Abstract: An image evaluation device (101) properly evaluating the graininess (or roughness) of an image is provided. The blurer (102) creates a second image b by blurring a first image a. The differentiator (103) creates a third image c presenting the difference between the first image a and second image b. The pixel value of each pixel of the third image c presents the difference in pixel value between the pixels at the same position in the first image a and second image b. The scanner (104) scans the pixels contained in the third image c, obtains the differences in pixel value between adjoining pixels, and obtains the respective probabilities of occurrence of the differences. The calculator (105) calculates the entropy from the obtained, respective probabilities of occurrence of the differences. The outputter (106) outputs the entropy as the evaluation value of the graininess (or roughness) of the first image.

Abstract: A system and method of video-based chew counting by receiving image frames from a video camera, determining feature points within the image frames from the video camera, generating a motion signal based on movement of the feature points across the image frames from the video camera, and determining a chew count based on the motion signal.

Abstract: The present invention is directed to a limited angle tomography in combination with a filtered back projection using a special filter operator X. The filter operator X used within the present invention makes it possible to perform region of interest reconstructions although delivering high quality reconstruction images as generated by high effort SART methods. The used filter operator is purely and solely mathematically determined and defined by the spatial geometry which is used for the limited angle tomography. Without having the need to perform several iterations, the present invention directly calculates a solution, i.e. reconstructed image, equivalent to known iteratively construction methods. Although, incomplete projection data p may only be used, the present invention provides for a high image quality.

Abstract: An electronic device and method capture multiple images of a scene of real world at a several zoom levels, the scene of real world containing text of one or more sizes. Then the electronic device and method extract from each of the multiple images, one or more text regions, followed by analyzing an attribute that is relevant to OCR in one or more versions of a first text region as extracted from one or more of the multiple images. When an attribute has a value that meets a limit of optical character recognition (OCR) in a version of the first text region, the version of the first text region is provided as input to OCR.

Abstract: Described, is a system for object detection via multi-scale attentional mechanisms. The system receives a multi-band image as input. Anti-aliasing and downsampling processes are performed to reduce the size of the multi-band image. Targeted contrast enhancement is performed on the multi-band image to enhance a target color of interest. A response map for each target color of interest is generated, and each response map is independently processed to generate a saliency map. The saliency map is converted into a set of detections representing potential objects of interest, wherein each detection is associated with parameters, such as position parameters, size parameters, an orientation parameter, and a score parameter. A post-processing step is applied to filter out false alarm detections in the set of detections, resulting in a final set of detections. Finally, the final set of detections and their associated parameters representing objects of interest is output.

Abstract: A method for detecting the presence of a logo in a current picture of a video is disclosed. The method comprises: determining a current candidate logo bounding box in the current picture and a preceding candidate logo bounding box in a picture preceding the current picture; detecting the presence of a logo in the current picture if at least one of the following conditions is fulfilled: the distance between the centers of the current and the preceding candidate logo bounding boxes is below a first threshold or an overlap between the current and the preceding candidate logo bounding boxes is above a second threshold; or an overlap between the current candidate logo bounding box and a saliency mask of the current picture is above a third, wherein the saliency mask identifies regions around saliency peaks.

Abstract: A method and an apparatus for tracking an object are disclosed. The method includes determining a first position by a first tracking template and determining a second position by a second tracking template, the first and second tracking templates being formed based on first and second feature sets, respectively, the first feature set being different from the second feature set, and the first feature set and the second feature set including one or more features; and determining a final position based on the first position and the second position, wherein the first tracking template is updated for each of a predetermined number of frames, the second tracking template is updated based on a predetermined rule, the second tracking template and the first tracking template are independently updated, and the update frequency of the second tracking template is lower than the first tracking template.

Abstract: According to one embodiment, an image processing apparatus includes a processed-image generating unit, a detection unit, and a calculation unit. The processed-image generating unit generates processed images by scaling the image picked up by the camera provided on a vehicle by respective ones of scale factors. The detection unit scans each processed image by a frame, determines likelihood using a dictionary of the detection object, and detects a scan frame having high likelihood. Each processed image is associated with respective image distance which is a predetermined estimated distance from the vehicle. The calculation unit determines an estimated distance from the vehicle to the detection object according to an image distance associated with a processed image to which the detected scan frame belongs, and calculates and outputs, based on a history of determined estimated distances and on the image distances, a time until the vehicle and the detection object collide.

Abstract: Automatically tracking and photographing celestial objects and a celestial-object auto-tracking photographing apparatus, in which the burden on the CPU can be reduced by eliminating unnecessary arithmetic processes and can clearly photograph an object(s) so as to appear stationary without using an equatorial, and without using an actuator, which must be precisely controlled. The method includes moving relative to a photographic apparatus due to diurnal motion, to photograph a trimming area that has been electronically trimmed from a part of an imaging area of an image sensor, moving while the celestial object is photographed, including obtaining movement information of an image on the imaging area; setting movement data for the trimming area based on the obtained movement information of the image; and carrying out a photographing operation while moving the trimming area based on the movement data of the set trimming area at each trimming area, upon being moved.

Abstract: A device may request, and a server may provide, access to information associated with an image based on trusted face recognition. The server may receive a first image, registration, and associated information from a first device. The first image may include feature data, which the server may extract to create a first feature template. The server may store, and correlate, the first feature template, registration and associated information for the first image. A second device may extract feature data from a second image, create, and provide to the server, a second feature template. The server may authenticate the second device. The server may compare the second feature template with stored feature templates to identify a match. The server may determine whether to share associated information for a match with, and return an access indication to, the second device based, in part, on the authentication.

Abstract: An apparatus for automatically identifying a surgical instrument, the apparatus comprising a capture module, an attribute database, a comparison module, and an exporting module, the capture module comprising hardware operable to capture multiple attributes of the surgical instrument, the attribute database comprising multiple stored attributes of a plurality of reference surgical instruments, the comparison module programmed to generate a comparison score for the surgical instrument, wherein the comparison module is programmed to generate the comparison score by receiving multiple attributes captured by the capture module and comparing it to the multiple attributes stored in the attribute database, and the exporting module configured to receive and export the comparison score generated by the comparison module.

Abstract: A method determining user liveness is provided that includes calculating, by a device, eye openness measures for a frame included in captured authentication data, and storing the eye openness measures in a buffer of the device. Moreover the method includes calculating confidence scores from the eye openness measures stored in the buffer, and detecting an eye blink when a maximum confidence score is greater than a threshold score.

Abstract: A method of acquiring a functional image whose artifacts due to a motion of an object are corrected includes acquiring functional image data of an object, acquiring structural image data of the object, acquiring motion information of the object based on the structural image data, correcting the functional image data based on the motion information related to motion of the object, and obtaining a functional image of the object.

Abstract: A system for tracking a moving target having up to six degrees of freedom and rapidly determining positions of the target, said system includes an easy to locate precision optical target fixed to the target. This system includes at least two cameras positioned so as to view the optical camera from different directions with each of the at least two cameras being adapted to record two dimensional images of the precision optical target defining precise target point. A computer processor is programmed to determine the target position of x, y and z and pitch, roll and yaw. In an embodiment, the system can be configured to utilize an iteration procedure whereby an approximate first-order solution is proposed and tested against the identified precise target points to determine residual errors which can be divided by the local derivatives with respect to each component of rotation and translation, to determine an iterative correction.

Abstract: An image processing device includes: a candidate abnormal region determining unit that determines a candidate abnormal region from an image using a first determination criterion; a bubble region determining unit that determines a bubble region from the image; a bubble inside determining unit that determines whether the candidate abnormal region is present inside the bubble region based on a determination result of the bubble region; and an abnormal region determining unit that determines whether the candidate abnormal region is an abnormal region using a second determination criterion different from the first determination criterion when the candidate abnormal region is determined to be present inside the bubble region.

Abstract: A method facilitates viewing of DICOM medical images by providing a 16-bit DICOM image on a computer readable storage medium, text-converted metadata of the DICOM image and an html-compatible conversion of the DICOM pixel data on a computer readable storage medium. Pixel data of the DICOM image is converted by dividing the 16-bit image into two 8-bit color channels stored in an image referenced by a web page using a uniform resource locator. The two 8-bit color channels are later reassembled within a portable web browser according to instructions set forth in computer readable program code associated with the web page.

Abstract: A determination assist system including a first image generating section for generating a first planar image based on data of a first test index; a second image generating section for generating a second planar image based on data of a second test index; a differentiation section which differentiates the first planar image and the second planar image to generate a first differential image and a second differential image, respectively; a binarization section which binarizes the first differential image to generate a first binary image including a first region which is not less than a first threshold and a second region which is less than the first threshold, and binarizes the second differential image to generate a second binary image including a third region which is not less than a second threshold and a fourth region which is less than the second threshold; and a determination image generating section.

Abstract: An image obtainment unit obtains a series of time series medical images about a specific organ in different phases. A registration unit performs registration of voxel positions in the series of time series medical images between the series of time series medical images. A conversion unit converts signal values at corresponding voxel positions of the specific organ into a same display voxel value in the series of time series medical images.

Abstract: A depth calculation device for calculating depth information on an object from captured first image and second image with different blur, the depth calculation device comprising: an extraction unit configured to extract a first frequency component and a second frequency component from each of the first image and the second image, the first frequency component being a component of a first frequency band, the second frequency component being a component of a second frequency band, the second frequency band being lower than the first frequency band; and a depth calculation unit configured to calculate the depth information from the frequency components extracted by the extraction unit.

Abstract: A system and method for automating an appropriate voxel prescription in a uniquely definable region of interest (ROI) in a tissue of a patient is provided, such as for purpose of conducting magnetic resonance spectroscopy (MRS) in the ROI. The dimensions and coordinates of a single three dimensional rectilinear volume (voxel) within a single region of interest (ROI) are automatically identified.