Abstract: An image identification system includes a first camera that includes a mask and an image sensor, the mask having a changeable mask pattern having a plurality of pinholes, and captures a computational image that is an image with blurring, an image identification unit that identifies the computational image using an identification model that uses the computational image captured by the first camera as input data and an identification result as output data, a mask identification unit that, after the mask pattern is changed, identifies the mask pattern that has been changed, and an identification model change unit that changes the identification model in accordance with the mask pattern identified by the mask identification unit.

Abstract: A third model training part trains a second neural network model by backpropagation using an error difference between: an identification result which a third neural network model including a trained first neural network model and the second neural network connected to each other outputs after receiving second sensing data and a first operation parameter, and correct identification information corresponding to the second sensing data. A second operation parameter acquisition part acquires a second operation parameter by updating the first operation parameter via the first neural network model by the backpropagation.

Abstract: The training system determines a plurality of sensor parameter candidates to be used for an operation of a sensor, generates a plurality of sensor data sets corresponding to each of the plurality of sensor parameter candidates and including sensor data to be obtained by the operation of the sensor and a plurality of pieces of correct answer identification information corresponding to each of the sensor data, generates a plurality of trained neural network model candidates corresponding to the plurality of sensor parameter candidates, calculates identification performance of the plurality of trained neural network model candidates, selects a pair of the trained neural network model candidate with the highest identification performance and the sensor parameter candidate corresponding to the trained neural network model candidate with the highest identification performance, and outputs the selected pair of the sensor parameter candidate and the trained neural network model candidate.

Abstract: An imaging system includes an imaging apparatus that repeatedly acquires a compressed image in which information regarding light of four or more wavelength bands from a target is compressed, and a processing apparatus. The processing apparatus extracts a partial region including a region of the target from the compressed image so as to compensate for a relative motion between the target and the imaging apparatus, and generates spectral images corresponding to wavelength bands, based on data of the partial region of the compressed image.

Abstract: A method for analyzing a three-dimensional model of an object which includes: obtaining the three-dimensional model generated based on images of the object, the images being imaged by respective cameras from respective viewpoints, the three-dimensional model including three-dimensional points each of which indicating a position of the object; obtaining a camera parameter of one camera among the respective cameras; generating, based on the camera parameter and the three-dimensional model, a depth image indicating a distance between the one camera and the object; generating a foreground image indicating an area in which the object is present in the one image imaged by the one camera; comparing the depth image and the foreground image to determine whether there is a deficiency of a three-dimensional point in the three-dimensional model; and outputting deficiency information if it is determined that there is the deficiency of the three-dimensional point in the three-dimensional model.

Abstract: A method for analyzing a three-dimensional model of an object which includes: obtaining the three-dimensional model generated based on images of the object, the images being imaged by respective cameras from respective viewpoints, the three-dimensional model including three-dimensional points each of which indicating a position of the object; obtaining a camera parameter of one camera among the respective cameras; generating, based on the camera parameter and the three-dimensional model, a depth image indicating a distance between the one camera and the object; generating a foreground image indicating an area in which the object is present in the one image imaged by the one camera; comparing the depth image and the foreground image to determine whether there is a deficiency of a three-dimensional point in the three-dimensional model; and outputting deficiency information if it is determined that there is the deficiency of the three-dimensional point in the three-dimensional model.

Abstract: A collation device includes: a storage that stores a search target image showing a search target; an acquisition unit that acquires a captured image generated by an imaging device; and a controller that determines whether the search target is included in the captured image. The controller searches out a collation area in the captured image, the collation area including a subject similar to at least a part of the search target, and selects, depending on the collation area, at least one of a whole of the search target image and a part of the search target image, and collates the selected at least one with the captured image so as to determine whether the search target is included in the captured image.

Abstract: A lighting unit has a plurality of light sources that emits excitation light having relative spectral distributions different from each other. An imaging unit simultaneously captures an image of fluorescent light emitted from the subject by the excitation light and an image of reflected light obtained by reflecting the excitation light by the subject, to generate a captured image. The arithmetic unit calculates a relative spectral distribution of the fluorescent light emitted from the subject by using the information about the relative spectral distribution of the reflected light for each of the plurality of light sources stored in the memory and the captured image for each of the plurality of light sources generated by the imaging unit.

Abstract: A lighting unit includes a plurality of light sources that respectively emit plural rays of illumination light. An imaging unit that simultaneously images plural rays of reflected light obtained by the plural rays of illumination light being reflected by a subject so as to obtain information about a plurality of colors, and generates a captured image including the information about the plurality of colors. A memory stores sensitivity information items that correspond to the plurality of light sources respectively. An arithmetic unit performs an arithmetic operation to generate a plurality of separated images from the captured image by using the sensitivity information items. The plurality of separated images correspond to the plurality of light sources respectively, and each of the plurality of separated images only includes information about a corresponding one of the plural rays of reflected light.

Abstract: An appearance inspection apparatus includes a lighting unit, an imaging unit, a memory, an operating unit, a detecting unit, and a determination unit. The lighting unit has a plurality of light sources emitting single-wavelength light with relative spectral distributions different from one another, and substantially simultaneously irradiates a photographic subject with illumination light. The imaging unit captures light discharged by the photographic subject. The memory stores information about sensitivity characteristics of the imaging unit for each color. The operating unit separates an image into a first, a second, and a third image, for each component of the single-wavelength light, using the information. The detecting detects information about a specific area of the photographic subject using the first and the second image. The determination unit extracts an amount of image characteristics corresponding to a characteristic part present in the specific area using the first and the third image.

Abstract: A collation device includes: a storage that stores a search target image showing a search target; an acquisition unit that acquires a captured image generated by an imaging device; and a controller that determines whether the search target is included in the captured image. The controller searches out a collation area in the captured image, the collation area including a subject similar to at least a part of the search target, and selects, depending on the collation area, at least one of a whole of the search target image and a part of the search target image, and collates the selected at least one with the captured image so as to determine whether the search target is included in the captured image.

Abstract: A lighting unit includes a plurality of light sources that respectively emit plural rays of illumination light. An imaging unit that simultaneously images plural rays of reflected light obtained by the plural rays of illumination light being reflected by a subject so as to obtain information about a plurality of colors, and generates a captured image including the information about the plurality of colors. A memory stores sensitivity information items that correspond to the plurality of light sources respectively. An arithmetic unit performs an arithmetic operation to generate a plurality of separated images from the captured image by using the sensitivity information items. The plurality of separated images correspond to the plurality of light sources respectively, and each of the plurality of separated images only includes information about a corresponding one of the plural rays of reflected light.

Abstract: An appearance inspection apparatus includes a lighting unit, an imaging unit, a memory, an operating unit, a detecting unit, and a determination unit. The lighting unit has a plurality of light sources emitting single-wavelength light with relative spectral distributions different from one another, and substantially simultaneously irradiates a photographic subject with illumination light. The imaging unit captures light discharged by the photographic subject. The memory stores information about sensitivity characteristics of the imaging unit for each color. The operating unit separates an image into a first, a second, and a third image, for each component of the single-wavelength light, using the information. The detecting detects information about a specific area of the photographic subject using the first and the second image. The determination unit extracts an amount of image characteristics corresponding to a characteristic part present in the specific area using the first and the third image.

Abstract: A lighting unit has a plurality of light sources that emits excitation light having relative spectral distributions different from each other. An imaging unit simultaneously captures an image of fluorescent light emitted from the subject by the excitation light and an image of reflected light obtained by reflecting the excitation light by the subject, to generate a captured image. The arithmetic unit calculates a relative spectral distribution of the fluorescent light emitted from the subject by using the information about the relative spectral distribution of the reflected light for each of the plurality of light sources stored in the memory and the captured image for each of the plurality of light sources generated by the imaging unit.

Abstract: A distance measurement apparatus includes: an imaging element that images an object by performing exposure and readout of electric charges sequentially for each row or column; an optical system that has a controllable in-focus position; an imaging control unit that moves the in-focus position at constant speed, and causes the imaging element to image the object sequentially while the in-focus position is being moved, to obtain blurred images; a distance measurement unit that measures a distance from a reference position in the optical system to the object using the blurred images and a point spread function dependent on object distance; and a correction unit that performs a correction process on the distance for each row or column according to a movement range of the in-focus position in which the in-focus position is moved during the exposure for each row or column when the blurred images are obtained.

Abstract: An imaging apparatus including: an imaging unit that images an object and generates imaging data; an image processor that generates image data from the imaging data, and generates an imaging check-purpose image from the image data; and a displaying unit that displays the imaging check-purpose image. The image processor detects a blur amount of the image data, and calculates information relating to a distance to the object using the blur amount. The image processor determines a focus state of the image data, and divides the image data into a first region including a focused region and a second region which is a region other than the first region. The image processor generates the imaging check-purpose image by performing, on the image data, enhancement processing of enhancing a visual difference between the image data of the first region and the image data of the second region using the distance-relating information.

Abstract: A set of compound lenses according to the present invention forms, on an imaging device, an optical image of an object. The set of compound lenses includes a focus lens group including one or more lenses; a driving unit shifting a range of focus by moving the focus lens group within a predetermined range during an exposure period; and a correcting lens group correcting a shift in a position of an image formed on the imaging device to one pixel or less, the shift occurring when the focus lens group moves within the predetermined range.

Abstract: A distance measurement apparatus includes: an imaging element that images an object by performing exposure and readout of electric charges sequentially for each row or column; an optical system that has a controllable in-focus position; an imaging control unit that moves the in-focus position at constant speed, and causes the imaging element to image the object sequentially while the in-focus position is being moved, to obtain blurred images; a distance measurement unit that measures a distance from a reference position in the optical system to the object using the blurred images and a point spread function dependent on object distance; and a correction unit that performs a correction process on the distance for each row or column according to a movement range of the in-focus position in which the in-focus position is moved during the exposure for each row or column when the blurred images are obtained.

Abstract: An exposure controller according to the present disclosure is to be arranged on an optical path, and includes first and second light quantity regulators, each of which has a first region that has a property of transmitting a light beam polarized in a particular direction and a second region that does not have the property of transmitting a light beam polarized in the particular direction. The exposure controller regulates the quantity of light by rotating the first and second light quantity regulators.

Abstract: An exposure controller according to the present disclosure is to be arranged on an optical path, and includes first and second light quantity regulators, each of which has a first region that has a property of transmitting a light beam polarized in a particular direction and a second region that does not have the property of transmitting a light beam polarized in the particular direction. The exposure controller regulates the quantity of light by rotating the first and second light quantity regulators.