Abstract: An image measurement apparatus includes: a lighting unit that emits a first narrowband light with a bandwidth (i) narrower than a bandwidth of a visible light and (ii) including a dominant wavelength of a color of a positive cell nucleus; an image obtaining unit that obtains an examination image by capturing an image of a pathologic examination specimen to which the first narrowband light is emitted; a cell nuclei extracting unit that extracts pixels of positive cell nuclei from the examination image by comparing pixel values of the examination image with a predetermined threshold; a positive proportion calculating unit that calculates a proportion of the positive cell nuclei among cell nuclei included in the pathologic examination specimen, using the pixels of the positive cell nuclei extracted by the cell nuclei extracting unit; and an output unit that outputs the proportion.

Abstract: In a learning process, first, images having different resolutions are obtained from a target region of the subject (S101). Further, the subject characteristic of the target region is obtained (S102). Then, the resolution conversion rules are learned from the images having different resolutions, and those are recorded to a storage device along with the subject characteristics (S103). When converting the resolutions, the resolution conversion rules learned for the corresponding subject characteristics are applied to each region of the original image so as to convert the resolutions of the original image.

Abstract: A diagnostic support apparatus includes a base vector matching unit configured to match test image base vectors used for a base representation of a test image feature quantity of a test image and normal image base vectors used for a base representation of a normal image feature quantity of a normal image, a lesion determination unit configured to determine that the test image includes an image of a lesion site when a difference between a test image base coefficient and a normal image base coefficient is greater than a threshold, the test image base coefficient being a coefficient with which the test feature quantity is transformed to the base representation, and the normal image base coefficient being a coefficient with which the normal feature quantity is transformed to the base representation, and a determination result output unit configured to output a result of the determination by the lesion determination unit.

Abstract: An image processing apparatus including: an examination image obtaining unit obtaining an examination image of an examination subject; a shift-invariant feature quantity calculating unit calculating, for each pixel, a shift-invariant feature quantity represented by predetermined base vectors, from the examination image obtained by the examination image obtaining unit; a selecting unit selecting, on the examination image, a pixel having a matching degree lower than or equal to a predetermined threshold, between (i) a relative positional relationship of classes in normal images each of which does not include a lesion site and (ii) a relative positional relationship of the classes to which shift-invariant feature quantities respectively belong in the examination image, the classes being obtained by clustering the shift-invariant feature quantities: calculated from pixels included in the normal images; and represented by the predetermined base vectors; and an output unit outputting a result of the selection perfo

Abstract: An image measurement apparatus includes: an image acquiring unit that acquires a sample image that is an image obtained by capturing an image of a sample; a standard color space converting unit that converts the sample image into a standard sample image that is an image in a standard color space; a color distribution normalizing unit that converts the standard sample image into a normalized sample image by converting pixel values of pixels in the standard sample image to cause a color distribution vector indicating a color distribution of the standard sample image to match a predetermined standard color distribution vector indicating a standard color distribution; and a positive rate acquiring unit that detects positive pixels by performing threshold processing on pixel values of pixels in the normalized sample image, and acquires a positive rate indicating a proportion of the detected positive pixels.

Abstract: A medical image compression device includes: a compression target obtaining unit obtaining a target medical image to be compressed and diagnostic finding information for the target image; a clinical condition range obtaining unit dividing the target image into regions for the respective clinical conditions based on the diagnostic finding information; a pixel value prediction unit, for an arbitrary pixel, referring to a prediction knowledge database, and calculating a prediction probability of a value of a prediction target pixel based on the clinical condition of the prediction target pixel and the appearance distribution of the value of the prediction target pixel; a coding unit coding the value of the prediction target pixel based on the prediction probability of the pixel value; and an output unit outputting a code of the prediction target pixel after being coded by the coding unit.

Abstract: The diagnostic support apparatus includes a feature quantity calculation unit vectorizing a test image into shift-invariant feature quantities, a base representation unit transforming the shift-invariant feature quantities of the test image into a linear combination of base vectors with first coefficients, the base vectors being calculated from a plurality of vectors representing shift-invariant feature quantities of a plurality of normal structural images including no lesion site, a lesion determination unit determining that the test image includes a lesion site when a difference between the first coefficients and second coefficients is greater than a determination threshold value, the second coefficients being used to transform shift-invariant feature quantities calculated from one of the normal structural images into a linear combination of the base vectors, and an output unit outputting a result of the determination by the lesion determination unit.

Abstract: A tactile feedback system includes: a removing section for removing a contact-device-specific oscillating waveform, included in both a first contact-generated waveform representing a frictional vibration produced when a contact device contacts with one object and a second contact-generated waveform representing a frictional vibration produced when the contact device contacts with another object, from the first contact-generated waveform; a superposing section for superposing a finger-pulp-specific oscillating waveform, included in both the first finger-pulp-generated waveform representing a frictional vibration produced when a person's finger pulp contacts with the one object and the second finger-pulp-generated waveform representing a frictional vibration produced when the finger pulp contacts with that another object, on the first contact-generated waveform from which the contact-device-specific oscillating waveform has been removed; and a simulating section for displaying a vibration stimulation based on t

Abstract: A digital specimen manufacturing device comprises: a reduction processing unit which generates a reduced image by reducing a high resolution image of a first magnification into a second magnification image; an operation instruction unit which instructs the imaging unit to update the second magnification and recapture the low resolution image when information indicates the difference between the reduced image and the low resolution image is not within the allowable error range; and an image processing unit which obtains a third magnification, and outputs an image of the digital specimen by reducing the high resolution image into an image of the third magnification which an image magnification greater than the updated second magnification and smaller than the first magnification.

Abstract: The present invention provides a technique for sensing and reproducing various feels, which a person gets discretely over a period of time, by time sequential sensing. A tactile processor includes: a movement measuring section for determining a status of contact between a person and an object; a physical measuring section for measuring a physical property value of the object; and a physical-psychological transformation section for generating a tactile feature quantity based on the physical property value that has been measured by the physical measuring section and on the weight of the physical property of an arbitrary object. The weight is variable according a status of contact between the person and the arbitrary object and is calculated based on not only a physical property value representing the status of contact between the person and the arbitrary object but also a tactile feature quantity representing a feel that the person gets when touching the arbitrary object.

Abstract: A recording process records low-resolution video data while obtaining a high-resolution image in a window region being a portion of an entire image. Then, the process learns, as a resolution conversion rule, a resolution increasing parameter by using the high-resolution image. In a resolution increasing process, the resolution of the recorded low-resolution video data is increased by using the resolution increasing parameter learned in the recording process.

Abstract: An image generating system determines respective luminance values of multiple polygons representing a surface of a subject rendered by reference to a texture image attached to the multiple polygons. The system includes a capturing section storing a texture image of an object deformed by external force; a memory section retaining a correspondence table including information about a position of one polygon set corresponding to a position on a surface of the object to which no external force is applied, information about a stress vector indicating external force applied to the position on the surface of the object and associated with the one polygon corresponding to the position on the surface of the object to which external force is applied, and information about the luminance value of the texture image of the object to which the external force is applied; and a texture mapping section making reference to the table.

Abstract: The resolution of an image of an object is increased. The illumination equation parameters of the object are estimated, and a resolution-increasing process is performed on the estimated illumination equation parameters. Then, the resolution-increased illumination equation parameters are synthesized together to produce a high-resolution image. If there is a pixel for which the estimation precision of the estimated illumination equation parameters does not satisfy a predetermined precision, the illumination equation parameters are estimated again while feeding back the resolution-increased illumination equation parameters.

Abstract: A tactile feedback system includes: a removing section for removing a contact-device-specific oscillating waveform, included in both a first contact-generated waveform representing a frictional vibration produced when a contact device contacts with one object and a second contact-generated waveform representing a frictional vibration produced when the contact device contacts with another object, from the first contact-generated waveform; a superposing section for superposing a finger-pulp-specific oscillating waveform, included in both the first finger-pulp-generated waveform representing a frictional vibration produced when a person's finger pulp contacts with the one object and the second finger-pulp-generated waveform representing a frictional vibration produced when the finger pulp contacts with that another object, on the first contact-generated waveform from which the contact-device-specific oscillating waveform has been removed; and a simulating section for displaying a vibration stimulation based on t

Abstract: The present invention realizes highly realistic texture mapping even if the object, to which a texture is going to be attached, has been deformed. The image generating system of this invention includes: a capturing section for storing data about a texture image representing a subject that has been deformed by external force; a memory section for retaining a table of correspondence in which for each of multiple polygons, associated with each other are: position information about a position where one polygon, to which no external force is applied, is located; information about a stress vector indicating external force applied to the position of that polygon; and information about the luminance value of a texture image when the external force is applied; and a texture mapping section for making reference to the table with the position information of the object's polygon, to which no external force is applied, and the information about the stress vector to act on the object's polygon.

Abstract: An image processing device and an image processing method capable of generating a moving image having a high resolution and a high frame rate are provided by suppressing the reduction in the amount of light incident on each camera.

Abstract: The shooting, recording and playback system 100 of the present invention receives incoming light 101, stores an image shot, and then subjects the image shot to be reproduced to resolution raising processing, thereby outputting RGB images with high spatial resolution and high temporal resolution (ROUT GOUT BOUT) 102. The system 100 includes a shooting section 103, a color separating section 104, an R imaging sensor section 105, a G imaging sensor section 106, a B imaging sensor section 107, an image shot storage section 108, an image shot writing section 109, a memory section 110, an image shot reading section 111, a spatial resolution upconverter section 112, a temporal resolution upconverter section 113, an output section 114, and a line recognition signal generating section 185. The system can get image data with high spatial resolution and high temporal resolution without getting the camera configuration complicated and without decreasing the optical efficiency.

Abstract: The present invention provides a technique for sensing and reproducing various feels, which a person gets discretely over a period of time, by time sequential sensing. A tactile processor includes: a movement measuring section for determining a status of contact between a person and an object; a physical measuring section for measuring a physical property value of the object; and a physical-psychological transformation section for generating a tactile feature quantity based on the physical property value that has been measured by the physical measuring section and on the weight of the physical property of an arbitrary object. The weight is variable according a status of contact between the person and the arbitrary object and is calculated based on not only a physical property value representing the status of contact between the person and the arbitrary object but also a tactile feature quantity representing a feel that the person gets when touching the arbitrary object.

Abstract: To provide an image capturing apparatus that detects a camera movement accurately and corrects image blurring appropriately. An image capturing apparatus (200) includes: an image sensor unit (103) that captures and outputs an input image (105); an output unit (121) that outputs an image of a framing area (160) of the input image (105); a motion vector calculation unit (106) and a stationary object detection unit (201) that detect motion vectors in an outer-frame area (161) of the input image (105) and derive detection accuracy; an outer-frame area adjustment unit (205) that adjusts the outer-frame area (161) in size so that the detection accuracy meets an outer-frame area change threshold (tr); and a camera movement calculation unit (113) and a framing area modification unit (115) that move the framing area (160) according to motion vectors in the adjusted outer-frame area (161), irrespective of motion vectors in the other area.

Abstract: In a learning process, first, images having different resolutions are obtained from a target region of the subject (S101). Further, the subject characteristic of the target region is obtained (S102). Then, the resolution conversion rules are learned from the images having different resolutions, and those are recorded to a storage device along with the subject characteristics (S103). When converting the resolutions, the resolution conversion rules learned for the corresponding subject characteristics are applied to each region of the original image so as to convert the resolutions of the original image.