Abstract: When correcting for artifacts on an attenuation map caused by an artifact source in a computed tomography image, nuclear images are reconstructed two or more times, each time using a different correction technique or uncorrected attenuation data. Corresponding voxels in the reconstructed images are compared to identify local areas that change, i.e., are fragile and therefore low-confidence, and areas that do not vary or exhibit little variance among the plurality of reconstructed images and are thus accorded a higher confidence. The reconstructed nuclear image is overlaid with color encoding indicative of the amount of confidence accorded to each voxel value obtained by attenuation-corrected tomographic reconstruction.

Abstract: Methods and systems for segmentation in echocardiography are provided. One method includes obtaining echocardiographic images and defining a search space within the echocardiographic images using a pair of one-dimensional (1D) profiles. The method also includes using an energy based function constrained by non-local temporal priors within the defined search space to automatically segment a contour of a cardiac structure with the 1D profiles.

Abstract: A computer-implemented image analysis process, including: accessing image data representing an image including an animal object representing an animal; selecting one more start points on a boundary of the animal object using an intensity gradient of the image; and generating boundary data, representing at least a portion of the boundary, starting at each of the selected one or more start points, using the intensity gradient.

Abstract: Systems, methods, and computer-readable storage media relate to segmenting an image series of at least one image of a region of interest of a subject. The methods, systems, and computer readable storage media can automatically segment interior and exterior boundaries relative to the region of interest (e.g., epicardial and endocardial boundaries with respect to a right ventricle) from an image series by combining sparse matrix transform, a training model, and a localized region based level set function.

Abstract: A mobile platform detects and tracks at least one target in real-time, by tracking at least one target, and creating an occlusion mask indicating an area in a current image to detect a new target. The mobile platform searches the area of the current image indicated by the occlusion mask to detect the new target. The use of a mask to instruct the detection system where to look for new targets increases the speed of the detection task. Additionally, to achieve real-time operation, the detection and tracking is performed in the limited time budget of the (inter) frame duration. Tracking targets is given higher priority than detecting new targets. After tracking is completed, detection is performed in the remaining time budget for the frame duration. Detection for one frame, thus, may be performed over multiple frames.

Abstract: A method is disclosed for determining a boundary surface network of the tubular object. In an embodiment, a representation of the tubular object is initially provided on the basis of image data and local dimension information is provided for points of the representation. A subdivided division structure presentation of the tubular object with division cells is then created, which based on the local dimension information, including a different spatial extent. Finally a boundary surface network is derived on the basis of the division structure presentation. Also described are a boundary surface network determination system and a division structure determination system for performing such a method.

Abstract: A computer alters at least one recognizable metric or text in a digitally-encoded photographic image by operating an alteration algorithm in response to user input data while preserving an overall aesthetic quality of the image and obscuring an identity of at least one individual or geographic location appearing in the image. An altered digitally-encoded photographic image prepared by the altering of the at least one recognizable metric or text in the image is stored in a computer memory. User feedback and/or automatic analysis may be performed to define parameter values of the alteration algorithm such that the alteration process achieves preservation of aesthetic qualities while obscuring an identity of interest.

Abstract: A classifier (20) is trained by a feature matrix (18, 18?) made up of feature vectors (F11, . . . , Fkm). The feature vectors are generated by operating on each of a plurality (k) of training image data sets with each of a plurality (m) of image processing algorithms (121, . . . , 12m) to generate processed and segmented images. Features of the segmented regions are extracted (14) to generate the feature vectors. In this manner, the classifier is trained with data generated with a variety of image processing algorithms.

Abstract: A state machine gesture recognition algorithm for interpreting streams of coordinates received from a touch sensor. The gesture recognition code can be written in a high level language such as C and then compiled and embedded in a microcontroller chip, or CPU chip as desired. The gesture recognition code can be loaded into the same chip that interprets the touch signals from the touch sensor and generates the time series data, e.g. a microcontroller, or other programmable logic device such as a field programmable gate array.

Abstract: A portion of imagery data is obtained from a digital slide and a protocol of image analysis/diagnostic tasks is performed on the portion of imagery data by a pathologist or an image analysis module. The result of each task (e.g., success or no success) is recorded and a score is determined for the portion of the imagery data. Multiple portions of imagery data from the digital slide are analyzed and scored and the various scores from the multiple portions of imagery data are calculated to determine an overall score for the digital slide. Regions of the digital slide can be scored separately. Multiple rounds of scoring (by different pathologists and/or different image analysis algorithms) may be employed to increase the accuracy of the score for a digital slide or region thereof.

Abstract: Systems and methods of determining nitrogen levels from a digital image and in-season nitrogen measurement and fertilization of non-leguminous crops from digital image analysis are disclosed herein. In particular, a method of determining leaf nitrogen concentration and yield from a digital photograph of a fully developed leaf (collared leaf) of a crop of non-legumes, such as corn, wheat, rice, cotton, potatoes sugarcane, turfgrass or forage grass species. The digital image is processed to determine a dark green color index (“DGCI”), which is closely related to leaf nitrogen concentration and yield. Standardized color disks having known DGCI values are included in the digital photograph and serve as an comparative standard. The comparative standard allows correction of DGCI of samples when using different cameras and/or when lighting conditions change. The DGCI values can then be used to determine the amount of nitrogen fertilizer that should be applied to recover crop yield potential.

Abstract: A system for contamination monitoring includes a tracking component, a material identification component, a procedural component, and a notification component. The tracking component tracks an individual and one or more objects in a work area using a three-dimensional tracking system. The material identification component identifies a material of the one or more objects based on a captured image. The procedural component determines that an object of the one or more objects is contaminated based on tracked locations of the one or more objects and the individual. The notification component provides a notification of the contamination.

Abstract: The present invention relates to the determination of the specific orientation of an object. In order to provide enhanced positioning information of an object to a user, a medical imaging system and a method for operating of a medical imaging system are proposed wherein 2D image data (14) of an object is acquired (12) with an imaging system, wherein the object is provided with at least three markers visible in the 2D image; and wherein (16) the markers are detected in the 2D image; and wherein the spatial positioning and rotation angle (20) of the object in relation to the system geometry is identified (18) on behalf of the markers; and wherein an object-indicator (24) is displayed (22) indicating the spatial positioning and rotation angle of the object.

Abstract: Embodiments include methods for predicting one or more characteristics of an individual, such as a human or non-human animal, by applying computational methods to image(s) of the individual to generate one or more metrics indicative of the characteristics. Embodiments determine predictors of characteristics by creating a sample library of individuals, determining facial measurements for each individual, determining relationships between facial measurements and additional library data, and selecting predictors from these relationships. Embodiments include methods for predicting characteristics of individuals not in the library. Embodiments include methods for predicting characteristics of groups using predicted characteristics of individuals. Embodiments determine suitability of a pair of individuals (from the same or different species) for a particular purpose, task, or relationship based on characteristics of individuals.

Abstract: A system for computer-aided detection uses a computer-implemented network structure to analyze patterns present in digital image slices of a human body and to generate a three-dimensional anatomical model of a patient. The anatomical model is generated by detecting easily identifiable organs first and then using those organs as context objects to detect other organs. A user specifies membership functions that define which objects of the network structure belong to the various classes of human organs specified in a class hierarchy. A membership function of a potentially matching class determines whether a candidate object of the network structure belongs to the potential class based on the relation between a property of the voxels linked to the candidate object and a property of the context object. Some voxel properties used to classify an object are location, brightness and volume. The human organs are then measured to assist in the patient's diagnosis.

Abstract: A vision based pedestrian and cyclist detection method includes receiving an input image, calculating a pixel value difference between each pixel and the neighbor pixels thereof, quantifying the pixel value difference as a weight of pixel, proceeding statistics for the pixel value differences and the weights, determining intersections of the statistics as a feature of the input image, classifying the feature into human feature and non-human feature, confirming the human feature belonging to cyclist according to the spatial relationship between the human feature and the detected two-wheeled vehicle, and retaining one detection result for each cyclist by suppressing other weaker spatial relationships between the human feature and the detected two-wheeled vehicle.

Abstract: A method is disclosed for the reconstruction of image data of an examination object from measurement data. First and second image data are reconstructed from the measurement data with a first and second respective image characteristic, with an enhanced signal-to-noise ratio of the second image characteristic relative to the first image characteristic. Enhanced image data is calculated using an iterative algorithm using the first and the second image data. In the case of the iterative algorithm, a low pass is applied to a difference between the first image data and the image data of an iteration cycle, and a high pass to a difference between the second image data and the image data of the iteration cycle.

Abstract: This invention discloses a method for utilizing soft X-ray microimaging for cancer cell image recognition. The method comprises the steps of 1) sample preparation; 2) pathological examination; 3) soft X-ray imaging; and 4) analysis and recognition. This invention applies soft X-ray microimaging for cancer cell image recognition, successfully obtains the soft X-ray microscopic image of a cancer cell by scanning the cancer cell with synchrotron radiation soft X-ray microimaging, provides recognition steps and experimental data, and establishes a method for utilizing soft X-ray microimaging for cancer cell image recognition. This invention creates a method for analyzing soft X-ray microscopic images, provides a novel synchrotron radiation soft X-ray pathological diagnosis method for cancer diagnosis, and provides an extremely valuable basis for the creation and clinical application of soft X-ray pathology in the 21st century.

Abstract: Disclosed are a magnetic ink character recognition method, apparatus and system. The method includes: reading a magnetic signal of a magnetic ink character on a medium to be recognized; acquiring the amplitude characteristic data of the magnetic ink character according to the magnetic signal thereof; and performing spectral angle cosine match processing on the amplitude characteristic data of the magnetic ink character to obtain the recognition result of the magnetic ink character. The present method can reduce the stability requirements on the magnetic signal and improve the recognition rate of the magnetic signal.

Abstract: A turbulence and winds aloft detection system may include an image capturing device for capturing a plurality of images of a visual feature of a selected celestial object; and an image processor configured to compare the plurality of images of the visual feature to detect a transit of a turbule of turbulent air between the image capturing device and the selected celestial object; compensate for one or more of apparent visual motion of celestial objects due to a planet's translation and rotation, the moon's revolution about the planet, and the atmosphere's refractive displacement of celestial objects; and compute a measurement of at least one of a velocity of the turbule and a height of the turbule relative to the planet.