Abstract: An image processing system includes a processor configured to acquire a processing target image, perform a classification process that classifies an observation method when the processing target image is captured to a first observation method or a second observation method based on an observation method classifier, perform a selection process that selects one of a plurality of detectors of region of interest for detecting a region of interest including a first detector of region of interest and a second detector of region of interest based on a classification result of the observation method classifier, and output a detection result based on the selected detector of region of interest.

Abstract: A diagnostic imaging support system includes: an image input unit that receives an input of an image; a first processing unit that detects a region of interest including a subject of interest from the image, classifies the detected region of interest, and outputs a first classification result; and a second processing unit that subjects the region of interest to semantic segmentation, classifies the region of interest based on a result of the semantic segmentation, and outputs a second classification result. When a predetermined condition related to the region of interest is met, the first classification result is employed as indicating a class of the region of interest, and, when the condition is not met, the second classification result is employed as indicating the class of the region of interest.

Abstract: An image processing system includes a processor configured to acquire, as a processing target image, an in-vivo image, operate in accordance with a trained model, and output a recognition result representing a result of recognition of a region of interest in the processing target image. The trained model is trained by having undergone pre-training using a first image group including images captured in a first observation method, and having undergone, after the pre-training, fine-tuning that uses a second image group including images captured in a second observation method, as well as that uses ground truth regarding the region of interest included in the second image group. The first observation method is an observation method using normal light as illumination light, and the second observation method is an observation method using special light as the illumination light or an observation method in which a pigment has been dispersed onto the subject.

Abstract: A diagnostic imaging support system includes: an image input unit that receives an input of an image; a first processing unit that detects a region of interest including a subject of interest from the image, classifies the detected region of interest, and outputs a first classification result; and a second processing unit that subjects the region of interest to semantic segmentation, classifies the region of interest based on a result of the semantic segmentation, and outputs a second classification result. When a predetermined condition related to the region of interest is met, the first classification result is employed as indicating a class of the region of interest, and, when the condition is not met, the second classification result is employed as indicating the class of the region of interest.

Abstract: A learning method performed by an image recognition device is provided which includes a convolutional neural network. The learning method includes performing first learning by the convolutional neural network by using a first image group captured at a first frame rate, the first image group being input from outside; and performing, after performing the first learning, second learning by using a second image group that is captured at a second frame rate that is lower than the first frame rate, the second image group being is input from outside, and the number of images in the second image group being less than that in the first image group.

Abstract: An image diagnosis support system includes: an input unit that receives an input of an image; a specifying unit that specifies a specular reflection region and a non-specular reflection region in a region of interest in the image; and a determination unit that determines whether the region of interest is an inadequate region that is inadequate for diagnosis on the basis of an image processing result for at least one of the specular reflection region and the non-specular reflection region.

Abstract: An image processing apparatus includes a processor. The processor is configured to: obtain a presumption result by presuming an operation state of a user who performs an operation while the user observes an image obtained by picking up an image of a subject; perform processing for correcting a specular reflection region included in the image obtained by picking up the image of the subject; and when detecting, based on the presumption result, that a first operation related to search for a desired object in the subject is performed, perform control for causing the image in which the specular reflection region is maintained to be outputted as an observation image, and when detecting that a second operation related to discrimination of the desired object found in the subject is performed, perform control for causing the image in which the specular reflection region is corrected to be outputted as an observation image.

Abstract: An image processing apparatus includes a processor. The processor is configured to: obtain a presumption result by presuming an operation state of a user who performs an operation while the user observes an image obtained by picking up an image of a subject; perform processing for correcting a specular reflection region included in the image obtained by picking up the image of the subject; and when detecting, based on the presumption result, that a first operation related to search for a desired object in the subject is performed, perform control for causing the image in which the specular reflection region is maintained to be outputted as an observation image, and when detecting that a second operation related to discrimination of the desired object found in the subject is performed, perform control for causing the image in which the specular reflection region is corrected to be outputted as an observation image.

Abstract: An image processing device includes a processor including hardware. The processor implements an image acquisition process that acquires time-series images that were captured in time series, and a process that detects a change position, the change position being a position at which an object captured within the time-series images changes from a first object to a second object. The processor implements the process that extracts a feature quantity from each of the time-series images, determines whether the object captured within each of the time-series images is the first object or the second object based on the feature quantity, extracts candidate positions for the change position based on the determination results, and compares the candidate positions based on the determination results to determine the change position.

Abstract: A learning method performed by an image recognition device is provided which includes a convolutional neural network. The learning method includes performing first learning by the convolutional neural network by using a first image group captured at a first frame rate, the first image group being input from outside; and performing, after performing the first learning, second learning by using a second image group that is captured at a second frame rate that is lower than the first frame rate, the second image group being is input from outside, and the number of images in the second image group being less than that in the first image group.

Abstract: An image processing device includes a processor including hardware. The processor implements an image acquisition process that acquires time-series images that were captured in time series, and a process that detects a change position, the change position being a position at which an object captured within the time-series images changes from a first object to a second object. The processor implements the process that extracts a feature quantity from each of the time-series images, determines whether the object captured within each of the time-series images is the first object or the second object based on the feature quantity, extracts candidate positions for the change position based on the determination results, and compares the candidate positions based on the determination results to determine the change position.

Abstract: A control unit detects a face area from a first image and a second image which differ in shooting conditions by a face detector. If an area of the first image which is in a position corresponding to a face area detected from the second image is not detected as a face area, the control unit extracts the area of the first image as a non-detected area, and based on the non-detected area, executes learning of the face detector so that the non-detected area is detected as a face area.

Abstract: A feature area extracting section extracts an area having a unique feature in an image input to an image selection support apparatus. A specific area feature collating and determining section determines whether or not the area having a feature and extracted by the feature area extracting section is a specific area. A specific area image reading section decides a rectangular area including the specific area, and reads image information of the rectangular area. The specific area image reading section has at least one of an enlargement displaying section which enlarges and displays the image information read by the specific area image reading section, a thumbnail display section which reduces and displays the input image, and an original image displaying section which enlarges and displays the input image.

Abstract: An imaging apparatus has the function of an optical zoom which optically converts the magnification of an image and the function of an electronic zoom which changes the size of an image by electrical signal processing. The function of the electronic zoom at least operates when the optical zoom is not set at the telephoto end. A total magnification is determined by changing magnification by the optical zoom and changing magnification by the electronic zoom. A pixel count s1 of an electronic imaging device, a pixel count s2 of a rectangle including the pixels on an imaging device which are used by the electronic zoom, and a pixel count s3 of an output satisfy s1?s2>s3 or s1>s2?s3.

Abstract: An imaging apparatus comprises an optical magnification changing mechanism which optically changes a magnification of an image, and an electronic magnification changing mechanism which reduces or expands a magnification with respect to image data by signal processing, the imaging apparatus providing a magnification-changed image according to a predetermined magnification based on the optical magnification changing mechanism and the electronic magnification changing mechanism. The optical magnification changing mechanism has at least two magnifications W and T (W<T) which are discrete each other, and has a switching mechanism which, when a predetermined magnification M (W<M<T) has been set, switches an image obtained by the magnification W and an expanding conversion using the electronic magnification changing mechanism and an image obtained by the magnification T and a reducing conversion using the electronic magnification changing mechanism.

Abstract: A control unit detects a face area from a first image and a second image which differ in shooting conditions by a face detector. If an area of the first image which is in a position corresponding to a face area detected from the second image is not detected as a face area, the control unit extracts the area of the first image as a non-detected area, and based on the non-detected area, executes learning of the face detector so that the non-detected area is detected as a face area.

Abstract: An image processing device includes an image input section receiving the input of an image, an image converter generating a converted image by magnifying or reducing the image, the input of which is received by the image input section, based on a predetermined conversion magnification, a small moving object probe specifying a small moving object area, which is an image area including a small moving object, in the image, the input of which is received by the image input section, a small moving object area converter generating a magnified image of the small moving object by magnifying the small moving object area, which is specified by the small moving object probe, and an image generator generating a synthetic image by synthesizing the magnified image of the small moving object generated by the small moving object area converter with the converted image generated by the image converter.

Abstract: An electronic camera detects a person's face image from an object image obtained by photographing an object, executes an enlarging process on the detected face image so as to obtain a face image whose face size is suitable, and displays the face image which is enlarged into the suitable size on a display device. When a plurality of people are present on the object image, the enlarged face images are switched by an image operating switch. As a result, the switched face image is displayed on the display device.

Abstract: An imaging apparatus comprises an optical magnification changing mechanism which optically changes a magnification of an image, and an electronic magnification change mechanism which reduces or expands a magnification with respect to image data by signal processing. The optical magnification changing mechanism is configured so that a magnification is discrete and a focal position changes together with a focal distance. The electronic magnification change mechanism carries out an interpolation process such that the number of pixels is increased with respect to a predetermined region of read image data during an expanding process, and carried out a process for discretely sampling a wide region as compared with a readout region obtained by the sampling provided when no magnification conversion is made, during a reducing process, thereby offsetting a change of the focal position in the optical magnification changing mechanism.

Abstract: A feature area extracting section extracts an area having a unique feature in an image input to an image selection support apparatus. A specific area feature collating and determining section determines whether or not the area having a feature and extracted by the feature area extracting section is a specific area. A specific area image reading section decides a rectangular area including the specific area, and reads image information of the rectangular area. The specific area image reading section has at least one of an enlargement displaying section which enlarges and displays the image information read by the specific area image reading section, a thumbnail display section which reduces and displays the input image, and an original image displaying section which enlarges and displays the input image.