Abstract: A context-based object classifying model is applied to a set of object location representations (12, 14), derived from an object detection applied to a frame (10) of a video stream, to obtain a context-adapted classification probability for each object location representation (12, 14). Each object location representation (12, 14) defines a region of the frame (10) and each context-adapted classification probability represents a likelihood that the region comprises an object (11, 13). The model is generated based on object location representations from previous frames of the video stream. It is determined whether the region defined by the object location representation (12, 14) comprises an object (11, 13) based on the context-adapted classification probability and a detection probability. The detection probability is derived from the object detection and represents a likelihood that the region defined by the object location representation (12, 14) comprises an object (11, 13).

Abstract: This application discloses a multimedia resource matching method performed at a computing device. The method includes: searching a first media resource set among a multimedia resource set, first target image frames of all media resources in the first media resource set meeting a target condition, and features of the first target image frames matching features in image frames of a to-be-matched multimedia resource according to a first matching condition; determining, among the first target image frames, second target image frames whose features match the features in the image frames of the to-be-matched multimedia resource according to a second matching condition; and obtaining matching information of the second target image frames and an identifier of a target media resource among the multimedia resource set, the matching information being used for indicating a total duration and a playback moment of the second target frame image in the target media resource.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive structural analysis. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform digital document analysis using at least one of spatial fingerprint document image pair distance measures for document image pairs, object fingerprint document image pair distance measures for document image pairs, and semantic fingerprint document image pair distance measures for document image pairs.

Abstract: A distributed learning method of a server managing an ID card recognition model includes releasing an ID card recognition model performing at least one convolution operation on an ID card image captured in a user terminal so that the user terminal uses the ID card recognition model, receiving update information of the ID card recognition model generated according to an ID card recognition result of the released ID card recognition model, and verifying the update information received from the user terminal and updating the ID card recognition model using the verified update information.

Abstract: To the standard operations of an inverted index database, a new “To” operator is added. The “To” operator treats the standard single-level linear collection of records as being organized into localized clusters. Techniques for hierarchical clusters are presented. During indexing, hierarchical clusters are serialized according to a uniform visitation procedure. Serialization produces bit maps, one for each hierarchical level, that preserve the hierarchical level of each record and its location in the serialization sequence. For non-hierarchical clusters, byte maps can be produced. The “To” operator accepts a list of records, each at a same hierarchical level in a cluster, and a specification of a hierarchical level that all the input records should be converted into. The “To” operator outputs a list of records, representing a conversion of the input records to the specified new level. Logical Forms, against which frame extraction rules match, can be stored in hierarchical clusters.

Abstract: The present disclosure is generally directed to systems and methods for executing optical character recognition faster than at least some traditional OCR systems, without sacrificing recognition accuracy. Towards this end, various exemplary embodiments involve the use of a bounding box and a grid-based template to identify certain unique aspects of each of various characters and/or numerals. For example, in one embodiment, the grid-based template can be used to recognize a numeral and/or a character based on a difference in centerline height between the numeral and the character when a monospaced font is used. In another exemplary embodiment, the grid-based template can be used to recognize an individual digit among a plurality of digits based on certain parts of the individual digit being uniquely located in specific portions of the grid-based template.

Abstract: The various embodiments described herein include methods, devices, and systems for imaging identification information. In one aspect, a video stream of a credential document is obtained via a camera. It is determined whether the video stream of the credential document meets one or more imaging criteria. In accordance with a determination that the imaging criteria are not satisfied, a first indication that the credential document is not ready to be imaged is presented. In accordance with a determination that the imaging criteria are satisfied a second indication that the credential document is ready to be imaged is presented.

Abstract: Methods for composition aware image search refinement using relevance feedback. A method includes receiving, in response to user input, a relevance area within a plurality of image results, wherein the plurality of image results are provided for display on a user interface in response to a first search query using a plurality of spatial anchors in association with respective semantic datasets, and wherein the relevance area is associated with a target semantic dataset. The method also includes determining a mapping from the target semantic dataset to the plurality of spatial anchors, adjusting, based on the mapping, the semantic datasets associated with the plurality of spatial anchors, and providing for display, in the user interface, a plurality of refined image results in response to a second search query using the plurality of spatial anchors in association with the adjusted semantic datasets.

Abstract: The disclosure relates to a method and to an image processing facility configured to carry out the method for the segmentation of image data of a target object. In the method, a first segmentation is generated by a trained algorithm. Furthermore, a statistical shape and appearance model is provided, which is trained on corresponding target objects. An interference region is further determined, in which the image data is impaired by an image artifact. A final segmentation of the image data is then generated by adjusting the shape and appearance model to the respective target object outside the interference region and using the first segmentation in the interference region.

Abstract: This disclosure describes techniques that include generating, based on a description of a scene, a movie or animation that represents at least one possible version of a story corresponding to the description of the scene. This disclosure also describes techniques for training a machine learning model to generate predefined data structures from textual information, visual information, and/or other information about a story, an event, a scene, or a sequence of events or scenes within a story. This disclosure also describes techniques for using GANs to generate, from input, an animation of motion (e.g., an animation or a video clip). This disclosure also describes techniques for implementing an explainable artificial intelligence system that may provide end users with information (e.g., through a user interface) that enables an understanding of at least some of the decisions made by the AI system.

Abstract: In a system in which a first electronic device, a server, and a second electronic device wirelessly communicate with each other, the first electronic device may detect object information associated with at least one object from a video being captured and may transmit the object information to the server, the server may identify a location of the object based on the object information and may transmit service information associated with the location of the object to the second electronic device, and the second electronic device may provide the service information to a user.

Abstract: A medical image processing apparatus according to an embodiment includes a processing circuit. The processing circuit specifies teaching data used for generation of a learned model. The processing circuit performs image analysis with respect to pieces of collected medical image data. The processing circuit extracts medical image data having an attribute common to the teaching data of the learned model from the pieces of medical image data based on an analysis result of the image analysis, as a candidate of the teaching data of the learned model.

Abstract: The present disclosure relates to the technical field of terminals, and particularly relates to a method and device for terminal-based object recognition, and an electronic device. The method includes: receiving a function instruction for simulated magnifier input to a terminal by a user; activating a camera of the terminal according to the function instruction for simulated magnifier; determining an object to be recognized based on an object photographed by the camera; acquiring a physical distance between the object to be recognized and the camera, and acquiring a preset focal length corresponding to the physical distance; generating, according to the preset focal length, a first image corresponding to the object to be recognized, and displaying the first image; performing image processing and image recognition on the first image; and displaying information of the object to be recognized at the terminal according to a result of image processing and image recognition.

Abstract: A system for facilitating lesion analysis accesses a first data structure comprising a plurality of entries including anatomic location information and annotation information associated with a plurality of lesions represented in a first set of cross-sectional images. The system displays a respective representation of each of the plurality of entries and presents a second set of cross-sectional images. The system receives user input triggering selection of a particular entry of the plurality of entries of the first data structure.

Abstract: A method for verifying authenticity of a physical document includes receiving an image of a physical document to be authenticated including the physical document and a background. A pre-processed image is produced that includes the physical document separated from the background. The producing includes separating the physical document from the background by semantic segmentation utilizing an artificial neural network trained using an augmented dataset generated by applying geometric transformations over different backgrounds. Features of the pre-processed image are extracted to determine a document type. In response to determining the document type of the physical document, the method includes verifying, utilizing a machine learning classifier, whether the physical document is authentic based on the extracted features relative to expected features for the corresponding document type. An indication of whether the physical document is authentic based on the verifying is generated.

Abstract: A universal color coding system, and a system and a method of manipulating colors using such color coding system. The color coding system includes a color mapper arranged to map a plurality of colors with a plurality of numerical codes, wherein the each of the plurality of numerical codes is a unique integer determined based on a combination of prime numbers.

Abstract: The present invention relates to the identification of regions of interest in medical images. More particularly, the present invention relates to the identification of regions of interest in medical images based on encoding and/or classification methods trained on multiple types of medical imaging data. Aspects and/or embodiments seek to provide a method for training an encoder and/or classifier based on multimodal data inputs in order to classify regions of interest in medical images based on a single modality of data input source.

Abstract: A similar picture identification method is described. According to the method, processing circuitry of a device obtains n first local regions of a first picture, the n first local regions being a first set of regions that is affine invariant, and obtains m second local regions of a second picture, the m second local regions being a second set of regions that is affine invariant. The processing circuitry obtains n first characteristic values respectively corresponding to the n first local regions, and obtains m second characteristic values respectively corresponding to the m second local regions. The processing circuitry further determines, according to a comparison result of the n first characteristic values and the m second characteristic values, whether the first picture is similar to the second picture, where n and m are positive integers.

Abstract: An information processing apparatus includes a first character recognition section that performs character recognition of an input image on an assumption that a character in the input image belongs to a first character type and outputs a first character recognition result being a result of the character recognition, a second character recognition section that performs character recognition of the input image on an assumption that the character in the input image belongs to a second character type and outputs a second character recognition section being a result of the character recognition, the second character type being a set obtained by adding at least one or more characters which do not belong to the first character type to a set of characters belonging to the first character type, and a matching section that performs matching of the first character recognition result with the second character recognition result, and, in a case where it is found that the first character recognition result does not match w

Abstract: A computer-based diagnostic system includes an image generation unit adapted to generate tomographic images of a patient's organ; a deep machine learning unit configured to process generated tomographic images of the patient's organ to classify organ regions of diseased functional tissue of the patient's organ as belonging to one of a set of abnormal image patterns using trained deep neural networks; and a clinical decision support unit adapted to process classification results of the deep machine learning unit to calculate a diagnostic result output via an interface of the clinical decision support unit.

Abstract: An image forming apparatus that determines whether an image having coincidence with a registered image is included in an input image and controls execution of a job that uses the input image based on a result of the determination. The image forming apparatus includes an input unit that inputs a first image as a candidate of the registered image, an evaluation unit that evaluates whether the first image is suitable for use in the determination, and a control unit registers the first image as the registered image if the evaluation unit evaluates that the first image is suitable for use in the determination, and prevents the first image from being registered as the registered image if the evaluation unit evaluates that the first image is unsuitable for use in the determination.

Abstract: In various implementations, specific attributes found in images can be used in a visual-based search. Utilizing machine learning, deep neural networks, and other computer vision techniques, attributes of images, such as color, composition, font, style, and texture can be extracted from a given image. A user can then select a specific attribute from a sample image the user is searching for and the search can be refined to focus on that specific attribute from the sample image. In some embodiments, the search includes specific attributes from more than one image.

Abstract: The various embodiments described herein include methods, devices, and systems for imaging identification information. In one aspect, a video stream of a credential document is obtained via a camera. It is determined whether the video stream of the credential document meets one or more imaging criteria. In accordance with a determination that the imaging criteria are not satisfied, a first indication that the credential document is not ready to be imaged is presented. In accordance with a determination that the imaging criteria are satisfied a second indication that the credential document is ready to be imaged is presented.

Abstract: A contemporary image is stored, is analyzed, and an associated data structure is generated. An image data structure may include image meta data, image classification data, image segment data, image caption data, or the like. The storage of the contemporary image is used as a triggering event and its data structure is used as an input to determine contextually relevant ancestral images. The contemporary image data structure is compared to respective data structures of ancestral images. A series of ancestral images are ranked based upon contextual similarly of their data structures to the contemporary image data structure. The most similar ancestral image is simultaneously displayed with the contemporary image. Interactions may be monitored, a prompt may be provided, a next ranked ancestral image may be displayed in place of the previous ancestral image, and/or a prompt to store a new contemporary image may be provided.

Abstract: Described herein is a system for automatically capturing images. A device may execute an application on the device. In response to receiving a request for capturing an image of a document, the application may control the operation of the camera to contemporaneously and continuously capture image frames of an area within the field of view of a camera of the device. The field of view may include an object and in turn may be included in the captured image frames. The application may determine whether the aspect ratio and real-world size of the object in the captured image frames corresponds with a specified threshold size and aspect ratio which corresponds with a given document type. In response to determining the object corresponds to the given document type, the camera may automatically extract an image of the object.

Abstract: An information retrieval system and method are presented. A template is retrieved from a template repository. The template repository stores a plurality of templates. Each of the plurality of templates includes a concept and a relationship from a knowledge model. The knowledge model defines a plurality of entities and interrelationships between one or more of the plurality of entities. The plurality of entities include concepts and instances. The template is transmitted to a client computer, and a statement is received from the client computer. The statement includes an instantiation of the template. A knowledge base is queried using the statement to generate a result listing identifying an item in the knowledge base. The knowledge base identifies a plurality of items. Each of the plurality of items is associated with at least one annotation identifying at one of the entities in the knowledge model.

Abstract: The various embodiments described herein include methods, devices, and systems for imaging identification information. In one aspect, a method of acquiring an image of a credential document is performed at a client device having a camera and a display. The method includes: (1) obtaining, via a user interface, information regarding a type of the credential document to be imaged; (2) obtaining a video stream of the credential document via the camera; (3) determining whether the video stream of the credential document meets one or more imaging criteria; (4) determining whether the credential document in the video stream has a credential document type that matches the obtained type of the credential document; and (5) in accordance with a determination that the imaging criteria are satisfied and that the credential document in the video stream does has a credential document type that matches the obtained type of the credential document, automatically capturing an image of the credential document.

Abstract: A memory control circuit includes an input circuit that receives data to be written to a storage having multiple nonvolatile memory cells, and a control circuit, when a second number of bits that are included in a first bit string and having a first number of bits and have a second logical value different from a first logical value equal to initial values stored in the multiple nonvolatile memory cells is equal to or smaller than a first threshold, writes the first bit string and the first additional value to the storage, and that associates, when the second number of the bits is larger than a second threshold larger than the first threshold, a second bit string obtained by reversing logical values of all the bits of the first bit string with a second additional value and writes the second bit string and the second additional value to the storage.

Abstract: A method, system, and computer program product of detecting defects in an object using a processor operatively connected to a memory, the method comprising: accommodating in the memory an image group comprising a reference image and an image; generating a set of correction parameters to be applied to pixels of an image from the image group, wherein the parameters are determined to minimize a combination of a first factor indicative of variability of the set, and a second factor indicative of a difference between an image from the image group as enhanced by applying the set and another image in the image group, wherein the combination increases as any factor increases; applying the set to the image of the image group to obtain an enhanced image; generating an optimal difference image between the enhanced image and the other image; and using the optimal difference image for detecting defect candidates.

Abstract: An apparatus includes a first acquisition unit configured to acquire main object information specifying a main object in generation of a layout image, a second acquisition unit configured to acquire object correlation information specifying an object having a correlation with the main object, an extraction unit configured to extract at least one image including the main object and at least one image including the object having the correlation with the main object from a plurality of images based on the acquired main object information and the acquired object correlation information acquired, and a generation unit configured to generate, using a layout template, a layout image in which the at least one image extracted by the extraction unit and including the main object and the at least one image extracted by the extraction unit and including the object having the correlation with the main object are laid out therein.

Abstract: Disclosed embodiments generally relate to logically describing and modeling the layout of an output (e.g., a document or a presentation) by capturing author intent. Author intent can be captured based on the author's selection of visual exemplars (e.g., lists, grids, collages, etc.) with which to express content. Each visual exemplar identifies one or more semantic expressions (e.g., specific, often implied, relationships that are represented in visual exemplars of content) that are represented by those visual exemplars. The identified semantic expressions form a contract that can be observed in any generated output. The output can be formatted and laid out in a variety of different ways (e.g., for a variety of different presentation devices) to provide aesthetic and semantic efficiency in the generated output while maintaining the intent of the author.

Abstract: A method for processing change-of-address (COA) forms. The method includes capturing a first image of a first COA form. The method includes assigning a unique identifier to the first COA form and associating the unique identifier with the first image data. The method includes transmitting the first image data and the unique identifier to a cloud computing system. The cloud computing system performs an optical-character-recognition process on the first image data to produce name and address data including both an old address and a new address, validates the name and address data, and stores the name and address data in a change of address database.

Abstract: This disclosure concerns the determination of electronic multispectral or hyperspectral images, such as by a processor in a camera. The processor receives first image sensor signals that are associated with a first wavelength and with multiple first imaging elements at respective first imaging element locations. The processor determines a spline approximation to the first image sensor signals across the first imaging element locations and determines the multispectral or hyperspectral image data by interpolating the spline approximation at the pixel location. Finally, the image data is stored on a data store. Using splines to interpolate the image sensor signals outperforms other methods, which means increased image quality due to more accurate interpolation. More specifically, using splines leads to a more accurate spectrum at each point and reduced spectral error compared to other methods.

Abstract: A method of extracting an image of a port wharf through multispectral interpretation includes: first, extracting a blurred coastline by assigning values to grayscale values; then, performing a smoothing and noise removal processing on a remote sensing image in a targeted area to extract edge information; sequentially, establishing a multispectral database of a targeted port wharf; and extracting a port wharf using a projected eigenvector, performing an MAF transformation on the regularized kernel function again, projecting multivariate observed values to original eigenvectors, and identifying a remote sensing image area corresponding to the original eigenvector smaller than a transformation variance as a port wharf to be extracted, and then carrying out a validation operation.

Abstract: An example method for verifying identity information includes: receiving image information transmitted and rendered by a client; extracting feature information from the image information; matching the feature information with the feature determination information collected in advance; the feature determination information having associated identity information; determining whether the client fits with the identity information when the match is successful. The example embodiment of the present disclosure identifies a user on the basis of the uniqueness of the image information rendered by different client environments and clients, ensuring the accuracy of identification of user identity information, meanwhile avoiding the problem that the user identity information cannot be identified due to the shutdown of Cookie by clients, and raising the success rate of identification of identity information.

Abstract: A method for providing encrypted information by an information entity to one or more operating entities, the information entity having a database for storing encrypted information and the one or more operating entities being configured to operate on the encrypted information, wherein the encrypted information is stored encrypted with an encryption key known to the one or more operating entities includes performing, by an operating entity, a request on the encrypted information, wherein plaintext information to be stored encrypted is provided in tuples, each having ID information, one or more fields with field information specifying the fields, and values, wherein at least the values are encrypted with non-deterministic order preserving encryption with at least one encryption key such that each plaintext value is encrypted into a set of encrypted values, and wherein the set of encrypted values is partitioned into a left set and a right set.

Abstract: A device, apparatus, and method provide logic for processing information. In one implementation, a device may include an image acquisition unit configured to acquire an image, and a transmission unit configured to transmit information associated with the image to an information processing apparatus, such as a server. The server may be associated with a first feature quantity dictionary. The device also may include a receiving unit configured to receive a second feature quantity dictionary from the server in response to the transmission. The second feature quantity dictionary may include less information than the first feature quantity dictionary, and the server may generate the second feature quantity dictionary based on the image information and the first feature quantity dictionary. The device may include an identification unit configured to identify an object within the image using the second feature quantity dictionary.

Abstract: The various embodiments described herein include methods, devices, and systems for imaging identification information. In one aspect, a method is performed at a client device having a camera and a display. The method includes: (1) obtaining information regarding a type of a document to be imaged; (2) obtaining a video stream of the document; (3) determining whether the video stream of the document meets one or more imaging criteria; (4) determining whether the document in the video stream has a document type that matches the obtained type; (5) if the imaging criteria are not satisfied or the credential document does not have a matching credential document type, presenting an indication that the document is not ready to be imaged; and (6) if the imaging criteria are satisfied and the document has a matching credential document type, presenting an indication that the document is ready to be imaged.

Abstract: A system for generating a disparity map includes: an image obtainer obtaining a left image and a right image; a matching cost calculator calculating a matching cost for each of a plurality of pixels of the left image and the right image; an accumulation and summation calculator calculating an accumulation value of one of the pixels based on the calculated matching cost, and calculating a relaxation accumulation value, which is an average of values obtained by multiplying each of relation coefficients between a disparity value of the one pixel and disparity values of surrounding pixels of the one pixel with the accumulation value of the one pixel; a disparity value deliver deriving a disparity value for each of the pixels based on the calculated relaxation accumulation value; and a disparity map generator generating the disparity map based on the derived disparity value.

Abstract: A set of trigrams can be generated for each document in a plurality of documents processed by an e-discovery system. Each trigram in the set of trigrams for a given document is a sequence of three terms in the given document. A set of trigrams for each similar document is then determined based on the set of trigrams for the original document. To facilitate identification of the similar documents, a full text index is then generated for the plurality of documents and the set of trigrams for each document are indexed into the full text index, as individual terms. Queries can be generated into the full text index based on trigrams of a document to determine other similar or near-duplicate documents. After a set of potentially similar documents are identified, a separate distance criteria can be applied to evaluate the level of similarity between the two documents in an efficient way.

Abstract: Methods and apparatus for determining whether query templates that have the same entity collection identifier are semantically equivalent query templates based on determining a similarity measure between the query templates. The similarity measure may be based on various factors. For example, in some implementations the similarity measure may be based on a number of the entities of the entity collection that instantiate both of the query templates in a record of past user queries. Also, for example, in some implementations the similarity measure may be based on a number of the entities of the entity collection that instantiate both of the query templates in a record of past user queries and are determined to be entities that satisfy a threshold level of entity similarity between the query templates. In some implementations, terms of two query templates that are determined to be equivalent may be determined to be synonymous.

Abstract: In a method and system for identifying objects in an image, an image and training data are received. The training data identifies a pixel associated with an object of a particular type in the image. A plurality of filtered versions of the image are developed. The training data and the plurality of filtered versions of the image are processed to develop a trained model for classifying pixels associated with objects of the particular type. The trained model is applied to the image to identify pixels associated a plurality of objects of the particular type in the image. Additional image processing steps are developed to further refine the identified pixels for better fitting of the contour of the objects with their edges.

Abstract: A computer-implemented method for predicting answers to questions concerning medical image analytics reports includes splitting a medical image analytics report into a plurality of sentences and generating a plurality of sentence embedding vectors by applying a natural language processing framework to the plurality of sentences. A question related to subject matter included in the medical image analytics report is received and a question embedding vector is generated by applying the natural language processing framework to the question. A subset of the sentence embedding vectors most similar to the question embedding vector is identified by applying a similarity matching process to the sentence embedding vectors and the question embedding vector. A trained recurrent neural network (RNN) is used to determine a predicted answer to the question based on the subset of the sentence embedding vectors.

Abstract: Apparatus, methods, and other embodiments associated with the spectral analysis of T2 spectral data are described. One example magnetic resonance imaging (MRI) method includes accessing a data set comprising T2 spectral data associated with a magnetic resonance imaging (MRI) signal received from an object. The method also includes decomposing the T2 spectral data with multi-exponential functions to determine T2 spectra corresponding to the T2 spectral data. The T2 spectra are portioned into a plurality of intervals defined by the T2 spectral data acquired in a predetermined time period.

Abstract: In some embodiments, a device captures video data of a person in front of a display while a user interface that is associated with a noticeboard is displayed on the display, after capturing the video data, in accordance with a determination that one or more object-identification criteria are met, identifies an object in the video data that is associated with the person in front of the display, in response to identifying the object in the video data, stores an image of the object in the video data, and after storing the image of the object, in accordance with a determination that object addition criteria have been met, adds the image of the object to the noticeboard. In some embodiments, the object-identification criteria include a criterion that is met when, in the video data, a predefined spatial relationship exists between the object and the person.

Abstract: An imaging apparatus acquires an image including a still image and a moving image, tracks a position of the object within an image capturing area of the image, records a luminance change within a region of the object being tracked, detects a point having a luminance change amount equal to or greater than a threshold, as a specular reflection area, calculates an object correction value, which is a color correction value of the object, based on color information of the specular reflection area, and corrects color overlap of the image based on the object correction value.

Abstract: According to an image forming apparatus of one embodiment, a business-type-based word database classifies and stores words for each business type. A business-type-based template database stores business-type-based templates in which plural icons to respectively invoke plural functions previously set for each business type are grouped. A word extraction unit extracts a word by analyzing character information included in print data. A coincidence number count unit compares the extracted word with the words stored in the business-type-based word database, and counts a coincidence number in a comparison result for each business type. A business type determination unit determines a business type of a user transmitting the print data based on the coincidence number. A template acquisition unit acquires a template relating to the determined business type of the user from the business-type-based template database. A display unit displays the acquired template on a screen.

Abstract: There is described herein a method and system for detecting, in a segmented image, the presence and position of objects with a dimension greater than or equal to a minimum dimension. The objects exhibit a property whereby a distance map of the object at a first scale and a distance map of the object at a second scale greater than the first scale differ by a constant value over a domain of the distance map of the object at the first scale. A distance map of a model object is compared to a distance map of a target object using a similarity score that is invariant to an offset.

Abstract: To improve a search accuracy in template matching based on a coarse-to-fine search method, a first pyramid is generated by hierarchizing a plurality of template images having different resolutions from each other in order of the resolution, a second pyramid is generated by hierarchizing a plurality of search target images having different resolutions from each other corresponding to the same resolutions as the template images in the first pyramid in order of the resolution, and a search process of searching for a feature image included in the template image of the first pyramid from the search target image in the second pyramid in a hierarchy of the same resolution. When the first pyramid is generated, the number of stages of the first pyramid is set such that a size of the feature image included in each of the template images is not smaller than a previously set threshold.

Abstract: An apparatus includes a first acquisition unit configured to acquire main object information specifying a main object in generation of a layout image, a second acquisition unit configured to acquire object correlation information specifying an object having a correlation with the main object, an extraction unit configured to extract at least one image including the main object and at least one image including the object having the correlation with the main object from a plurality of images based on the acquired main object information and the acquired object correlation information acquired, and a generation unit configured to generate, using a layout template, a layout image in which the at least one image extracted by the extraction unit and including the main object and the at least one image extracted by the extraction unit and including the object having the correlation with the main object are laid out therein.