Abstract: An automated and extensible system is provided for the analysis and retrieval of images based on region-of-interest (ROI) analysis of one or more true objects depicted by an image. The system uses an ROI database that is a relational or analytical database containing searchable vectors representing images stored in a repository. Entries in the ROI database are created by an image locator and ROI classifier that locate images within the repository and extract relevant information to be stored in the ROI database. The ROI classifier analyzes objects in an image to arrive at actual features of the true object. Graphical searches may also be performed.

Abstract: Methods, systems, and articles of manufacture for annotating of an image are disclosed. These include scoring the image using a plurality of trained classifiers, wherein each of the trained classifiers corresponds to at least one of a plurality of image groups clustered based upon image similarity, and wherein each image group is associated with a set of weighted labels; selecting one or more of the image groups based upon the scoring; aggregating one or more sets of weighted labels associated with the selected one or more image groups; and annotating the image using the aggregated one or more sets of weighted labels.

Abstract: According to one embodiment, an image diagnosis apparatus includes a line shape information generating unit and a comparing unit. The line shape information generating unit is configured to generate first line shape information corresponding to a first medical image and second line shape information corresponding to a second medical image, respectively. The comparing unit is configured to compare the generated first line shape information with the second line shape information.

Abstract: A method for determining a location of a target includes, at a first location, determining first location coordinates of a measuring device using one or more GNSS signals, determining a first gravitational direction, and capturing a first image using the camera. The method also includes, at a second location, determining second location coordinates of the measuring device, and capturing a second image. The method further includes determining a plurality of correspondence points between the first and second images, determining a first plurality of image coordinates for the plurality of correspondence points in the first image, determining a second plurality of image coordinates for the plurality of correspondence points in the second image, and determining the location of the target using at least the first plurality of image coordinates, the second plurality of image coordinates, and the first gravitational direction.

Abstract: A method for occupancy detection is disclosed. The method may include capturing an image, moving a sliding window over said image, determining features for intensity image and gradient image, generating a strong classifier, detecting shape of object; and determining occupancy.

Abstract: There is provided a position detection system including an imaging unit to capture an image of a projection plane of an electromagnetic wave, an electromagnetic wave emission unit to emit the electromagnetic wave to the projection plane, a control unit to control emission of the electromagnetic wave by the electromagnetic wave emission unit, and a position detection unit including a projected image detection section to detect a projected image of an object existing between the electromagnetic wave emission unit and the projection plane based on a difference between an image of the projection plane captured during emission of the electromagnetic wave by the electromagnetic wave emission unit and an image of the projection plane captured during no emission of the electromagnetic wave, and a position detection section to detect a position of the object based on a position of the projected image of the object.

Abstract: A depth image of a scene may be observed or captured by a capture device. The depth image may include a human target and an environment. One or more pixels of the depth image may be analyzed to determine whether the pixels in the depth image are associated with the environment of the depth image. The one or more pixels associated with the environment may then be discarded to isolate the human target and the depth image with the isolated human target may be processed.

Abstract: An image processing apparatus for extracting a contour of an object which extracts boundary candidate points from the image and sets reference areas each having one of boundary candidate points as a center and includes small areas. A first reference area is set from the reference areas and a first small area is set from small areas included in the first reference area. From reference areas, a second reference area is set, whose feature is similar to that of the first reference area and as a second small area, a small area is set which has a feature amount similar to that of the first small area among small areas included in the second reference area. The boundary candidate points is tracked to extract the contour of the object based on the first reference area, the second reference area, the first small area, and the second small area.

Abstract: Embodiments generally relate to summarizing a photo album in a social network system. In one embodiment, a method includes grouping photos into a plurality of groups of photos, and selecting a plurality of representative photos, where each representative photo represents a respective group from the plurality of groups, where the selecting is based on a quality score of each of the photos, and where each quality score is based on different types of attributes. The method also includes enabling the plurality of representative photos to be shared.

Abstract: A data processing apparatus that executes determining processing, using a plurality of stages, for determining whether or not a partial image sequentially extracted from an image of each frame of a moving image corresponds to a specific pattern, assigns a plurality of discriminators to each stage such that a plurality of partial images are processed in parallel. The data processing apparatus divides an image into a plurality of regions, and, for the image of each region, calculates a passage rate or accumulated passage rate from a ratio between the number of partial images input to a stage and the number of partial images determined to correspond to the specific pattern. The assignment of the discriminators to each stage is changed based on the passage rate or accumulated passage rate of the image processed immediately of a region to which the partial image extracted from the image being processed belongs.

Abstract: Systems for matching face shapes may include a computer-readable non-transitory storage medium and an executing hardware unit. The storage medium may include a set of instructions for target object shape matching. The executing hardware unit may be in communication with the storage medium and may be configured to execute the set of instructions. The executing hardware unit may be configured to obtain a target object image for shape matching; determine a shape character of the target object image based on a shape of the target object image; determine similarities between the target object image and a plurality of template images of reference objects based on the shape character of the target object image and shape characters of the reference objects in the plurality of template images; and select a template image from the plurality of template images that has a largest similarity to the target object image.

Abstract: Systems and methods of providing an attractiveness analysis are disclosed. In some embodiments, an electronic analysis platform is configured to obtain image data and curvature data to provide an attractiveness analysis to a user via a physical interface. Curvature data could comprise any data indicative of a curvature of a physical feature or a depiction thereof, including shadow data and pixilation data.

Abstract: According to the pattern shape determining method of the embodiment, a first reference position of a pattern shape is set on a first pattern and a second reference position of a pattern shape is set on a second pattern. Moreover, an allowable dimensional difference between the first pattern and the second pattern is set to a value corresponding to a distance from the first reference position. Then, it is determined whether the second pattern has a pattern shape identical with the first pattern, based on whether a dimensional difference between the first pattern and the second pattern is within a range of an allowable dimensional difference set at a position at which the dimensional difference is calculated.

Abstract: Some examples of a sketch-based image recognition system may generate a model for identifying a subject of a sketch. The model is formed from a plurality of images having visual features similar to the visual features of the sketch. The model may include object topics representative of categories which may correspond to the subject of the sketch and shape topics representative of the visual features of the sketch.

Abstract: Systems and methods may include utilizing a structured light pattern that may be, among other things, decoded in the three directions (e.g., vertical, horizontal, and diagonal). In one example, the method may include detecting a first feature of a target image in a return image, designating a feature type of the first feature, and an index with the letter, wherein the index is associated with the pattern slide. The method may also include calculating a horizontal position in the pattern slide of the first feature, calculating a vertical position in the pattern slide of the first feature, and calculating a depth of the first feature.

Abstract: A computer implemented method for determining shape from differential motion with unknown reflectance includes deriving a general relation that relates spatial and temporal image derivatives to bidirectional reflectance distribution function BRDF derivatives, responsive to 3D points and relative camera poses from images and feature tracks of an object in motion under colocated and unknown directional light conditions, employing a rank deficiency in image sequences from the deriving for shape determinations, under predetermined multiple camera and lighting conditions, to eliminate BDRF terms; and recovering a surface depth for determining a shape of the object.

Abstract: A system and method for detecting a circular shape from a sequence of ordered points is disclosed. In one embodiment, the method comprises receiving a sequence of ordered points, selecting a subset of the sequence of ordered points, determining if the subset defines a circular shape, and storing an indication of whether or not the subset defines a circular shape. Various metrics for determining if the subset defines a circular shape, which allow for a trade-off between accuracy and complexity, are disclosed.

Abstract: A feature tracking technique for detecting and tracking feature points with primary colors. An energy value may be computed for each color channel of a feature. If the energy of all the channels is above a threshold, then the feature may be tracked according to a feature tracking method using all channels. Otherwise, if the energy of all of the channels is below the threshold, then the feature is not tracked. If the energy of at least one (but not all) of the channels is below the threshold, then the feature is considered to have primary color, and the feature may be tracked according to the feature tracking method using only the one or more channels with energy above the threshold. The feature tracking techniques may, for example, be used to establish point trajectories in an image sequence for various Structure from Motion (SFM) techniques.

Abstract: Disclosed is a method of generating image-processing component data which is used when an image of a component to be mounted by a component mounting apparatus is recognized. The method includes extracting first component shape data from CAD data of the component, measuring second component shape data from an image of the component obtained by an imaging device, and generating image-processing component data based on the first and second component shape data.

Abstract: A method and system for probe-based pattern matching including an apparatus for synthetic training of a model of a pattern. The apparatus comprises a sensor for obtaining an image of the pattern and a processor for receiving the image of the pattern from the sensor and running a program. In the steps performed by the program a boundary of the pattern in the image is identified. A plurality of positive probes are placed at selected points along the boundary of the pattern and at least one straight segment of the boundary of the pattern is identified. The at least one straight segment of the boundary is extended to provide an imaginary straight segment and a plurality of negative probes are placed at selected points along the imaginary straight segment, where each negative probe has a negative weight.

Abstract: Text recognition techniques are described. In one or more implementations, image data is received via a network at a service provider. One or more image deblurring or curve correction techniques are applied to the image data, text is recognized from the deblurred image data using one or more optical character recognition techniques, and the recognized text is exposed for access via the network.

Abstract: The capture and alignment of multiple 3D scenes is disclosed. Three dimensional capture device data from different locations is received thereby allowing for different perspectives of 3D scenes. An algorithm uses the data to determine potential alignments between different 3D scenes via coordinate transformations. Potential alignments are evaluated for quality and subsequently aligned subject to the existence of sufficiently high relative or absolute quality. A global alignment of all or most of the input 3D scenes into a single coordinate frame may be achieved. The presentation of areas around a particular hole or holes takes place thereby allowing the user to capture the requisite 3D scene containing areas within the hole or holes as well as part of the surrounding area using, for example, the 3D capture device. The new 3D captured scene is aligned with existing 3D scenes and/or 3D composite scenes.

Abstract: Examples disclose a method executed on a computing device to locate a clothing region within an image to segment into a region of related clothing. Further, the examples provide detecting a feature of the related clothing. Additionally, the examples also disclose determining a style of the related clothing in the region based on the detection of the feature.

Abstract: A method, system, and machine-readable medium for classifying an image element as one of a plurality of categories, including assigning the image element based on a ratio between an unoccluded perimeter of the image element and an occluded perimeter of the image element and coding the image element according to a coding scheme associated with the category to which the image element is classified. Exemplary applications include image compression, where categories include image foreground and background layers.

Abstract: An automated hydrogen bubble detection apparatus includes a horizontal support surface on which a test coupon can be supported, a transparent tube having an open top and an open bottom and operable to contain a test solution when positioned on a test coupon, a camera arranged to view a test solution in the transparent tube, and a controller in communication with the camera and effective to operate the camera such that at least one video segment is recorded by the camera and analyzed to detect first bubble and continuous bubble generation. A method of evaluating corrosion resistance of coatings on aluminum and steel in acidic solution is also included.

Abstract: A system and method of creating a smooth analytical representation of a geometry using a discrete set of points. A meshfree representation of the geometry is generated. The representation includes a set of points. A starting point and an edge length range are then used to generate a set of vertices from the set of points. The vertices are used to generate a coarse mesh, which, in turn, is used to generate a Reproducing Kernel Element Method (RKEM) representation of the geometry. The points of the meshfree representation that were not included in the set of vertices are then applied to the RKEM representation. The quality of the RKEM representation is assessed and compared to a predetermined standard. Additional sets of vertices from the meshfree representation are generated repeatedly and all remaining operations are repeated until the quality of the RKEM at least meets the predetermined standard. This provides a smooth, analytical RKEM representation of the geometry.

Abstract: The invention relates to a detection system for automatic detection of bone cancer metastases from a set of isotope bone scan images of a patients skeleton, the system comprising a shape identifier unit, a hotspot detection unit, a hotspot feature extraction unit, a first artificial neural network unit, a patient feature extraction unit, and a second artificial neural network unit.

Abstract: Disclosed is a method of forming an output shape parameterised by control points from an input shape. An input shape is received formed by a plurality of segments. The shape is classified as one of a plurality of predefined template shapes. The method then determines a representative form for the input shape based on a similarity measure between the input shape and the classified template shape. The representative form is selected according to the similarity measure from the group consisting of the classified template shape, and a non-template shape based on the segments of the input shape, the non-template shape having at least one control point derived from at least one control point of the classified template shape. The method then stores the determined representative form as the output shape parameterised by the derived control points.

Abstract: A method and apparatus to read an analog dial utility meter including a plurality of analog dials, where each dial includes a rotating dial indicator is provided. The apparatus is configured to analyze a digital image of the analog dial utility meter to determine a value of each dial of the utility meter. The method comprises receiving a digital image of the analog dial utility meter, and performing one or more processing and analysis steps to determine a meter reading of the utility meter.

Abstract: Embodiments of the present invention includes a method of determining MSER on a processing system that includes a parallel processor such as a GPU, the method including method steps carried out in parallel. Embodiments of the present invention also include an apparatus that includes a parallel processor and that is operative to carry out the method, and also logic, e.g., executable instructions configured on a non-transitory computer-readable media operative to carry out the method, and a non-transitory computer-readable medium encoded with such instructions. The method includes assigning to the pixels in an image metapixels of all connected pixels at a level, carrying out watershed in parallel on metapixels to determine catchment basins, and carrying out further steps, including steps executed in parallel to determine the MSER of the image.

Abstract: A method and apparatus for encoding an image is provided. An image coding unit, including a region that deviates from a boundary of a current picture, is divided to obtain a coding unit having a smaller size than the size of the image coding unit, and encoding is performed only in a region that does not deviate from the boundary of the current picture. A method and apparatus for decoding an image encoded by the method and apparatus for encoding an image is also provided.

Abstract: A method and apparatus for encoding an image is provided. An image coding unit, including a region that deviates from a boundary of a current picture, is divided to obtain a coding unit having a smaller size than the size of the image coding unit, and encoding is performed only in a region that does not deviate from the boundary of the current picture. A method and apparatus for decoding an image encoded by the method and apparatus for encoding an image is also provided.

Abstract: A method and apparatus for encoding an image is provided. An image coding unit, including a region that deviates from a boundary of a current picture, is divided to obtain a coding unit having a smaller size than the size of the image coding unit, and encoding is performed only in a region that does not deviate from the boundary of the current picture. A method and apparatus for decoding an image encoded by the method and apparatus for encoding an image is also provided.

Abstract: Systems, methods, and computer-readable media for gesture recognition are disclosed. The systems include, for example, at least one processor that is configured to receive at least one image from at least one image sensor. The processor may also be configured to detect, in the image, data corresponding to an anatomical structure of a user. The processor may also be configured to identify, in the image, information corresponding to a suspected hand gesture by the user. In addition, the processor may also be configured to discount the information corresponding to the suspected hand gesture if the data corresponding to the anatomical structure of the user is not identified in the image.

Abstract: Embodiments described herein use depth images to extract user behavior, wherein each depth image specifies that a plurality of pixels correspond to a user. In certain embodiments, information indicative of an angle and/or curvature of a user's body is extracted from a depth image. This can be accomplished by fitting a curve to a portion of a plurality of pixels (of the depth image) that correspond to the user, and determining the information indicative of the angle and/or curvature of the user's body based on the fitted curve. An application is then updated based on the information indicative of the angle and/or curvature of the user's body. In certain embodiments, one or more average extremity positions of a user, which can also be referred to as average positions of extremity blobs, are extracted from a depth image. An application is then updated based on the average positions of extremity blobs.

Abstract: From a sample image, a fertilization test method determines the ratio of fertilized cells in the image by identifying cells in the image and calculating cell properties for each cell. An area is determined between a cell body and an outer search limit to search for a fertilization membrane. A cell outline is defined for each cell and cell membrane edges are found within the search area by changing the cell outline size between the cell body boundary the outer search limit, checking for a match with detected cell membrane edges. A cell is determined to be fertilized based on matches between detected cell membrane edges and the cell outline, patterns of contrast changes indicated by a cell membrane, or circles fit to cell membrane edges.

Abstract: A method for biometric identification for use with a computing device is provided herein. The method includes capturing a temporal sequence of images of the face of a user at different locations within a three-dimensional interaction space. The method further includes extracting one or more face descriptors from the images and generating a biometric template compiling the face descriptors.

Abstract: A shape may be virtually generated from a formula specifying a scalable property of the shape that determines the appearance of the shape as the size of the shape is changed. Once the shape is generated, a reflection and/or shadow may be generated according to one or more customizable parameters specifying different properties of the reflection and/or shadow. Reflections and shadows may be regenerated with shapes each time the shapes are resized. Each generated shape, reflection, and/or shadow may then be outputted to a display. Systems, methods, and computer readable media are provided.

Abstract: A method for generating individual glyphs, and a system and method for inspecting individual glyphs are disclosed. The system includes a true resolution imaging device configured to capture an image of a printed glyph. A registry service has a database for storing other glyphs and/or parameters of other glyphs. An analysis system, in selective communication with the registry service, includes computer software configured to receive the captured image; an image analysis program configured to perform forensic analysis on the received image to determine parameter(s) associated with the glyph; and an image comparison program configured to i) compare the glyph parameter(s) with parameters stored in the registry for other glyphs or with parameters determined, by image analysis program, for the other glyphs stored in the registry, and ii) generate a probability that the glyph and object are authentic based upon the comparison.

Abstract: A computer implemented method and system determines a center point of a circular object in an image. A circular object identification system identifies prospective center points of the circular object for each of multiple pixel points at a predetermined distance along a gradient direction determined for each of the pixel points, constructs an axis between the corresponding prospective center points and a corresponding pixel point, and locates prospective circumference points at predetermined angles from the constructed axis.

Abstract: According to embodiments of the invention, there is provided a computer program product, a method, and a system to clean an image produced by the system. A digital canvas representation of an initial condition is produced. A set of real-time digital information is captured to form an unconstrained digital representation of the set of real-time digital information. A constraining digital mask based on the digital canvas representation of the initial condition is applied to the unconstrained digital representation of the set of real-time digital information to form a constrained digital representation of the set of real-time digital information. The constrained digital representation of the set of real-time data is stored, allowing an application program to use the constrained representation of the real-time data.

Abstract: The described implementations relate to computer vision. In one case image data is received. Resource constraints associated with processing the image data are evaluated. Further, a visual recognition and detection processing strategy is selected for the image data based at least in part on the evaluated resource constraints.

Abstract: A lighting module of a hair/fur pipeline may be used to produce lighting effects in a lighting phase for a shot and an optimization module may be used to: determine if a cache hair state file including hair parameters exists; and determine if the cache hair state file includes matching hair parameters to be used in the shot, and if so, the hair parameter values from the cache hair state file are used in the lighting phase.

Abstract: An object detection apparatus, a program, and an integrated circuit enable the contour of an object to be detected in an appropriate manner in an image including an object and its background with almost no contrast between them in a predetermined direction of the image. A vertical direction edge extraction filter in a filtering unit extracts, from an input image, a contour component in a first direction (e.g., vertical direction) of the image. A horizontal direction continuity detection unit in the filtering unit detects, in a second direction (e.g., horizontal direction) perpendicular to the first direction, the continuity of the contour component extracted by the vertical direction edge extraction filter. An object area detection unit detects (estimates) the contour of the object in the image based on the continuity of the contour component in the second direction (e.g., horizontal direction) detected by the horizontal direction continuity detection unit.

Abstract: A system and a method for near-duplicate image detection performed by a physical computing system includes applying a feature determining function to a number of images, a feature being defined by a geometric shape, comparing characteristics of said geometric shapes defining said features from at least two of said number of images, and characterizing said at least two of said number of images as a near-duplicate match if a predetermined percentage of said features of said at least two images match.

Abstract: A system and method to classify forms. An image representing a form of an unknown document type is received. The image includes line-art. Further, a plurality of template models corresponding to a plurality of different document types is received. The plurality of different document types is intended to include the correct document type of the unknown document. A subset of the plurality of template models are selected as candidate template models. The candidate template models include line-art junctions best matching line-art junctions of the received image. One of the candidate template models is selected as a best candidate template model. The best candidate template model includes horizontal and vertical lines best matching horizontal and vertical lines of the received image, respectively, aligned to the best candidate template model.

Abstract: Shape-based search of a collection of content associated with one or more images of inventory items (“inventory images”) is enabled at least in part by associating the collection of content and/or its associated inventory images with representative refinement shapes. Inventory items may be grouped into categories and at least one refinement shape may be created for each of the categories. A refinement-shape hierarchy may be created by arranging the refinement shapes into parent and child refinement shapes. Inventory images may be associated to at least one of the refinement shapes of the refinement-shape hierarchy based at least in part on similarities between the refinement shapes and shapes of the inventory items reflected in the inventory images.

Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.

Abstract: Systems, computer program products, and methods can identify a training set of content, and generate one or more clusters from the training set of content, where each of the one or more clusters represent similar features of the training set of content. The one or more clusters can be used to generate a classifier. New content is identified and the classifier is used to associate at least one label with the new content.

Abstract: A method of defining model characters of a font. The method includes receiving a string of characters, receiving an image that includes an occurrence of the string, identifying objects in the image, determining, for each respective object, which of the objects satisfies first criteria indicating that the respective object likely corresponds to a character in the string, determining, for each respective object satisfying the first criteria, which of the objects satisfies second criteria indicating that the respective object belongs to a sequence of objects likely to correspond to the string, and defining, for each respective object satisfying the second criteria, a model character for each character of the string based upon a corresponding object of the sequence of objects. The first criteria may include aspect ratio criterion, size criterion, or both, and the second criteria may include alignment criterion, spacing criterion contrast criterion, encompassment criterion, or combinations thereof.