Abstract: Systems and methods for user-configurable financial instrument inspection are provided. A user may select the type of financial performance information and presentation format of the financial performance information to be displayed when the user selects a particular financial instrument. The user may associate a set of financial performance information and presentation format with a particular financial market for financial instruments. The financial instrument inspector may also facilitate trading of financial instruments.

Abstract: A web platform for automated investment management services is provided. The platform may enable the automated management of client funds, invested in stocks and other traded assets such as commodities and gold, as well as other traded securities and financial instruments like stock options, stock funds, stock indexes, bonds and structured products. The platform may support customization based on each client's investment profile and policy. Agents may be dynamic and thus may enable the implementation of portfolio strategies that automatically adapt to changes in global financial and stock markets risk, as well as return and currency factors. In some embodiments, the platform may utilize genetic learning algorithms. The platform may support market making and distribution of third party funds and instruments, as well as an investor community, where clients can provide agents to allow others to co-invest.

Abstract: A method includes receiving first user input indicating selection of a guaranteed income option to fund essential retirement expenses. The method further includes receiving second user input indicating selection of an investment option to fund lifestyle retirement expenses. The method also includes receiving third user input indicating selection of an unexpected liability coverage option, wherein the unexpected liability coverage option includes a long-term care funding option, an unexpected legal expense funding option, or any combination thereof. The method includes receiving fourth user input indicating selection of one or more legacy planning options. The method also includes generating a retirement plan based on the first user input, the second user input, the third user input, and the fourth user input.

Abstract: A system and method for providing commoditized insurance products to at least one consumer is disclosed. The system includes a commoditized insurance product including an activation code and an insurance company that underwrites the commoditized insurance product and provides the commoditized insurance product to a retail outlet. Based on consumer purchase of the commoditized product at the retail outlet and initiation of an activation process, the insurance company receives an activation code associated with the commoditized insurance product and provides verification queries to the consumer, and based on positive responses to the queries activates the policy providing the selected insurance coverage for the consumer.

Abstract: Systems and methods include a database maintained by a financial institution that stores transaction data associated with a previous financial transaction performed via a financial account of a respective account holder, wherein the transaction data comprises a transaction location and a transaction timestamp, a spend memory processor of the financial institution that retrieves the transaction data from the database, interacts with a social linking application programming interface (API) to receive, via a network, social data from a social networking site, wherein the social data comprises a social location and a social timestamp, compares the social data to the transaction data, and creates a spend memory record based on one or more similarities between the social data and the transaction data, and a communication interface of the financial institution that provides the spend memory record to a mobile device associated with the account holder.

Abstract: A social graph may be modeled as a collection of claims. Each claim is associated with an author, an audience, and an assertion about a fact. Probabilistic information may be collected from various sources for a claim, enabling a social networking system to evaluate a truthfulness of the assertion made in the claim. User-declared profile information may be evaluated as claims. A user, entity, or application may make claims about any assertions made in the social networking system. Reputation scores may be determined for users based on evaluations of their historical assertions. Claims may be evaluated for truthfulness using a probabilistic prediction model using heuristics analysis, regression analysis, and machine learning methods. A claims-based profile of users may be provided to viewers based on the contexts in which the claims were made. Viewers may view claims made about users, such as the users' biographical information, contact information, expertise, and interests.

Abstract: A social networking system associates one or more objects in the social networking system with a link to content external to the social networking system. This allows information about the object to be used as a proxy for information about the external content. An index associating objects in the social networking system with links to content external to the social networking system is maintained. A received link to external content are parsed into components, such as a domain name, a path, and a query string, and the components are compared to the index to identify an object associated with one or more of the comments of the received link. One or more rules may be applied to increase the likelihood of the identified object having similar subject matter as the external content.

Abstract: A method and system are disclosed for managing catalog resources within a social commerce environment. Users are referred by a plurality of affiliates to a social commerce marketplace system. Once referred, the users are presented with a customized social commerce storefront that is associated with an individual affiliate. Each of the customized social commerce storefronts comprises a micro catalog of purchasable products, which is a subset of a master catalog comprising a set of available products. Social data associated with the user and catalog data associated with the purchasable products is processed to generate product catalog data to the user, which is then provided to the user. The user reviews the social commerce content and selects individual purchasable products for purchase.

Abstract: An endorsement application can allow a user to endorse a product on a social network website when the product is purchased at a physical merchant point of sale terminal. Users of social network websites have been given the opportunity to endorse products that they have located or purchased online, but purchasers of products in person have not had that opportunity. The endorsement application can operate on a user's mobile device and can recognize a product purchased through near field or other communication using the mobile device. The application can isolate the product identification and product marketing data supplied by the point of sale terminal or other source and offer the user the opportunity to endorse the product on a social network website. If the user endorses the product, the application sends the endorsement to the user's account on the social network website for display to the user's community.

Abstract: The present invention relates, according to one aspect, to a method for creating a group comprising at least one of a plurality of first parties and a plurality of second parties, the method comprising the steps of a first party preparing a first data set, a second party preparing a second data set, determining a correspondence indicator indicating a degree of correspondence between the first data set and the second data set, and storing said correspondence indicator and an identifying indicator for at least one of said first party and said second party linked to each other, wherein said first type of data includes objective information, and wherein said second type of data includes subjective information.

Abstract: Methods and systems are provided for determining the intent of a recommendation made by a user of a mobile application where the application includes a plurality of separable components, any one or more of which the recommendation can apply to. An application in which a user recommendation control is provided for presentation to a user also includes a tag indicating how a recommendation of the application should be interpreted with respect to the components included therein. The tag can be set by the application developer and can be in the form of text (e.g., a keyword or term) or a uniform resource locator (URL). Where a tag references multiple components of an application, a recommending user can be presented with a recommendation intent query. The recommendation intent query allows a user to designate one or more components of the application to which the user's recommendation should be attributed.

Abstract: A technique allows a smart meter to receive a mask. The smart meter may receive the mask from a utility company or an escrow service. The smart meter may apply the mask to original metered data on a continuous schedule, on a periodic schedule, or on a determined schedule, or on a randomized schedule to conceal the original metered data. The smart meter may apply different masks at different times. The smart meter transmits the concealed metered data as augmented metered data remotely to an electric utility via a communication network.

Abstract: Systems and methods facilitate and automate well abandonment procedures. In an embodiment, well field data for a plurality of wells is categorized into well types. An inspection set of wells, including wells of each type, is determined from the entire plurality of wells. Inspection data is collected for each well type, including environmental, regulatory, and well condition data. The inspection data is extrapolated onto wells with similar types for the entire filed and analyzed. The analysis may include determining an optimal sequence of well abandonment activities, and an estimate of costs for abandoning each well, all wells of each type, and the entire well field. In an embodiment, a risk assessment analysis is performed and may include an analysis of factors that may change the cost of abandoning the well field or a sequence of well abandonment activities.

Abstract: A system for measuring and verifying energy savings resulting from energy conservation measures in a building includes one or more energy meters and a controller. The energy meters are configured to measure an actual amount of building energy usage The controller is configured to determine an actual amount of energy savings resulting from the energy conservation measures during the measurement and verification period and to calculate a least amount of energy savings resulting from the energy conservation measures. The least amount of energy savings is a lower confidence bound on the actual amount of energy savings. The controller is configured to cause a building management system for the building to stop performing a measurement and verification process before a normal end of the measurement and verification period in response to the least amount being greater than a target amount of energy savings to be achieved by the energy conservation measures.

Abstract: A system for incentivizing travel patterns to reduce traffic congestion includes a negotiator that receives a travel template from a traveler, transmits a set of journey options to the traveler, receives a journey selected from the journey options, and sends a journey contract to the traveler based on the selected journey, a journey generator that determines the set of journey options based on the travel template, the traveler's historical behavior, and current network conditions, a rewards engine that calculates the reward associated with each journey option based on a reduction in cost for the journey, a location arbitrator that receives location information from the traveler as the travelers performs the journey in the journey contract, and a verification engine that verifies, whether the traveler's journey complied the terms of the journey contract, and determines the traveler's reward as calculated by the rewards engine based on a degree of compliance with the contract.

Abstract: Methods and systems for fulfillment gateway are described. In one embodiment, a prescription order for a prescription drug is received from an order processing station. An order message associated with the prescription order is generated. The order message has a prescription parameter and a dispensation preference for fulfilling the prescription order. The order message is assigned to an order fulfillment station based on the prescription parameter, the dispensation preference and a dispensary attribute of the order fulfillment station. In other embodiments, the order message is selected for delivery based on based on the prescription parameter, the dispensation preference and a dispensary attribute of the order fulfillment station. Additional methods and systems are disclosed.

Abstract: The present disclosure relates to an automated system for regulating the allocation of resources, or the dissemination of information within a healthcare facility. The automated system includes a context providing system capable of determining the state of a parameter and a facilities management system in communication with the context providing system. An integration protocol is configured to facilitate communication between the context providing system and the facilities management system and the facilities management system allocates resources or disseminates information based upon the value of the parameter provided by the context providing system.

Abstract: A method for using a health information exchange system which stores patient record data regarding a multiplicity of patients, to serve a first plurality of EMRs each interacting with an EMR community including a set of at least one EMR, the method comprising: for each individual EMR within the first plurality of EMRs, performing a computerized context interception process using a processor to intercept context from the individual EMR and to identify there within an event whereby a health provider using the individual EMR calls up an individual patient's record from said individual EMR; and responsive to identification of the event, using a computerized output device for providing patient record data, pertaining to the individual patient, to the health provider.

Abstract: An information processing apparatus for determining a placement of an image capturing apparatus capable of accurately measuring the position and orientation of an object through model fitting includes a holding unit that holds a 3D model representing a 3D shape of the object, a generating unit that generates candidates of the position and orientation of the image capturing apparatus relative to the object, an evaluating unit that evaluates the candidates of the position and orientation of the image capturing apparatus relative to the object based on a result of matching between data that virtually generates the object observed when the image capturing apparatus is placed in the position and orientation generated by the generating unit and the 3D model, and a determining unit that determines the position and orientation of the image capturing apparatus relative to the object based on the result of evaluation performed by the evaluating unit.

Abstract: A method that incorporates teachings of the present disclosure may include embedding a watermark in media content for presentation at a rendering device using an editor to associate the watermark with one or more metadata pointers that point to additional media content according to an embedded link of the watermark to generate a group of one or more metadata pointers where the watermark includes an embedded link to additional media content used to modify the media content based on a content exchange between the rendering device and a computer. The method may further include storing the group of one or more metadata pointers, where a selection of the watermark invokes access to the altered media content containing the additional media content associated with the watermark, thereby producing the altered media content at the one or more user devices. Other embodiments are disclosed.

Abstract: A memory stores first video information displayed on a display screen. A processor generates embedded information varying temporally and superimposes the embedded information on an image part at least corresponding to an edge of the display screen in the first video information so as to generate second video information on which the embedded information is superimposed. An output interface outputs the second video information.

Abstract: A method for capturing an image of a traffic sign by an image sensor is disclosed. The method may include capturing, by the image sensor, at least one image including the traffic sign, wherein the image sensor is mounted in a vehicle. The method may include detecting, by a processor, the traffic sign in the at least one image. The method may also include in response to detecting the traffic sign, determining, by the processor, at least one direction of the image sensor based on the at least one image and motion of the vehicle. In addition, the method may include adjusting, by the processor, the image sensor to the at least one direction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a data entity that causes a processing unit to process a computational graph. In one aspect, method includes the actions of receiving data identifying a computational graph, the computational graph including a plurality of nodes representing operations; obtaining compilation artifacts for processing the computational graph on a processing unit; and generating a data entity from the compilation artifacts, wherein the data entity, when invoked, causes the processing unit to process the computational graph by executing the operations represented by the plurality of nodes.

Abstract: One embodiment provides for a general-purpose graphics processing unit comprising multiple processing units and a pipeline manager to distribute a thread group to the multiple processing units, wherein the pipeline manager is to distribute the thread group as multiple thread sub-groups.

Abstract: Embodiments relate to a configurable convolution engine that receives configuration information to perform convolution and other deep machine learning operations on streaming input data of various formats. The convolution engine may include two convolution circuits that each generate a stream of values by applying convolution kernels to input data. The stream of values may each define multiple channels of image data. A channel merge circuit interleaves the streams of values from the convolution circuits to generate an output stream of output values. The output stream includes the data multiple channels of each input stream arranged in an interleaved manner.

Abstract: Techniques are provided for implementing a graphics processing unit (GPU) service platform that is configured to provide topology aware grouping and provisioning of GPU resources for GPU-as-a-Service. A GPU server node receives a service request from a client system for GPU processing services provided by the GPU server node, wherein the GPU server node comprises a plurality of GPU devices. The GPU server node accesses a performance metrics data structure which comprises performance metrics associated with an interconnect topology of the GPU devices and hardware components of the GPU sever node. The GPU server node dynamically forms a group of GPU devices of the GPU server node based on the performance metrics of the accessed data structure, and provisions the dynamically formed group of GPU devices to the client system to handle the service request.

Abstract: A mechanism is described for facilitating dynamic merging of atomic operations in computing devices. A method of embodiments, as described herein, includes facilitating detecting atomic messages and a plurality of slot addresses. The method further includes comparing one or more slot addresses of the plurality of slot addresses with other slot addresses of the plurality of slot addresses to seek one or more matched slot addresses, where the one or more matched slot addresses are merged into one or more merged groups. The method may further include generating one or more merged atomic operations based on and corresponding to the one or more merged groups.

Abstract: An image processing device that transforms an image includes a storage unit configured to store coordinate values in a coordinate system of a pre-transformed image, each of the coordinate value corresponding to a grid point in a coordinate system of a transformed image, a selection unit configured to select a grid point in the vicinity of a target pixel in the transformed image, a calculation unit configured to refer to the pre-transformed coordinate value, corresponding to the selected grid point and stored in the storage unit, and to calculate a pre-transformed coordinate value corresponding to the target pixel, using the referred coordinate value, and an output unit configured to output a pixel value of the coordinate value calculated in the pre-transformed image, as a pixel value of the target pixel in the transformed image.

Abstract: An image processor inputs a first image and outputs a downscaled second image by upscaling the second image to a third image, wherein the third image is substantially the same size as the first image size with a third resolution, associating pixels in the second image with a corresponding group of pixels from the third set of pixels, sampling a first image area at a first location of the first set of pixels to generate a first image sample, sampling a second image area of the third set of pixels to generate a second image sample, measuring similarity between the image areas, generating a perceptual image value, recursively adjusting values of third set of pixels until the image perception value matches a perceptual standard value, and adjusting pixel values in the second image to a representative pixel value of each of the corresponding group of pixels.

Abstract: An image processing method is provided, including obtaining an input image, generating a distance field image including distance values by calculating each of the distance values respectively corresponding to pixels of the obtained input image, and enlarging the input image using the generated distance field image, wherein the generating of the distance field image includes, with respect to each pixel of the input image, determining each pixel as a center pixel and determining pixels at a constant distance away from the center pixel as reference pixels, calculating a shortest distance from among distances between the center pixel and reference pixels indicating an edge among the reference pixels, and determining the calculated shortest distance as a distance value corresponding to each pixel.

Abstract: A method for generating a plurality of vector images with specified dimensions includes: storing a composite image comprised of one or more base vector graphics images; receiving a data file from an external computing system, wherein the data file includes a plurality of dimensional data sets, each dimensional data set comprising at least a length and a height; parsing the received data file to identify each of the plurality of dimensional data sets and the associated length and width; generating a vector graphics image file for each of the plurality of dimensional data sets, wherein the vector graphics image file comprises an image based on the stored composite image and has dimensions based on the length and height associated with the respective dimensional data set; and transmitting the generated vector graphics image file for each of the plurality of dimensional data sets to the external computing system.

Abstract: Systems and methods of enhancing the resolution of digital terrain models (DTM) for location-based applications and analyses. The DTM enhancement process takes the signature of the input image (e.g., via the input image and a noise surface file with similar characteristics as the sensor used to capture the input image) and applies it to the DTM without including large features such as buildings. The disclosed methods include utilize a process similar to that used for enhancing a DSM based on mapping the changing intensity from the image file to changes in elevation in the DSM using a regression over a local neighborhood of pixels. Further, the disclosed methods do not rely on information about the sensors and are extendable to be able to utilize any types of images. Additionally, the disclosed embodiments are sensor agnostic and can be applied on any type of image collected by any type of sensor.

Abstract: Image capture systems and methods may include one or more video capture devices capable of capturing one or more video frames. The video frames may include geographic position data and orientation data associated therewith, and may be stored on one or more non-transient computer readable medium. The computer system may marshal each video frame to one or more processors from a bank of processors for geo-referencing and overlaying of geographic information system (GIS) data on the video frames in real time.

Abstract: A method for normalizing an image by an electronic device is described. The method includes obtaining an image including a target object. The method also includes determining a set of windows of the image. The method further includes, for each window of the set of windows of the image, predicting parameters of an illumination normalization model adapted to the window using a first convolutional neural network (CNN), and applying the illumination normalization model to the window to produce a normalized window.

Abstract: There is provided a method for transforming convolutional layers of a CNN including m convolutional blocks to optimize CNN parameter quantization to be used for mobile devices, compact networks, and the like with high precision via hardware optimization. The method includes steps of: a computing device (a) generating k-th quantization loss values by referring to k-th initial weights of a k-th initial convolutional layer included in a k-th convolutional block, a (k?1)-th feature map outputted from the (k?1)-th convolutional block, and each of k-th scaling parameters; (b) determining each of k-th optimized scaling parameters by referring to the k-th quantization loss values; (c) generating a k-th scaling layer and a k-th inverse scaling layer by referring to the k-th optimized scaling parameters; and (d) transforming the k-th initial convolutional layer into a k-th integrated convolutional layer by using the k-th scaling layer and the (k?1)-th inverse scaling layer.

Abstract: An image processing apparatus includes an edge detecting unit, a rectangular object detecting unit, and an arrangement processing unit. The edge detecting unit is configured to (a) search each target line in a page image that includes plural rectangular objects for edges of the plural rectangular objects, and (b) detect the edges of the plural objects on the target line on the basis of density variation between pixels in the target line. The rectangular object detecting unit is configured to (a) detect the plural rectangular objects on the basis of the detected edges, and (b) determine respective positions, respective sizes and respective tilt angles of the plural rectangular objects. The arrangement processing unit is configured to rotate areas of the plural rectangular objects specified by the determined positions, the determined sizes and the determined tilted angles by angles corresponding to the tilted angles, respectively.

Abstract: A method and apparatus for determining an auto white balance (AWB) gain based on determined depth information. The method may include receiving an image captured by an image sensor, determining depth information associated with the captured image, assigning weights to a plurality of illuminants based on the determined depth information, determining an auto white balance gain based on the assigned weights and statistics of the captured image, and applying the auto white balance gain to the captured image.

Abstract: An image processing unit performs gamma correction on a video signal using a gamma characteristic selected from among a plurality of gamma characteristics. Further, in a case where a gamma characteristic used in the gamma correction is changed by selection of the gamma characteristic, the image processing unit calculates a contour correction characteristic corresponding to the changed gamma characteristic and performs contour correction using the contour correction characteristic on the video signal.

Abstract: An image processing device includes at least one processor that acquires a plurality of viewpoint images, and selectively applies a plurality of different image processings to image data based on the plurality of viewpoint images. The plurality of different image processings includes an adjustment process of adjusting a perceived resolution of an image, the adjustment process including a shift synthesis process of relatively shifting the plurality of viewpoint images to synthesize the plurality of viewpoint images that are relatively shifted, and a viewpoint change process of changing a viewpoint by changing a weighting coefficient when the plurality of viewpoint images are synthesized. In addition, the at least one processor sets the image processing by the image processing unit, exclusively setting one of the plurality of different image processings and a parameter of the image processing set by the setting unit to be applied to the image data.

Abstract: Embodiments of the present application provide image processing methods and apparatus. A image processing method disclosed herein comprises: acquiring, from an image, two regions which have a textural similarity higher than a first value and have different depths; performing frequency-domain conversion on each of the regions, to obtain a frequency-domain signal of each region; and optimizing the image at least according to the frequency-domain signal of each region, the depth of each region and a focusing distance of the image.

Abstract: A method for image de-blurring includes estimating an intermediate image L by marking and constraining an edge region and a smooth region in an input image; estimating a blur kernel k by extracting salient edges from the intermediate image L, wherein the salient edges have scales greater than those of the blur kernel k; and restoring the input image to a clear image by performing non-blind deconvolution on the input image and the estimated blur kernel k. Imposing constraints on the edge region and the smooth region allows the intermediate image to maintain the edge while effectively removing noise and ringing artifacts in the smooth region. The use of the salient edges in the intermediate image L enables more accurate blur kernel estimation. Performing non-blind deconvolution on the input image and the estimated blur kernel k restores the input image to a clear image achieving desired de-blurring effect.

Abstract: According to an aspect of the present disclosure, there is provided a method of image processing. The method comprises receiving image data. Image processing is applied to the image data, whereby to produce a processed image. The method then comprises producing consistency data associated with the image processing, wherein the consistency data is indicative of a consistency of at least one region of the processed image with the received image data. Both the processed image and the consistency data are used as inputs to a decision process of a computer vision system.

Abstract: A system for background image subtraction includes a computing device coupled with a 3D video camera, a processor of the device programmed to receive a video feed from the camera containing images of one or more subject that include depth information. The processor, for an image: segments pixels and corresponding depth information to identify foreground regions associated with a target user.

Abstract: A system, method, and computer program product are provided for automatically generating a wafer image to design coordinate mapping. In use, a design of a wafer is received by a computer processor. In addition, an image of a wafer fabricated from the design is received by the computer processor. Further, a coordinate mapping between the design and the image is automatically generated by the computer processor.

Abstract: At a first timing when a tightening machine temporarily tightens a bolt, a distance sensor acquires a first distance image. A distance sensor controller measures a first recess amount of the head of the bolt at the first timing by the first distance image. A manipulator controller is configured to change a relative posture of an image sensor relative to the head of the bolt in accordance with a rotation angle by which the bolt is rotated from the first timing to a second timing. The distance sensor acquires a second distance image at the second timing, and the distance sensor controller measures a second recess amount of the head of the bolt at the second timing by the second distance image, so as to measure an axial tension of the bolt by use of a difference between the first recess amount and the second recess amount.

Abstract: A method includes: displaying a first image of a first assembly unit within a user interface; locating a first virtual origin at a first feature on the first assembly unit; displaying a first subregion of the first image within the user interface responsive to a change in a view window of the first image; recording a geometry and a position of the first subregion relative to the first virtual origin; locating a second virtual origin at a second feature—analogous to the first feature—on a second assembly unit represented in the second image; projecting the geometry and the position of the first subregion onto the second image according to the second virtual origin to define a second subregion of the second image; and, in response to receipt of a command to advance from the first image to the second image, displaying the second subregion within the user interface.

Abstract: A metrology system for obtaining a measurement representative of a thickness of a layer on a substrate includes a camera positioned to capture a color image of at least a portion of the substrate. A controller is configured to receive the color image from the camera, store a predetermined path in a coordinate space of at least two dimension including a first color channel and a second color channel, store a function that provides a value representative of a thickness as a function of a position on the predetermined path, determine a coordinate of a pixel in the coordinate space from color data in the color image for the pixel, determine a position of a point on the predetermined path that is closest to the coordinate of the pixel, and calculate a value representative of a thickness from the function and the position of the point on the predetermined path.

Abstract: The invention relates to a method for measuring a dental object (1) using a dental camera (2). During measurement, several optical three-dimensional images (3, 50, 51) of the object (1) are produced. During measurement, an acoustic sound (10, 12) is generated by means of a sound producer (9, 11), said sound (10, 12) being used as feedback for the user and information relating to the current status of a recording of the images (3, 50, 51) and/or relating to image requirements of the dental camera (2) are transmitted to the user. Then, each individual image (3, 50, 51) it is automatically checked by a computer (6) as to whether an overlapping area (7, 8) between the images (3, 50, 51) which are to be combined meets the defined recording requirements for a correct recording.

Abstract: A method of evaluating a surgical margin of tumor tissues of a living subject includes acquiring images of a specimen of the tumor tissues; calculating a three-dimensional (3D) morphological surface of the specimen from the acquired images and displaying the 3D morphological surface; obtaining, from the 3D morphological surface, a plurality of specimen locations to cover a surface of the specimen; acquiring optical data at each specimen location; evaluating a margin status of the specimen at each specimen location to either positive or negative based on the acquired optical data; and displaying the margin status of the specimen on the 3D morphological surface of the specimen with morphological orientations.

Abstract: An information processing apparatus includes a processor and a memory containing instructions that cause the processor to perform operations. The operations include obtaining a group of candidates of corresponding points which are pairs of feature points in a first space and feature points in a second space, calculating a plurality of displacement fields under a plurality of different regularization conditions based on the candidate group, calculating a feature point group which has been subjected to a plurality of displacements by displacing the feature points in the first space by the plurality of displacement fields, and calculating matching degrees of the corresponding points included in the candidate group in accordance with the feature point group which has been subjected to the plurality of displacements.