Abstract: Disclosed are a system and a method for motion editing multiple synchronized characters. The motion editing system comprises: a Laplacian motion editor which edits a spatial route of inputted character data according to user conditions, and processes the distortion of the interaction time; and a discrete motion editor which applies a discrete transformation while the character data is processed.

Abstract: A technique for controlling a navigation device to generate a navigation maneuver graphics for a road junction maneuver is proposed. A device embodiment of this technique comprises a routing module adapted to provide routing information pertaining to a scheduled route, with the scheduled route comprising the road junction. Furthermore, an interface to a map database is provided, with the map database containing road data pertaining to the upcoming road junction. A processor of the navigation device analyzes the road data to determine one or more junction geometry parameters of the road junction and to compose, based on the junction geometry parameters and from a plurality of pre-defined graphical junction elements, junction graphics data representative of the road junction. The processor is further adapted to generate, from the routing information and the junction geometry parameters, maneuver indication graphics data representative of the junction maneuver.

Abstract: A curve division device is provided enabling a multiprocessor system to perform effective curve division on Bézier curves. The curve division device comprises: N (N?2, N being an integer) processor elements; a reception unit receiving curve information indicating a Bézier curve; a first execution unit causing the N processor elements to execute a division algorithm of taking the curve information as initial input data and repeatedly (i) generating two divided curves by dividing the Bézier curve indicated by the input data, (ii) selecting one of the divided curves according to the assigned setting value, and (iii) defining new input data indicating the divided curve selected for subsequent division, until the divided curve selected by each processor element is different; and a second execution unit causing each processor element to execute a determination algorithm of determining line segments approximating a divided curve resulting from the division algorithm.

Abstract: A system, method and a computer-readable medium for creating texture exemplars from images are provided. The texture exemplars are created by receiving an image containing a plurality of pixels representing a plurality of textures, wherein each texture in the plurality of textures is configured to be selectable by a user, determining a desired texture in the plurality of textures contained within the image and defining a scale of the desired texture, generating a heat mapping of the image, wherein the heat mapping indicates location of the desired texture, generating, based on the heat mapping, a plurality of tiles corresponding to the defined scale of the desired texture, and generating an exemplar of desired texture.

Abstract: A method for generating time-resolved 3D medical images of a subject by imparting temporal information from a time-series of 2D medical images into 3D images of the subject. Generally speaking, this is achieved by acquiring image data using a medical imaging system, generating a time-series of 2D images of a ROI from at least a portion of the acquired image data, reconstructing a 3D image substantially without temporal resolution from the acquired image data, and selectively combining the time series of 2D images with the 3D image. Selective combination typically involves registering frames of the time-series of 2D images with the 3D image, projecting pixel values from the 2D image frames “into” the 3D image, and weighting the 3D image with the projected pixel values for each frame of the time-series of 2D images.

Abstract: A dictionary of atoms for coding data is learned by first selecting samples from a set of samples. Similar atoms in the dictionary are clustered, and if a cluster has multiple atoms, the atoms in that cluster are merged into a single atom. The samples can be acquired online.

Abstract: A method and system for achieving accurate segmentation of characters with respect to a license plate image within a tight bounding box image. A vehicle image can be captured by an image capturing unit and processed utilizing an ALPR unit. A vertical projection histogram can be calculated to produce an initial character boundary (cuts) and local statistical information can be employed to split a large cut and insert a missing character. The cut can be classified as a valid and/or a suspect character and the suspect character can be analyzed. The suspect character can be normalized and passed to an OCR module for decoding and generating a confidence quote with every conclusion. The non-character images can be rejected at the OCR level by enforcing a confidence threshold. An adjoining suspect narrow character can be combined and the OCR confidence of the combined character can be assessed.

Abstract: A method for searching a database comprising data related to a plurality of fingerprints. In step 301, two or more feature points in an image of an unknown fingerprint are identified. A plurality of properties are generated in step 302. The plurality of properties are based on the two or more feature points. In step 303, a number comprising a plurality of digits, e.g. binary digits, is assigned to each of the plurality of properties. In a subsequent step, step 304, a numeric representation of said fingerprint is generated based on the assigned numbers. The numeric representation is generated by interleaving the plurality of digits, such that the digits of the numeric representation are arranged in an interleaved or intertwined manner within the numeric representation. In step 305, the numeric representation is used as a search argument when searching the database. The invention also relates to an apparatus and computer program product.

Abstract: A system and method of use are provided for generating video fingerprints that are robust to rotation, stretching, scaling, flipping and other affine transformations. The system and method are based on determining points of interest for a target video image and a collection of images stored in a database. A method of identifying a copied video image is also provided through comparison of the fingerprint of the target video image with fingerprints of images in a database. The method of video fingerprinting involves: defining points of interest from a video image, determining an oriented bounding area encompassing said points of interest that have been transformed by the same transformations used to produce the oriented bounding area and creating a fingerprint by encoding the points of interest as Gray Code such that similar images have a small Hamming distance and dissimilar images have a large Hamming distance.

Abstract: Identifying and ensuring object authenticity can occur by identifying an object by acquiring an image of the object, identifying flaws present in or on the object, associating the flaws with respective locations or regions in the image, determining a quality score indicating a condition of the object based at least upon an analysis of the identified flaws, and generating and storing a data record with all of this identifying information. A tag which provides an identifier that links the object to the data record is placed on the object. When authenticity of the object needs to be verified at a later time, the tag identifier is retrieved and used to retrieve the data record. The identifying information can then be compared with the object as it currently appears. If the object as it currently appears corresponds with the identifying information, authenticity is verified. Otherwise, fraud can be suspected.

Abstract: An image conversion parameter calculation device accurately calculates a conversion parameter for image alignment with a processing amount that does not depend on the size of an image to be aligned. A pixel selection element randomly selects pixels from a predetermined number or pixels of not more than the predetermined number from a first image. A parameter derivation element derives a conversion parameter by performing processing for pixels selected by the pixel selection element, the conversion parameter being a parameter for converting, to the first image, a second image that is subject to image alignment with the first image.

Abstract: A method of embedding image-related information in an image, the method including: receiving an image including a plurality of frames; receiving information related to the image; generating a codeword by encoding the image-related information; and embedding the image-related information in the image by substituting macroblocks included in at least one of the plurality of frames of the image based on the generated codeword.

Abstract: A method of decoding an image includes performing entropy-decoding to obtain quantized transformation coefficients of at least one transformation unit in a coding unit of the image, determining a prediction mode of at least one prediction unit in the coding unit from information indicating a prediction mode for the at least one prediction unit, when the prediction mode is determined to be an inter prediction mode, not in an intra prediction mode, determining a size of the at least one transformation unit in the coding unit regardless of a size of the at least one prediction unit in the coding unit, performing inverse-quantization and inverse-transformation on the quantized transformation coefficients of the at least one transformation unit to obtain residuals, and performing inter prediction for at least one prediction unit in the coding unit to generate a predictor and restoring the image by using the residuals and the predictor.

Abstract: An image processing apparatus is provided. A silhouette extractor may extract a silhouette image of a target object from an input depth image. A first calculator may determine a location of at least one limb of the target object and a location of at least one joint connecting the at least one limb by applying a rectangle fitting algorithm with respect to the silhouette image.

Abstract: Potential threat items may be concealed inside objects, such as portable electronic devices, that are subject to imaging for example, at a security checkpoint. Data from an imaged object can be compared to pre-determined object data to determine a class for the imaged object. Further, an object can be identified inside a container (e.g., a laptop inside luggage). One-dimensional Eigen projections can be used to partition the imaged object into partitions, and feature vectors from the partitions and the object image data can be used to generate layout feature vectors. One or more layout feature vectors can be compared to training data for threat versus non-threat-containing items from the imaged object's class to determine if the imaged object contains a potential threat item.

Abstract: An image processing apparatus includes an image input unit configured to input an image, a scanning unit configured to scan a detection window on the input image, a first discrimination unit configured to determine whether a pattern within the detection window is a subject based on a plurality of characteristic amounts obtained from within a first region among a plurality of regions within the detection window, and a second discrimination unit configured to determine, if it is determined that the pattern is not the subject by the first discrimination unit, whether the pattern is the subject based on a plurality of characteristic amounts obtained from a second region in which a probability that occlusion of the subject occurs is higher than that in the first region among the plurality of regions. Accordingly, a subject can be detected efficiently, and omissions of detection can be reduced.

Abstract: An apparatus and method to find a specified number of corners and/or interest points in an image is presented. In some embodiments, a method to find a specified number of corners in a digital image comprises receiving a digital image containing a plurality of candidate corners; directly calculating a threshold score (S) for a center pixel, for each of the plurality of candidate corners, to form a plurality of scores; sorting, by the plurality of scores, the plurality of candidate corners to form a sorted list; and selecting corner locations sequentially from the sorted list based on the certain number of corners. The methods described may be implemented using any combination of hardware, software and firmware.

Abstract: Contact-less remote-sensing crack detection and/quantification methodologies are described, which are based on three-dimensional (3D) scene reconstruction, image processing, and pattern recognition. The systems and methodologies can utilize depth perception for detecting and/or quantifying cracks. These methodologies can provide the ability to analyze images captured from any distance and using any focal length or resolution. This adaptive feature may be especially useful for incorporation into mobile systems, such as unmanned aerial vehicles (UAV) or mobile autonomous or semi-autonomous robotic systems such as wheel-based or track-based radio controlled robots, as utilizing such structural inspection methods onto those mobile platforms may allow inaccessible regions to be properly inspected for cracks.

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: According to one embodiment, a facial image search system including attribute discrimination module configured to discriminate attribute based on facial feature extracted, a plurality of search modules configured to store facial feature as database in advance, add facial feature extracted to database, calculate degree of similarity between facial feature extracted and facial feature contained in database, setting module configured to generate setting information by associating with any attribute with information indicating search module, and control module configured to identify one or a plurality of search modules based on setting information and attribute and transmit facial feature extracted by feature extraction module to identified search modules.