Abstract: An object tracking device includes an image buffer configured to store a plurality of images included in a video, a detection part configured to detect an object position by executing a detection process with respect to an object reflected in the plurality of images, a tracking part configured to execute a tracking process with respect to a tracking-image string representing a scope of images ranging from an image producing an object-detection result and an image producing a next object-detection process, and an integration part configured to calculate an integrative object position by integrating a detection result and a tracking result. Herein, the scope of images is determined based on an execution timing or a termination timing of the detection process, thus executing the detection process and the tracking process in parallel.

Abstract: The present invention provides a new image processing device that is robust against a change in capturing conditions. An image processing device 100 has an acquisition unit 110 for acquiring an image, a smoothing unit 120 for smoothing the acquired image with a prescribed smoothing level, a binarization unit 130 for binarizing the smoothed image, and a control unit 140 for making the smoothing unit 120 execute multiple sessions of smoothing differing in the smoothing level.

Abstract: The present invention provides a new image processing device that is robust against a change in capturing conditions. An image processing device 100 has an acquisition unit 110 for acquiring an image, a smoothing unit 120 for smoothing the acquired image with a prescribed smoothing level, a binarization unit 130 for binarizing the smoothed image, and a control unit 140 for making the smoothing unit 120 execute multiple sessions of smoothing differing in the smoothing level.

Abstract: An object tracking device includes an image buffer configured to store a plurality of images included in a video, a detection part configured to detect an object position by executing a detection process with respect to an object reflected in the plurality of images, a tracking part configured to execute a tracking process with respect to a tracking-image string representing a scope of images ranging from an image producing an object-detection result and an image producing a next object-detection process, and an integration part configured to calculate an integrative object position by integrating a detection result and a tracking result. Herein, the scope of images is determined based on an execution timing or a termination timing of the detection process, thus executing the detection process and the tracking process in parallel.

Abstract: An object tracking means tracks objects in a video image. An object consolidation determination means generates a “container” which includes a plurality of objects located in proximity. When an object separation determination means determines that an object is released from the “container”, the object tracking means restarts tracking the object released from the “container”.

Abstract: An object tracking means tracks objects in a video image. An object consolidation determination means generates a “container” which includes a plurality of objects located in proximity. When an object separation determination means determines that an object is released from the “container”, the object tracking means restarts tracking the object released from the “container”.

Abstract: In order to reduce the labor and processing load required during list production and list verification without requiring a specialized reading apparatus, and achieve sufficient identification performance, this management system includes a list storage means that stores a list of objects to be managed, an identification image generating means that detects, from an input image, an identifying part of the objects to be managed and generates the identification image in which the identifying part detected is depicted at a predetermined orientation and size in an image region, an identification image recording means that, when a first image capturing the identifying part of an object to be managed is inputted, records an identification image generated from the first image in the list of objects to be managed as the identification image of a designated identification unit and an identification image verification means that, when a second image capturing the identifying part of an object to be managed is inputted, us

Abstract: An image comparison unit (81) compares a query image with a registered image to detect, in the registered image, a region corresponding to the query image. An action information determining unit (82), on the basis of intermediate information in which sub-region information identifying sub-regions in the registered image and action information representing information processing to be executed by a target device are associated with each other, identifies sub-regions on the basis of the sub-region information, chooses a sub-region having the highest degree of matching with the detected region among the identified sub-regions, and identifies action information corresponding to the chosen sub-region. An action information execution unit (83) causes the target device to execute information processing corresponding to the action information.

Abstract: In order to reduce the labor and processing load required during list production and list verification without requiring a specialized reading apparatus, and achieve sufficient identification performance, this management system includes a list storage means that stores a list of objects to be managed, an identification image generating means that detects, from an input image, an identifying part of the objects to be managed and generates the identification image in which the identifying part detected is depicted at a predetermined orientation and size in an image region, an identification image recording means that, when a first image capturing the identifying part of an object to be managed is inputted, records an identification image generated from the first image in the list of objects to be managed as the identification image of a designated identification unit and an identification image verification means that, when a second image capturing the identifying part of an object to be managed is inputted, us

Abstract: A feature point matching device includes a position feature generation unit for generating a position feature quantity for a feature point based on a position of the feature point included in an image, a pixel value feature generation unit for generating a pixel value feature quantity for the feature point based on a pixel value of the feature point included in the image, and a feature matching unit for matching a first feature point and a second feature point based on a degree of matching between a first position feature quantity generated from a first image and a second position feature quantity generated from a second image and a degree of matching between a first pixel value feature quantity generated from the first image and a second pixel value feature quantity generated from the second image.

Abstract: An image comparison unit (81) compares a query image with a registered image to detect, in the registered image, a region corresponding to the query image. An action information determining unit (82), on the basis of intermediate information in which sub-region information identifying sub-regions in the registered image and action information representing information processing to be executed by a target device are associated with each other, identifies sub-regions on the basis of the sub-region information, chooses a sub-region having the highest degree of matching with the detected region among the identified sub-regions, and identifies action information corresponding to the chosen sub-region. An action information execution unit (83) causes the target device to execute information processing corresponding to the action information.

Abstract: A shot image processing system (100) includes a mobile terminal (1) that shoots an image of a conversion target region containing a character and/or an image, and displays the shot image containing the conversion target region on a display unit; a server that receives the shot image from the mobile terminal (1), wherein the server (2) determines a specifying method for specifying a location of the conversion target region in the received shot image, and transmits the determined specifying method to the mobile terminal, and the mobile terminal (1) specifies the location of the conversion target region in the shot image based on the specifying method received from the server (2), converts the conversion target region specified in the shot image into a prescribed format, and displays a converted image obtained by the conversion on the display unit (16).

Abstract: A feature point matching device includes a position feature generation unit for generating a position feature quantity for a feature point based on a position of the feature point included in an image, a pixel value feature generation unit for generating a pixel value feature quantity for the feature point based on a pixel value of the feature point included in the image, and a feature matching unit for matching a first feature point and a second feature point based on a degree of matching between a first position feature quantity generated from a first image and a second position feature quantity generated from a second image and a degree of matching between a first pixel value feature quantity generated from the first image and a second pixel value feature quantity generated from the second image.

Abstract: The arrangements of feature points are computed based on feature points acquired from checking target images. The feature amount having invariants as elements regarding a geometrical transformation is generated for each of the checking target images based on a computed result. And when checking whether or not the feature point arrangements of the checking target images are the same feature point arrangements by using the feature point amounts of the checking target images, at least each of the feature point arrangements that are bases for generating the feature amounts is stored, and a parameter regarding the geometrical transformation is computed based on the feature point arrangements of the checking target images. By utilizing the computed parameter regarding the geometrical transformation, whether or not the feature point arrangements of the checking target images are the same feature point arrangements is checked.

Abstract: [Problem] To provide an image comparison device which improves comparison precision and processing speed when deriving integrated comparison result on the basis of comparison results for individual local areas.

Abstract: An arithmetic device (400) calculates a moving amount based on an image sensed before movement and an image sensed after movement. The arithmetic device (400) generates a difference image with minimum noise using the calculated moving amount. The arithmetic device (400) removes noise from the difference image by performing image processing of the difference image. The arithmetic device (400) determines based on the size of a binarized region in a binarized difference image whether an obstacle exists. This makes it possible to accurately calculate the moving amount and accurately determine whether an obstacle exists.

Abstract: The arrangements of feature points are computed based on feature points acquired from checking target images. The feature amount having invariants as elements regarding a geometrical transformation is generated for each of the checking target images based on a computed result. And when checking whether or not the feature point arrangements of the checking target images are the same feature point arrangements by using the feature point amounts of the checking target images, at least each of the feature point arrangements that are bases for generating the feature amounts is stored, and a parameter regarding the geometrical transformation is computed based on the feature point arrangements of the checking target images. By utilizing the computed parameter regarding the geometrical transformation, whether or not the feature point arrangements of the checking target images are the same feature point arrangements is checked.

Abstract: The present invention provides a solution for interleaving data frames, in a semiconductor device manufacturing system in which the processing apparatus for conducting a process on any one of a semiconductor substrate and a thin film on a surface thereof; a self-diagnostic system for diagnosing a state of the processing apparatus; and a parameter fitting apparatus for maintaining a parameter of the self-diagnostic system when an inspection result of the semiconductor substrate having undergone the process has been determined to be correct, and for changing the parameter of the self-diagnostic system when the inspection result has been determined to be incorrect.

Abstract: The present invention provides a solution for interleaving data frames, in a semiconductor device manufacturing system in which the processing apparatus for conducting a process on any one of a semiconductor substrate and a thin film on a surface thereof; a self-diagnostic system for diagnosing a state of the processing apparatus; and a parameter fitting apparatus for maintaining a parameter of the self-diagnostic system when an inspection result of the semiconductor substrate having undergone the process has been determined to be correct, and for changing the parameter of the self-diagnostic system when the inspection result has been determined to be incorrect.

Abstract: An arithmetic device (400) calculates a moving amount based on an image sensed before movement and an image sensed after movement. The arithmetic device (400) generates a difference image with minimum noise using the calculated moving amount. The arithmetic device (400) removes noise from the difference image by performing image processing of the difference image. The arithmetic device (400) determines based on the size of a binarized region in a binarized difference image whether an obstacle exists. This makes it possible to accurately calculate the moving amount and accurately determine whether an obstacle exists.