Abstract: A detection system fusing motion detection and object detection for various applications such as tracking, identification, and so forth. In an application framework, model information may be developed and used to reduce the false alarm rate. With a background model, motion likelihood for each pixel, for instance, of a surveillance image, may be acquired. With a target model, object likelihood for each pixel of the image may also be acquired. By joining these two likelihood distributions, detection accuracy may be significantly improved over the use of just one likelihood distribution for detection in applications such as tracking.

Abstract: In selected embodiments, a computer-implemented method for analyzing customer movement in a retail environment includes capturing an image of an individual at multiple locations within a retail environment and tracking the elapsed time between the individual's appearance at the various locations. For areas of the store at increased risk for shoplifting, the elapsed times may be compared to predetermined upper and/or lower elapsed time thresholds or windows to determine whether an individual is likely to commit a crime in the retail environment. The thresholds or window may be empirically determined based on analysis of historical security video footage and security incident records.

Abstract: The present invention discloses a method for generating a bone mask. The method comprises the following steps: performing a noncontrast computed tomography scan on a subject in axial mode to get a first data set; after the subject injected with a contrast medium, performing a postcontrast computer tomography angiography scanning on the subject in helical mode to get a second data set; reconstructing the two mentioned data set to acquire a first reconstruction image and a second reconstruction image respectively; resampling the first reconstruction image based on the second reconstruction image by using a computer to get a third reconstruction image; and thresholding values of data which are greater than or equal to a scheduled Hounsfield unit in the third reconstruction image to get a bone mask.

Abstract: Embodiments of the invention provide methods and systems for generating a color-textured three-dimensional dental model that is specific to a patient. According to one embodiment, generating a patient-specific color-textured three-dimensional dental model can comprise obtaining a three-dimensional dental model of a patient. For example, obtaining the three-dimensional dental model can comprise obtaining volumetric image data of a dentition of the patient and generating the three-dimensional dental model based on the volumetric image data. Two-dimensional intra-oral image data of the patient can also be obtained. For example, obtaining the two-dimensional intra-oral image data can comprise obtaining a plurality of photographs. The patient-specific color-textured three-dimensional dental model can be generated based on the three-dimensional dental model and the two-dimensional intra-oral image data.

Abstract: An image processing method includes: receiving an input image; referring to a first threshold value to compare a reference background image and the input image to determine a first foreground image within the input image; referring to the first foreground image to determine a second foreground image, which is different from the first foreground image, within the input image; and referring to a second threshold value, which is different from the first foreground image, to compare the reference background image and the second foreground image to determine a third foreground image within the input image. In addition, when generating the foreground image, a shadow effect is removed via a shadow removal method according to the present invention, and a better output image can thereby be derived.

Abstract: An image processing apparatus includes: an image transformation parameter calculation device which calculates an image transformation parameter for matching an acquired first image and a second image with each other among detected plurality of corresponding points; an image transformation device which transforms the second image using the calculated image transformation parameter and acquires the transformed image as a third image; and a feature point existing region determination device which determines whether or not the feature point extracted from the first image is positioned in an invalid image region at an edge of the image, the invalid image region being generated by execution of a predetermined filtering process on the first image, wherein the corresponding point detection device tracks the feature point determined that the feature point extracted from the first image is positioned in the invalid image region, using the first image and the third image.

Abstract: Automatic measurement of morphometric and motion parameters of a coronary target includes extracting reference frames from input data of a coronary target at different phases of a cardiac cycle, extracting a three-dimensional centerline model for each phase of the cardiac cycle based on the references frames and projection matrices of the coronary target, tracking a motion of the coronary target through the phases based on the three-dimensional centerline models, and determining a measurement of morphologic and motion parameters of the coronary target based on the motion.

Abstract: Embodiments of the invention are directed to using image data and contextual data to determine information about a scene, based on one or more previously obtained images. Contextual data, such location of image capture, can be used to determine previously obtained images related to the contextual data and other location-related information, such as billboard locations. With even low resolution devices, such as cell phone, image attributes, such as a histogram or optically recognized characters, can be compared between the previously obtained images and the newly captured image. Attributes matching within a predefined threshold indicate matching images. Information on the content of matching previously obtained images can be provided back to a user who captured the new image. User profile data can refine the content information. The content information can also be used as search terms for additional searching or other processing.

Abstract: A system and method for processing image data to be displayed on a display device, where the display device requires more power to be driven to display image data comprising particular spatial frequencies in one dimension than to be driven to display image data comprising the particular spatial frequencies in a second dimension. The method includes receiving image data and filtering the received image data such that the image data at particular spatial frequencies in a first dimension are attenuated more than the image data at particular spatial frequencies in a second dimension.

Abstract: This disclosure describes various exemplary user interfaces, methods, and computer program products for the interactively ranking image search results refinement method using a color layout. The method includes receiving a text query for an image search, presenting image search results in a structured presentation based on the text query and information from an interest color layout. The process creates image search results that may be selected by the user based on color selection palettes or color layout specification schemes. Then the process ranks the image search results by sorting the results according to similarity scores between color layouts from the image search results and the interest color layout from a user based on the color selection palettes and the color layout specification schemes.

Abstract: A device is trained for face recognition. A first acquired digital image of a scene includes a face. Face image data is extracted and stored in a face image library along with an unique identifier. A second acquired digital image may or may not include the face of the same person as the face in the first acquired digital image. Face recognition is applied to extracted face data of the second digital image, and the face of the first digital image is displayed as a match to the face of the second digital image when the first and second images are determined to match or the second digital image or a face therein is identified with biometric data stored along with the first digital image when the faces in the first and second images are determined to match.

Abstract: A face area is detected from an image captured by an image pickup device, pixel values of the image are adjusted based on information concerning the detected face area, a person area is detected from the adjusted image, and the detected face area is integrated with the detected person area. With this configuration, it is possible to accurately detect an object even in a case, for example, where the brightness is varied.

Abstract: Methods and a processing device are provided for restoring pixels damaged by artifacts caused by dust, or other particles, entering a digital image capturing device. A user interface may be provided for a user to indicate an approximate location of an artifact appearing in a digital image. Dust attenuation may be estimated and an inverse transformation, based on the estimated dust attenuation, may be applied to damaged pixels in order to recover an estimate of the underlying digital image. One or many candidate source patch may be selected based on having smallest pixel distances, with respect to a target patch area. The damaged pixels included in the target patch area may be considered when calculating the pixel distance with respect to candidate source patches. RGB values of corresponding pixels of source patches may be used to restore the damaged pixels included in the target patch area.

Abstract: Methods, systems and computer readable media for processing one or more biological specimens carried by specimen slides. Images of objects in a specimen are acquired and objects of interest in the acquired images are identified. Additional images of identified objects of interest may be acquired at multiple wavelengths. Cellular features of objects of interest are extracted from images and may be used for classifying the specimen, e.g., as normal or suspicious/abnormal, based a probabilistic model that utilizes the extracted features.

Abstract: Several related inventions for estimating scattered radiation in radiographic projections are disclosed. Several of the inventions use scatter kernels of various forms, including symmetric and asymmetric forms. The inventions may be used alone or in various combinations with one another. The resulting estimates of scattered radiation may be used to correct the projections, which can improve the results of tomographic reconstructions. Still other inventions of the present application generate estimates of scattered radiation from shaded or partially shaded regions of a radiographic projection, which may be used to correct the projections or used to adjust the estimates of scattered radiation generated according to inventions of the present application that employ kernels.

Abstract: Presented is a system and method for detecting turbulence in the atmosphere comprising an image capturing device for capturing a plurality of images of a visual feature of a celestial object such as the sun, combined with a lens having focal length adapted to focus an image onto image capturing device such that the combination of the lens and the image capturing device are adapted to resolve a distortion caused by a turbule of turbulent air, and an image processor adapted to compare said plurality of images of said visual feature to detect the transit of a turbule of turbulent air in between said image capturing device and said celestial object, and compute a measurement of the angular velocity of the turbule. A second plurality of images is used to triangulate the distance to the turbule and the velocity of the turbule.

Abstract: A robot system includes a robot having a movable section, an image capture unit provided on the movable section, an output unit that allows the image capture unit to capture a target object and a reference mark and outputs a captured image in which the reference mark is imaged as a locus image, an extraction unit that extracts the locus image from the captured image, an image acquisition unit that performs image transformation on the basis of the extracted locus image by using the point spread function so as to acquire an image after the transformation from the captured image, a computation unit that computes a position of the target object on the basis of the acquired image, and a control unit that controls the robot so as to move the movable section toward the target object in accordance with the computed position.

Abstract: An image processing apparatus includes: a pixel difference calculator for calculating a difference value between each first pixel of a previous image and a second pixel of a present image and at a position corresponding to said each first pixel, and outputting a plurality of pixel differences; a counter counting a number of positive pixel differences and a number of negative pixel differences in the pixel differences of a sampling window; a motion level determining unit calculating a motion level of a pixel in the sampling window according to the numbers of the positive and negative pixel differences; a blending value determining unit determining a blending value according to the motion level; and an output unit adding together weights of the present and previous images according to the blending value to generate and output an output image. An image processing method is also disclosed.

Abstract: A first ranging apparatus includes a light-emitting unit for emitting a series of first through fourth modulated lights which have respective different start phases at which the first through fourth modulated lights start being emitted, a light-detecting unit for detecting reflected lights from an object that is irradiated with the first through fourth modulated lights, and a calculating unit for calculating the distance up to the object based on the phase difference between the first through fourth modulated lights and the reflected lights. The light-emitting unit comprises a start phase controller for controlling the start phases. The light-detecting units samples the amounts of the reflected lights in exposure periods established at a constant cycle length from the time when the modulated lights start being emitted.

Abstract: A primarily hand-held or adjustable-mount iris recognition device wherein feedback to the operator is provided by visible illumination or imagery projected onto the face of the subject, as well as an audio signal, while infra-red illumination is projected onto the face of the subject as an illumination source for an iris recognition process. When the device is pointed in the direction of the subject, the infra-red illumination is directed to illuminate primarily the eye region whereas the visible illumination is directed to illuminate primarily other regions including the cheeks. The visible illumination is configured such that the position of the visible illumination on the face indicates to the operator whether the iris recognition device is pointed in the correct direction and at the correct distance for optimal iris recognition.