Abstract: A system and method for coordinating processing of a cardholder present financial transaction between the cardholder and a merchant system. The system collects a transaction amount of the financial transaction associated with merchant identification information of the merchant system. The system sends an authentication request using a wireless communication protocol configured for proximity communication between a communication interface of a computer device and a wireless communication enabled integrated circuit (IC) chip of a payment card, the authorization request including an IC command expected by computer hardware of the IC chip. The system receives an authentication response from the computer hardware of the IC chip by the wireless communication protocol, the authentication response including an encrypted value generated by the computer hardware of the IC chip.

Abstract: Methods and systems are provided for facilitating control of a child's purchasing of products from a merchant using a credit card, debit card, gift card, secure token, mobile device, or the like. A payment provider, such as Paypal, Inc., can authorized the purchase of a product from the merchant if both the child and the parent are checked in with the same merchant via one or more social networks (thereby indicating that the child and the parent are in or near the same store). This requirement for proximity between the child and the parent can provide the parent with an opportunity to more closely monitor purchases made by the child.

Abstract: An apparatus comprises a memory and a processor. The memory is operable to store information associated with a user account. The processor can receive a message indicating that a transaction associated with a card has occurred and receive a first input indicating that the transaction is fraudulent. The processor can receive a second input indicating that a report should be filed and present, on a display, a plurality of questions to determine whether the card has been stolen. The processor can receive a third input indicating an answer to each of the plurality of questions and present, on the display, an affidavit. The processor can receive a fourth input indicating the affidavit has been electronically signed and present, on the display, a confirmation message indicating that the report has been filed.

Abstract: A method for updating expiry information of an account is provided. Additionally, a prediction computing device for updating expiry information of an account is provided. Further, a computer-readable storage medium having computer-executable instructions embodied thereon for updating expiry information of an account is provided.

Abstract: A system and method for providing advertising server optimization for online computer users is disclosed. A particular embodiment includes obtaining an advertisement; defining a set of features of the advertisement; generating a predicted click through rate (CTR) corresponding to the advertisement based in part on the set of features; ranking the advertisement based on the generated click through rate; and serving the advertisement based on the ranking.

Abstract: Methods and apparatus to estimate demography based on aerial images are disclosed. An example method includes analyzing a first aerial image of a first geographic area to detect a first plurality of objects, analyzing a second aerial image of a second geographic area to detect a second plurality of objects, associating first demographic information to the second plurality of objects, the first demographic information obtained by a sampling of the second geographic area, and comparing the second plurality of objects to the first plurality of objects to estimate a demographic characteristic of the first geographic area based on the comparison.

Abstract: Selecting a content filler from a plurality of content fillers in a satellite broadcast comprises receiving a content in a first broadcast frequency channel, and a plurality of content fillers in a respective plurality of second broadcast frequency channels, wherein the content includes a gap in content to be filled by one of the plurality of content fillers, the gap in content defined by a start indicator and an end indicator. The receiver transmits the content to a display device. The receiver determines a second broadcast frequency channel, from among the plurality of second broadcast frequency channels and responsive to receiving the start indicator, switches to the determined second broadcast frequency channel, transmits the content filler in the determined second broadcast frequency channel to the display device. Responsive to receiving the end indicator, the receiver switches to the first broadcast frequency channel and transmits the content to the display device.

Abstract: Selecting a content filler from a plurality of content fillers in a satellite broadcast comprises receiving a content in a first broadcast frequency channel, and a plurality of content fillers in a respective plurality of second broadcast frequency channels, wherein the content includes a gap in content to be filled by one of the plurality of content fillers, the gap in content defined by a start indicator and an end indicator. The receiver transmits the content to a display device. The receiver determines a second broadcast frequency channel, from among the plurality of second broadcast frequency channels and responsive to receiving the start indicator, switches to the determined second broadcast frequency channel, transmits the content filler in the determined second broadcast frequency channel to the display device. Responsive to receiving the end indicator, the receiver switches to the first broadcast frequency channel and transmits the content to the display device.

Abstract: A device for making a one-touch connection wireless communication using a merchandising product with a marketing message. A merchant delivers a merchandising product to a user. The merchandising device contains an electronic module that comprises memory that stores multimedia and an identifier such as telephone number. The electronic module contains the components necessary to play the multimedia on an output device, such as a speaker or video screen. The electronic module also contains the components necessary to connect to a wireless network and to place a wireless communication using the wireless network to the identifier when a dial switch is triggered. The electronic module is activated by a main switch. In one embodiment, upon activation, the electronic module plays the multimedia on the output device. When the user triggers the dial switch, the module makes a wireless communication with the stored identifier. The wireless communication may be voice, text, e-mail and/or other digital data.

Abstract: A system and method of selective advertising where an advertiser can decide whether or not to advertise to a certain user based on credential information submitted by that user. The user provides his or her credential information to a search engine and enters a search query. In response, the search engine evaluates the user's credential information and compares that information to criteria provided by advertisers that participate with that search engine. The search engine determine which advertisers have indicated a willingness to advertise to a user with the submitted credentials and selectively provides matching search results.

Abstract: System and methods for physical toy and virtual toy interactions are disclosed. According to aspects of the invention, a system for purchasing a physical toy and a corresponding virtual toy comprises a video game console, a physical toy, and a virtual toy corresponding to the physical toy. The virtual toy corresponding to the physical toy may be made available in a video game played on the video game console. The physical toy may be purchased by a user of the system from an external merchant. The virtual toy corresponding to the physical toy may be separately purchased by the user from a purchasing system within the video game. The physical toy may be registered with the gaming platform. If the user registers the physical toy with the gaming platform and the user previously purchased the virtual toy, the system refunds to the user the purchase price of virtual toy.

Abstract: Systems and methods to provide search results along a corridor are discussed. In an example, a method for providing search results along a corridor can include displaying an interface enabling a user to define a route of travel, accessing a search corridor, filtering a plurality of search results, and displaying the search results. The search corridor encompassing at least a portion of the route of travel, and based at least in part on the route of travel, a mode of transportation, and a route deviation threshold. The plurality of search results including an associated geographic location, and filtered based at least in part on the search corridor. Displaying the search results can include a representation of the search corridor, the route of travel, and the filtered set of search results.

Abstract: Methods and arrangements involving portable devices, such as smartphones and tablet computers, are disclosed. Exemplary arrangements utilize the camera portions of such devices to identify nearby subjects, and take actions based thereon. Others rely on near field chip (RFID) identification of objects, or on identification of audio streams (e.g., music, voice). Some of the detailed technologies concern improvements to the user interfaces associated with such devices. Others involve use of these devices in connection with shopping, text entry, sign language interpretation, and vision-based discovery. Still other improvements are architectural in nature, e.g., relating to evidence-based state machines, and blackboard systems. Yet other technologies concern use of linked data in portable devices—some of which exploit GPU capabilities. Still other technologies concern computational photography. A great variety of other features and arrangements are also detailed.

Abstract: The invention provides: methods, languages, and systems for parallel algorithmic trading of financial instruments. Each instrument of interest is included in a parallel list, in a reference list, or in both lists. Market data messages are decoded by parallel threads and converted into data series. The number of the threads is preferably equal to the number of the messages in a set of messages. A trader/market regulator selects or creates a trading/overseeing algorithm consisting of expressions based on data series extracted from the messages and on predefined functions. Some of the expressions have outputs representing buy/sell/cancel orders or have outputs aimed for overseeing trading activity. The algorithm is executed by parallel threads. The number of the threads is preferably equal to the number of the instruments in the parallel list.

Abstract: Various techniques can be used to customize payroll element templates. One method involves accessing a predefined payroll element template; receiving a template modification value, which is input by a payroll user in response to a question in a predefined payroll questionnaire; customizing the predefined payroll element template, based upon the template modification value, to create a customized payroll element template; and storing the customized payroll element template.

Abstract: A method for querying the collective social network on behalf of a limited group of users is described. The method consists of a system that schedules and executes searches according to a set of search objectives specified by the users. The system searches each member's social network for a connection that matches any search objective.

Abstract: Techniques for identification of a trigger-type leader in a social network are described. According to various embodiments, a specific content item posted by a particular actor of a plurality of actors and interactions by other actors of the plurality of actors with the specific content item are identified. A leadership score associated with the particular actor is then calculated, the leadership score indicating a propensity of the particular actor to stimulate discussion among actors of the online social network service. The particular actor is then classified as an information trigger among the plurality of actors of the online social network service, based on the calculated leadership score.

Abstract: The system and method of the invention describes a unique and simplified design for Hotel Central Reservations Systems that reduces cost and response time by factors of 2 to 10 times. The system accepts ARI information from Property Management Systems and services availability requests from external sources such as Global Distribution Systems or Online Travel Agencies, and proprietary web sites or call centers. The system provides for complete generality with respect to room types and rate management by hotel and by day, for an arbitrary number of room types and for an arbitrary number of days in the future, for specific rates for each room type, each day. The system of the invention can be implemented as a web service, a service appliance, or as a separate software product that would integrate with an existing HCRS. The system could also be used by rental car or airline CRSs.

Abstract: Concepts and technologies are disclosed herein for providing an electronic document processing system, an electronic document generation mechanism, an encrypted digital certificate generator, a tool for coordinating the processing of electronic documents, a packaging mechanism for finalizing and authenticating electronic documents, a tracking log for recording relevant electronic document information, and a transferring protocol for transferring the ownership of electronic documents. The present disclosure also is directed to an electronic authentication system including an electronic document authentication watermark seal or signature line for confirming a document's signing within the view.

Abstract: Methods and systems may include logic to identify a plurality of blocks in image data having one or more top-left dependent pixels, and select the plurality of blocks in a wavefront order for processing. In addition, the logic may process a plurality of pixels in each block in the wavefront order. The system may also include a display device to output a result associated with processing the plurality of pixels.

Abstract: A method for calculating a feature descriptor on a single instruction, multiple data (SIMD) processor is described. The method includes generating histogram bin indexes in a first register. The method also includes generating weights in a second register. The method further includes updating an entire histogram table in a register file based on the histogram bin indexes and the weights without storing any histogram bin to memory. Histogram bins are updated in parallel with a single instruction.

Abstract: Disclosed herein is a shared memory systems that use a combination of SBR and MRRR techniques to calculate eigenpairs for dense matrices having very large numbers of rows and columns. The disclosed system allows for the use of a highly scalable tridiagonal eigensolver. The disclosed system likewise allows for allocating a different number of threads to each of the different computational stages of the eigensolver.

Abstract: A computer-implemented method comprises: extracting a setting from a description file of a virtual pan-tilt-zoom (PTZ) camera used to capture an original image through a wide-angle lens; determining a first set of coordinates of a pixel of the original image for each cell of a sparse conversion map represented as a first look-up table, wherein the sparse conversion map corresponds to a sparse grid of pixels of an output image; determining, via interpolating the first set of coordinates, a second set of coordinates of a pixel of the original image for each cell of a full conversion map, wherein the second set of coordinates is represented as a second look-up table, wherein the full conversion map corresponds to a full grid of pixels of the output image; instructing a display to present the output image, wherein the original image is less rectilinear than the output image.

Abstract: A system and method for registering a test image with a reference image requires decimation of both images to create corresponding image pyramids. A Log-Polar Transformation (LPT) is then applied to corresponding pixels from the same highest levels of the respective pyramids. Next, these pixels are manipulated to establish a Normalized Correlation Coefficient (NCC) for their respective correlations. Approximately the highest 10% of correlated pixels are then retained to identify related pixels in the next lower level of their respective pyramids. Again, LPT is applied to these related pixels and they, in turn, are manipulated to establish NCC correlations for identifying pixels to be retained. This process is successively accomplished for each lower level of the pyramid until the lowest levels (i.e. the test image and the reference image) are correlated and used for registration of the test image.

Abstract: Provided are an image restoration method and device. The method comprises: processing image blocks, which are initially registered, to acquire connection curves among the image blocks; constructing an ambient field of images to be restored by means of the connection curve; by minimizing energy of the connection curve in the ambient field, registering the image blocks; and performing image filling on the registered image blocks to acquire a restored image. The device comprises: a processing unit used for processing the image blocks, which are initially registered, to acquire the connection curve among the image blocks; an ambient field construction unit used for constructing the ambient field of the image to be restored by means of the connection curve; a registering unit used for registering the image blocks by minimizing the energy of the connection curve in the ambient field; and a filling unit used for performing image filling on the registered image blocks to acquire the restored image.

Abstract: Provided are a method and apparatus for interpolating an image. The method includes: selecting a first filter, from among a plurality of different filters, for interpolating between pixel values of integer pixel units, according to an interpolation location; and generating at least one pixel value of at least one fractional pixel unit by interpolating between the pixel values of the integer pixel units by using the selected first filter.

Abstract: An image processor generates a Super-Resolution (SR) frame by upscaling. A Human Visual Preference Model (HVPM) helps detect random texture regions, where visual artifacts and errors are tolerated to allow for more image details, and immaculate regions having flat areas, corners, or regular structures, where details may be sacrificed to prevent annoying visual artifacts that seem to stand out more. A regularity or isotropic measurement is generated for each input pixel. More regular and less anisotropic regions are mapped as immaculate regions. Higher weights for blurring, smoothing, or blending from a single frame source are assigned for immaculate regions to reduce the likelihood of generated artifacts. In the random texture regions, multiple frames are used as sources for blending, and sharpening is increased to enhance details, but more artifacts are likely. These artifacts are more easily tolerated by humans in the random texture regions than in the regular-structure immaculate regions.

Abstract: In an ultrasonic diagnostic apparatus, a scan converter module generates display frame data from received frame data using a conversation table adapted to the specific display resolution of a display device. Received frame data is stored in a first frame memory, and display frame data is stored in a second frame memory. A control unit selects the conversion table corresponding to the specific display resolution of the display device from among a group of conversion tables. An address converter generates an address set corresponding to a display address using the selected conversion table. Interpolation is then performed based on the echo data specified by this.

Abstract: A method includes estimating structure models for a voxel(s) of a spectral image based on a noise model, fitting structure models to a 3D neighborhood about the voxel(s), selecting one of the structure models for the voxel(s) based on the fittings and predetermined model selection criteria, and de-noising the voxel(s) based on the selected structure model, producing a set of de-noised spectral images. Another method includes generating a virtual contrast enhanced intermediate image for each energy image of a set of spectral images corresponding to different energy ranges based on de-noised spectral images, decomposed de-noised spectral images, an iodine map, and a contrast enhancement factor; and generating final virtual contrast enhanced images by incorporating a simulated partial volume effect with the intermediate virtual contrast enhanced images.

Abstract: An image processing apparatus for reducing fluctuations due to a heat haze in an image including a stationary region and a moving object obtains histogram of gradation distribution for each of a target image to be corrected and a frame for correction, and corrects the target image by using the frame for correction while changing a mixing ratio between the target image and the frame for correction depending on similarity between histograms. To adaptively control a size of image blocks for the histograms, the apparatus calculates two indices having different robustness to deformation of an object from image blocks of each of the target image and the frame for correction, and determines suitability of the image block size based on a relationship of the indices. The difference between the histograms and the sum of absolute differences (SAD) between the pixel values can be used as the two indices.

Abstract: An image processing system includes an a noise detection unit that extracts a local statistical characteristic of a predicted original image according to a local statistical characteristic of an observed image and a local statistical characteristic of a predicted noise image, sets a flag level indicating a distortion state for each of pixels of the observed image according to the local statistical characteristic of the predicted original image, zones the observed image through a filter window, determines distortion states of adjacent pixels, corrects the flag level, and detects noise, and a noise removal unit that adaptively sets a filter size according to the corrected flag level and removes the noise, when the corrected flag level is determined through the noise detection unit, and therefore it is possible to implement adaptive noise detection and removal techniques of a distorted image damaged by noise, and detect a contour to the corresponding pixels into undistorted pixels.

Abstract: Disclosed are methods and apparatus for qualifying a photolithographic reticle. A reticle inspection tool is used to acquire images at different imaging configurations from each of the pattern areas of a calibration reticle. A reticle near field is recovered for each of the pattern areas of the calibration reticle based on the acquired images from each pattern area of the calibration reticle. Using the recovered reticle near field for the calibration reticle, a lithography model for simulating wafer images is generated based on the reticle near field. Images are then acquired at different imaging configurations from each of the pattern areas of a test reticle. A reticle near field for the test reticle is then recovered based on the acquired images from the test reticle.

Abstract: Patient radiation exposure during computerized tomography (CT) scans is estimated. More specifically, efficient approaches for generating a suitable patient model which may be used to make an estimate of a radiation dose received at specific anatomical landmarks or organs of the patient are provided. Further disclosed are approaches for estimating the patient dose by interpolating the results of multiple simulations, and for enabling a service provider to host a dose estimation service made available to multiple CT scan providers.

Abstract: Apparatus for performing an imaging procedure comprising processing volumetric image data comprising an image processing unit configured to obtain first image data representative of a region including at least one vessel and at least one associated feature, and second image data representative of at least part of the region, an image refinement unit configured to process the first image data and the second image data to produce a combined image representative of the at least one vessel, wherein the associated feature is removed or reduced in intensity in the combined image, and a rendering unit configured to render the combined image as a simulated view that simulates a view obtainable from an alternative imaging procedure.

Abstract: A system 100 for processing medical images, the system being arranged for obtaining a first medical image 102 and a second medical image 104, the first medical image and the second medical image being rigidly registered medical images of an anatomical structure, and the system comprising a displacement estimator 120 for establishing displacement vectors 122 for at least a first portion of the first medical image, the displacement vectors matching the first portion of the first medical image to a second portion of the second medical image, a deformation estimator 140 for, in dependence on the displacement vectors, establishing deformation values 142 for the first portion, the deformation values representing a deformation of the first portion with respect to the second portion, and a visualization generator 160 for generating visualization data 162 for, when being displayed on a display 180, establishing a multi-dimensional graph 182 comprising magnitudes of the displacement vectors as first variables 184 and t

Abstract: A method of and apparatus for changing lesion classification data, the method including determining whether at least one mass is included in an image of an object, determining whether the at least one mass corresponds to a lesion by using first data including at least one first information, selecting a false negative (FN) mass which has been determined as not corresponding to the lesion among the at least one mass, based on a first input, and changing the first data to second data by using second information of the selected FN mass.

Abstract: There is described a system, method, and computer-readable medium having stored thereon executable program code for generating a final Cobb angle prediction for idiopathic scoliosis, the method comprising: receiving patient-specific 3D morphological spine parameters, a selected curve type, and a selected skeletal maturity; applying the patient-specific 3D morphological spine parameters, a selected curve type, and a selected skeletal maturity to a predictive model based on 3D morphological spine parameters, curve type, and skeletal maturity, and generating the final Cobb angle prediction by modeling a progression curve of the idiopathic scoliosis.

Abstract: Methods, systems, workstations, viewers, grossing stations and computer include a display and a viewer circuit configured to cause the display to concurrently display: (i) a macroscopic view of a grossing specimen with virtual cut location marks associated with orientation and location of actual physical cut locations used to obtain tissue samples from the grossing specimen and (ii) at least one digital microscopic whole-slide image (WSI) of a tissue section from the specimen. The display can show the at least one WSI image on the display with a relevant cut location mark on the macroscopic view shown visually enhanced from other cut location marks on the macroscopic view to thereby allow a user to visually connect where the tissue section in the WSI image was obtained during a grossing procedure.

Abstract: A system for hemolysis detection, where the system generally includes—individually or in combination—a containment apparatus for holding the blood sample and a software application for analyzing the blood sample. The containment apparatus houses the sample therein, and blocks out any light from penetrating the apparatus and reflecting off of the sample. In conjunction, the software application uses camera color for processing the color of the sample to determine the hemoglobin level in plasma based on the color.

Abstract: An image processing apparatus according to an embodiment includes an acquiring unit and a determination unit. The acquiring unit acquires information of a relative position between a radiographic space where a subject is radiographed by an X-ray diagnosis apparatus and a scanning space where the subject is scanned by an ultrasound probe. The determination unit determines a position almost the same as the position scanned by the ultrasound probe in the radiographic space, according to the information of the relative position acquired by the acquiring unit. The acquiring unit acquires the information of the relative position based on an X-ray image radiographed by the X-ray diagnosis apparatus.

Abstract: A method and apparatus for detecting a three-dimensional (3D) point cloud point of interest (POI), the apparatus comprising a 3D point cloud data acquirer to acquire 3D point cloud data, a shape descriptor to generate a shape description vector describing a shape of a surface in which a pixel point of a 3D point cloud and a neighboring point of the pixel point are located, and a POI extractor to extract a POI based on the shape description vector is disclosed.

Abstract: A method and system for physiological image registration and fusion is disclosed. A physiological model of a target anatomical structure in estimated each of a first image and a second image. The physiological model is estimated using database-guided discriminative machine learning-based estimation. A fused image is then generated by registering the first and second images based on correspondences between the physiological model estimated in each of the first and second images.

Abstract: Method and/or apparatus embodiments for automatically identifying caries, executed at least in part on data processing hardware, can acquire, multiple reflectance images of a tooth, wherein each reflectance image includes at least red, green, and blue intensity values for a region of pixels corresponding to the tooth. Each reflectance image in the plurality of reflectance images is processed by (i) defining a tooth region within the reflectance image; and (ii) identifying caries within the defined tooth region for each reflectance image. The reflectance images are registered and the registered processed images are combined to form a result image that shows the identified caries. In one embodiment, multiple reflectance images of a tooth are taken from substantially the same camera position.

Abstract: A system includes a sensor to generate a first image having a first two-dimensional image pixel data set. A database provides a second image having a second two-dimensional image pixel data set that includes a three-dimensional positional data set describing a navigational position of each pixel in the second two-dimensional image pixel data set. A vision module includes an edge extractor to extract image edge features from the first two-dimensional pixel data set and image edge features from the second two-dimensional image pixel data set. The vision module includes a feature correlator to determine a navigational position for each pixel in the first two-dimensional data set based on an image edge feature comparison of the extracted edge features from the first and second two-dimensional image pixel data sets.

Abstract: A monitoring system for monitoring a monitoring area, having an input interface for accepting monitoring images of the monitoring area, having a localization module for locating at least one moving monitoring object in the monitoring area, wherein the localization module is designed to locate a position of the monitoring object, having a definition module for defining a position-dependent protected area in the monitoring area, and having a monitoring module for monitoring the protected area, wherein the definition module is designed to define the position-dependent protected area on the basis of the position of the moving monitoring object.

Abstract: A method and apparatus for data driven editing of rib centerlines is disclosed. A user input location indicating an inaccuracy in a rib centerline extracted from a medical image volume is received. A local correction of the rib centerline is performed. A portion of the rib surrounding a current centerline point to be corrected is segmented based on image data of the medical image volume. A corrected centerline point for the current centerline point is generated based on the segmented portion of the rib. The centerline correction is then extended to subsequent points along the rib centerline.

Abstract: Image segmentation utilizing 3D image data. A plurality of pixels of an image frame may be segmented based at least on a function of pixel color and a pixel depth over the spatial positions within the image frame. A graph-cut technique may be utilized to optimize a data cost and smoothness cost in which at least the data cost function includes a component that is a dependent on a depth associated with a given pixel in the frame. In further embodiments, both the data cost and smoothness functions are dependent on a color and a depth associated with each pixel. Components of at least the data cost function may be weighted for each pixel to arrive at most likely segments. Segmentation may be further predicated on a pre-segmentation label assigned based at least on a 3D spatial position clusters.

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: The edge detection method according to an embodiment of the present disclosure may include: convolving pixels to be processed, based on templates in respective predetermined directions for edge detection operators and a logarithm of grayscale values for respective pixels adjacent to the pixels to be processed, so as to obtain brightness differential approximations in the respective predetermined directions for the pixels to be processed; calculating gradient magnitudes of the pixels to be processed, based on the brightness differential approximations in the respective predetermined directions for the pixels to be processed; comparing the gradient magnitudes of the pixels to be processed with a gradient magnitude threshold, and selecting the pixels to be processed whose gradient magnitudes are larger than or equal to the gradient magnitude threshold as edge pixels; and extracting a contour of a target within an image, based on the resultant edge pixels.

Abstract: A navigation system comprises an image sensor operable to obtain a first image at a first moment in time and a second image at a second moment in time; an inertial measurement unit (IMU) operable to obtain measurement data corresponding to the first and second moments in time; and a processing unit coupled to the image sensor and the IMU. The processing unit is operable to estimate motion between the first and second moments in time based on the measurement data from the IMU; calculate a plurality of transformations based on the estimated motion; apply each of the plurality of transformations to the first image to produce a plurality of predicted images; compare the second image to each of the plurality of predicted images; select the predicted image from the plurality of predicted images which most closely matches the second image; and compensate for error in the IMU measurement data based on the transformation corresponding to the selected predicted image.