

A state of a sample surface is accurately determined without lowering analysis efficiency. There is provided an apparatus for determining a state of a sample to be analyzed contained in a container, in which the apparatus acquires an image of the sample, analyzes a position and a size of an object to be detected with respect to a detection range set in the image by using the image of the sample, and determines the state of the sample based on a result of the analysis.

Apparatus, method for determining state of sample, and analysis system

Reaction values indicating based on which areas in an input image a plurality of identification results representing the states of cells or tissues are judged are calculated, and differences between a plurality of reaction values are obtained to thereby calculate the degree to which cells or tissues in an area of interest likely are in each state. Thereby, each state of cells or tissues can be visualized at an accurate position in an area of interest; therefore, diagnostic assistance to pathologist becomes possible.

Image diagnosis assisting apparatus, image diagnosis assisting method and sample analyzing system

A diagnostic imaging assistance apparatus according to the present invention performs a process of inputting images of a tissue and a cell, a process of extracting feature amounts of a wide view and a narrow view from a target image to be processed, a process of classifying whether the target images having different views are normal or abnormal from the feature amounts, and a process of classifying a lesion likelihood using a classification result.

Diagnostic imaging assistance apparatus and system, and diagnostic imaging assistance method

An image processing apparatus includes: a storage unit configured to store map information to which object information indicating an object and a position thereof is added, and a plurality of different classifiers for classifying an object in an image; an object detecting unit configured to detect an object in a target image; and an object recognizing unit configured to select any of the classifiers based on a photographing position that is a position at which the target image has been photographed and the object information added to the map information and, using the selected classifier, recognize the object detected by the object detecting unit.

Image processing apparatus, image processing system, and image processing method

The present invention realizes determination of tissues and cells from an image by calculating feature values of a deformed degree of the cells even in a case where the tissues or the cells have various shapes. An image diagnosis support apparatus according to the present invention executes processing of inputting an image of cells, processing of extracting the feature values of a plurality of direction components from a target image of the processing, processing of determining whether or not the image corresponds to one-classification by using the plurality of feature values, and processing of determining whether or not the determination processing is finished with respect to all of the classifications set in advance (FIG.).

Cytologic diagnosis support apparatus, cytologic diagnosis support method, remote diagnosis support system, service providing system, and image processing method

An image processing apparatus includes: a contrast correcting unit which creates a contrast-corrected image in which contrast of an input image photographed by an in-vehicle camera that is mounted to a vehicle is corrected; a color analyzing unit which creates a color-corrected image in which a color of the input image is corrected; an object detecting unit which detects a first target object included in the input image based on the contrast-corrected image, and which detects a second target object included in the input image based on the color-corrected image; and an object association analyzing unit which recognizes the first target object and the second target object based on a time series association between the first target object and the second target object detected by the object detecting unit.

Image processing apparatus, warning apparatus, image processing system, and image processing method

An image processing device includes a contrasting correction unit, a color analysis unit, an object detection unit, and an object relation analysis unit. The contrasting correction unit creates a contrasting corrected image by correcting contrasting of an input image captured by a vehicle camera. The color analysis unit creates a color corrected image by correcting colors of the input image. The object detection unit detects a main sign included in the input image based on the contrasting corrected image and detects an auxiliary sign included in the input image based on the color corrected image. The object relation analysis unit recognizes a traffic sign as a combination of a main sign and auxiliary sign by associating the main sign and the auxiliary sign with each other based on a positional relationship between the main and auxiliary signs, which are detected by the object detection unit, in the input image.

Image processing device, alarming apparatus, image processing system, and image processing method

Provided is a technique for, even when the lightness of an image contained in a video changes, accurately separating the background of the image and an object in the background and thus efficiently collecting images that contain a target object to be detected, and also suppressing the amount of data communicated between a terminal device and a server. In the present invention, a terminal device accurately separates the background of an image and an object (i.e., a target object to be detected) in the background so as to simply detect the object in the background, and transfers to a server only candidate images that contain the detected object. Meanwhile, as such simple target object detection may partially involve erroneous detection, the server closely examines the candidate images to identify the target object to be detected, and thus recognizes the object.

Object detection system, object detection method, POI information creation system, warning system, and guidance system

The purpose of the present invention is to provide image processing technology that can reduce shimmering in the entirety of images that include both still regions and moving bodies. This image processing device finds gradient distribution for each of a frame to be corrected and a frame for correction, changes, according to the degree of similarity in the gradient distribution, the proportion in which the frame to be corrected and the frame for correction are used, and then corrects the frame to be corrected using the frame for correction (see FIG.).

Image processing device, imaging device, monitoring system, encoding device, image processing method

Even when the brightness of an image in a video changes, detection of an object in the background is realized by accurately separating the object in the background from the background of the image. An image processing device in accordance with the present invention executes a process of converting a color space of a processing target image and acquiring color information on the converted color space, a process of calculating, for the target image, an average value of the brightness of color information on a target region that contains an object to be detected, and a process of comparing, for the target region, the brightness of color information on each pixel with the calculated average value, a process of generating a corrected image with corrected brightness/darkness, and a process of extracting the object on the basis of the corrected image (See FIG.).

Image processing device, image processing method, POI information creation system, warning system, and guidance system

Apparatus including: a unit detecting a motion vector, among plural number of fields included in motion pictures, or fields, produced from the plural number of fields; a unit for converting the motion pictures into light-emission data for sub-fields; a unit for reconstructing the light-emission data for sub-fields, via calculating using the motion vector; and a unit for displaying the picture using the light-emission data outputted from the sub-field reconstruction unit, wherein the sub-field reconstruction unit selects the motion vector ending at a reconstruction target pixel of other one (1) field, among the motion vectors detected by the motion vector detection unit, and calculates a position vector, by multiplying a predetermined function onto this, and thereby reconstructing light-emission data for one (1) sub-field of the reconstruction target pixel, using the light-emission data for sub-fields corresponding to the one (1) sub-fields within the pixel, which is indicated by the position vector.

Growing community of inventors

Tokyo, Japan

Hideharu Hattori