Abstract: Methods and apparatus, including computer program products, for determining parameter values for adjusting an image. A first function of a local attribute is specified based on values of the local attribute in the image. A second function of the local attribute is specified based on an image adjustment depending upon an adjustment parameter. An object function value is calculated for each of two or more values of the adjustment parameter, each object function value including accumulated differences, between the first and second function at multiple values of the local attribute. Based on the calculated object function values, a value of the adjustment parameter is determined for adjusting the image.

Abstract: Techniques for positioning images in an electronic document. The images may encode information that can be decoded by devices configured to read the images. An area within the electronic document for positioning the image and a set of one or more colors to be used for the image are determined. The determined area and set of colors are such that the image when positioned in the electronic document blends in with the contents of the electronic document while still being clearly visible for reading by reader devices that are configured read and decode the information encoded by the image.

Abstract: An apparatus for processing a non-interlaced image includes a wavelet transform part and a determination part. The wavelet transform part performs two-dimensional discrete wavelet transform of a level higher than or equal to level one on the data of the non-interlaced image. The determination part determines the movement speed of an object within the non-interlaced image based on at least the values of the wavelet coefficients of a 1LH sub-band of the wavelet coefficients obtained by the wavelet transform unit.

Abstract: In the event of displaying only increase (or disappearance) of shadows in a difference image generated based on a display mode selected by a user, a difference image is subjected to gradient conversion so that only the luminance of the region(s) where a shadow has increased (or disappeared) differs from the luminance of other regions, and the difference image thus subjected to gradient conversion is displayed, thereby displaying the states of shadow change independently. Also, negative/positive information in a past image and a current image is extracted, and further, correlation of the diagnostic judgment reference of shadows on the difference image is input. Definition of the shadow stipulates whether the parts of the affected portion improving or deteriorating are to correspond to high concentration (high luminance level) or low concentration (low luminance level) on the difference image. This facilitates observation of changes in shadows.

Abstract: A machine-accessible medium containing software code that, when read by a computer, causes the computer to perform method for filtering a video in a video system. The method may include generating a foreground mask and a background model from a video, where the foreground mask comprises moving pixels in the video and the background model comprises a statistical description, including a mean and a variance value, for each pixel in the video. Then the background model variance is filtered with a one-dimensional high pass filter in a single orientation. Next, for each linear grouping of pixels in the single orientation of the filtered variance, a first edge pixel is detected between a high-variance group of pixels and a low-variance group of pixels. Then a first waterline position is detected as an area bounded by the first edge pixels.

Abstract: Methods, systems and apparatus, including computer program products, for processing an image. A first tone value is determined for a location within the image based upon attributes of pixels within a first neighborhood surrounding the location. The first tone value specifies a local weight for a first tone adjustment in the image. A second tone value is determined for the location based upon attributes of pixels within a second neighborhood surrounding the location. The second tone value specifies a local weight for a second tone adjustment in the image. The image is adjusted at the location using the first and second tone adjustments according to the local weights specified by the first and second tone values, respectively.

Abstract: In the event of displaying only increase (or disappearance) of shadows in a difference image generated based on a display mode selected by a user, a difference image is subjected to gradient conversion so that only the luminance of the region(s) where a shadow has increased (or disappeared) differs from the luminance of other regions, and the difference image thus subjected to gradient conversion is displayed, thereby displaying the states of shadow change independently. Also, negative/positive information in a past image and a current image is extracted, and further, correlation of the diagnostic judgment reference of shadows on the difference image is input. Definition of the shadow stipulates whether the parts of the affected portion improving or deteriorating are to correspond to high concentration (high luminance level) or low concentration (low luminance level) on the difference image. This facilitates observation of changes in shadows.

Abstract: Computer software for and a method of determining location of a target image within a two-dimensional input image by employing a three-dimensional reference image comprising determining object edge points in the input image; given estimated seeker line-of-sight orientation and range data, computing a two-dimensional reference image from the three-dimensional reference image; applying a weighted-direction-cross-product Hough Transform to the object edge points and points of the two-dimensional reference image; classifying the input image as containing a target image or not; if the image contains a target image, identifying a location of the target image within the two-dimensional input image; computing confidence measure as to the selected location of the target image; and in the case of sequential decision, also performing confidence accumulation through multi-frames or multi-looks.

Abstract: To reduce the fluoroscopic noise in an image I acquired at a date t, the pixels of this image are paired with the pixels of an image I? acquired at a date t?1. For a pixel with coordinates (x,y) of the image I, a convolution is done with a core U equivalent to a low-pass filter whose coefficients have been modified as a function of the neighborhood of the pixel with coordinates (x,y) in the image I. For the pixel paired in the image I?, a convolution is done with the core U whose coefficients have been modified as a function of the neighborhood of the pixel with coordinates (x,y) in the image I?. The result of the two convolutions is associated linearly in order to obtain a filtered value for the pixel with coordinates (x,y). These operations are repeated for each pixel of the image I.

Abstract: The invention is a process to compare two digital images (and usually more) and to identify objects in each image. After object identification, object descriptors are formed. The object descriptors of the objects in one frame are compared to those of objects in the second frame, allowing the tracking of an object in the two frames. The movement of each tracked object within the two frames is quantified, and the second frame is corrected to account for the object's movement.

Abstract: Dynamic warp map generation system and corresponding method are disclosed. A compactor obtains spatial transformation parameters along with geometric and optical distortion parameters and combines them to form hybrid grid data in a hybrid vector space. This vector space is divided into hybrid blocks. In each hybrid block, the grid dataset is fitted with a hypersurface and the surface coefficients are saved in an interface. A decompactor obtains dynamic control parameters representing varying distortion parameters and generates a hybrid space vector. According to the hybrid space vector, a warp map is decoded from the hypersurface coefficients that compensates for dynamic geometric and optical distortions. In another example of the present invention, the dynamic warp map generation system is used for color gamut transformation.

Abstract: A process and a device for the automatic rectification of images, where at least one image is rectified by a mapping function onto a reference image and at least some of the parameters of the mapping function are unknown are disclosed.

Abstract: In one embodiment, an image processing system includes a first computer that processes image and a second computer connected with the first computer via a network. The second computer transmits the image to the first computer via the network after adjusting the resolution of the image to the lowest resolution determined by the first computer so that the first computer can process the transmitted image. Accordingly, the first computer can process the transmitted image at a satisfactory level, and at the same time, the image processing system can reduce network traffic therein.

Abstract: A data compressing and decompressing device is adapted to be used with an image pickup device and a frame buffer. The data compressing and decompressing device includes a first data register in communication with the image pickup device, a first encoder in communication with the first data register, a second encoder in communication with the first encoder and the frame buffer, a decoder in communication with the frame buffer, and a second data register in communication with the decoder. The second encoder encodes the difference into a length-variable recovery data code in a first condition of the difference, encodes the difference into a first constant-length recovery data code in a second condition of the difference, and encodes the difference into a second constant-length recovery data code in a third condition of the difference.

Abstract: In order to model a fluoroscopic noise present in a radiography operation, two successive images of a same zone are used so that it is possible to pair the dots of the two images as a function of the zone of the space that they represent. The pairs of dots are grouped in sub-groups according to their gray level. For each sub-group, the mean standard deviation ? of the Pi(x, y)?Pi?1(x, y) values is computed. A sub-group is discriminated by eliminating the dots for which Pi(x, y)?Pi?1(x, y) is greater than the mean of the values Pi(x, y)?Pi?1(x, y) plus k times the mean standard deviation. These computations are repeated a certain number of times. Once the sub-group is discriminated, its centering is assessed. A sub-group is non-centered if its mean is greater than 1.5 times its mean standard deviation. Pairs of dots (v, ?) are then obtained. From these dots, an iterative regression is performed to obtain a model of noise according to ?(v)=?.?v+?.

Abstract: A method for encoding a syntax element contained in a precoded video signal into a coded bit stream, the precoded video signal representing at least one video frame, the syntax element being associated with a predetermined portion of the video frame and being indicative of as to whether the predetermined portion of the video frame is precoded in a first or a second way into the precoded video signal is described. The method comprises investigating as to whether a neighboring portion of the video frame neighboring the predetermined portion is precoded in the first way or the second way, in order to obtain a binary value; assigning one of at least two context models to the predetermined portion of the video frame based on the binary value, wherein each context model is associated with a different probability estimation; and arithmetically encoding the syntax element into the coded bit stream based on the probability estimation with which the assigned context model is associated.

Abstract: A method for adjusting an image signal by a processor includes providing a first low pass filter and a second low pass filter, generating an energy ratio of a band-pass image signal and the image signal according to the standard deviation of a first low pass signal of the first low pass filter and a second low pass signal of the second low pass filter, providing an image adjustment parameter and generating a weighting coefficient of the image signal according to the energy ratio and the image adjustment parameter, generating a third low pass filter according to the weighting coefficient of the image signal, the image adjustment parameter, the first low pass signal of the first low pass filter and the second low pass signal of the second low pass filter, and adjusting the image signal according to the image signal and the third low pass filter.

Abstract: Methods and apparatus for spectrally-encoding plural source images and for providing the spectrally-encoded plural source images in a composite image, for rendering the composite image in a physical form, or for recovering at least one of the encoded source images from the rendered composite image such that the recovered source image is made distinguishable. Source image confusion in a rendered composite image is controlled by application of a illuminant-neutral gray component replacement (GCR) technique to the darkness common to the different colorants under the multiple illuminants.

Abstract: A method and apparatus is provided to determine affine disparity and affine invariant pattern distance from two image patterns. The method formulates the problem of determining affine disparity and affine invariant distances between two image patterns as one of finding an affine transform for an adjustable hypercolumn (HC) reference frame that maximally compensates the affine difference of the two image patterns. The image HC-coding and the difference vector is computed from two image patterns using specific orientation (SO) simple cell receptive fields employed in an HC-reference system. The Lie derivative of the difference vector is computed from image patterns using Lie germs. In accordance with one aspect of the invention, the affine transform that maximally compensates the affine difference between two image patterns is found by a gradient system wherein the gradient is calculated from the difference vector and its Lie derivatives.

Abstract: The present invention is a method of controlling a robotic mechanism comprising both active and passive joints, where the motion of one or more of the passive joints is constrained by one or more constraints imposed on the mechanism by the environment, the mechanical construction of the mechanism or the nature of the task. The method is capable of controlling mechanisms with multiple sets of passive joints with multiple environmental constraints restricting the motion of the mechanism. In a preferred embodiment the novel method is used to control a surgical robot holding a surgical instrument inserted into a patient through a natural or man-made orifice.