Abstract: A method and apparatus for the analysis of magnified video image data to develop quantitative functional and morphological indices for cell-to-cell adhesion. Such induces permit distinction between different adhesion modalities and identification of various adhesion pathways of cells, for example lymphocytes time resolved measurements can also be done to track individual cells or cell clusters.

Abstract: The present invention relates to image analysis methods and systems for identifying objects in a background by generating a description, which may be either a histogram or co-occurrence matrix, of the gray level space of the image by using an entropic kernel to recursively analyze the gray level space for candidate objects and validating the presence of valid objects by comparing the candidate object attribute values to a defined set of valid object attribute values contained in a driver. The present invention includes recursive, iterative and parallel processing methods. The methods may be used in a wide variety of industrial inspection techniques, including colony counting and the identification of discrete features in carpets and of pigment elements embedded in a polymer.

Abstract: An image processor (10) is provided in which imaging data obtained by an image sensor (12) is processed for purposes of detecting motion. An optical flow field generator (16) processes the image data to provide condition number-based smoothed optical flow vectors, and stores those smoothed vectors in memory (18). The optical flow field stored in memory (18) is accessed and further processed by analyzer (20) for purposes of providing users with information on the motion of objects in the image plane of image sensor (12). Such user information may be displayed on a monitor (22).

Abstract: An adaptive learning type general purpose image measurement and recognition method includes the steps of extracting a large number of basic initial features having values which are invariant to parallel displacement of an object to be caught in an image frame and which have additivity with respect to the image frame, and performing statistical feature extraction having a learning function on the basis of a multivariate analysis method applied to the extracted initial features to thereby adaptively enable use for various types of measurement.

Abstract: A method of processing a first series of values representing a row of pixels of a digitized image for differentially encoding the first series of pixel values to generate a first series of codes representing a first series of differential values; expanding each code of the first series into a group of codes to form a second series of codes, each group of codes representing a plurality of differential values whose sum is the differential value represented by the corresponding code of the first series; and decoding the second series of codes to generate a second series of pixel values for display. By transmitting or recording the first series of codes and then effectively dividing each received or reproduced differential value into two or more smaller differential values, known apparatus can be made with little modification to expand each line of a received image by a factor of two or more, depending on the number of codes in each group.

Abstract: An apparatus and method for automated assay of biological specimens positioned on microscope slides. The apparatus comprises an interactive optical subsystem for viewing the biological specimen on the slide and for producing an interactive video signal corresponding to the viewed image. An automated optical subsystem includes a single high power microscope objective for scanning a rack of slides, portions of which having been previously identified for assay in the interactive optical means. The system also includes a processor for processing the interactive and automatic video signals for the two optical subsystems. The processor receives the automatic video signal and performs biological assay functions upon it. A method and apparatus are also disclosed for marking points for later analysis on the microscope slides and for associating an analysis function with each marked point.

Abstract: In a fingerprint scanning device for use in identification, a fingerprint image input device is provided to photoelectronically input a specified fingerprint of an entrant. A monochrome image data of the ridge pattern of the entrant fingerprint is stored as fingerprint image data. A feature extraction device has a calculator which treats the ridge pattern image with one-dimensional group-delay spectrum transform in X- and Y-directions. The feature extraction device has the characteristic of isolating and emphasizing peaks of the individual frequency spectra in the form of differential with respect to a phase component frequency in Fourier transform analysis, and determining group-delay spectra in X- and Y-direction respectively as fingerprint feature portions.

Abstract: An image is analyzed by random or pseudorandom sampling. Information about attributes such as skew, typeface, and character size and spacing is obtained by measuring a characteristic at a number of sampled locations and combining the results to obtain a measure of the characteristic for the image. The number of sampled locations is smaller than the number of locations in the image, but is large enough to achieve a degree of statistical significance. The sampled locations can be selected by obtaining a random or pseudorandom number indicating a candidate location and then applying a criterion to determine whether the candidate location is an appropriate starting point for the measurement. For example, the criterion can be that the location must be a pixel within a character or must be a pixel of a given color at an edge. The measurement can indicate a distance from each sampled location in each of a number of directions, such as the distance to an edge.

Abstract: A method and apparatus for transforming image data by recursively interleaving the data to generate blocks of component image coefficients having form suitable for subsequent quantization, motion estimation, and/or coding. In preferred embodiments, the transformed data are in optimal form for coding by conventional circuitry in accordance with the conventional JPEG or MPEG compression algorithm. In preferred embodiments, the invention includes two memory arrays (each having capacity to store one or more N.times.M image data blocks), and an analyzer connected between the memory arrays. The analyzer receives horizontal vectors (such as full rows) of an image data block stored in the first memory, transforms each horizontal vector into two vectors (each comprising half as many words as the horizontal vector), interleaves the two vectors, and writes the resulting interleaved data (an orthogonal representation of the horizontal vector) into a row of the second memory.

Abstract: A method for discerning whether an object to be inspected is acceptable or not is based on feature values with respect to a binary-coded image of the object.

Abstract: Matching probability among planar point patterns is calculated by a mating probability calculating device to decide the corresponding relationship therebetween and the best point matching is then selected by a mating point selecting device. The similarity therebetween is computed by a similarity calculating device to decide correct the results of pattern matching. An algorithm associated with the devices is also provided.

Abstract: Method of processing signal data on the basis of Principal Component Transform, apparatus for performing the method. A method is proposed for determining approximations of eigenvectors of a covariance matrix associated with signal data on the basis of the Principal Component Transform. Successive iterations on estimates enhance the development into the direction of the principal component considered. The method is applicable to the Singular Value Decomposition of data matrices. The operations to be performed are similar to those required in a neural net for adapting the synaptic coefficients. Apparatus are proposed for performing the method.

Abstract: A pattern defects inspection system inspects the presence/absence of pattern defects in a photomask as an object to be inspected in which a chromium pattern and a phase shift pattern are formed together. Measurement data output from a sensor circuit for generating measurement pattern data by inspecting measurement patterns corresponding to two types of patterns formed on the object by radiating light on the object, and two identifiable design data stored in a magnetic disk unit in advance, i.e., chromium pattern design data used to form a chromium pattern and phase shift pattern design data used to form a phase shift pattern, are read out by a bit pattern generator for performing development processing. The two types of bit data obtained by the bit pattern generator are synthesized according to the same coordinate definition. The synthesized design data is compared with the measurement data by a comparator. As a result, the presence/absence of pattern defects in the object can be determined.

Abstract: The present invention relates to a method of identifying and characterizing, by color, at least one valid object having at least one predetermined attribute value in a background. The method generates a plurality of images of a candidate object and the background, where each image is one of three primary color images or a black-and-white image. The method searches the image for a candidate object using an automatically calculated threshold gray level and determines the interior points of the candidate object. The method further determines the gray level value of the interior points in the image and calculates a color parameter for the interior points. The method thus enables one to characterize the candidate object by the color parameter and validate the candidate object having the valid object predetermined attribute value.

Abstract: A diacritical marker recognition system and method recognizes diacritical markers in a character image based upon an analysis by a neural network of the portion of the character image most likely to contain a diacritical marker. Once the neural network determines that a diacritical marker most likely exists in the character image, the system determines by using heuristics whether a diacritical marker exists or whether the character image appears to contain a diacritical marker which is actually a regular character.

Abstract: In the pattern matching method, when a reference pattern is extracted from the reference picture, check search is carried out repeatedly a plural number of times while conducting picture compressions on the reference picture with the compression start position being changed to obtain correlation values between the reference picture and the reference pattern. Based on the correlation values obtained by the check search, the number of times of search to be done actually and the picture compression ratio for the actual search are determined.

Abstract: The present invention relates to an image analysis method for determining the interior points of an object in a background when the contour, or perimeter points, of the object are known. By accessing the interior points of an object, textural and color information can be derived, thereby allowing for object recognition. Further, the ability to determine interior points of an object allows for complete identification of all objects in an image. By determining the interior points, one may "blacken out", or effectively remove previously identified objects from an image, creating a remainder image for further searching.

Abstract: A histogram is prepared using the heights of characters in an input alphanumeric character image data set. Based on this histogram, reference line characters are detected from the character row. The upper and lower extracting ordinates of each character in the character row are obtained. Then, the average of each of the upper and lower extracting ordinates in the character row is determined as the ordinate of a reference line for the character row. Thus obtained reference line is used for character recognition.

Abstract: A method and apparatus for passive autoranging. Two cameras having different image parameters (e.g., focal gradients) generate two images of the same scene. A relaxation procedure is performed using the two images as inputs to generate a blur spread. The blur spread may then be used to calculate the range of at least one object in the scene. In one preferred embodiment, a temporal relaxation procedure is employed to focus a third camera. In another preferred embodiment, a spatial relaxation procedure is employed to determine the range of a plurality of objects.

Abstract: The acceptability of images is determined by comparing each image to a template image which may be an average of several images which are known to be acceptable. The amount by which the image deviates from the template image is used as a measure of the acceptability of the image. Portions of the image at or near edges in the images may be automatically excluded from this test. Another test which includes the edge portions excluded from the first test may be performed to ensure that all portions of the image are inspected. For example, this other test may include ensuring that the correct number of edge pixels are present in the image as a whole.