Abstract: The degree of similarity between corresponding local feature amounts out of a plurality of local feature amounts of the object in the input image and a plurality of local feature amounts of an object in an image registered in advance is obtained. At least one degree of similarity is selected out of the obtained degrees of similarity based on a capturing condition for the object in the input image and a capturing condition for the object in the registered image, and one degree of similarity is derived from the at least one selected degree of similarity. It is determined based on the one derived degree of similarity whether the object in the input image belongs to the same category as the object in the registered image.

Abstract: A computer model of a physical object may be formed by registering multiple images of the physical object by using a registration process based on characteristic features of the physical object. Multiple images may be registered by aligning characteristic curves of the physical object that have been identified through imaging. A curve-based registration process may be used in dental applications to register multiple images of a patient's oral anatomy to form a computer 3D model from which a patient-specific dental restoration may be designed.

Abstract: An information processing system may include a memory storing instructions and one or more processors configured to execute the instructions to receive inputs of pictures imaged by a plurality of imaging apparatuses. The system may detect a moving body appearing in an inputted picture imaged by a first imaging apparatus among the plurality of imaging apparatuses. The system may predict a time period in which the moving body will appear in a picture imaged by a second imaging apparatus among the plurality of imaging apparatuses, based on a calculated probability that the moving body will appear in the picture imaged by the second imaging apparatus and an elapsed time after the moving body leaves an imaging range. The system may notify the predicted time period in which the moving body is predicted to appear in the picture imaged by the second imaging apparatus.

Abstract: A method for detecting and tracking a target includes detecting the target using a plurality of feature cues, fusing the plurality of feature cues to form a set of target hypotheses, tracking the target based on the set of target hypotheses and a scene context analysis, and updating the tracking of the target based on a target motion model.

Abstract: Enhanced contrast between an object of interest and background surfaces visible in an image is provided using controlled lighting directed at the object. Exploiting the falloff of light intensity with distance, a light source (or multiple light sources), such as an infrared light source, can be positioned near one or more cameras to shine light onto the object while the camera(s) capture images. The captured images can be analyzed to distinguish object pixels from background pixels.

Abstract: In a mask inspection apparatus, an optical image acquisition unit acquires an optical image of a pattern in a mask by irradiating light. A reference image generation unit generates a corresponding reference image. A defect detection unit detects a defect of the pattern by comparing the two images. A misplacement data processing unit obtains a misplacement amount of the pattern from the images, and generates misplacement data. A misplacement map processing unit generates and outputs the map to the defect detection unit. The defect detection unit includes, a first comparison unit for comparing the images, a threshold value reconfiguring unit for specifying a portion of the map corresponding to the defect detected, reconfiguring a threshold value according to the shape of the defect and the misplacement direction of the optical image of the specified portion, and a second comparison unit for re-comparing both images using the reconfigured threshold value.

Abstract: Techniques to verify a participant's visit to a specific location are described. An embodiment may provide a system that generates a pattern that is unique to the location, and that may further be unique to a date or time, a transaction, or other criteria. Participants may capture the pattern, for example, using a mobile device, and transmit the pattern to a verification system. The verification system may decode, translate, decrypt or otherwise obtain information from the pattern. The information obtained from the pattern may be used to verify that the pattern came from the location. The participant may then receive credit for the visit. Other embodiments are described and claimed.

Abstract: A video action detection system uses feature a data extractor to extract feature data from video data at detected spatiotemporal interest points. A feature data quantizer assigns the extracted feature values to bins of a feature vector. Bin values are computed from a sum of contributions of spatiotemporal points of interest that have been assigned to the bin, with a bin dependent adjustment of a size of the sum and/or the contributions. The video action detection system computes a sum of match scores between the feature vector and reference vectors for the predetermined type of action. The bin dependent adjustment of the size of the sum and/or the contributions is adapted in a training step, based on partial match scores for individual bins obtained using an initial action detector.

Abstract: A position information adding apparatus includes: a reference position setting unit which sets a plurality of reference positions for each of a plurality of pictures contained in digitalized video data; a region setting unit which sets a first position information adding region at a first position defined based on at least any of the plurality of reference positions and a second position information adding region at a second position different from the first position, for each of the plurality of pictures; and a position information embedding unit which embeds a first moving pattern which moves on the pictures in a first temporal period into the first position information adding region and a second moving pattern which moves on the pictures in a second temporal period into the second position information adding region.

Abstract: An image processing system and method is provided. The image processing system includes extracting a first local statistical characteristics from an observed image, generating a low-pass filter according to the first local statistical characteristics to generate a predicted noise image, and extracting second local statistical characteristics from the predicted noise image, extracting a third local statistical characteristics from a predicted original image using the first local statistical characteristics of the observed image and the second local statistical characteristics of the predicted noise image, and setting a flag level indicating a noise level for each pixel of the observed image according to the third local statistical characteristics of the predicted original image to detect noise, and setting a filter coefficient according to the flag level of the detected noise to remove the noise, and restoring the observed image.

Abstract: Techniques for improved focusing of camera arrays are described. In one embodiment, a system may include a processor circuit, a camera array, and an imaging management module for execution on the processor circuit to capture an array of images from the camera array, the array of images comprising first and second images taken with first and second values of an exposure parameter, respectively, the first value different than the second value, to estimate a noise level, to normalize an intensity of each image based upon the noise level of the respective image, to produce a respective normalized image, to identify candidate disparities in each of the respective normalized images, to estimate a high dynamic range (HDR) image patch for each candidate disparity, and to compute an error from the HDR image patch and an objective function, to produce a disparity estimate. Other embodiments are described and claimed.

Abstract: An automated self-monitored alarm verification solution including at least a premises portion, a server portion, and an end user device portion. Alarm verification includes capturing by an image capture device at least one image in response to a detection event, and transmitting a first data signal including the image to a local signal processing device. The signal processing device transmits a second signal including at least a portion of the image to a remote hosted server according to at least a first set of predetermined parameters. After receiving the second signal, the server transmits a third signal including at least a portion of the image from the hosted server to a user device. Using the user device, a user views the image and indicates a validity status of the alarm based at least in part on the content of the image.

Abstract: A non-parametric method of, and system for, dimensioning an object of arbitrary shape, captures a three-dimensional (3D) point cloud of data points over a field of view containing the object and a base surface on which the object is positioned, detects a base plane indicative of the base surface from the point cloud, extracts the data points of the object from the point cloud, processes the extracted data points of the object to obtain a convex hull, and fits a bounding box of minimum volume to enclose the convex hull. The bounding box has a pair of mutually orthogonal planar faces, and the fitting is performed by orienting one of the faces to be generally perpendicular to the base plane, and by simultaneously orienting the other of the faces to be generally parallel to the base plane.

Abstract: Image-processing apparatus and methods to adaptively vary an interest point threshold value and control a number of interest points identified in an image frame are described. Sub-regions of an image frame may be processed in a sequence, and an interest point threshold value calculated for each sub-region. The calculated value of the interest point threshold may depend upon pre-selected values and values determined from the processing of one or more prior sub-regions. By using adaptive thresholding, a number of interest points detected for each frame in a sequence of image frames may remain substantially constant, even though objects within the frames may vary appreciably.

Abstract: A measurement vector of compressive measurements is received. The measurement vector may be derived by applying a sensing matrix to a source signal. At least one first feature vector is generated from the measurement vector. The first feature vector is an estimate of a second feature vector. The second feature vector is a feature vector that corresponds to a translation of the source signal. An anomaly is detected to in the source signal based on the first feature vector.

Abstract: Foreground feature data and motion feature data is determined for frames of video data acquired from an object region of interest. The frames are labeled as “object present” if the determined foreground feature data value meets a threshold value, else as “object absent; and as “motion present” if the motion feature data meets a motion threshold, else as “static.” The labels are used to classify segments of the video data comprising groups of consecutive video frames, namely as within a “no object present” segment for groups with “object absent” and “static” labels; within a “object present and in transition” segment for groups “object present” and “motion present” labels; and within a “object present and stopped” segment for groups with “object present” and “static” labels. The presence or motion state of an object at a time of inquiry is thereby determined from the respective segment classification.

Abstract: A conversion apparatus is disclosed, including: a storage unit; and a processor configured to perform a conversion process. In the conversion process, a handwriting input for a specific position in a text is received. Conversion candidates for the handwriting input is generated based on context information acquired by analyzing before, after, or around the specific position of the text.

Abstract: According to one embodiment, a surgical system includes an imaging system, a determination unit, and a control unit. The imaging system is configured to acquire image information. The determination unit is configured to determine, based on the image information, whether an abnormal state has occurred in the surgical system. The control unit is configured to switch to an abnormality time control mode of executing abnormality-handling processing, when the determination unit determines that an abnormal state has occurred.

Abstract: An image processing apparatus includes a component acquisition unit that acquires a chromaticity component and a luminance component from each of a process target image and a reference image, a feature quantity extraction unit that extracts a feature quantity from the chromaticity component and the luminance component of each of the process target image and the reference image, a chromaticity component adjustment unit that matches the chromaticity component of the process target image to the chromaticity component of the reference image using the feature quantity of the chromaticity component, and a luminance component adjustment unit that matches the luminance component of the process target image to the luminance component of the reference image in a non-dark region other than a dark region, and reduces an amount of adjustment in the adjustment of the dark region to be smaller than an amount of adjustment applied to the non-dark region.

Abstract: The invention relates to a method for evaluating a plurality of chronologically staggered images, said method comprising the following steps: detecting a plurality of objects in a first image and storing each of the plurality of objects as tracks with a first capture time and/or a first capture location, preferably in a track list, detecting a plurality of objects in further images and identifying each of the detected objects as an object assigned to the respective stored track, wherein the respective track is updated by the current position of the identified object and, in the respective further images, objects detected for the first time are stored with assigned tracks, and wherein a covered path length, a distance and/or a time difference from the first capture time is determined as a capture period for each of the objects or tracks, wherein the path length, the distance and/or the capture period are compared with a respective predefined threshold value, and wherein the objects or tracks are classifie