Abstract: Implementations relate to providing visual effects for images. In some implementations, a method includes detecting one or more objects in an image. The method identifies one or more important objects of the objects, where the important objects are determined to have an importance measurement satisfying a predetermined threshold indicating their importance to a viewer of the image. The method determines an application of a visual image effect to the image based on the important objects.

Abstract: The disclosed embodiments relate to a system and method for calibrating optical character recognition (OCR) processes for an image captured through a mobile computing device. During operation, the system adjusts the OCR process through pre-recognition functions, OCR functions and/or post-recognition functions with multiple sets of parameter settings. With each of these sets, the system scores the OCR process output against an image with known text. Once the sets are scored, the system sorts the sets of parameters, removes some sets, then mixes and mutates the remaining sets in a process akin to evolutionary biology. By repeating this procedure, the system produces a set of parameter settings that can be used to calibrate OCR processing.

Abstract: Provided is an operating method of a measuring apparatus measuring a wavefront of a target. The operating method includes measuring a measurement wavefront on the basis of the wavefront of the target, measuring reference slope information and first to third slope information respectively corresponding to a reference direction and first to third directions on the basis of the measurement wavefront, obtaining first to third rotation angles on the basis of the measured reference slope information and first to third slope information, and outputting a wavefront of which an error is corrected, which is generated by rotation errors on the basis of the obtained first to third rotation angles, wherein the first to third rotation angles are differences in angle between the reference direction and the first to third directions.

Abstract: Disclosed are an apparatus for sensing a moving golf ball and a method for sensing the moving golf ball using the apparatus. The apparatus includes an image acquisition unit for acquiring consecutive images of a ball, an image processing unit for extracting a feature portion of the ball from the acquired images, and a spin calculation unit for performing any one of forward operation analysis and inverse operation analysis to calculate spin of the ball.

Abstract: Disclosed herein are methods and systems for highlighting box surfaces and edges in mobile box dimensioning. An embodiment takes the form of a method that includes obtaining a three-dimensional (3D) point cloud from a depth sensor when the depth sensor is positioned such that an aiming indicator appears on a first surface of an object; processing the 3D point cloud to identify an extent of the first surface; further processing the 3D point cloud to identify a second surface that is adjacent and normal to the first surface, and to identify an extent of the second surface; and displaying at least part of the 3D point cloud via a user interface, including displaying the identified first surface in a first color and the identified second surface in a second color different from the first color.

Abstract: Provided are a shape recognition device, a shape recognition program, and a shape recognition method capable of obtaining more accurate information for recognizing an outer shape of a target object. A shape recognition device according to the present invention includes: an outer shape detection unit that detects an outer shape of a hand; a reference point extraction unit that extracts a central point of a maximum inscribed circle of the detected outer shape as a reference point; a distance measurement unit that measures a distance between the reference point and each of a plurality of outer shape points on the outer shape; and a feature recognition unit that determines a feature part of the outer shape from the plurality of outer shape points on the basis of the distance.

Abstract: A method and a system for localizing at least one circular object in a video frame captured by an image capture unit are disclosed. The method includes the steps of: A. performing edge detection to obtain a plurality of image edge points in the video frame; B. extracting a contour set of image contours by linking neighboring edge points; C. generating a plurality of circle samples from the extracted contour set by a structural sampling process; and D. localizing the at least one circular object from the generated circle samples by calculating a respective fitness score for each of the circle samples to measure the supporting evidence of the image edge points on a neighborhood of each of the circle samples, and by choosing the circle sample(s) whose fitness score(s) is/are greater than a threshold value as the circular object(s) found in the video frame.

Abstract: Described herein are technologies for facilitating three-dimensional imaging based on prior image data. In accordance with one aspect, deformable registration is performed to align three-dimensional (3D) image data to a sparse set of two-dimensional (2D) projection image data of at least one structure of interest. An iterative reconstruction scheme may then be performed to minimize a difference between the aligned 3D image data and the 2D image data.

Abstract: A system for detecting and tracking a curvilinear object in a three-dimensional space includes an image acquisition system including a video camera arranged to acquire a video image of the curvilinear object and output a corresponding video signal, the video image comprising a plurality n of image frames each at a respective time ti, where i=1, 2, . . . , n; and a data processing system adapted to communicate with the image acquisition system to receive the video signal.

Abstract: A method, system and computer program product for processing hierarchical data is provided. A method for processing hierarchical data in a relational database includes receiving an input parameter in an initial query for querying an array in a hierarchical data object stored in a table of a relational database, and transforming the initial query into a transformed query configured to place all elements of the array into a different table and to apply a sub-query against the table for the input parameter. Once transformed, predicate evaluation logic of a relational engine of the relational database is applied to the transformed query that is then mapped to the initial query. Finally, responsive to receiving a subsequent instance of the initial query, the mapping is referred to in order to replace the initial query with the transformed query and to subsequently apply the predicate evaluation logic to the transformed query.

Abstract: A method, system and computer program product for processing hierarchical data is provided. A method for processing hierarchical data in a relational database includes receiving an input parameter in an initial query for querying an array in a hierarchical data object stored in a table of a relational database, and transforming the initial query into a transformed query configured to place all elements of the array into a different table and to apply a sub-query against the table for the input parameter. Once transformed, predicate evaluation logic of a relational engine of the relational database is applied to the transformed query that is then mapped to the initial query. Finally, responsive to receiving a subsequent instance of the initial query, the mapping is referred to in order to replace the initial query with the transformed query and to subsequently apply the predicate evaluation logic to the transformed query.

Abstract: Dynamic texture mapping is used to create a photorealistic three dimensional animation of an individual with facial features synchronized with desired speech. Audiovisual data of an individual reading a known script is obtained and stored in an audio library and an image library. The audiovisual data is processed to extract feature vectors used to train a statistical model. An input audio feature vector corresponding to desired speech with which the animation will be synchronized is provided. The statistical model is used to generate a trajectory of visual feature vectors that corresponds to the input audio feature vector. These visual feature vectors are used to identify a matching image sequence from the image library. The resulting sequence of images, concatenated from the image library, provides a photorealistic image sequence with facial features, such as lip movements, synchronized with the desired speech. This image sequence is applied to the three-dimensional model.

Abstract: Image editing techniques are disclosed that support a number of physically-based image editing tasks, including object insertion and relighting. The techniques can be implemented, for example in an image editing application that is executable on a computing system. In one such embodiment, the editing application is configured to compute a scene from a single image, by automatically estimating dense depth and diffuse reflectance, which respectively form the geometry and surface materials of the scene. Sources of illumination are then inferred, conditioned on the estimated scene geometry and surface materials and without any user input, to form a complete 3D physical scene model corresponding to the image. The scene model may include estimates of the geometry, illumination, and material properties represented in the scene, and various camera parameters. Using this scene model, objects can be readily inserted and composited into the input image with realistic lighting, shadowing, and perspective.

Abstract: Architecture for real-time extraction of maximally stable extremal regions (MSERs) is disclosed. The architecture includes communication interface and processing circuitry that is adapted in hardware to receive a data streams of an intensity image and a depth image in real-time and provide intensity labels for image regions within the intensity image that match a given intensity threshold and provide depth labels for image regions within the depth image that match a given depth threshold. The processing circuitry is also adapted in hardware to find intensity extremal regions within the intensity image based upon the intensity labels and to find depth extremal regions within the depth image based upon the depth labels. The processing circuitry determines strong extremal regions based upon significant overlap between the intensity extremal regions and depth extremal regions. The processing circuitry then determines X-MSER ellipses parameters based upon the strong extremal regions and X-MSER criteria.

Abstract: A device and method for providing a user interface using information is provided. The device includes a display unit, a sensor and a controller. The display unit displays at least one graphic user interface (GUI). The sensor generates a sensor signal according to a user's finger touch input. The controller receives the sensor signal from the sensor, identifies a touch area and an adjacent area based on the received sensor signal, generates touch finger shape-based information according to the identified touch area and the identified adjacent area, and controls the display unit to display the GUI according to the generated finger shape-based information.

Abstract: Implementations relate to feature mask determination for images. In some implementations, a computer-implemented method to determine a feature mask for an image includes estimating one or more prior regions in the image that define a feature in the image. The method determines superpixels based on multiple pixels of the image similar in color. The method constructs a graph, each node of the graph corresponding to a superpixel, and determines a superpixel score for each superpixel based on a number of pixels of the superpixel. The method determines one or more segmented regions in the image based on applying a graph cut technique to the graph based at least on the superpixel scores, and determines the feature mask based on the segmented regions. The feature mask indicates a degree to which pixels of the image depict the feature. The method modifies the image based on the feature mask.

Abstract: A dynamic time-evolution Boltzmann machine capable of learning is provided. Aspects include acquiring a time-series input data and supplying a plurality of input values of input data of the time-series input data at one time point to a plurality of nodes of the mode. Aspects also include computing, based on an input data sequence before the one time point in the time-series input data and a weight parameter between each of a plurality of input values of input data of the input data sequence and a corresponding one of the plurality of nodes of the model, a conditional probability of the input value at the one time point given that the input data sequence has occurred. Aspects further include adjusting the weight parameter so as to increase a conditional probability of occurrence of the input data at the one time point given that the input data sequence has occurred.

Abstract: A method for detecting a generalized passerby includes: acquiring an input image; determining whether a preset common feature of a wheel exists in the input image; selecting an image window at left side or right side or upper side of a center of a region where the preset common feature of the wheel is located in a case that the preset common feature of the wheel exists in the input image; inputting the selected image window into a preset upper-body classifier; detecting whether an upper body of a passerby exists in the selected image window and outputting a first detection result.

Abstract: An image processing apparatus comprises a region discrimination unit configured to discriminate object regions included in an image; a first calculation unit configured to calculate representative luminance values of a plurality of object regions discriminated by the region discrimination unit; a second calculation unit configured to calculate luminance distribution information of each of the plurality of object regions discriminated by the region discrimination unit; a determination unit configured to determine tone characteristics based on the representative luminance values of the plurality of object regions calculated by the first calculation unit and the pieces of luminance distribution information of the plurality of object regions calculated by the second calculation unit; and an image processing unit configured to perform tone correction processing based on the tone characteristics determined by the determination unit.

Abstract: A method and apparatus for guiding a mobile platform within an environment may be provided. A number of first type of data streams and a number of second type of data streams may be generated using a plurality of data systems. A probability distribution may be applied to each of the number of second type of data streams to form a number of modified data streams. The number of first type of data streams and the number of modified data streams may be fused to generate a pose estimate with a desired level of accuracy for the mobile platform with respect to an environment around the mobile platform.

Abstract: A method for processing an image, including: identifying a group of keypoints in the image; for each keypoint, calculating a corresponding descriptor array including plural array elements, each array element storing values taken by a corresponding color gradient histogram of a respective sub-region of the image in the neighborhood of the keypoint; for each keypoint, subdividing the descriptor array in at least two sub-arrays each including a respective number of elements of the descriptor array, and generating a compressed descriptor array including a corresponding compressed sub-array for each of the at least two sub-arrays, each compressed sub-array obtained by compressing the corresponding sub-array by vector quantization using a respective codebook; exploiting the compressed descriptor arrays of the keypoints for image analysis.

Abstract: Disclosed are an apparatus and a method of detecting a human component from an input image. The apparatus includes a training database (DB) to store positive and negative samples of a human component, an image processor to calculate a difference image for the input image, a sub-window processor to extract a feature population from a difference image that is calculated by the image processor for the positive and negative samples of a predetermined human component stored in the training DB, and a human classifier to detect a human component corresponding to a human component model using the human component model that is learned from the feature population.

Abstract: A method of image reconstruction for a magnetic resonance imaging (MRI) system having a plurality of coils includes obtaining k-space scan data captured by the MRI system, the k-space scan data being representative of an undersampled region over time, determining a respective coil sensitivity profile for the region for each coil of the plurality of coils, and iteratively reconstructing dynamic images for the region from the k-space scan data via an optimization of a minimization problem. The minimization problem is based on the determined coil sensitivity profiles and redundant Haar wavelet transforms of the dynamic images.

Abstract: A template document and a reference document that contains objects (e.g. text objects) are received, for example, from a scanner. A plurality of common objects between the template document and the reference document are identified. Locations of the plurality of common objects in the template document and the reference document are identified. One or more distances between the locations of the plurality of common objects in the template document and the reference document are also identified. A determination is made whether the one or more distances between the plurality of common objects in the template document and the reference document are substantially the same. In response to determining that the one or more distances between the plurality of common objects in the template document and the reference document are substantially the same, the template document and the reference document are grouped as common documents.

Abstract: A method for text-to-image matching includes generating representations of text images, such as license plate images, by embedding each text image into a first vectorial space with a first embedding function. With a second embedding function, a character string, such as a license plate number to be matched, is embedded into a second vectorial space to generate a character string representation. A compatibility is computed between the character string representation and one or more of the text image representations to identify a matching one. The compatibility is computed with a function that uses a transformation which is learned on a training set of labeled images. The learning uses a loss function that aggregates a text-to-image-loss and an image-to-text loss over the training set. The image-to-text loss penalizes the transformation when it correctly ranks a pair of character string representations, given an image representation corresponding to one of them.

Abstract: According to one embodiment, a handwritten document processing apparatus includes an inputter, classifier, divider, and determiner. The inputter inputs stroke data. The classifier classifies the stroke data into data of a plurality of ruled lines and stroke data other than ruled lines. The divider divides a region including the plurality of ruled lines into first regions each corresponding to a cell bounded by four ruled lines and second regions each including at most three ruled lines. The determiner determines whether a ruled line in the second region is a first ruled line, to one end point of which a ruled line is not connected, or a second ruled line, to one end point of which a virtual circumscribed ruled line is connected.

Abstract: According to one aspect of the present disclosure, a method and technique for dynamic adjustment of authentication mechanism is disclosed. The method includes: collecting location data of one or more agents relative to an agent attempting to authenticate to a data processing system; determining if the location data meets a threshold value; and responsive to the location data meeting the threshold value, relaxing an authentication scheme for the attempting agent to authenticate to the data processing system.

Abstract: A system for controlling vehicle systems includes a haptic actuator, a gesture detection device, a controller, and a plurality of vehicle systems. The gesture detection device captures movements of a vehicle driver or passenger and outputs data representing a gesture made by the vehicle driver or passenger. The controller is coupled to the gesture detection device and receives a signal from the gesture detection device indicative of the gesture. The controller is coupled to the haptic actuator, and selects a haptic effect based on the detected gesture and sends a signal to the haptic actuator to provide the selected haptic effect. The controller is also coupled to the vehicle systems, and based on the detected gesture, the controller sends a signal to one of the vehicle systems to perform a particular action. The particular action of the vehicle system is matched with the selected haptic effect.

Abstract: An image processing device includes a composite processing unit that generates a composite image for display by including a through image generated based on a captured image signal obtained by performing photoelectric conversion for light incident from a subject in an image for a compositing process and composites a captured image of a recording time point in the image for a compositing process in accordance with a compositing arrangement state of the through image in the composite image for display, and a display control unit that performs display control for the composite image for display.

Abstract: Method and system for detecting objects of interest in a camera monitored area are disclosed. Statistical analysis of block feature data, particularly Sobel edge and spatial high frequency responses is used to model the background of the scene and to segregate foreground objects from the background. This technique provides a robust motion detection scheme prone to catching genuine motions and immune against false alarms.

Abstract: The disclosure provides an image processing device, image processing method, scanner and storage medium. The image processing device is used for tracing a boundary of an object image in an image, the boundary being continuous and the rate of change in slope between adjacent points on the boundary being slow. The image processing device includes: a boundary estimation unit, adapted to estimate the location of the boundary of the object image; an interfering gradient processing unit, adapted to process an interfering gradient near the estimated boundary, so as to reduce the interfering gradient or remove the interfering gradient from the image; and a boundary tracing unit, adapted to trace the boundary in the image having the interfering gradient processed. By using the technique of the disclosure, the accuracy of tracing a boundary of an image is improved significantly.

Abstract: Disclosed are a touch gesture recognition apparatus and method that can be, or applied to, both a single-touch system and a multi-touch system. The touch gesture recognition method recognizes touch gestures using the diagonal-line length of a bounding box created based on touch location information and variations in the diagonal-line length. After a gesture is recognized, the recognized gesture is mapped to an input event of a user input device and feedback according to the input event is provided.

Abstract: An input user interface device includes an image pickup unit which picks up an image including an object image, a shape detection unit which detects a shape of the object image in the image picked up by the image pickup unit, a determination unit which determines whether the shape of the object image detected by the shape detection unit corresponds to a shape associated with a gesture command or a shape associated with a position designation command for designating a position data, and a command deciding unit which decides the gesture command or the position designation command on the basis of the decision by the deciding unit.

Abstract: A method and apparatus for describing an image are disclosed. The method for describing an image according to an embodiment of the invention includes: transforming an image from a BGR color space into a Gaussian derivative color model; and transforming the image from the Gaussian derivative color model into an optical reflection invariant color space, wherein the process of transforming the image from the Gaussian derivative color model into the optical reflection invariant color space includes: determining, for each pixel on the image, color channels of the pixel corresponding to the optical reflection invariant color space according to a first coefficient and a second coefficient of the pixel in the Gaussian derivative color model. The embodiments of the invention can alleviate an error in a description of an image of the same contents but with a significant change in color.

Abstract: A display drive integrated circuit includes a single full frame memory having a first half frame memory region and a second half frame memory region, a mode determination unit and a control unit. The mode determination unit determines the received image data type (still image or video) and accordingly selects a normal mode or an enhance mode associated with a display quality. The control unit operates in the normal mode or the enhance mode in response to an output of the mode determination unit. In an enhance mode, the control unit divides the single full frame memory into a first half frame memory region and a second half frame memory region to store compressed image data of a current frame in the first half frame memory region and compressed image data of a previous frame in the second half frame memory region.

Abstract: There is described a method for the creation of at least a second, virtual image (200) from a first image (100) captured by a user or retrieved from a storage device to aid interpretation of image content. This allows, for instance, implementing a multishot image quality enhancement scheme based on the real image and the virtual image.

Abstract: A device for determining a gesture includes a light emitting unit, an image sensing device and a processing circuit. The light emitting unit emits a light beam. The image sensing device captures an image of a hand reflecting the light beam. The processing circuit obtains the image and determine a gesture of the hand by performing an operation on the image; wherein the operation includes: selecting pixels in the image having a brightness greater than or equal to a brightness threshold; sorting the selected pixels; selecting a first predetermined percentage of pixels from the sorted pixels; dividing the adjacent pixels in the first predetermined percentage of pixels into a same group; and determining the gesture of the hand according to the number of groups of pixels. A method for determining a gesture and an operation method of the aforementioned device are also provided.

Abstract: A method and an arrangement for use in a device, such as a communication device, may be configured to generate an assembly based on one or more images. The system may include an image retrieval portion for retrieving the one or more images from an image source, an arrangement for fetching data corresponding to the one or more images, and converting the data to presentable information, and an arrangement for generating the assembly including the one or more images and the presentable information provided with description.

Abstract: An image measuring system comprises a projection optical system, having a light source for emitting and projecting an illumination light through a light projection optical axis. The system further comprises a photodetection optical system, having an image pickup element, which receives a retroreflection light from an object to be measured through a photodetection optical axis, and a control arithmetic device for processing the data taken by the image pickup element. The projection optical system comprises a light projection unit for directing the light projection optical axis toward the object to be measured and projecting the illumination light, a projection angle changing means for rotating the light projection unit in an elevating and a horizontal direction and for changing a projection angle of the illumination light, and a direction detecting means for detecting a direction angle of the light projection optical axis with respect to the photodetection optical axis.

Abstract: A reading apparatus includes a first generation unit, a determination unit, a second generation unit, and an association unit. The first generation unit generates data of a first target object obtained by using an image capture unit attached above a reading platen to read the first target object placed in a reading area of the reading platen. The determination unit determines, in a state where the first target object is placed in the reading area, whether a second target object has been placed in the reading area. The second generation unit generates data of a second target object obtained by using the image capture unit to read the second target object. The association unit associates, in response to determining that the second target object has been placed in the reading area, the data of the first target object with the data of the second target object.

Abstract: A video processing device has an input for receiving video data, at least one processing circuit, for generating processed video data from the received video data, and a memory, for receiving the processed video data. An output circuit reads the processed video data from the memory, and generates frames of data including at least the processed video data. In order to be able to operate with an output clock frequency that may differ from the ideal output clock frequency, it is possible to vary the frame size, that is, the number of pixels of data in a frame. If an amount of processed video data stored in the memory exceeds an upper threshold, then the frame size can be reduced by reducing the number of pixels of blanking data in the output frame, thereby increasing the rate at which data is read from the memory.

Abstract: A computing device and/or application executing on the device can utilize fingertip tracking using a camera. However, when the fingertip is in a dead zone (an area that is not viewable by the camera), the fingertip tracking cannot function properly. Nevertheless, the position of the fingertip, when in the dead zone, can still be estimated. An image of a user's hand can be captured by at least one camera. A portion of a pointing finger can be detected in the captured image. An orientation of the portion of the pointing finger can be determined. One or more joint lines of the pointing finger can be identified. Based on data about a slant and/or a bend of the pointing finger obtained using information relating to the identified joint line(s), and/or on data obtained via calibration and/or historic/current usage, the position of the fingertip, when in the dead zone, can be approximated.

Abstract: A noninvasive, quantitative imaging technique is presented for detecting and diagnosing liver disease, such as cirrhosis. The technique includes: capturing scan data from a subject using computed tomography or another type of imaging method and extracting image data representing the liver from the scan data. Various measures of the liver may be obtained from image data and then used to compute random variables of a statistical model, where the model is predictive of a medical condition of the liver and comprised of random variables that are indicative of at least one of a shape or texture of the liver. Output from the statistical model provides an indication of an undesirable condition of the liver.

Abstract: An image processing apparatus comprises an anchor point candidate information extraction unit configured to decide coordinates of anchor point candidates and attributes of the anchor point candidates based on a plurality of predetermined extraction rules and a sequence of coordinate points that expresses an outline of image data; an anchor point decision unit configured to decide an anchor point candidate to be reduced based on the attributes of the anchor point candidates and priority orders set in advance for the attributes, and configured to decide anchor points by reducing the decided anchor point candidates to be reduced; a control point coordinate decision unit configured to decide control point coordinates based on the anchor points decided by the anchor point decision unit and the sequence of coordinate points; and a data output unit configured to output information including the coordinates of the decided anchor points and the decided control point coordinates.

Abstract: A measuring device to aid mattress selection has an upstanding frame with a plurality of vertically space-apart horizontal illuminated strips. A camera mounted in front of the frame takes front view and side view images of a person standing in front of the illuminated strips. These images are delivered to an associated computer having means to determine the body mass distribution and the spine curvature of the person based on the images of the strips taken by the camera and in particular based on those portions of the image of the illuminated strips blocked by the person standing in front of the illuminated strips. This information can then be used to aid in appropriate mattress selection for the person.

Abstract: This shape data generation method include: setting an input shape that has a simple shape that has a same topology as the target shape for a target shape that is a shape of a transformation target identified from image data; identifying first vertices that satisfy a predetermined condition including a first condition that a normal line of a certain vertex of the plural vertices crosses with the target shape, among plural vertices of the input shape; transforming the input shape so that a first vertex is moved in a direction of a normal line of the first vertex by a first distance that is shorter than a distance up to the target shape; and performing the identifying and the transforming a predetermined number of times while changing the input shape after the transforming as the input shape to be processed.

Abstract: Interactive drawing recognition is described using status determination. In one example, a computer system status is determined and then used to determine a type of drawing. A user drawing is observed and a library of drawing templates associated with the determined drawing type is accessed. The observed drawing is compared to the drawing templates to identify the observed drawing, and attributes are assigned to the identified drawing.

Abstract: An information processing device includes: a recognizer configured to recognize a predetermined part of a body of a person from an input image including the person; an evaluator configured to evaluate a difference between a recognized input part and a reference part serving as a basis; and a notifying unit configured to notify information relating to the difference of the input part from the reference part based on an evaluation result.

Abstract: Techniques for object detection are provided that employ limited learned attribute ranges. One or more objects are initially detected for a full range of one or more attributes at each location of an image. Thereafter, a set of positional constraints are generated indicating an expected range of values for each position in the image for one or more of the attributes based on the detected objects employing a geometric model of a scene in the image. Objects are then detected in the image using the expected range of values for each position in the image for the one or more the attributes. The attributes comprise, for example, one or more of size, pose and rotation of the objects. A best fit is computed to the geometric model to generate the set of positional constraints, for example, using a least squares approach.

Abstract: A method of processing an image by using an image processing apparatus is provided. The method includes acquiring, by the image processing apparatus, a target image, extracting a shape of a target object included in the target image, determining a category including the target object based on the extracted shape, and storing the target image by mapping the target image with additional information including at least one keyword related to the category.