Abstract: There are performed three types of object shooting, i.e., a projection pattern shooting using a pattern including both characterization of a stripe based on a color and characterization based on a gradation of the same component, a flash shooting without a pattern and a non-flash shooting without a pattern. A two-dimensional image information generation portion corrects the influence of a surface reflectivity of an object or external light from the three types of images, and estimates a pattern structure using the characteristic based on a color with respect to an object having a white-based color or a low-saturation color and based on a gradation with respect to an object having a high-saturation color. A depth calculation portion specifies the correspondence relationship between the estimated pattern structure and information of the projected pattern, and calculates a depth of each part of the object based on a result of specification.

Abstract: A plurality of signal processing functions are achieved with the same arithmetic processing circuit by controlling wiring arrangements or signal modulation in accordance with a predetermined arrangement control signal that is output based on circuit arrangement information read from a circuit arrangement information storage unit. Hierarchical parallel processing is realized with small-scale circuit configuration. Further, detection of a predetermined feature and integration of the detection results can be efficiently performed.

Abstract: An initial similarity candidate calculator calculates a similarity between first and second images, which are expressed by quantized DCT coefficients, on the basis of at least first and second image feature amounts of the first and second images. A coefficient conversion processor executes a coefficient conversion process for at least one of the first and second image feature amounts. Based on an image feature amount obtained by that process, a similarity calculator calculates a similarity between the first and second images. Then, a final similarity between the first and second images is determined from the calculated similarities.

Abstract: In an apparatus for authenticating a user by employing feature points of a fingerprint image of the user, a fingerprint image input circuit scans a fingerprint of a user to be registered to provide a first fingerprint image and a fingerprint of a user to be authenticated to provide a second fingerprint image. A host provides registered feature points data corresponding to the first fingerprint image and target feature points data corresponding to the second fingerprint image. A security token circuit estimates a position difference and a direction difference between pairs of a registered feature point and a target feature point and corrects the two feature points based on the position difference and the direction difference to provide authentication result data.

Abstract: An image system with an imaging device obtains and presents at least one image. An eye gaze system associated with the imaging device determines a non-closed loop portion of the at least one image that an eye of a viewer observes. The image system associates the at least one image with the non-closed loop portion of the at least one image. An image processor analyzes the image based at least in part on the image itself together with data representative of the gaze information to determine the content of the image, where the gaze information is a non-closed loop portion of the image that an eye of a viewer observes. The image system associates the content with the image.

Abstract: The present invention is a method of categorizing an image as handwritten, machine-printed, and unknown. First, the image is received. Next, connected components are identified. Next, a bounding box encloses each connected component. Next, a height and width is computed for each bounding box. Next, a sum and maximum horizontal run for each connected component are computed. Next, connected components that are suspected of being characters are identified. If the number of suspected characters is less than or equal to a first user-definable number then the image is categorized as unknown. If the number of suspected characters is greater than the first user-definable number then determine if matches exist amongst the suspected characters. Next, compute a score based on the suspected characters and the number of matches and categorize the image as either handwritten, machine-printed, or unknown.

Abstract: A reticle inspection apparatus for detecting defects on a reticle 16 includes an image data generator 42 for generating image data of the reticle 16, a definition analyzer 44 for analyzing definition of image from the image data, a definition judge device 45 for judging whether or not the definition of image is within a predetermined reference range and a sensor position regulating stage 34 for correcting a position of a position sensor 33 when the definition of image is out of the reference range. The reticle inspection apparatus constructed as mentioned is reliable and capable of automatically diagnosing an error of an auto-focusing function of the reticle inspection apparatus due to deformation, etc., of the reticle inspection apparatus.

Abstract: A current frame portion (21) stores therein the most recent information of an image of those fingerprint images input from an inputted unit (1), while a previous frame portion (22) stores therein image information saved in the current frame portion (21). A pixel comparing portion (31) compares mutually corresponding pixel gray-level value information saved in the current frame portion (21) and the previous frame portion (22) respectively. A gray-level-value-changed pixels counting portion (32) counts the gray-level-value-increased pixels and the gray-level-value-decreased pixels based on the resultant information of that comparison of the pixel gray-level values. A pick-up timing deciding portion (33) utilizes the results obtained by the gray-level-value-changed pixels counting portion (32), to automatically detect a fingerprint image appropriate for matching in order to thus decide pick-up timing and also in order to output to an output unit (4) an appropriate fingerprint image based on the decision results.

Abstract: A system is described for linking traditional media works, such as print and broadcast media for example, to a more interactive media conduit, such as the Internet. The system avoids the need to modify the media work in anyway. Instead, it employs a passive recognition system that uniquely identifies the specific work, such as a particular television or radio broadcast or printed commercial. The identification may be based in intra-work and/or extra-work information. Several different embodiments/environments are described. The best embodiment may depend, at least in part, on costs of hardware and communication. These costs can change over time. In one embodiment, all of the databases and computation are performed at the user's premises. In another embodiment, all of the databases and computation occur at remote sites that user premise equipment can query using uniquely identifying extra-work information, such as the time, place and station on which the work was broadcast.

Abstract: The present invention provides an image and video indexing scheme for content analysis. According to the invention, a database of images or videos is compressed. By examining patterns in the compression scheme of each image or video, the present invention identifies the content of the data. In one embodiment, an unsupervised learning method is employed where each image or video is sub-divided into smaller blocks (8 pixels×8 pixels, for instance) and each of the smaller blocks is examined for its compression pattern. Then, the patterns associated with each of the smaller blocks is recorded for each of the images in the database and content is retrieved from the database by associating certain patterns or groups of patterns with certain content.

Abstract: The pattern-collating device includes as feature point pairs, among feature points which are portions indicating respective features of an examination target graphic which is the graphic to be compared and a model graphic which is the reference graphic, those which mutually correspond in said examination target graphic and said model graphic and a similarity determination section which calculates the similarity between the examination target graphic and the model graphic based on correspondence of the feature points by the feature point pair formation section, wherein the similarity determination section calculates the similarity between the examination target graphic and the model graphic based on a probability that the number of the feature point pairs between an arbitrary graphic and the model graphic, is not less than the number of the feature point pairs between the examination target graphic and the model graphic previously obtained by the feature point pair formation section.

Abstract: A method for increasing efficiency of interaction by an operator with data on a computer display includes presenting the data to the operator on the computer display, and providing multiple instances of an on-screen control at different locations on the display for selection by the operator using a pointing device linked to the display. The control is actuated responsive to the selection by the operator of any of the instances of the control on the display.

Abstract: The invention improves the appearance of freehand drawn lines and shapes in an electronic document by first recognizing freehand drawn lines and shapes and generating a line made up of sequential straight line segments for the freehand drawn line when the line does not form a closed line and generating a multiple straight-line-segment shape when the line forms a closed line. If a multiple segment shape is being reshaped, a basic shape is selected from reference ideal shapes as the basic shape of the multiple segment shape. The basic shape is adjusted to provide a specific shape as an improved shape for the freehand drawn shape. The recognition of the freehand drawn lines and shapes is accomplished by comparing source segments of a source freehand drawn line to a straight line and substituting a straight line segment for a source segment if the deviation between the source segment and the straight line is below a predetermined value.

Abstract: In the case where variations in ground objects in one and the same area are detected between a line drawing map describing profile lines of the ground objects or a reference line drawing/image obtained by picking up the ground objects from above, and a target image obtained by picking up the ground objects in the same area from above later on, a variation detecting apparatus collates the reference line drawing/image with the target image so as to obtain variation indexes indicating whether there are variations or not in the ground objects respectively, and displays ground objects which can be judged to have variations or ground objects which cannot be judged as to whether there are variations or not on the basis of the variation indexes, in a display mode in which an area of the reference line drawing/image including the ground objects and an area of the target image including the ground objects can be compared with each other.

Abstract: In transmitting image data from multiple cameras to an image processing section to produce a synthesized image from respective camera images, the amount of data transmitted through a transmission path can be cut down without sacrificing the quality of the synthesized image. In accordance with a correspondence between the synthesized and camera images as described on a mapping table, a resolution specifier specifies resolutions, which should be necessary for image synthesis, for respective areas of each camera image. A compressor, provided for each of the cameras, compresses the associated camera image data according to the resolutions specified. In this manner, the image data, which has been compressed in accordance with the correspondence between the synthesized and camera images, is transmitted through the transmission path.

Abstract: The capacity of a character feature dictionary is reduced, and stored as a feature dictionary. The capacity is reduced by clustering feature vectors in units of columns or rows for character features, by making m column vectors represent the column or row features, and by assigning 1 to m identification numbers. The capacity of the dictionary can be further reduced by representing a column or row feature with an addition sum of other column or row features, or differential features after clustering is performed, or by performing dimension compression for character features. Word recognition is performed by synthesizing a word feature for a comparison based on a word list to be recognized, and by making a comparison between a feature extracted from an input word and the synthesized feature. Or, a comparison between input word and input word features whose numbers of dimensions are different may be made with nonlinear elastic matching.

Abstract: A process for measuring skin ashing is provided. The process comprises selecting a desired skin testing area and acguiring an image of the area using x-polarization technique. The image is analyzed by obtaining a light distributing image, storing the difference between this image and the original image and using a differential in intensity to define ashing.

Abstract: Method and system of detecting and analyzing the presence of a logo in one or more datastreams. In the method, at least one video datastream of an event is first received. Next, one or more regions of interest (ROIs) for the logo in one or more images comprising the at least one datastream are identified. The one or more ROIs are analyzed to detect if the logo is present in the ROI. If so, the detection of the presence of the logo is used in making either a broadcasting decision or an advertising decision.

Abstract: In order to provide a database constructing system in which information from a plurality of persons can be automatically collected without being limited to a customer visiting a store and personal goods to wear or carry which the person likes associated with the personal characteristics to construct database, the database constructing system comprises a web server 11 for showing information on eyeglass frame; a statistical analyzing means 24 for dividing a personal facial picture 22a into component to classify them into a type of every facial component 22c and statistically analyzing a relationship between the type of every component 22c and a selected eyeglass frame 14 in order to collect data for associating a personal facial type with the selected eyeglass frame 14 on the basis of the personal facial picture 22a and information on the eyeglass frame 14 selected by the person transmitted to the web server 11 by using a web browser; and a memory means 21 for associating and preserving the information on type

Abstract: An improved interpolation method in which a threshold value used for determining a pixel value of a pixel generated by interpolation according to a context which is a state value of adjacent pixels. In the interpolation method, the ambiguity between the interpolation value and the threshold value is removed by using the context, thereby reducing the blocking and smoothing phenomena in the restored binary image.