Abstract: Disclosed is a method of detecting a predetermined mark embedded in an image. The mark (29) comprises a predetermined arrangement of a plurality of elements (30), each element having a predetermined colour characteristic and predetermined shape. The method processes (20) the image to provide an encoded representation of the image at a predetermined resolution (eg. 200 dpi). The coordinate positions for substantially each of the elements of the mark embedded in the image are detected (22), wherein the detection is characterised by applying at least one mask (80) to substantially each pixel of the encoded representation. From the coordinate positions, a set of spatial features representing a spatial arrangement of the detected elements are then determined (23). The determined set of spatial features is then compared (24) to a known set of spatial features to provide a confidence level measure for a degree of matching between the known set and the determined set of spatial features.

Abstract: A motion estimation method is provided. In the method, respective mean difference values for a current search point within a search block and neighboring search points within the search block are calculated. Then, motion estimation is performed around the current search point if the mean difference value of the current search point is smaller than the mean difference values of the neighboring search points. On the other hand, motion estimation is performed based on the mean difference values of at least some of the neighboring search points if the mean difference value of the current search point is not smaller than the mean difference values of at least one the neighboring search points. The motion estimation method of the present invention does not deteriorate the quality of pictures during image compression in contrast to conventional motion estimation methods and enhances image compression speed by reducing remarkably computational complexity.

Abstract: An image processing system and method visually documents and displays changes between historical and later mammographic images, preferably in three dimensions. A composite image is created which visually emphasizes temporal differences between the historical and later images. Preferably three-dimensional, digitized images, displayable in various projections, are stored for archival purposes on computer readable media. An image processor preferably exploits an optical correlator to register the historical and later images accurately and provide correlation values as temporal scalars of the differences. The registered images are then compared, voxel-by-voxel, to detect temporal differences. The composite image is displayed with synthetic colors or other visual clues to emphasize apparent changes (for example, tumor growth or shrinkage).

Abstract: A tomographic image reading method for extracting a comparison image corresponding to a diagnostic image, the diagnostic image being one of first tomographic images, the comparison image being one of second tomographic images, the method including the steps of: inputting the first images and the second images; generating a first projection image from the first images and a second projection image from the second images; measuring shift amount between the first projection image and the second projection image by using a template; correcting the slice position according to the shift amount; and displaying the diagnostic image and the comparison image to a monitor.

Abstract: The present invention relates to a method for processing mail to be returned to sender, according to which the extent of video-coding required when great quantities of mail sent by large mailers are to be returned to sender is reduced considerably. According to the invention similarities in the areas containing the senders' addresses are determined at the image level. In the case of mail where the address field images present a defined degree of similarity only one image is video-coded. The remaining mail displaying a defined degree of similarity to the video-coded item of mail is assigned to the corresponding sender.

Abstract: The truth of a paper type to be examined is judged by measuring, with respect to each of true paper types previously prepared, a plurality of types of characteristic amounts by a plurality of types of sensors for each of a plurality of portions for examination previously determined, analyzing principal components on the basis of obtained results of the measurement, to find an equation of straight line corresponding to the predetermined principal component, and producing reference data composed of a value relating to the predetermined principal component for the portion for examination on the basis of the foundation of straight line.

Abstract: A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the regions, approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

Abstract: Content data is judged to determine whether data prepared by a digital device were altered by performing an authentication process using a medium on which content data are recorded; reading the content data from the medium; embedding, in the content data, data for verifying the pertinent content; extracting, from the content data, the data for verifying the pertinent contents; using the results of the extraction to determine whether the content data were altered. Preferably, the means includes means for identifying any portion containing altered data.

Abstract: The invention relates to an image processing method for noise filtering an image sequence representing a threadlike structure on a background, including an acquisition of point data in first and second sequence images and an estimation of the corresponding filtered point data for constructing a filtered second image. The method is, performed in each sequence image, and includes: extracting the threadlike structure points, forming strings from the extracted points, temporally filtering the data of the points located outside the strings denoted background points, spatially filtering the data of the string points, and constructing the filtered second image data by performing an insertion of the spatially filtered data of the string points into the temporally filtered data of the background points.

Abstract: A method and apparatus for classifying or annotating image and video content by assigning each class of event, action, region or object a unique symbol and then building symbol strings to represent sequences in space or time. The symbol strings can be decoded using a library of annotated PT descriptors to automatically label the image and video content. Furthermore, the PT descriptors can be used for searching by sketch or searching by example where the search query input is converted to symbol strings, which are efficiently compared based on the presence and relative counts of PT descriptors mapped into a PT matrices. The Precedence Template (PT) descriptor can be used for classifying and querying video based on the spatial and temporal orderings of regions, objects, actions or events. Applied to video, the PT descriptors provide a way to compare the temporal order of events, actions, or objects such as those represented in a scene transition graph, key-frame list, or event string.

Abstract: The invention provides a motion vector searcher which includes an inter-block difference arithmetic operation section for calculating and outputting difference amounts between an original image MB and a plurality of search MBs, an additional amount arithmetic operation section for outputting a correction difference amount obtained by adding an additional amount, which relies upon a horizontal component and a vertical component of each of the motion vectors and a state of coding, to each of the difference amounts and for outputting a motion vector based on the motion vector, and a motion vector determination section for determining an optimum motion vector which exhibits the highest one of correlation degrees between the original image MB and the search MBs. With this arrangement, reduction of the information amount of motion vectors is achieved when the compression ratio is high and the transmission rate is low.

Abstract: A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the region, approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

Abstract: A method and apparatus for retrieving multimedia data using shape information. The multimedia data retrieval apparatus comprises a shape information feature extractor for receiving shape information of a query image and extracting a feature of the received shape information using a shape information descriptor based on eigen vectors of a multilayer covariance matrix, an image feature extractor for extracting a feature of each image data in the same manner as the shape information feature extractor, a multimedia database creator for creating a multimedia database on the basis of the features extracted by the image feature extractor, a similarity comparator for comparing the feature of the query image extracted by the shape information feature extractor with the features of the image data in the multimedia database to calculate similarities therebetween, and a compared result output unit for outputting the results calculated by the similarity comparator.

Abstract: A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the region approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

Abstract: A method and apparatus detects the presence of a watermark in digital data. The digital data may represent picture or sound information and maybe in the form of a broadcast television signal or a signal that has been recorded on a recording medium such as a compact disc. The watermark includes coefficients which have been subject to an inverse local orthogonal transform before being embedded in the input data. In order to detect the presence of the watermark, the input watermarked data is first forward transformed and subtracted from the watermark coefficients so as to derive the data coefficients. The data coefficients are squared and formed into a local average to obtain a measure of the power in the local average. The watermark coefficients are divided by the local average so as to scale them and the scaled watermark coefficients are cross-correlated with the input data to detect whether the watermark is present.

Abstract: A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the region, approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

Abstract: A computer aided detection method and system to assist radiologists in the reading of medical images. The method and system has particular application to the area of mammography including detection of clustered microcalcifications and densities. A microcalcification detector is provided wherein individual detections are rank ordered and classified, and one of the features for classification is derived using a multilayer perceptron. A density detector is provided including an iterative, dynamic region growing module with embedded subsystem for rank ordering and classification of a best subset of candidate masks. A post processing stage is provided where detections are analyzed in the context of a set of images for a patient. Three analysis methods are used to distribute a limited number of detections across the image set and further within each image, and additionally to perform a normalcy classification.

Abstract: A system and corresponding method for head tracking and color video acquisition via near infrared luminance keying is disclosed. The head of the local user is tracked in real time by uniformly illuminating a rear projection screen that surrounds a display cube with light having a wavelength in the near-infrared spectrum. A near-infrared image of the head of the local user is acquired by a near-infrared camera equipped with filters that discern the difference between the illuminated rear projection screen and any foreground illumination. A color image of the head of a local user and the projection of a remote location are acquired by a color camera, placed in close proximity to the near-infrared camera. A bounding box is then placed around the head of the local user in the near-infrared image. This bounding box is then translated to the view space of the color camera. This translated image is then used to crop the color image. The cropped color image is then transmitted to the remote location.

Abstract: An object recognition system having at least two image sensors and a controller that is adapted for measuring the distance from the system to a physical object with respect to respective windows of a n image captured by the sensors. The controller is further programmed to form clusters by uniting adjacent windows that have similar measure distances. The controller is programmed to judge whether each of the clusters is valid or invalid based on the attributes of the cluster and to recognize an object based on the clusters judged to be valid.

Abstract: The invention relates to an associated information adding apparatus and method for adding information associated with image data as an electronic watermark to the image data, and an associated information detecting apparatus and method for detecting the associated information. Particularly, the apparatus includes a memory for storing a unit watermark, a unit watermark repeating section for repeatedly reading the unit watermark from the memory by using a surplus obtained by dividing a pixel position coordinate value of a pixel in a vertical direction and a horizontal direction of an image by a size of a vertical and horizontal repetitive unit of the unit watermark, and an adding section for adding the unit watermark read out from the unit watermark repeating section to information of the image so that the unit watermark is repeated vertically and horizontally on the image. By this, since it is sufficient if the memory stores only the unit watermark, there is an effect that the memory to be used may be small.