Abstract: A list for accurately identifying objects with different sizes that are the same attributes can be generated automatically. A classification unit classifies, from a group of images consisting of images including objects with any of a plurality of attributes, each of the images including the objects that have an identical attribute and have different real sizes into an identical cluster. An output unit outputs each of clusters into which at least two of the images are classified as a list of images with different real sizes of the objects for the identical attribute.

Abstract: A segmentation recognition method includes: an object detection step of detecting an object image in a target image by inputting bounding box information including a coordinate and category information of each bounding box defined in the target image to an object detection model that uses a machine learning approach; a filtering step of selecting effective training mask information from training mask information associated with foregrounds in the target image based on the bounding box information; a bounding box branch step of recognizing the object image using weight information of the object detection model as an initial value of weight information of an object recognition model that recognizes an object of the object image; and a mask branch step of generating mask information having a shape of the object image using the selected effective training mask information as training data and using weight information of the object recognition model as an initial value of weight information of a segmentation shape

Abstract: Even if an object to be detected is not remarkable in images, and the input includes images including regions that are not the object to be detected and have a common appearance on the images, a region indicating the object to be detected is accurately detected. A local feature extraction unit 20 extracts a local feature of a feature point from each image included in an input image set. An image-pair common pattern extraction unit 30 extracts, from each image pair selected from images included in the image set, a common pattern constituted by a set of feature point pairs that have similar local features extracted by the local feature extraction unit 20 in images constituting the image pair, the set of feature point pairs being geometrically similar to each other.

Abstract: The present invention makes it possible to cause an action recognizer capable of recognizing actions with high accuracy and with a small quantity of learning data to learn. An input unit 101 receives input of a learning video and an action label indicating an action of an object, a detection unit 102 detects a plurality of objects included in each frame image included in the learning video, a direction calculation unit 103 calculates a direction of a reference object, which is an object to be used as a reference among the plurality of detected objects, a normalization unit 104 normalizes the learning video so that a positional relationship between the reference object and another object becomes a predetermined relationship, and an optimization unit 106 optimizes parameters of an action recognizer to estimate the action of the object in the inputted video based on the action estimated by inputting the normalized learning video to the action recognizer and the action indicated by the action label.

Abstract: Objectness indicating a degree of accuracy of a single object is accurately estimated. An edge detection unit 30 detects an edge for a depth image, an edge density/uniformity calculation unit 40 calculates an edge density on the periphery of a candidate region, an edge density inside the candidate region, and edge uniformity on the periphery of the candidate region. An objectness calculation unit 42 calculates the objectness of the candidate region based on the edge density on the periphery of the candidate region, the edge density inside the candidate region, and the edge uniformity on the periphery of the candidate region.

Abstract: An object is to accurately recognize an action of a subject. A direction alignment unit 24 is configured to perform at least one of rotation and inversion on an image based on an action direction of a desired subject in the image, so as to obtain an adjusted image. An action recognition device 26 is configured to recognize an action of the desired subject using the adjusted image as an input.

Abstract: A low-resolution image can be converted into a high-resolution image in consideration of differential values of the images. A learning conversion unit 22 inputs a first image for learning to a conversion processing model for converting the first image into a second image having a higher resolution than the first image to acquire the second image for learning corresponding to the first image for learning. Then, a differential value calculation unit 24 calculates a differential value from the acquired second image for learning, and calculates a differential value from a correct second image corresponding to the first image for learning. Then, the learning unit 26 causes the conversion processing model to learn by associating the calculated differential value of the second image for learning with the differential value of the correct second image.

Abstract: An object is to make it possible to precisely infer a geometric transformation matrix for transformation between an image and a reference image representing a plane region even if correspondence to the reference image cannot be obtained. A first line segment group extraction unit 120 extracts, out of a line segment group in an image, line segments that correspond to a direction that is parallel or perpendicular to a side of a rectangle included in the image, from the inside of the rectangle, takes the extracted line segments to be a first line segment group, and extracts a plurality of line segments different from the first line segment group out of the line segment group.

Abstract: A list for accurately identifying objects with different sizes that are the same attributes can be generated automatically. A classification unit classifies, from a group of images consisting of images including objects with any of a plurality of attributes, each of the images including the objects that have an identical attribute and have different real sizes into an identical cluster. An output unit outputs each of clusters into which at least two of the images are classified as a list of images with different real sizes of the objects for the identical attribute.

Abstract: The present invention makes it possible to estimate, with high precision, a candidate region indicating each of multiple target objects included in an image. A parameter determination unit 11 determines parameters to be used when detecting a boundary line of an image 101 based on a ratio between a density of boundary lines included in an image 101 and a density of boundary lines in a region indicated by region information 102 indicating the region including at least one of the multiple target objects included in the image 101. A boundary line detection unit 12 detects the boundary line in the image 101 using the parameter. For each of the multiple target objects included in the image 101, the region estimation unit 13 estimates the candidate region of the target object based on the detected boundary line.

Abstract: Objectness indicating a degree of accuracy of a single object is accurately estimated. An edge detection unit 30 detects an edge for a depth image, an edge density/uniformity calculation unit 40 calculates an edge density on the periphery of a candidate region, an edge density inside the candidate region, and edge uniformity on the periphery of the candidate region. An objectness calculation unit 42 calculates the objectness of the candidate region based on the edge density on the periphery of the candidate region, the edge density inside the candidate region, and the edge uniformity on the periphery of the candidate region.

Abstract: Even if an object to be detected is not remarkable in images, and the input includes images including regions that are not the object to be detected and have a common appearance on the images, a region indicating the object to be detected is accurately detected. A local feature extraction unit 20 extracts a local feature of a feature point from each image included in an input image set. An image-pair common pattern extraction unit 30 extracts, from each image pair selected from images included in the image set, a common pattern constituted by a set of feature point pairs that have similar local features extracted by the local feature extraction unit 20 in images constituting the image pair, the set of feature point pairs being geometrically similar to each other.

Abstract: An object is to make it possible to precisely infer a geometric transformation matrix for transformation between an image and a reference image representing a plane region even if correspondence to the reference image cannot be obtained. A first line segment group extraction unit 120 extracts, out of a line segment group in an image, line segments that correspond to a direction that is parallel or perpendicular to a side of a rectangle included in the image, from the inside of the rectangle, takes the extracted line segments to be a first line segment group, and extracts a plurality of line segments different from the first line segment group out of the line segment group.

Abstract: A low pass filter including: a coil that includes a band-shaped conductor and is wound a plurality of times around an axis; a capacitor that has one terminal connected to the conductor and the other terminal connected to ground; a cooling plate in contact with an end surface of the wound coil with respect to a direction of the axis; and a ceramic layer that has a flat surface and is disposed on the end surface of the would coil facing the direction of the axis, wherein the ceramic layer contacts the cooling plate, and the cooling plate includes a flow path through which water flows.

Abstract: A coil cooling structure comprises a coil which includes a strip-shaped conductor wound around a specific axis a plurality of times; an alumina layer which is formed on an end surface of the coil in the direction of the specific axis through thermal spraying of alumina and whose surface is flattened; a cooling plate which is mainly formed of alumina and has a flow passage for a cooling medium; and an adhesive which bonds the alumina layer and the cooling plate and which elastically deforms depending on a difference in thermal expansion between the alumina layer and the cooling plate.

Abstract: An electromagnetic coil includes a conductor winding 12a formed by winding a conductor 12b a plurality of times about a predetermined axis, and a ceramic layer 12c formed through thermal spraying on an axial end surface of the conductor winding 12a, and having a flattened surface. A maximal value t12 of thickness of the ceramic layer 12c is set to three times or less a maximal value t11 of depth of the recesses formed at the surface of turns of the conductor 12b at the axial end surface.

Abstract: An electromagnetic coil includes a conductor winding 12a formed by winding a conductor 12b a plurality of times about a predetermined axis, and a ceramic layer 12c formed through thermal spraying on an axial end surface of the conductor winding 12a, and having a flattened surface. A maximal value t12 of thickness of the ceramic layer 12c is set to three times or less a maximal value t11 of depth of the recesses formed at the surface of turns of the conductor 12b at the axial end surface.

Abstract: A plasma processing apparatus includes: a processing container capable of maintaining an atmosphere having a pressure lower than atmospheric pressure; an evacuation unit reducing a pressure of an interior of the processing container; a gas introduction unit introducing a process gas to the interior of the processing container; a microwave introduction unit introducing a microwave to the interior of the processing container; and a lifter pin ascendably and descendably inserted through a placement platform provided in the interior of the processing container, an end surface of the lifter pin supporting an object to be processed, the object to be processed being supported by the lifter pin at a first position proximal to an upper surface of the placement platform when the microwave is introduced and plasma is ignited, the object to be processed being supported by the lifter pin at a second position after the plasma ignition, the second position being more distal to the placement platform than the first position.

Abstract: A locking mechanism for a cover is provided which locks the cover in a closed state. The locking mechanism includes a slider that is elastically urged in a direction perpendicular to the opening and closing direction of the cover so as to suppress movement of the slider in one direction when the cover is opened. When the cover is closed, the slider is pressed down by the protrusion to release the slider so as to allow the slider to slide, and the engaging portions engage the locking portions of first and second protrusions, respectively, so as to lock the cover.

Abstract: Deflection control apparatus for a beam index color television receiver includes a phase-locked loop for synchronizing an oscillating signal with an index signal generated by an electron beam scanning index stripes on the screen of the cathode ray tube of the receiver. The oscillating signal is supplied to a color switcher so that the scanning electron beam is modulated with color information corresponding to the respective color phosphor stripe being scanned. An error signal representative of the horizontal scanning speed of the beam is supplied to a deflection device to cause the generation of a compensating magnetic field to correct for non-linearities in the scanning speed. A compensation circuit delays the error signal so that the elapsed time from the detection of the scanning of one of the index stripes to the time of generation of the compensating magnetic field in accordance therewith equals one horizontal line period.