Abstract: A method for following hand movements in an image flow, includes receiving an image flow in real time, locating in each image in the received image flow a hand contour delimiting an image zone of the hand, extracting the postural characteristics from the image zone of the hand located in each image, and determining the hand movements in the image flow from the postural characteristics extracted from each image. The extraction of the postural characteristics of the hand in each image includes locating in the image zone of the hand the center of the palm of the hand by searching for a pixel of the image zone of the hand the furthest from the hand contour.

Abstract: A system and method for improved viewing and navigation of large digital images, such as whole slide images used in microscopy. The system and method displays the digital image along with movable navigation and field of view boxes that enable a viewer to pan the digital image in an accurate manner, and also performs automatic absolute reorientation of the digital image and automatic relative reorientation of subsequent digital images in relation to the first digital image.

Abstract: An image processing apparatus includes a face-image detector configured to detect a region of a face image from an image supplied thereto. A face-direction detector is configured to detect a direction that a face in the detected face image is facing and a feature-position detector is configured to detect feature positions corresponding to features of the face from the detected face image and the detected face direction. A feature-value calculator is configured to calculate feature values at the detected feature positions and a mapper is configured to map the calculated feature values using predetermined mapping functions. A a recognizer is configured to recognize whether the detected face is a registered face, using the mapped feature values and feature values registered in advance.

Abstract: Image search results are obtained by providing weights to visual features to emphasize features corresponding to objects of interest while simultaneously deemphasizing irrelevant or inconsistent features that lead to poor search results. In order to minimize the impact of visual features that are unreliable or irrelevant with respect to the objects of interest in the image, context-dependent weights are provided to detect visual features such that those visual features pertaining to the objects of interest are more heavily weighted than those visual features that pertain to irrelevant or unreliable portions of the image. Visual features may be weighted for images in a searchable database. Training data may be obtained and used in weighting visual features in a query image and, alternatively, in searchable database images.

Abstract: The invention relates to a method and a device for representing a two-dimensional digital image on a projection surface, whereby at least one projector projects the content of an image buffer onto the projection surface. The aim of the invention is to provide a method and a device which allow to project a digital image onto a background having any surface structure and/or color in such a manner that any influences on the image caused by the background are compensated to the last pixel for at least one special observer perspective. In a special embodiment, definition of the representation is optimized to the last pixel even on an uneven background. For this purpose, the digital image is processed during a rendering step by geometrically distorting it using a two-dimensional pixel-offset field which contains information on the projection surface, and by manipulating the color of the image by means of a two-dimensional surface texture of the projection surface.

Abstract: Presented is a method of automatically performing an action, based on graphical input. The method comprises: receiving, for a user, an input image; comparing the input image with the contents of a user-customized database comprising a plurality of records, each record representing a predefined class of image, wherein the user has previously associated records in the database with respective specified actions; attempting to recognize the image, based on the similarity of the input image to one of the predefined classes of image represented in the user-customised database; and if the image is recognized, performing the action previously associated by the user with the class. Also presented is apparatus for recognizing an image and a method of constructing a user-customized database.

Abstract: The present invention relates to a process for the automatic determination of the coefficient of a slope from a motor vehicle fitted with a camera.

Abstract: Images of items of jewelry having gemstones embedded therein are imaged and analyzed to determine the weights associated with the gemstones and, separately the precious metal in which the gemstones are encased without having to remove the gemstones from the jewelry.

Abstract: Detectors capable of accurately detecting and tracking moving features of such as faces within a video stream are sometimes too slow to be run in real-time. The present invention rapidly scans video footage in real-time and generates a series of preattemptive triggers indicating the frames and locations within the frames at our deserving of further investigation by a sub real-time detector. The triggers are generated by looking for peaks in a time variant measure such as the amount of symmetry within a frame or portion of a frame.

Abstract: Over the past few years there has been a dramatic proliferation of digital cameras, and it has become increasingly easy to share large numbers of photographs with many other people. These trends have contributed to the availability of large databases of photographs. Effectively organizing, browsing, and visualizing such .seas. of images, as well as finding a particular image, can be difficult tasks. In this paper, we demonstrate that knowledge of where images were taken and where they were pointed makes it possible to visualize large sets of photographs in powerful, intuitive new ways. We present and evaluate a set of novel tools that use location and orientation information, derived semi-automatically using structure from motion, to enhance the experience of exploring such large collections of images.

Abstract: A method for optically measuring an object by means of an optical recording apparatus includes a triangulation method. A first shutter means is used to produce a first pattern and to project the first pattern as a first projection beam onto the object to be measured. At least one further shutter means is used to produce a further pattern and to project the further pattern as a further projection beam onto the object to be measured. The first pattern and the further pattern are passed back from the object as observation beams and are recorded by at least one recording means in order to obtain a three-dimensional data record of the object. The projected first pattern and the further pattern are recorded at the same time in at least one triangulation recording using the at least one recording means.

Abstract: A technique of efficiently extracting and synthesizing an object image from a plurality of images captured at different image magnifications. An image processing method of the present invention includes the steps of generating a first background image corresponding to a first image captured at a predetermined image magnification, extracting a first object image from the first image, generating a second background image corresponding to a second image captured at an image magnification higher than the predetermined image magnification, based on the first background image and the first object image, and extracting a second object image from the second image and the second background image.

Abstract: Some embodiments of the present invention may relate to a device and a method of enabling an automatic global matching of a plurality of images to provide a substantially consistent planar representation of a fundus. According to some embodiments of the invention, a device for enabling an automatic global matching of a plurality of images to provide a substantially consistent planar representation of a fundus may include a local matching module and a global matching module. The local matching module may be adapted to locally match a pair of overlapping images. As part of locally matching the images, the local matching module may be adapted to provide a best offset vector for the images based upon a matching of features from overlapping portions of the images. The global matching module may be adapted to globally match at least a triplet of locally matching pairs of images whose best offset vector sum is substantially zero.

Abstract: An apparatus and method for projecting a spatial image is disclosed. In one embodiment, the apparatus includes i) a monitor, which outputs the spatial image, ii) an image direction control unit, which controls the direction of the spatial image outputted from the monitor and controls a viewing angle, and iii) a half-mirror, which transflects the spatial image whose direction is adjusted by the image direction control unit. At least one embodiment of the present invention modifies the conventional barrier technology, which has been used to control 3D images or viewing angles, to enhance a sense of realism by adjusting the direction of light emitted from a display device.

Abstract: Contrast and lightness measures are used to first classify the image as being one of non-turbid and turbid. If turbid, the original image is enhanced to generate a first enhanced image. If non-turbid, the original image is classified in terms of a merged contrast/lightness score based on the contrast and lightness measures. The non-turbid image is enhanced to generate a second enhanced image when a poor contrast/lightness score is associated therewith. When the second enhanced image has a poor contrast/lightness score associated therewith, this image is enhanced to generate a third enhanced image. A sharpness measure is computed for one image that is selected from (i) the non-turbid image, (ii) the first enhanced image, (iii) the second enhanced image when a good contrast/lightness score is associated therewith, and (iv) the third enhanced image. If the selected image is not-sharp, it is sharpened to generate a sharpened image. The final image is selected from the selected image and the sharpened image.

Abstract: Systems and methods for processing extracted plane features are provided. In one embodiment, a method for processing extracted plane features includes: estimating an area of each plane of a plurality of planes extracted from data collected by an imaging sensor; generating a list of detected planes including the area of each plane; filtering the list of detected planes to produce a list of candidates for merger, filtering the list of detected planes discarding any plane not satisfying an actual points received criteria; applying a primary merge algorithm to the list of candidates for merger that iteratively produces a list of merged planes by testing hypothetical merged planes against a merging criteria, the hypothetical merged planes each comprising a plane from the list of merged planes and a plane from the list of candidates for merger; and outputting a final list of planes.

Abstract: Systems and methods of recognizing a business document and creating a document signature. In one embodiment, a business document is scanned and a business document image is created. The business document image is compared to a template database. If a matching template is found, document fields are defined and extracted. If no matching document template is found, the document image is compared to a skeleton database. If a matching document skeleton in found, document fields are defined and extracted. A document skeleton is generated and then stored in the template database. If no matching document skeletons are found in the skeleton database, document fields are manually extracted. A document skeleton is then generated from the identification of static and variable strings and stored in the skeleton database. Document fields are validated after all document fields have been extracted.

Abstract: An attribute-information-area extracting unit extracts an attribute information area in which attribute information is displayed when the attribute information area does not change between certain frames of adjacent scenes obtained by dividing a video content by a scene dividing unit. A character-areas extracting unit extracts character areas in which video attribute information in individual characters that is metadata of the video content of the attribute information area are present, and a character-area-meaning assigning unit assigns meanings to the character areas. A character-area reading unit reads the video attribute information, from the character areas to which meanings are assigned, thereby outputting the video attribute information.

Abstract: A communication system that integrates audio and visual messaging, including a mobile communication device for receiving visual messages and for transmitting voice messages to a recipient, a base station system in communication with the mobile communication device, an electronic mail gateway for delivering visual messages to the base station system for transmission to the mobile communication device, and an integrated mail gateway for receiving from the base station a voice message and addressing information that were both transmitted from the mobile communication device. The integrated mail gateway is programmed to create an e-mail message comprising the voice message. The integrated mail gateway is also programmed to use the addressing information to address the e-mail message, and to send the addressed e-mail message to the recipient.

Abstract: Computer graphics may be detected in digital images by extracting a first set of features from an input digital image, extracting a second set of features from a prediction-error image derived from the input digital image, and applying a classification algorithm to the first set of features and the second set of features to determine if the combined sets of features indicate that the input digital image corresponds to computer graphics.

Abstract: Vehicle segmentation and counting method based on the property of color variation and headlight information combining change detection in nighttime traffic environment (one-way road with coming direction) is provided. The goal is to reduce the effect of ground-illumination that decreases the accuracy of vehicle segmentation. Besides, the amount of traffic flow is calculated and it can be used in other post-applications, such as traffic-flow reporting or controlling.

Abstract: Systems and methods for enhancing the combined image of multiple attributes without comprising the image of either attribute. The combined image of the multiple attributes is enhanced for analyzing a predetermined property revealed by the attributes. The combined image can be interactively manipulated to display each attribute relative to an imaginary light source or highlighted using a specular component. The systems and methods are best described as particularly useful for analytical, diagnostic and interpretive purposes.

Abstract: A method and system for retouching digital images for a motion picture removes semi-transparent artifacts or ‘blotches’ caused by contaminates in the optical path of the camera. This approach provides the benefit of only having to retouch a single average image that is than automatically applied via a correction power map to the entire sequence of images for the affected scene. The formation of an average image tends to reinforce the artifacts making them easier to identify and reduce background detail making it easier to retouch the artifact.

Abstract: Some embodiments of the present invention may relate to a device and a method of enabling the stabilization of a series of retinal angiography images to provide a coherent serial display, the method comprising: locally matching a pair of overlapping images, said locally matching includes at least providing a best offset vector for the images, wherein the best offset vector is provided based upon a matching of features from overlapping portions of the images; globally matching at least a triplet of matching pairs of images, wherein pairs of globally matching images include locally matching pairs whose best offset vector sum is substantially zero; choosing a key image; and aligning all the remaining images to the key image.

Abstract: This invention provides an improved method for evaluating the quality of images using a test Skr-matrix system. The index k refers to the fractal level in an Skr-matrix, having matrices themselves as elements. The index r?k refers to the Kronecker sub-level to which a typical internal sum structure is present. Skr-matrices can be explained in terms of cognition numbers, basic components, eigenvalues and sine-like eigenvectors. Skr-matrices also form vector spaces in which matrix distances can be properly calculated. The image Skr-quality parameters are derived from an intermediate quasi-Skr-matrix and its best-Skr-approximation in relation to a theoretical reference Skr-matrix. Useful applications are in the field of analogue and digital cameras, scanners, vision sensors, monitors, printers, spectrophotometers, infrared cameras, copying machines, TV-screens, GPS screens, X-rays, Gamma rays, Laser rays, or every other component in the image production and image handling field.

Abstract: The present invention relates to a real-time nighttime vehicle detection and identification system comprises an illuminant object image segmentation device 1, an illuminant object classifying device 2, a vehicle lighting object identification device 3, a vehicle position determining device 4 and a vehicle tracking device 5. Under various circumstances of road lighting during nighttime, the system can efficiently and accurately demarcate and identify the lamps of oncoming and preceding vehicles and accurately provides the driver with auxiliary information needed to analyze the traffic conditions in front of the vehicle during the conditions met on the road at that time.

Abstract: A method of filtering video packets for video stream monitoring is provided. A video packet of a video stream is received. One or more features are extracted from a specified frame of the video packet via one or more histograms and frequency domain coefficients of the specified frame. One or more concept detectors are implemented on the one or more features creating one or more confidence values. The confidence values are transmitted to a display module for filtering of video packets.

Abstract: A method of navigation in three-dimensional, electronic image data sets is disclosed, whereby the image data sets contain three-dimensional image data subsets. The method includes optically representing at least one two-dimensional projection of an image data set that includes a two-dimensional subprojection of at least one image data subset, optically highlighting the at least one two-dimensional subprojection, receiving a user input directed to the selection of a certain subprojection, and optically representing, in accordance with said user input, at least one additional two-dimensional projection of the image data set that includes a two-dimensional projection of the selected image data subset. The method can be used for an image data set that is formed by fusion of at least two source image data sets. The source image data sets can especially comprise computer tomography and a positron-emission tomography image data set.

Abstract: A method of calculating an aerial image of a spatial light modulator array includes calculating pair-wise interference between pixels of the spatial light modulator array; calculating effective graytones corresponding to modulation states of the pixels; and calculating the aerial image based on the pair-wise interference and the effective graytones. The graytones depend only on the modulation states of the pixels. The pair-wise interference depends only on position variables. The position variables are position in an image plane and position in a plane of a source of electromagnetic radiation. The pair-wise interference can be represented by a matrix of functions. The pair-wise interference can be represented by a four dimensional matrix. The effective graytones are approximated using sinc functions, or using polynomial functions.

Abstract: A method and algorithm for measuring the symmetry (SYM=total symmetry) of N points based on counting the number of “elementary symmetric recognition acts”, or having two distances d(A,B) and d(C,D) be equal within a given tolerance t. The same algorithm can be adapted to measure un-normalized positional entropy deficit (UPED) and positional entropy of N points. These parameters (SYM and UPED) come out almost the same for small occupation numbers (1<=k<=4). Here the occupation number k is the number of equal distances in the figure for a given value d. The algorithm can be incorporated into an imaging device, such as computer graphic programs or cameras, to solve problems of defect detection, say in gems, or object detection.

Abstract: A shape measurement apparatus includes a work stage supporting a target substrate, a pattern-projecting section including a light source, a grating part partially transmitting and blocking light generated by the light source to generate a grating image and a projecting lens part making the grating image on a measurement target of the target substrate, an image-capturing section capturing the grating image reflected by the measurement target of the target substrate, and a control section controlling the work stage, the pattern-projecting section and the image-capturing section, calculating a reliability index of the grating image and phases of the grating image, which is corresponding to the measurement target, and inspecting the measurement target by using the reliability index and the phases. Thus, the accuracy of measurement may be enhanced.

Abstract: A short-time Goertzel transform is applied to the image signal to transform it into a representation of the spatial frequency component corresponding to the periodic pattern. This representation is processed. Next the inverse of the transformation is computed and the result of the inverse transformation is removed from the image signal.

Abstract: A digital image is processed to provide an estimation of the position in the image plane of a vanishing point. The processing includes detecting pairs of similar image patches and identifying a concurrent set of straight virtual lines that substantially converge at a point on the image plane, each line passing through a pair of similar image patches within the image.

Abstract: In the image forming apparatus, a plurality of pages of data are reduced and created as collected data, and specific information corresponding to a sheet of print medium is created. The collected data and the specific information are edited in a data editing section and transmitted to a printing section. Even when a plurality of the pages of data is printed in a sheet after reduced, the specific information is printed on non-reduced condition, thus making it possible to print the specific information which is easily distinguished.

Abstract: At least one image captured from a printed document and at least one image captured from a display surface other than a printed document are processed. A surface-type-identification module accepts as input both types of images and identifies, for a particular image, the type of surface from which the image was captured. A display-surface-preprocessing module preprocesses the at least one embedded-interaction-code image captured from a display surface other than a printed document. A printed-document-preprocessing module preprocesses the at least one embedded-interaction-code images captured from a printed document. An embedded-interaction-code-processing module outputs location information for at least one of the at least one image captured from a printed document and the at least one image captured from a display surface other than a printed document.

Abstract: An image scanning apparatus arranged to press an original document placed on a glass plate by a platen cover and to scan the original document by a line sensor includes a light source used when scanning image information, a first detection sensor arranged to detect as a first timing a state in which the cover is opened at, for example, an angle of 20 degrees, a second detection sensor arranged to detect as a second timing a state, for example, that is immediately before the cover closes the glass plate, and an original document size determining unit arranged to determine the size of the original document based on the differential data, which is calculated from first image information scanned at the first timing and second image information scanned at the second timing.

Abstract: A method of measurement of proximity of a second contour to a first contour, comprises for each point of the first contour, a step of association with a point of the second contour determined as the closest, and a step of pairing each point of the second contour with one or zero points of the first contour, by determining the point of the first contour which is closest from among the set of points of the first contour that are associated with said point of the second contour. A method of automatic identification of targets applies this proximity measurement process to determine the measure of proximity of a template contour, applied as second contour, to an image contour, applied as first contour.

Abstract: The invention relates to a method for optically scanning the three-dimensional geometry of an object by means of triangulation, in which a pattern (9, 9?) is projected onto the object (7) to be scanned in order to obtain a 3D data set, and the projected pattern (9, 9?) is recorded in an image (40, 41). In a first step for the production of at least one first image (40), a first pattern (9) is projected and in a second step for the creation of at least one further image (40), a further pattern (9?) deviating from the first as regards position or shape is projected onto the object (7) to be scanned and the image (41) is created. The first image (40) and the further image (41) comprise at least one common point (44). The 3D data acquired from the images (40, 41) are merged in a subsequent step on the basis of the 3D data of the at least one common point (44) such that the 3D data acquired from said images (40, 41) agree at least with reference to the 3D data of the common point (44) in the 3D data set.

Abstract: A camera tracking apparatus for calculating in real time feature information and camera motion information based on an input image includes a global camera tracking unit for computing a global feature map having feature information on entire feature points; a local camera tracking unit for computing in real time a local feature map having feature information on a part of the entire feature points; a global feature map update unit for receiving the computed feature information from the global and local camera tracking units to update the global feature map; and a local feature selection unit for receiving the updated feature information from the global feature map update unit to select in real time the feature points contained in the local feature map. The local camera tracking unit computes the local feature map for each frame, while the global camera tracking unit computes the global feature map over frames.

Abstract: A method of selecting images for lenticular printing. The method comprises receiving a sequence having a plurality of images, selecting a segment of the sequence according to one or more lenticular viewing measures, and outputting the segment for allowing the lenticular printing.

Abstract: A method and apparatus for adjusting brightness of an image are provided, in which number distribution information of pixel brightness is detected, and the brightness of a specific area of the image is adjusted using characteristic values according to a distribution characteristic of the detected number distribution information. Accordingly, a decrease in an image recognition characteristic of a human being is compensated for in a specific area, such as, low-brightness area, of an image.

Abstract: Image recognition and distance calculation methods and devices are provided. First, an image corresponding to a level ruler is obtained, wherein the image includes a first predefined scale and a second predefined scale projected on the level ruler. Then, a baseline height of a baseline mark in the level ruler is determined according to the image. The heights of the first predefined scale and the second predefined scale are calculated according to the baseline height of the baseline mark, the position of the baseline mark in the image, and the positions of the first predefined scale and the second predefined scale in the image. Thereafter, a distance to the level ruler is calculated according to a height difference between the heights of the first predefined scale and the second predefined scale.

Abstract: A method is for filtering tomographic 3D images of an examination object. The examination object is imaged by using a volume model that divides the volume of the examination object into a multiplicity of three-dimensional image voxels with individual image values, wherein the image value of each voxel reproduces an object-specific property of the examination object in this volume. After the reconstruction of the total volume for each voxel, variances are calculated in a prescribed region or radius R in order to determine contrast jumps and their spatial orientation with their tangential planes T. The image values in the tangential plane T are filtered with a two-dimensional convolution, and subsequently the original voxel data are mixed in weighted fashion with the filtered voxel data.

Abstract: Methods, systems, and apparatuses are provided for estimating a location on an object in a three-dimensional scene. Multiple radiation patterns are produced by spatially modulating each of multiple first radiations with a distinct combination of one or more modulating structures, each first radiation having at least one of a distinct radiation path, a distinct source, a distinct source spectrum, or a distinct source polarization with respect to the other first radiations. The location on the object is illuminated with a portion of each of two or more of the radiation patterns, the location producing multiple object radiations, each object radiation produced in response to one of the multiple radiation patterns. Multiple measured values are produced by detecting the object radiations from the location on the object due to each pattern separately using one or more detector elements. The location on the object is estimated based on the multiple measured values.

Abstract: Disclosed herein are methods and systems for encoding digital watermarks into content signals. Also disclosed are systems and methods for detecting and/or verifying digital watermarks in content signals. According to one embodiment, a system for encoding of digital watermark information includes: a window identifier for identifying a sample window in the signal; an interval calculator for determining a quantization interval of the sample window; and a sampler for normalizing the sample window to provide normalized samples. According to another embodiment, a system for pre-analyzing a digital signal for encoding at least one digital watermark using a digital filter is disclosed.

Abstract: An image forming apparatus and method for grouping pages with an image processing apparatus includes scanning each of a plurality of pages, detecting one or more features of each of the scanned pages, and grouping each of the plurality of scanned pages into at least first and second groups based on the detected features. Each of the at least first and second groups comprises at least one of the plurality of scanned pages.

Abstract: The invention relates to a human eye detection method, apparatus, system and storage medium.

Abstract: Systems and methods for enhancing the combined image of multiple attributes without comprising the image of either attribute. The combined image of the multiple attributes is enhanced for analyzing a predetermined property revealed by the attributes. The combined image can be interactively manipulated to display each attribute relative to an imaginary light source or highlighted using a specular component. The systems and methods are best described as particularly useful for analytical, diagnostic and interpretive purposes.

Abstract: A data processing apparatus and data processing method enabling a camera generating image data to be identified easily with a high reliability, which identify if a predetermined image generating apparatus having distinctive variations in light receiving intensity of individual light receiving elements and generating image data based on light receiving results of the plurality of light receiving elements generated the first image data to be identified, wherein a correlation detector detects correlation between first image data and second image data for reference generated using a predetermined image generating apparatus and a CPU identifies if the first image data was generated using an image generating apparatus based on that correlation.

Abstract: A method and system for determining the orientation of an image of a picture within a scanned image, including the steps of locating in the scanned image the contour of the image of the picture, determining a plurality of bounding boxes confining the contour of the image of the picture, selecting one of the plurality of bounding boxes that is substantially aligned with the contour of the image of the picture, and calculating an angle of rotation of the picture based on the selected bounding box.