Abstract: Systems and methods for descriptor vector computation are described herein. An embodiment includes (a) identifying a plurality of regions in the digital image; (b) normalizing the regions using at least a similarity or affine transform such that the normalized regions have the same orientation and size as a pre-determined reference region; (c) generating one or more wavelets using dimensions of the reference region; (d) generating one or more dot products between each of the one or more wavelets, respectively, and the normalized regions; (e) concatenating amplitudes of the one or more dot products to generate a descriptor vector; and (f) outputting a signal corresponding to the descriptor vector.

Abstract: Methods, storage mediums, and systems for image data processing are provided. Embodiments for the methods, storage mediums, and systems include configurations to perform one or more of the following steps: background signal measurement, particle identification using classification dye emission and cluster rejection, inter-image alignment, inter-image particle correlation, fluorescence integration of reporter emission, and image plane normalization.

Abstract: A method of automatically identifying bone components in a medical image data set of voxels, the method comprising: a) applying a first set of one or more tests to accept voxels as belonging to seeds, wherein none of the tests examine an extent to which the image density has a local maximum at or near a voxel and falls steeply going away from the local maximum in both directions along an axis; b) applying a second set of one or more tests to accept seeds as bone seeds, at least one of the tests requiring at least one voxel belonging to the seed to have a local maximum in image density at or near said voxel, with the image density falling sufficiently steeply in both directions along at least one axis; and c) expanding the bone seeds into bone components by progressively identifying candidate bone voxels, adjacent to the bone seeds or to other previously identified bone voxels, as bone voxels, responsive to predetermined criteria which distinguish bone voxels from voxels of other body tissue.

Abstract: A computer-automated method for detecting a vessel in water based on an image of a portion of Earth includes generating a thermal anomaly mask. The thermal anomaly mask flags each pixel of the image initially deemed to be a wake pixel based on a comparison of a thermal value of each pixel against other thermal values of other pixels localized about each pixel. Contiguous pixels flagged by the thermal anomaly mask are grouped into pixel clusters. A shape of each of the pixel clusters is analyzed to determine whether each of the pixel clusters represents a possible vessel detection event. The possible vessel detection events are represented visually within the image.

Abstract: A method of classifying and organizing digital images utilizing optical metadata (captured using multiple sensors on the camera) may define semantically coherent image classes or annotations. The method defines optical parameters based on the physics of vision and operation of a camera to cluster related images for future search and retrieval. An image database constructed using photos taken by at least thirty different users over a six year period on four different continents was tested using algorithms to construct a hierarchal clustering model to cluster related images. Additionally, a survey about the most frequent image classes shot by common people forms a baseline model for automatic annotation of images for search and retrieval by query keyword.

Abstract: Various systems, methods, and programs embodied in computer-readable mediums are provided for fingerprint liveness detection. In one embodiment, a method for determining fingerprint liveness is provided that comprises receiving a plurality of image analysis data of a fingerprint image; condensing the plurality of image analysis data; and determining liveness of the fingerprint image based upon the condensed data.

Abstract: Provided is an image evaluation apparatus for evaluating each of a plurality of images, the images including objects that each belong to a cluster. The image evaluation apparatus calculates (i) a first value pertaining to an object appearing in an image (for instance, the first value indicates a frequency at which the object appears in the plurality of images) according to a cluster that the object belongs to and (ii) a second value pertaining to the object (for instance, the second value indicates an occupation degree of the object in the image) according to an appearance characteristic that the object exhibits in the image. The image evaluation apparatus further calculates, according to the first value and second value, an importance degree of the object and an importance degree of the image.

Abstract: A clustering processing apparatus comprises: N clustering units that group samples included in the data block into clusters, each clustering unit sequentially taking each sample as a target, grouping the target sample into one of the clusters within the data block, storing cluster information including identification on each cluster into which the samples are grouped within the data block, and storing sample assignment information indicating the cluster to which the target sample belongs; a cluster information transferring unit that selects cluster information on a cluster to be integrated from the cluster information when a predetermined condition is met, and transfers the selected cluster information to a third storage unit; and an updating unit that integrates clusters selected based on the cluster information stored in the third storage unit into an integrated cluster, and updates the sample assignment information based on information of the integrated clusters.

Abstract: A method is provided for operating a computer to analyze image evaluation data from electronic survey respondents to evaluate preferences related to two dimensional and three dimensional images. Data files, which include designated area data, image attributes, and survey respondent opinions for one or more images in an electronic survey, are received. A graphical user interface permits an operator to reformat the designated area data and set analysis parameters. Cluster analysis is performed on the data files to reduce the dimensionality of the designated area data and to classify areas of the survey images that generate positive and negative responses. The analysis produces coordinate data to map cluster classifications and for construction of a heat map. In association with descriptive statistical analysis, cluster score evaluation is performed to identify the clusters of interest. Respondent comments and results from the statistical analysis are linked to clusters of interest.

Abstract: This patent discloses a system to compile a landmark image search result. The system may determine a rank of each image within a visual cluster according to at least one of a low-level self-similarity score, a low-level discriminative modeling score, and a point wise linking score. The landmark image search result may be compiled as a function of the rank of each image.

Abstract: An exemplary method includes receiving an image data set that comprises a multidimensional property space and data classifiable into data classes, determining a projection vector for data of the data set wherein the projection vector maximizes a ratio of between-class scatter to within-class scatter, selecting a reference for the vector, projecting at least some of the data onto the vector, measuring distances from the reference to at least some of the data, classifying at least some of the data into data classes based on a nesting analysis of the distances, eliminating the classified data from the image data set to produce a modified image data set and deciding whether to determine another projection vector for the modified image data set. Various other exemplary methods, devices, systems, etc, are also disclosed.

Abstract: Properties of pixels of a digital image are sampled within different subdivisions of an editing tool impression to produce different pixel property distributions. The property distributions from each region may be automatically classified to identify different edit classes within the property space, which are then used to apply an edit effect to the digital image within the tool impression. The edit classes are represented by an edit profile, the generation of which may be completely automated based on selection of a tool impression, or partially automated using the selection of the tool impression and receipt of classification guidance input, such as one or more parameters received from user input or a configuration file. The edit classes may also be generated without reference to the pixel property distributions, such as via user input.

Abstract: A method is provided for dividing a pattern into a plurality of sub-patterns, each sub-pattern being adapted for use with an image search method that can provide a plurality of sub-pattern search results. The method represents the pattern as a plurality of feature points, generates candidate partitions of the plurality of feature points, and then scores the candidate partitions by examining characteristics of each potential sub-pattern of each candidate partition. The highest-scoring partition is selected, and then it is applied to the plurality of feature points, creating one or more sub-pluralities of features. The invention advantageously provides a plurality of sub-patterns where each sub-pattern contains enough information to be located with a feature-based search method, where that information has been pre-evaluated as being useful and particularly adapted for running feature-based searches.

Abstract: A database of images may be accessed. A feature set may be computed for each image, respectively. Each feature set includes feature integers quantized from interest points of a corresponding image. An initial set of clusters of the feature sets is found based on min hashes of the feature sets. Given the clusters of feature sets, descriptors for each of the clusters are computed, respectively, by selecting feature integers from among the feature sets in a cluster. The clusters are then refined by comparing at least some of the feature sets with at least some of the cluster descriptors, and based on such comparing adding some of the feature sets to clusters whose feature descriptors have similarity to the feature sets.

Abstract: In the case of collecting samples, it is difficult to select a representative point of a target area. Thus, the samples are collected from certain positions, resulting in generation of variations of data. The target area is specified on an image to extract features from the target area. Further, clustering is performed for the features on a feature space to obtain representative features, and the obtained representative features are extracted as sampling points.

Abstract: A method for performing image recognition is disclosed. The method includes obtaining a collection of pixels and grouping at least some of the pixels into a set of cluster features based on gradient magnitude. For each cluster feature in the set, statistical variables are generated. The statistical variables represent a collective property of the pixels in the cluster feature. The statistical variables are utilized as a basis for comparing the collection of pixels to a different collection of pixels.

Abstract: An image managing apparatus is provided. The apparatus includes image information storage means that stores image information corresponding to captured image data, and cluster managing means that manages the image information by hierarchical clusters that include a plurality of layers of clusters and whose structure is fixed from an uppermost layer to a predetermined layer on the way to a lowermost layer.

Abstract: According to one embodiment, an electronic apparatus includes a grouping module, an attribute determination module, a grouping attribute setting module, a group selection module, and a video generating module. The grouping module classifies contents, to which time information is added, into groups based on the time information. The attribute determination module determines attributes of each of the contents by analyzing features of the contents. The grouping attribute setting module sets, with respect to each of the groups, selected attributes as grouping attributes for the group, the selected attributes being selected from the attributes of the contents in the group under a predetermined condition. The group selection module selects, from the groups, at least one group for which the grouping attribute agreeing with or relating to an input search key are set. The video generating module generates video data by using the contents in the selected groups.

Abstract: A method and system for performing gesture recognition of a vehicle occupant employing a time of flight (TOF) sensor and a computing system in a vehicle. An embodiment of the method of the invention includes the steps of receiving one or more raw frames from the TOF sensor, performing clustering to locate one or more body part clusters of the vehicle occupant, locating the palm cluster of the vehicle occupant, calculating the location of the tip of the hand of the vehicle occupant, determining whether the hand has performed a dynamic or a static gesture, retrieving a command corresponding to one of the determined static or dynamic gestures, and executing the command.

Abstract: A system and method for determining a classifier to discriminate between two classes—object or non-object. The classifier may be used by an object detection program to detect presence of a 3D object in a 2D image (e.g., a photograph or an X-ray image). The overall classifier is constructed of a sequence of classifiers (or “sub-classifiers”), where each such classifier is based on a ratio of two graphical probability models (e.g., Bayesian networks). A discrete-valued variable representation at each node in a Bayesian network by a two-stage process of tree-structured vector quantization is discussed. The overall classifier may be part of an object detector program that is trained to automatically detect many different types of 3D objects (e.g., human faces, airplanes, cars, etc.). Computationally efficient statistical methods to evaluate overall classifiers are disclosed. The Bayesian network-based classifier may also be used to determine if two observations (e.g., two images) belong to the same category.

Abstract: The present invention provides a method and module for preprocessing ultrasound imaging. The method comprises a calculation step for constructing a multivalue vector field and a smoothing step for smoothing the whole volume data. The method further comprises a judgement step and minification and magnification steps. The module includes a calculation unit, a smoothing unit, a judgement unit, a minification unit and a magnification unit. According to the method for preprocessing ultrasound imaging, speckle noise can be eliminated effectively by calculating a mean value of a plurality of nodes distributed over the surface, so as to implement the smoothing. Therefore, this method is capable of smoothing data without compromising details.

Abstract: A system and method of efficiently and effectively triaging an image that may include one or more target entities are provided. An image that may include one or more target entities is retrieved. The retrieved image is then divided into a plurality of sub-images, and each sub-image is displayed in a display region to a user. Each sub-image that was previously displayed is then divided into a plurality of sub-images, and each sub-image that was just divided is displayed to the user in the display region. The steps in the previous sentence are then repeated a determined number of times. During the initial display of the sub-images, and during each subsequent recursion, data are collected from the user and estimates of target entity locations are derived from the collected data.

Abstract: Methods and systems for comparing and organizing color themes and word tag associations. One embodiment comprises a method for determining associated color themes based on an identified color theme by determining the distance between the identified color theme and each color theme of the collection of color themes, wherein each distance includes a color-based distance and the determined subset of associated color themes from the collection is based at least in part on the calculated distances from the identified color theme. Another embodiment comprises a method that allows an application to suggest tags for an identified color theme based on its similarity to color themes and associated tags of the color theme collection. Another embodiment suggests color themes based on an identified tag, and yet another embodiment suggests tags based on an identified tag.

Abstract: Systems and methods are disclosed for identifying objects captured by a depth camera by condensing classified image data into centroids of probability that captured objects are correctly identified entities. Output exemplars are processed to detect spatially localized clusters of non-zero probability pixels. For each cluster, a centroid is generated, generally resulting in multiple centroids for each differentiated object. Each centroid may be assigned a confidence value, indicating the likelihood that it corresponds to a true object, based on the size and shape of the cluster, as well as the probabilities of its constituent pixels.

Abstract: A data visualization device comprises a focal attribute calculator for calculating a focal value of each of a plurality of data input items, and for categorizing each of the plurality of data input items as either non-cluster blobs or second blobs. The device further comprises a clustering attribute calculator for clustering data input items categorized as second blobs into one or more cluster blobs, and a visualization shaper for arranging the one or more cluster blobs and the non-cluster blobs, relative to each other in accordance with the focal values of the data input items of respective blobs.

Abstract: Provided is a face clustering device that detects a face included in an image, detects a direction of the detected face, detects, taking into account the detected direction of the face, a face with a similar feature and forms a collection of pieces of face information showing a feature of this face, narrows down, for each collection of pieces of face information which has been formed, the number of pieces of face information to a number set in advance for each face direction and sets each collection of pieces of face information for which the number has been narrowed down as a unit group, and performs, with the set unit group as a unit, clustering based on pieces of face information included in each unit group.

Abstract: A method of automatically extracting data from an electronic document including tables is provided. The method includes: automatically identifying rows of the table using gaps in horizontal projections of the plurality of image sections, wherein at least some of the identified rows in close proximity are collected to form table formations; and automatically identifying columns of the table using at least some of the plurality of image sections that are vertically aligned, wherein the identified columns are grown in each of the table formations using gaps in vertical projections of the plurality of image sections until an obstruction is reached. The method further includes automatically identifying labels in the plurality of corresponding image sections to associate the identified labels with at least one of the identified columns and the identified rows; and automatically extracting data from cells of the table formed by the identified rows and columns.

Abstract: A method for performing image recognition is disclosed. The method includes obtaining a collection of pixels and grouping at least some of the pixels into a set of cluster features based on gradient magnitude. For each cluster feature in the set, statistical variables are generated. The statistical variables represent a collective property of the pixels in the cluster feature. The statistical variables are utilized as a basis for comparing the collection of pixels to a different collection of pixels.

Abstract: A system and method of saving digital content classified by person-based clustering. The system for saving digital content classified by person-based clustering, includes a database to save a plurality of digital content classified by person-based clustering; a data structure generation unit to generate a data structure composed of a plurality of nodes using the plurality of digital content; a face recognition unit to extract a face descriptor of new digital content to be saved in the database; a cluster classification unit to classify the new digital content and the plurality of digital content by the person-based clustering using the extracted face descriptor, and a data structure update unit to update the data structure according to the classification.

Abstract: Face-based image clustering systems and methods are described. In one aspect, face regions are detected in images. At least one respective parameter value is extracted from each of the face regions. Ones of the face regions associated with parameter values satisfying a cluster seed predicate are classified as cluster seed face regions. The cluster seed face regions are clustered into one or more clusters. A respective face model is built for each of the clusters. The face models are stored. In another aspect, face regions are detected in images. At least one respective parameter value is extracted from each of the face regions. The face regions are ranked based on the extracted parameter values. The face regions are clustered in rank order into one or more clusters. Representations of ones of the clusters are rendered on a display.

Abstract: Methods, apparatuses, and systems for grouping digital media items based on shared features. Multiple digital images are received. Metadata about the digital images is obtained either by analyzing the digital images or by receiving metadata from a source separate from the digital images or both. The obtained metadata is analyzed by data processing apparatus to identify a common feature among two or more of the digital images. A grouping of the two or more images is formed by the data processing apparatus based on the identified common feature.

Abstract: An information processing apparatus, which creates a tree structure used by a recognition apparatus which recognizes specific information using the tree structure, including a memory unit which stores data including the information to be recognized and data not including the information so as to correspond to a label showing whether or not the data includes the information, a recognition device which recognizes the information and outputs a high score value when the data including the information is input, and a grouping unit which performs grouping of the recognition devices using a score distribution obtained when the data is input into the recognition devices.

Abstract: In some embodiments, the technology compares multimedia content to other multimedia content via a content analysis server. In other embodiments, the technology includes a system and/or a method of comparing video sequences. The comparison includes receiving a first list of descriptors pertaining to a plurality of first video frames and a second list of descriptors pertaining to a plurality of second video frames; designating first segments of the plurality of first video frames that are similar and second segments of the plurality of second video frames that are similar; comparing the first segments and the second segments; and analyzing the pairs of first and second segments to compare the first and second segments to a threshold value.

Abstract: Systems and methods are described for a face annotation framework with partial clustering and interactive labeling. In one implementation, an exemplary system automatically groups some images of a collection of images into clusters, each cluster mainly including images that contain a person's face associated with that cluster. After an initial user-labeling of each cluster with the person's name or other label, in which the user may also delete/label images that do not belong in the cluster, the system iteratively proposes subsequent clusters for the user to label, proposing clusters of images that when labeled, produce a maximum information gain at each iteration and minimize the total number of user interactions for labeling the entire collection of images.

Abstract: A social network application may identify images having common links between a first user's image collection and a second user's image collection. The common links may be identified through metadata or similar portions of the images. Using the first user's image collection, elements of interest may be identified and compared to a second user's image collection to find matches. When matches are found, the results may be selected from groups of results to show a diverse set of matches. The user may be presented with options to select and add matched images to the user's collection, as well as to browse more images that match one or more of the groups.

Abstract: An image display apparatus includes: an image information storage that stores image information including locations where images are captured as information corresponding to captured image data; a cluster managing section that manages the image information with hierarchical clusters including a plurality of clusters configured in a plurality of layers; a display layer designation section that designates a layer to be displayed as a display layer among from an uppermost layer through a lowermost layer in the plurality of layers; a display condition designation section that designates a display condition of the image data; a conditional filtering section that selects such image data in the display layer that the image information thereof exists within a predetermined range based on the display condition; and a drawing section that draws in the display layer, as an image location display, the image captured locations of the image data selected based on the image information.

Abstract: A method and system analyzes data acquired by image systems to more rapidly identify objects of interest in the data. In one embodiment, z-depth data are segmented such that neighboring image pixels having similar z-depths are given a common label. Blobs, or groups of pixels with a same label, may be defined to correspond to different objects. Blobs preferably are modeled as primitives to more rapidly identify objects in the acquired image. In some embodiments, a modified connected component analysis is carried out where image pixels are pre-grouped into regions of different depth values preferably using a depth value histogram. The histogram is divided into regions and image cluster centers are determined. A depth group value image containing blobs is obtained, with each pixel being assigned to one of the depth groups.

Abstract: Method for at least one of model-based classification and target recognition of an object. The method includes recording an image of an inanimate object, determining a feature that represents a part of the inanimate object, determining at least one condition associated with the feature that indicates an applicability of the feature based on at least one of geometry of the object, distance of the object from a camera, illumination conditions, contrast, speed of the object, height of the object, and relative position of the object to a camera, and carrying out the at least one of classification and target recognition of the object by recording the feature when the at least one condition indicates the applicability of the feature. At least one of object classification and target recognition is carried out for a feature of the object that is visible and recordable according to the position of the object.

Abstract: Systems and methods for space-time video montage are described. In one aspect, one or more arbitrary space-time volumes representing informative video portion(s) of at least one input video data sequence are identified. A video summary representing a montage of the at least one input video data sequence is generated for presentation to user from the one or more arbitrary space-time volumes.

Abstract: A manufacturing method of a plugged honeycomb structure including attaching a transparent sheet to an end face of a honeycomb structure; picking up an image of the end face; with respect to cells positioned at other than outermost peripheral portion of a honeycomb structure (usual cells), subjecting the picked-up image to image processing, recognizing positions to be plugged on said sheet, and with respect to cells positioned at outermost peripheral portion (outermost peripheral cells), positions of the cells are recognized based on an average cell pitch calculated from the positions of the cells, subjecting to a perforation treatment based on the recognized positions of the sheet, submerging an end portion into a plugging slurry in which a material of the plugging portions is slurried, filling holes made at the respective sheet with the slurry to form the plugging portions.

Abstract: The invention concerns a method for determining feature data that represents information about the shape of an object. A partitioning scheme (RP) is determined that defines a plurality of cells (p) in the space in which the object is located such that at least some of the cells (p) each contain a respective portion of the object, and the feature data is determined for the object on the basis of at least one property of the respective portions of the object that are contained in the plurality of cells (p). According to a first aspect of the invention, at least two of the plurality of cells (p) overlap each other at least in part, and according to a second aspect of the invention, at least some of the boundaries of the cells (p) delimit a plurality of regions (r) in the space in which the object is located such that the respective portions of the object that are contained in the plurality of regions (r) are approximately equal to each other with respect to a predetermined measurement metric.

Abstract: This disclosure describes techniques for determining a shape of a signal. In particular, a kernel is applied to a portion of a signal to compute at least a first, first order derivative of the portion of the signal and a second, first order derivative of the portion of the signal in a single pass of the kernel. The shape of the portion of the signal is determined based on the first and second first order derivatives. In one example, the shape of the portion of the signal is determined based on the ratio of the first, first order derivative and the second, first order derivative. These techniques may be particularly effective for detecting edges within image signals. However, the techniques may be used to detect the shape of significant changes within any signal that represents a variable that is changing over time, space or other dimension.

Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the step of performing a filter response technique to identify patches of uniform reflectance within the image. In a further exemplary embodiment, the method comprises the additional step of utilizing the identified patches of uniform material reflectance to generate single material token regions for use in processing material and illumination aspects of the image.

Abstract: The present invention relates to a method for multi-layer classifier applying on a computer readable medium for classifying multiple image samples. The method at least comprising the following steps: (a) receiving a plurality of samples; (b) providing a plurality of attributes, and evaluating a significance of the attributes by a selection criterion; (c) selecting at least one cut-point to establish a discriminant analysis model; (d) proceeding a step of evaluating a performance of the discriminant analysis model by adding the attributes to the discriminant analysis model; and (e) providing a stop criterion. The present invention also provides a computer readable medium for classifying multiple image samples by using the method for multi-layer classifier.

Abstract: A system and method for generating cluster spine groupings for display is provided. A set of spines is obtained. Each spine in the set includes a grouping of clusters that share a common concept and are arranged linearly along a vector. Those spines that are unique from each other spine are identified. At least one remaining spine from the set of spines is selected. The remaining spine is compared to the unique spines. At least one spine group is formed by grafting the remaining spine onto the unique spine that is most similar. The spine group is displayed.

Abstract: Apparatus, methods, systems and devices for identifying and tracking a human hand in a video. The steps for identifying the hand includes detecting parallel lines (bars), detecting curved fingertips (curves), grouping the detected parallel lines and curved fingertips according to a parallel line decision tree and a curved fingertip decision tree, respectively, and merging the parallel line group and the curved fingertip group to identify candidate hands.

Abstract: In an intelligent video surveillance system, video processing software performs a number of operations on video data received from a camera, including foreground extraction, shadow removal and object tracking. The foreground extraction stage classifies each pixel of a received frame as representing either foreground or background. Since shadow regions can be wrongly classified as foreground, a two-branch shadow removal operation is employed, comprising weak shadow removal (32) and strong shadow removal (33). The purpose of weak shadow removal (32) is to remove only the most severe shadows in each frame. Conversely, the purpose of strong shadow removal (33) is to remove substantially every shadow present in each frame. By comparing the overlap of foreground regions in the two resulting images, it is possible to identify foreground regions that have fragmented due to strong shadow removal, and thereafter classify them as representing a common foreground object.

Abstract: A memory footprint of an Modified Quadratic Discriminant Function (MQDF) pattern recognition classifier is reduced without resulting in unacceptable classification accuracy degradation. Covariance matrices for multiple classes are clustered into a smaller number of matrices where different classes share the same set of eigenvectors. According to another approach, different numbers of principal components are stored for different classes based on criteria such as class usage frequency, larger variation in writing, and the like, resulting in fewer principal components to be stored in memory.

Abstract: Methods for dimensionality reduction of large data volumes, in particular hyper-spectral data cubes, include providing a dataset ? of data points given as vectors, building a weighted graph G on ? with a weight function w?, wherein w? corresponds to a local coordinate-wise similarity between the coordinates in ?; obtaining eigenvectors of a matrix derived from graph G and weight function w?, and projecting the data points in ? onto the eigenvectors to obtain a set of projection values ?B for each data point, whereby ?B represents coordinates in a reduced space. In one embodiment, the matrix is constructed through the dividing each element of w? by a square sum of its row multiplied by a square sum of its column. In another embodiment the matrix is constructed through a random walk on graph G via a Markov transition matrix P, which is derived from w?. The reduced space coordinates are advantageously used to rapidly and efficiently perform segmentation and clustering.

Abstract: A method of generating an image collection is described. A plurality of images are retrieved (step 202) and the images are divided into clusters according to a predetermined characteristic of the content of the images (step 204). At least one of the clusters is selected based on a number of images in each cluster (step 206). For each selected cluster, at least one image is selected on the basis of a predetermined criterion (step 208) and an image collection 5 comprising the selected images is generated (step 210).