Abstract: Provided is an image processing apparatus including a processor. The processor is configured to: reconstruct, by employing a plurality of time-series images acquired by an endoscope, three-dimensional information of an imaging subject containing relative dimensions; calculate, on the basis of focus information of each of the plurality of images, scale information for converting the relative dimensions of the three-dimensional information to absolute dimensions; convert, by employing the scale information, the relative dimensions to the absolute dimensions; and output three-dimensional information containing the absolute dimensions.

Abstract: Provided is an image processing apparatus including a processor. The processor is configured to: reconstruct, by employing an image set acquired by means of an endoscope, three-dimensional information of an imaging subject; estimate, by means of an estimator, imaging-subject distances from the image set by employing a learning parameter; calculate, on the basis of the estimated imaging-subject distances and the imaging-subject distances in the three-dimensional information, a scale coefficient; convert relative dimensions of the three-dimensional information to absolute dimensions by employing the scale coefficient; and output the three-dimensional information containing the absolute dimensions.

Abstract: An image pickup apparatus has a first/second optical system transmitting light through a first/second optical path, the second optical system having parallax with the first optical path; a switcher switching between the first and second optical paths in time series; an image sensor forming a first image and a second image by capturing subject images according to the light transmitted through the first optical path and the second optical path respectively; and a processor processing a signal output from the image sensor, wherein the processor calculates a motion vector in each divided region of a first base image from the first base image and a first reference image captured, interpolates an interpolation motion vector for each pixel of the first base image from the motion vector, and corrects the first base image or the first reference image to form a prediction image of the first image.

Abstract: An image processing apparatus includes a processor including hardware. The processor is configured to: acquire video data; estimate a spatial distribution of a predetermined biological component for which a component spectrum temporally varies with respect to image data of a predetermined frame among a plurality of frames included in the video data; generate biological component video data in which the biological component is extracted from the video data based on the estimated spatial distribution of the biological component in the image data of the predetermined frame; and generate periodic variation video data of the biological component by applying, to the biological component video data, a filter for extracting a predetermined frequency component.

Abstract: In an imaging apparatus, two pupils of a pupil division optical system transmits light of a first wavelength band and light of a second wavelength band. An amount of components of the first wavelength band in first transmittance characteristics and second transmittance characteristics is more than an amount of components of the second wavelength band in the first transmittance characteristics and the second transmittance characteristics. An amount of components of the second wavelength band in third transmittance characteristics is more than an amount of components of the first wavelength band in the third transmittance characteristics. A processor is configured to generate a color image including a first signal that is based on the first transmittance characteristics as a first channel and a second signal that is based on the second transmittance characteristics as a second channel and a third channel.

Abstract: An image pickup apparatus has a first/second optical system transmitting light through a first/second optical path, the second optical system having parallax with the first optical path; a switcher switching between the first and second optical paths in time series; an image sensor forming a first image and a second image by capturing subject images according to the light transmitted through the first optical path and the second optical path respectively; and a processor processing a signal output from the image sensor, wherein the processor calculates a motion vector in each divided region of a first base image from the first base image and a first reference image captured, interpolates an interpolation motion vector for each pixel of the first base image from the motion vector, and corrects the first base image or the first reference image to form a prediction image of the first image.

Abstract: In an imaging apparatus, two pupils of a pupil division optical system transmits light of a first wavelength band and light of a second wavelength band. An amount of components of the first wavelength band in first transmittance characteristics and second transmittance characteristics is more than an amount of components of the second wavelength band in the first transmittance characteristics and the second transmittance characteristics. An amount of components of the second wavelength band in third transmittance characteristics is more than an amount of components of the first wavelength band in the third transmittance characteristics. A processor is configured to generate a color image including a first signal that is based on the first transmittance characteristics as a first channel and a second signal that is based on the second transmittance characteristics as a second channel and a third channel.

Abstract: An image processing apparatus includes a processor including hardware. The processor is configured to: acquire video data; estimate a spatial distribution of a predetermined biological component for which a component spectrum temporally varies with respect to image data of a predetermined frame among a plurality of frames included in the video data; generate biological component video data in which the biological component is extracted from the video data based on the estimated spatial distribution of the biological component in the image data of the predetermined frame; and generate periodic variation video data of the biological component by applying, to the biological component video data, a filter for extracting a predetermined frequency component.

Abstract: In a measuring device, a second objective optical system is arranged to have a parallax with respect to a first objective optical system. An imaging unit captures a first subject image formed through the first objective optical system at a first imaging timing and captures a second subject image formed through the second objective optical system at a second imaging timing different from the first imaging timing. A virtual image generating unit generates a virtual image based on the first subject image acquired in a case in which the imaging unit is assumed to capture the first subject image at the second imaging timing. A measurement processing unit measures a shape of a subject on the basis of a second image based on the second subject image and the virtual image.

Abstract: In a measurement device, an imaging unit generates a first image and a second image. A subject distance detection unit detects a subject distance. A motion detection unit detects an amount of motion of the imaging unit. A measurement availability determination unit determines whether or not measurement is executable by comparing the amount of motion with an allowable threshold value according to the subject distance. A measurement processing unit executes a measurement process on the basis of the first image and the second image when the measurement availability determination unit determines that the measurement is executable.

Abstract: In a measurement device, an imaging unit generates a first image and a second image. A subject distance detection unit detects a subject distance. A motion detection unit detects an amount of motion of the imaging unit. A measurement availability determination unit determines whether or not measurement is executable by comparing the amount of motion with an allowable threshold value according to the subject distance. A measurement processing unit executes a measurement process on the basis of the first image and the second image when the measurement availability determination unit determines that the measurement is executable.

Abstract: In a measuring device, a second objective optical system is arranged to have a parallax with respect to a first objective optical system. An imaging unit captures a first subject image formed through the first objective optical system at a first imaging timing and captures a second subject image formed through the second objective optical system at a second imaging timing different from the first imaging timing. A virtual image generating unit generates a virtual image based on the first subject image acquired in a case in which the imaging unit is assumed to capture the first subject image at the second imaging timing. A measurement processing unit measures a shape of a subject on the basis of a second image based on the second subject image and the virtual image.

Abstract: A biological information measurement apparatus includes: a plurality of first pixels configured to generate a first imaging signal based on received light; a plurality of second pixels configured to generate a second imaging signal based on the received light; a time series signal generation unit configured to generate a first time series signal by connecting representative values of first imaging signals in time series and generate a second time series signal by connecting representative values of second imaging signals in time series; a signal component separation unit configured to separate a plurality of signal components from each of the first and second time series signals; and a biological information component selector configured to select a signal component in accordance with the biological information, among the plurality of signal components separated by the signal component separation unit.

Abstract: A biological information measurement apparatus includes: a plurality of first pixels configured to generate a first imaging signal based on received light; a plurality of second pixels configured to generate a second imaging signal based on the received light; a time series signal generation unit configured to generate a first time series signal by connecting representative values of first imaging signals in time series and generate a second time series signal by connecting representative values of second imaging signals in time series; a signal component separation unit configured to separate a plurality of signal components from each of the first and second time series signals; and a biological information component selector configured to select a signal component in accordance with the biological information, among the plurality of signal components separated by the signal component separation unit.

Abstract: An image processing apparatus obtains a motion vector between at least three images including first, second, and third images obtained through continuous shooting under different exposure conditions and computes a first motion vector between the first and second images and a second motion vector between the first and third images in a plurality of positions on the first image. A reliability level of the motion vector is determined, and an estimated motion vector between the first and second images is computed for the first motion vector having low reliability based on the second motion vector computed in the corresponding position and the shooting interval between the images. In a case where the second motion vector computed in a position corresponding to that of the first motion vector having low reliability has high reliability, the first motion vector having low reliability is substituted with the estimated motion vector.

Abstract: An image processing apparatus obtains a motion vector between at least three images including first, second, and third images obtained through continuous shooting under different exposure conditions and computes a first motion vector between the first and second images and a second motion vector between the first and third images in a plurality of positions on the first image. A reliability level of the motion vector is determined, and an estimated motion vector between the first and second images is computed for the first motion vector having low reliability based on the second motion vector computed in the corresponding position and the shooting interval between the images. In a case where the second motion vector computed in a position corresponding to that of the first motion vector having low reliability has high reliability, the first motion vector having low reliability is substituted with the estimated motion vector.

Abstract: An image processing apparatus for correcting a positional deviation between a plurality of images obtained in time series and performing synthesis processing on the plurality of corrected images determines a motion vector between the plurality of images, corrects the positional deviation between images on the basis of the determined motion vector, and generates a synthesized image by synthesizing the plurality of images subjected to the positional deviation correction. The image processing apparatus extracts a filter area in which filter processing is to be performed on the basis of a degree of inconsistency occurring when the positional deviation between the plurality of images is corrected, determines a filter kernel on the basis of an imaging condition, and performs filter processing based on the filter kernel on the filter area of the synthesized image.

Abstract: A motion vector measurement condition setting unit determines a measurement precision, which is used when measuring a motion vector between a plurality of images, on the basis of information indicating a distortion in an optical system and sets a plurality of motion vector measurement regions in which the motion vector is to be measured on an image. A motion vector calculation unit determines the motion vector between the plurality of images in each of the plurality of motion vector measurement regions at the determined measurement precision. A motion vector integration processing unit determines a positional displacement amount between the plurality of images on the basis of the motion vector determined in each of the plurality of motion vector measurement regions.

Abstract: A plurality of images are combined while suppressing a luminance change and the occurrence of artifacts. An image processing apparatus includes a measurement-area setting section that sets, in each of a plurality of images to be combined, a motion-vector measurement area that is used to measure at least one motion vector; a calculation section that calculates the motion vector between the images, in the motion-vector measurement area set by the measurement-area setting section; a reliability calculation section that calculates the reliability of the motion vector; and an image composition section that corrects misalignment between the images based on the motion vector and combines the images based on a composition ratio for each pixel, determined based on a feature quantity between the images for the pixel and the reliability of the motion vector.

Abstract: An image processing apparatus for correcting a positional deviation between a plurality of images obtained in time series and performing synthesis processing on the plurality of corrected images determines a motion vector between the plurality of images, corrects the positional deviation between images on the basis of the determined motion vector, and generates a synthesized image by synthesizing the plurality of images subjected to the positional deviation correction. The image processing apparatus extracts a filter area in which filter processing is to be performed on the basis of a degree of inconsistency occurring when the positional deviation between the plurality of images is corrected, determines a filter kernel on the basis of an imaging condition, and performs filter processing based on the filter kernel on the filter area of the synthesized image.