Abstract: A range map of a visual scene generated by a stereo vision and associate image processing system, and is filtered to remove objects beyond a region of interest and for which a collision is not possible, and to remove an associated road surface. Objects clustered in range bins are separated by segmentation. A composite range map is generated using principale components analysis and processed with a connected-components sieve filter. Objects are identified using one or more of a harmonic profile and other features using an object recognition processor using a combination of inclusive, exclusive and harmonic networks to generate a classification metric.

Abstract: A method for detecting color transitions in at least one portion of a document of value by determining for each image elements whether color coordinate values in the color space that are allocated to the image element correspond to a reference color distribution, which is given by at least one predetermined, closed reference surface in the color space, that is given by at least one linear segment predetermined for the document of value and a predetermined distance of the points of the reference surface from the at least one linear segment. The method further has the steps comparing the positions of the image elements whose color coordinate values are disposed inside or outside of the reference surface to predetermined reference positions on the document of value and detecting in dependence on the result of the comparison a presence or an absence of a color transition caused by soiling or color wear.

Abstract: A panoramic image producing apparatus provides an intensity image production unit which produces intensity images from an input source image captured by an imaging device, a reference image data storage unit for storing a reference image which is used to compute the motion data of the intensity image and its absolute motion data, an absolute motion data calculation unit which uses the intensity image of the target image by first computing its relative motion data with respect to the reference image and using its result to compute the absolute motion data with respect to the target image, an image stitching unit to produce a panoramic image by using the absolute motion data computed above to stitch together the input source images, and a reference image setting unit which sets the target image as the new reference image under certain conditions.

Abstract: An object-enabled navigation system assists a vision-impaired user in navigating an environment. The system captures 3D movement of a moving object within the environment, wherein the three-dimensional movement is determined using at least one image capture device aimed at the moving object. The system predicts a mobile path of the visually-impaired user. The system determines whether the movement of the moving object will intersect with the mobile path of the vision-impaired user and informs the vision-impaired user whether the movement of the moving object will intersect the mobile path of the vision-impaired user.

Abstract: This invention relates to a method of assessing the change in size of cancerous lesions in humans utilizing CT scans through the application of a boundary detection algorithm capable of detecting subtle changes in CT images. The change assessment method may include the steps for defining boundary regions on a CT scan image, analyzing said boundaries utilizing a computational program containing statistical analysis techniques, and producing a medically useful output showing any change in lesion size. The change assessment method may also be interfaced with other medical diagnostic techniques or devices that are known in the art.

Abstract: The invention discloses motion detecting method and apparatus thereof. The method and apparatus are utilized to detect a motion condition of a target pixel.

Abstract: A multi-stage method of visual object detection is disclosed. The method was originally designed to detect humans in specific poses, but is applicable to generic detection of any object. A first stage comprises acts of searching for members of a predetermined general-class of objects (such as humans) in an image using a cognitive swarm, detecting members of the general-class of objects in the image, and selecting regions of the image containing detected members of the general-class of objects. A second stage comprises acts of searching for members of a predetermined specific-class of objects (such as humans in a certain pose) within the selected regions of the image using a cognitive swarm, detecting members of the specific-class of objects within the selected regions of the image, and outputting the locations of detected objects to an operator display and optionally to an automatic response system.

Abstract: A plurality of features determined from at least a portion of an image containing information about an object are processed with an inclusive neural network, and with a plurality of exclusive neural networks, so as to provide a plurality of inclusive probability values representing probabilities that the portion of the image corresponds to at least one of at least two different classes of objects, and for each exclusive neural network, so as to provide first and second exclusive probability values representing probabilities that the portion of the image respectively corresponds. or not. to at least one class of objects. The plurality of inclusive probability values, and the first and second exclusive probability values from each of the exclusive neural networks, provide for identifying whether the portion of the image corresponds, or not, to any of the at least two different classes of objects.

Abstract: A method is provided for authenticating an image printed at a predefined print resolution or in accordance with a predetermined print grid. The method includes the steps of scanning the image to produce digital data and segmenting the data into first and second groups corresponding, respectively, to first and second predefined sections of the image. Next, a determination is made concerning the anticipated spatial position of select columns of digital data from each of the first and second groups of data. By examining the data, differences may be identified between the anticipated and actual spatial position of the columns, to determine the authenticity of the image. The identified differences which may include (i) a rotary/linear displacement in the actual spatial position of the select columns. (ii) a change in beat frequency between sections of the image, and/or (iii) a phase shift in a beat frequency.

Abstract: Coherent motion regions extend in time as well as space, enforcing consistency in detected objects over long time periods and making the algorithm robust to noisy or short point tracks. As a result of enforcing the constraint that selected coherent motion regions contain disjoint sets of tracks defined in a three-dimensional space including a time dimension. An algorithm operates directly on raw, unconditioned low-level feature point tracks, and minimizes a global measure of the coherent motion regions. At least one discrete moving object is identified in a time series of video images based on the trajectory similarity factors, which is a measure of a maximum distance between a pair of feature point tracks.

Abstract: A device includes an incident arm, a detection arm, a sample stage, and an image processing computer. The incident arm includes a light source and a first polarizing element, and is disposed on one side of the sample stage. The detection arm includes a second polarizing element and a photoelectric detector, and is disposed on a light-detection path. The photoelectric detector is connected to the computer. The device further includes a device for adjusting polarization angles of the first and second polarizing elements. A method includes: illuminating a sample surface using linearly polarized light with a certain polarization angle; detecting outgoing polarized light by a photoelectric detector; adjusting polarization angles of the incident and detected polarized light, and repeating the above two steps to obtain a series of polarized images, each image corresponding to incident and detected polarization angles; and computer processing the obtained images to obtain sample information.

Abstract: The present invention relates generally to generating travel-logs or geographical representation of encountered media. One claim recites a method including obtaining a plurality of imagery, wherein each item of imagery from the plurality of imagery comprises steganographic encoding, the steganographic encoding altering data representing the imagery, the steganographic encoding comprising multi-bit data, and wherein the presence of the multi-bit data is imperceptible to a human observer of the imagery absent machine-detection; detecting the multi-bit data from the plurality of imagery, wherein the multi-bit data is associated with geolocation metadata; and providing a geographic path associated with the plurality of imagery based at least in part on the geolocation metadata. The geographic path is provided for display to a user relative to a graphical map. Of course, other different claims are provided as well.

Abstract: An acceptor device for sheet objects such as banknotes, comprises a sensor to derive data corresponding to a spatial array of data samples from a face of a sheet object, said data being configured in a sampling frame that lies within a range of positional relationships to a reference frame. The acceptor device also comprises a processor operable to process the data to determine the relationship between the reference frame and the sampling frame for the sensed data, and being operable to transform pre-selected regions of the sensed data from the sampling frame so as to correspond to data in the reference frame, and to make a comparison of the transformed data with reference data corresponding to the pre-selected regions in the reference frame and to the sheet object depending on the outcome of the comparison.

Abstract: A method for diagnosis and evaluation of tooth decay comprises: locating in an x-ray image the contour of the dento-enamel junction (DEJ); measuring optical density along contours substantially parallel to and on either side of the DEJ contour; and calculating at least one numerical decay value from the measured optical densities. A method for diagnosis and evaluation of periodontal disease comprises: measuring in an x-ray image a bone depth (BD) relative to the position of the cemento-enamel junctions (CEJs) of adjacent teeth; measuring bone density along a contour between the adjacent teeth; and calculating a numerical crestal density (CD) value from the measured bone density. Calibration standards may be employed for facilitating calculation of the numerical values. A dental digital x-ray imaging calibration method for at least partly correcting for variations of the optical densities of images acquired from the dental digital x-ray imaging system.

Abstract: The present invention relates to a device and a method for synchronizing an image capture device with a first image data set. The image capture device is used for recording a second image data set of a periodically moving area or object. Each first image data set contains information as to the point in time, relative to the periodically moving area or object, when recording took place. The device additionally acquires periodically recurring, current information of the area as well as information concerning the recording instant of the first image data set. From the periodically recurring information and the recording instant of the first image data set, a triggering instant is derived which controls at least one recording of the second image data set by the image capture device in such a way that the second image data set contains image data synchronized to the first image data set.

Abstract: A method for detecting a moving target is disclosed that receives a plurality of images from at least one camera; receives a measurement of scale from one of a measurement device and a second camera; calculates the pose of the at least one camera over time based on the plurality of images and the measurement of scale; selects a reference image and an inspection image from the plurality of images of the at least one camera; and detects a moving target from the reference image and the inspection image based on the orientation of corresponding portions in the reference image and the inspection image relative to a location of an epipolar direction common to the reference image and the inspection image; and displays any detected moving target on a display. The measurement of scale can derived from a second camera or, for example, a wheel odometer.

Abstract: An image processing apparatus includes a memory unit which stores data of a first projection image and data of a second projection image, which are associated with the same object and are captured in different imaging directions, a display unit which displays the data of the first projection image and the data of the second projection image, a designation operation unit which is configured to designate a plurality of points on the displayed first and second projection images, and an operation supporting unit which generates operation supporting information for supporting an operation of designating, by the designation operation unit, the plurality of points on the second image, which anatomically correspond to the plurality of points designated on the first projection image.

Abstract: The path and/or position of an object is tracked using two or more cameras which run asynchronously so there is need to provide a common timing signal to each camera. Captured images are analyzed to detect a position of the object in the image. Equations of motion for the object are then solved based on the detected positions and a transformation which relates the detected positions to a desired coordinate system in which the path is to be described. The position of an object can also be determined from a position which meets a distance metric relative to lines of position from three or more images. The images can be enhanced to depict the path and/or position of the object as a graphical element. Further, statistics such as maximum object speed and distance traveled can be obtained. Applications include tracking the position of a game object at a sports event.

Abstract: An apparatus and method for automatically inspecting and repairing printed circuit boards includes an inspection functionality automatically inspecting printed circuit boards and providing a machine readable indication of regions thereon requiring repair. An automatic repair functionality employs the machine readable indication to repair the printed circuit boards at some of the regions thereon requiring repair. An automatic repair reformulation functionality automatically reinspects the printed circuit boards following an initial automatic repair operation, and provides to the automatic repair functionality a reformulated machine readable indication of regions thereon requiring repair.

Abstract: A fingerprint input apparatus for providing a plurality of inputs while moving a finger to acquire a fingerprint image, the fingerprint input apparatus determining an intersection of the plurality of input partial fingerprint images to calculate a relative location between the plurality of partial fingerprint images on the basis of the intersection and outputting the calculated relative location with the plurality of partial fingerprint images to an external device. The intersection of the plurality of partial fingerprint images is obtained, for example, on the basis of a density distribution of dots constituting each of the image. The relative location is at least one of the moving direction, the moving distance, and the angle of rotation. Thereby, there is no movable part and thus it eliminates a need for providing the external device with software processing for calculating the relative location of the partial fingerprint images, thereby achieving downsizing and power saving of the apparatus.