Abstract:
An image processing apparatus includes: a color feature data calculation unit configured to calculate color feature data of each pixel in an intraluminal image or color feature data of each small region obtained by dividing the intraluminal image into a plurality of small regions; a residue candidate distribution determination unit configured to determine, from among the color feature data, color feature data distributed on a side comparatively strong in redness to be a mucosa distribution and determine color feature data distributed on a side comparatively weak in redness to be a residue candidate distribution; and a residue distribution determination unit configured to determine, from among distributions of the color feature data determined to be the residue candidate distribution, a residue candidate distribution distributed on a side strong in yellowness with reference to the mucosa distribution to be a residue distribution.
Abstract:
An endoscope apparatus includes a processor. An image signal includes a first image signal corresponding to first light and a second image signal corresponding to second light. The processor determines at least one of whether or not a submucosa region or a bleeding region is included in an image based on the image signal. In a case where the submucosa region is included, the processor performs conversion processing that increases a combination ratio of the second image signal to the first image signal in an image region including the submucosa region, and allocates a combined image signal to a G-channel. In a case where the bleeding region is included, the processor performs conversion processing that increases a combination ratio of the first image signal to the second image signal in an image region including the bleeding region, and allocates the combined image signal to the G-channel.
Abstract:
An image processing device includes: an image acquisition unit configured to acquire images including at least one narrow-band image and having different wavelength component distributions from one another; an absorption information extracting unit configured to extract absorption information from a first image on the basis of a specific frequency component in the first image and correlation between the first image and a second image, the first image being a narrow-band image among the images, the second image being an image different from the first image among the images, the absorption information being image information indicating a change in absorption caused by absorption of narrow-band light used in capturing of the first image by a light absorber; and a display image generating unit configured to generate an image for display by combining the absorption information with at least any one of the images.
Abstract:
An image processing apparatus for processing an image acquired by imaging a living body includes: a narrow-band image acquisition unit configured to acquire at least three narrow-band images with different center wavelengths from one another; a depth feature data calculation unit configured to calculate depth feature data which is feature data correlated to a depth of a blood vessel in the living body based on a difference, between the narrow-band images different from one another, in variation of signal intensity due to an absorption variation of light with which the living body is irradiated; and an enhanced image creation unit configured to create, based on the depth feature data, an image in which the blood vessel is highlighted according to the depth of the blood vessel.
Abstract:
An image processing apparatus includes: an abnormality candidate region identifying unit configured to identify a candidate region for an abnormality from an image obtained by imaging inside of a lumen of a living body; a surrounding region determining unit configured to determine a surrounding region surrounding the candidate region; a shape information calculating unit configured to calculate shape information of the candidate region and shape information of the surrounding region in a depth direction with respect to a screen; and an abnormality region determining unit configured to determine whether or not the candidate region is an abnormality, based on a correlation between the shape information of the candidate region and the shape information of the surrounding region.
Abstract:
An endoscope processor comprises a processor. The processor causes a light source to generate, as illumination light, light in a first wavelength band in which hemoglobin absorption is smaller than that in a green band and light in a second wavelength band which is different from the first wavelength band. The processor causes an endoscope to image a return light so as to output an image signal. The processor acquires a first image obtained by the light in the first wavelength band from the image signal and detects unevenness information on mucosa from the first image. The processor acquires a second image obtained by the light in the second wavelength band from the image signal and synthesizes the unevenness information with the second image so as to generate a display image in which an uneven region in the second image is emphasized.
Abstract:
An endoscope processor comprises a processor. The processor causes a light source to generate, as illumination light, light in a first wavelength band in which hemoglobin absorption is smaller than that in a green band and light in a second wavelength band which is different from the first wavelength band. The processor causes an endoscope to image a return light so as to output an image signal. The processor acquires a first image obtained by the light in the first wavelength band from the image signal and detects unevenness information on mucosa from the first image. The processor acquires a second image obtained by the light in the second wavelength band from the image signal and synthesizes the unevenness information with the second image so as to generate a display image in which an uneven region in the second image is emphasized.
Abstract:
An endoscope apparatus includes comprises a processor. The processor causes the light source device to produce narrow band light as illumination light, and the narrow band light has a peak wavelength between a wavelength band including a local maximum of a hemoglobin absorption characteristic and a wavelength band including a local minimum of the hemoglobin absorption characteristic. The processor receives an image signal from the imaging device that outputs the image signal based on return light. The processor uses an image produced in response to the image signal to identify a state of the living body by identifying at least one of whether or not stomach mucosa is in a sterilized state, or whether or not the stomach mucosa is inflamed mucosa, outputs state identifying information indicating the state of the living body, and controls wavelength characteristics of the illumination light based on the state identifying information.
Abstract:
An endoscope apparatus includes: a light source device alternately emitting a first illumination light group including green light and a second illumination light group not including the green light; an image sensor including color filters of a plurality of colors; and a processing circuit. The processing circuit generates a display image on the basis of an image obtained with the first illumination light group and an image obtained with the second illumination light group. The first illumination light group further includes blue narrowband light together with the green light. The processing circuit generates a green channel image in the display image on the basis of a green image and a blue narrowband image.
Abstract:
An image processing device is configured to perform enhancement processing on a specific image, using multiple images of types that are different from one another at least one of which is captured at a time different from a time at which other images are captured. The image processing device includes a processor comprising hardware, the processor being configured to execute: acquiring the multiple images; calculating information representing a state of at least one of the multiple images that is used for enhancement; and creating an enhanced image by performing the enhancement processing on an image to be enhanced based on the information representing the state and the multiple images.