Abstract: The present invention is a method of fingerprint verification that includes the steps of capturing a complete fingerprint of a number of enrollees; capturing a portion of a claimant's fingerprint, where the portion is less than an entire fingerprint; dividing the portion of the claimant's fingerprint into a number of segments; comparing each of the segments against the fingerprint of the enrollee the claimant claims to be; generating a correlation score for each of the segments; calculating a distance error for the segments; combining the distance errors into an average distance error; generating a verification vector based on each of the correlation scores for each of the segments and the distance error; establishing a threshold vector; and comparing the verification vector against the threshold vector in order to determine whether or not the claimant is the enrollee the claimant claims to be.

Abstract: A method of identifying an individual from examination of their natural physical characteristics is shown. The method comprises obtaining from an individual during a registration process, a fingerprint image having at least one registration pore and at least one registration macrofeature; wherein registration pore data is derived from the registration pores, and registration macrofeature data is derived from the registration macrofeatures. In a bid step, a fingerprint image having at least one bid pore and at least one bid macrofeature is obtained; wherein bid pore data is derived from the bid pores and bid macrofeature data is derived from the bid macrofeatures. Bid associated data is constructed from associating the bid pore data with the bid macrofeature data, and constructing registration associated data derived from associating the registration pore data with the registration macrofeature data.

Abstract: Methods and apparatus for the accurate determination of the identity of human beings by comparing a fingerprint image with previously recorder templates utilize an oil impregnated material to condition a finger by releasing a controlled amount of a lubricant on the finger prior to recording the finger with an electronic scanner. The conditioned finger in then scanned and a fingerprint image is acquired. Different orthogonal sets of features, including but not limited to, minutiae and meniscus or global ridge frequency information are extracted from the fingerprint image. To enhance the matching accuracy, these features are then fused using a rank score combining method. The fused score is compared to a threshold to identify the human being. During the scanning process, the scanned finger is monitored electronically to determine the consistency in position, the quality of the image, and the stationary of the finger.

Abstract: In order to classify fingerprint images with a high precision by integrating classification results and their merits of different classification means making use of their probability data, a fingerprint image classification system of the invention includes: a plurality of classification units (12 and 15), each of the plurality of classification units (12 and 15) generating an individual probability data set (17 or 18) indicating each probability of a fingerprint image (16) to be classified into each of categories; a probability estimation unit (13) for estimating an integrated probability data set (19) from every of the individual probability data set (17 and 18); and a category decision unit (14) for outputting a classification result of the fingerprint image (16) according to the integrated probability data set (19).

Abstract: A method and ultra-compact system has been developed for illuminating and detecting the surface topography of an object such as the finger of an individual. The system is capable of producing high-contrast images which can be electronically transmitted in real-time, or stored using electronic or photographic recording devices. Light traveling within a light transmitting substrate is redirected by a slanted-fringe light diffractive grating preferably embodied within a volume hologram. The volume hologram, either of the reflection or transmission type, is attached to the light transmitting substrate, and functions to diffract light striking thereupon and illuminate an object having topographical surface structure. After being spatially and intensity modulated in accordance with topographical details of the illuminated object, the modulated light passes back through the light transmitting substrate and the volume hologram, onto an image detection array, for subsequent analysis.

Abstract: A fingerprint image is divided into blocks of pixels. The blocks are marked as directional or non-directional. The blocks are also determined to be within the foreground or background of the image. Contiguous regions of blocks that are in the foreground and are directional are selected. The quality measure is the ratio of the area of all these selected contiguous regions to the total area of the fingerprint image (i.e., the foreground.) The contribution of each of the blocks of the regions to the quality measure can be given by a distance from a block containing a reference point (a block of reference) within the foreground. Further, the block of reference can be located at the centroid of the foreground. Images are judged to be of poor quality if the quality measure is below a quality threshold and are judged to be of good quality if the quality measure is above the quality threshold. Optionally, poor quality images are examined further to determine if they are smudged or come from a dry finger.

Abstract: A biometric time and attendance device for scanning an epidermal portion of a human body, generating an epidermal topographical pattern and transmitting the epidermal topographical pattern to a host computer for determining access privileges and for updating epidermal topographical database.

Abstract: A system and method match a search print with one or more file prints stored in a database, wherein each of said prints including minutiae. The system and method receive a minutiae match report which includes a list of file prints which are possible matches with the search print. The minutiae match report is based on at least a comparison of coordinate locations and angles of rotation of the minutiae in the file prints with the minutiae in the search prints. The system and method determine an offset between a first singularity in the search print and a corresponding first singularity in the file print. Additionally, the system and method determines a first angle between at least one singularity in the search print and at least one minutia of the search print. A second angle between a corresponding at least one singularity in the file print and a corresponding at least one minutia of the file print is determined.

Abstract: To provide a stripe pattern matching system enabling to verify minutia correspondence between a searching stripe pattern and a filed stripe pattern independent of position or direction of the searching stripe pattern, correspondence value between them is evaluated by comparing their distances, directions or relations to their each neighboring minutiae by a pairing examination means (16). The most appropriate rotation angle and the most appropriate shifting coordinates for adjusting the searching stripe pattern to the filed stripe pattern is obtained by selecting a most appropriate axial candidate giving the most concentrated coordinate deviations referring to deviation distributions of correspondence values accumulated on a deviation plane memory (18) by applying each axial candidate as the coordinate adjustment reference. Therefore, the most appropriate coordinate adjustment can be performed even when either or both of absolute direction and position cannot be specified, in the invention.

Abstract: The present invention is a method and apparatus for automatically placing a first unknown image, such as an unknown fingerprint image, into one of a plurality of categories. The invention includes storing in a library a plurality of value series, each of which series is derived from the frequency representation of an image category. The categorization process and apparatus takes the frequency image of a first unknown pattern to create a first frequency image. The frequency image plane of the first (unknown) frequency image is divided into a plurality of frequency image plane regions. Each of the frequency image plane regions may be an angular segment radiating from the origin of the frequency image plane. A region value is assigned to each of the frequency image plane regions based on the total energy in the frequency image in that region. The region values for the first frequency image are combined to generate a first series of region values.

Abstract: A local information extracting portion 11 extracts a plurality of ridge line candidate images for each of local regions into which an image has been divided. A first ridge line candidate image selecting portion 12 selects a first ridge line candidate image that has high likelihood of a ridge line for each local region. A connectivity evaluating portion 13 evaluates the connectivity of first ridge line candidate images between each local region. A clustering portion 14 clusters local regions corresponding to the evaluated result of the connectivity evaluating portion 13 and generates a local region group. A cluster evaluating portion 15 determines an initial local region group that is a local region group having high likelihood of a ridge line. A ridge line image restoring portion 16 outputs a first ridge line candidate image for each local region that is included in the initial local region group.

Abstract: A base pair of minutia is selected in the latent fingerprint under consideration and each tenprint or reference fingerprint. For each selected base pair, those sets of minutia pairs are selected which satisfy apriori constraints including angle, distance and ridge counts, to generate a first set of minutia which support the fingerprint correspondence. A second set of the supporting minutia pairs is generated from the first set, which doesn't contain pairs which are inconsistent with the base pair/bias angle. A third set is established using "dynamic programming" to determine the largest topologically self-consistent subset of the second set. The minutia pairings are counted in the third set, to thereby establish a merit of the base pair. For each of the minutia of the latent fingerprint, a correspondence group is generated, of a predetermined number of minutia of the tenprint which have the greatest merit.

Abstract: Linear structures are used to identify persons. In order to be able to combine a multiplicity of such linear structures in a database, their original images are analyzed and reconstructed using orthonormal basic functions. A preferred direction of the linear structure is determined for each pixel. A quality measure is used to evaluate the reliability of the analyzed data. Singularities (SI) and minutiae (MI) are extracted and stored.

Abstract: A method to extract automatic high level features of a gray level ridge flow image including the automatic determination of the location of the high level features including the core and delta points of a fingerprint image in the form of a gray level image, comprising the following five steps:(1) determining a ridge flow direction of each gray level pixel of a fingerprint image and assign it with a direction code;(2) finding out a block directional flow and assigning each with appropriate direction code thereof;(3) correcting block flow directions in which a detection of the flow direction is affected image an input image quality in order to be immune from noises infiltrated during the acquiring process;(4) locating the delta points which are based on a corrected block direction flow diagram to locate from zero to a few delta points; and(5) locating the core points which are based on a corrected block direction flow diagram to locate one to two core points.

Abstract: A skin pattern classification system extracts ridge line data and valley line data from image data of a skin pattern. Minutiae are extracted from the ridge line data and the valley line data. Subsequently, minutia correspondence information is obtained by detecting mutual correspondence among the minutiae from the ridge line data, valley line data and the minutiae. Skin patterns are obtained by finding and tracing characteristic lines referring to the minutia correspondence information, the ridge line data and the valley line data, and the characteristic lines and the minutia correspondence information serve to provide pattern classification.

Abstract: A method and apparatus for collecting medical data from a test subject while preserving anonymity for the test subject. The method includes steps of collecting a sample from the test subject and taking biometric data from the test subject. The biometric data permit a high order of probability of correlation of the test subject with the sample and with test results derived from the sample. The method desirably further includes a step of providing the test subject with a unique correlating code also for permitting unique correlation of the test subject with the sample and with test results derived from the sample, and further desirably includes a step of labeling the sample with information including the biometric data.

Abstract: When a request to access a file or the like is made, a characteristic measuring unit measures the physical characteristic of a user of a computer system. A data degenerating unit processes the measured physical characteristic as degenerated characteristic data like a one-dimensional projection and outputs the degenerated characteristic data to the computer system. The computer system sends this characteristic data to an identification server via a communication network. The identification server performs an identification process in accordance with characteristic data preregistered in a file system. In accordance with the identification result, it is determined whether or not to approve the access authorization by the user and the permission or rejection of the access is sent back to the computer system via the communication network.

Abstract: A fingerprint image is divided into blocks of pixels. The blocks are determined to be within the foreground or background of the image. Poor quality images are examined to determine if the imaging process is corrupted, e.g. by a wet finger, by determining if a smudginess measure is above a smudginess threshold. For each foreground block, a mean intensity (.mu.) of pixels is computed for those pixels whose intensities are smaller than the mean intensity of all pixels within the respective foreground block. Further the standard deviation (.cuberoot.) of intensities of all pixels within the respective foreground block is computed. For a foreground block with good contrast, .mu. is small and .cuberoot. is large. But for a block with low contrast due to smudginess, .mu. is small and .cuberoot. is small. Subsequently, to measure the contrast (a contrast measure) within a block, a function of the product (C.sub.S) of corresponding .mu. and corresponding .cuberoot. is determined.

Abstract: A method and apparatus for collecting medical data from a test subject while optionally preserving anonymity for the test subject. The method includes steps of collecting a sample from the test subject and taking biometric data from the test subject. The biometric data permit a high order of probability of correlation of the test subject with the sample and with test results derived from the sample. The method optionally further includes a step of providing the test subject with a unique correlating code also for permitting unique correlation of the test subject with the sample and with test results derived from the sample, and further desirably includes a step of labeling the sample with information including the biometric data.

Abstract: A fingerprint image is processed from its original gray tone image to a binary (black and white) image. The "ridge" skeletal image is formed of the black portions of the binary image, being derived from the ridges of the fingerprint. A separate "valley" skeletal image is formed of the white portions of the binary image, being derived from the valleys interposed between the ridges. Ridge minutiae are detected from the ridge skeletal image and processed to eliminate apparently inappropriate minutiae. Separately, valley minutiae are detected from the valley skeletal image and processed to eliminate apparently inappropriate minutia. Then the ridge and valley minutiae are processed together. Only those ridge minutiae that can be correlated locally with individual valley minutiae survive to be passed to a fingerprint matcher.

Abstract: A technique for detecting and verifying a fingerprint includes a skin resistance sensing array for translating the skin resistance of a fingertip into an electrical signal. The fingertip is moved relative to the skin resistance sensing array in a first linear direction for producing a reference trajectory signal which is stored into a memory. The fingertip is again moved relative to the skin resistance sensing array in a second linear direction for producing a sample trajectory signal. The second linear direction of movement is offset from the first linear direction of movement by a predetermined angle. A processor is provided for performing a set of functions on the reference trajectory signal and the sample trajectory signal. The sample trajectory signal is correlated with the reference trajectory signal for producing a verification signal related to the probability that the fingertip generated both the sample trajectory signal and the reference trajectory signal.

Abstract: The present invention has the object of accurately detecting fingerprint fingertip orientation by a process of calculating inner products of ridge directions in the peripheral areas of an inputted fingerprint and radial line directions, finding an inner product sequence in which the inner products are sequenced upon making one revolution from a certain initial point, finding sequence errors between the inner product sequence and a plurality of inner product sequence patterns of differing fingertip orientations for a standard fingerprint, and establishing the fingertip orientation of the inputted fingerprint as the fingertip orientation of the standard fingerprint having the minimum sequence error.

Abstract: The present invention provides an image processing apparatus and method comprising a memory for storing address information of a binary registered image. An original test image is converted into a binary test image so that the ratio of the total number of black pixels to the total number of black and white pixels lies within a predetermined range. The binary test image is aligned to the binary registered image in order to compare the two images. A degree of concordance between the binary test image and the binary registered image is determined if the comparison satisfies a predetermined condition of concordance. A degree of discordance between the binary test image and the binary registered image is determined if the comparison satisfies a predetermined condition of discordance. The binary test image is determined to originate from the same object as the binary registered image according to the degree of concordance and the degree of discordance between the two images.

Abstract: A system for automatically classification of human fingerprints. An unidentified fingerprint is processed to produce a direction map. The direction map is processed to generate a course direction map. The coarse direction map is input to a locally connected, highly constrained feed-forward neural network. The neural network has a highly structured architecture well-suited to exploit the rotational symmetries and asymmetries of human fingerprints. The neural network classifies the unidentified fingerprint into one of five classifications: Whorl, Double Loop, Left Loop, Right Arch and Arch.

Abstract: In a method for comparing one fingerprint to another, there is recorded for each fingerprint the location and angle of minutiae along with a quality measure of each minutiae, and the core and delta location along with the local average image. An image state map defining high quality image areas with and without minutiae and areas of low image quality is also recorded. In matching fingerprints, ridge angle maps are used to align fingerprint images, then state maps are compared, followed by a comparison of minutiae locations.

Abstract: Feature points data and quality grade data of fingerprint images are stored in a data base with a respective register number of each fingerprint as an index for access. A verification method dictionary contains different verification methods for different quality grade data. A verifier unit refers to the verification method dictionary to select a verification method adapted for the quality grade data of the fingerprint to be compared.

Abstract: A method and apparatus for improving the optical boundary between a person's fingerprint ridges and the surface platen of a live-scan-imaging apparatus includes providing an absorbent pad containing chemicals selected from the nonvolatile oils, oil amides, fatty alcohols and fatty acid esters, placing the person's finger to be scanned on the surface of the absorbent pads to coat the fingerprint ridges and subsequently placing the person's finger with the coated fingerprint ridges on the platen of the imaging apparatus to provide a high contrast between the ridges and valleys of the fingerprint area.

Abstract: A thin, inexpensive, removable platen for a direct fingerprint reader without a permanently attached platen. A removable platen is formed as a transparent area on a credit card, passport or identification card or as a separate card. The portable platen on the card is inserted over an imaging area of the direct fingerprint reader. Light from the direct fingerprint reader passes through an optical surface formed on the underside of the portable platen, is reflected off the fingerprint and passes back through the optical surface to the imaging apparatus where the image is digitized and analyzed. The optical surface is formed such that the incident light is not refracted away from the fingerprint and the reflected light from the fingerprint is not refracted away from the imaging apparatus.

Abstract: A fraud-proof identification system is provided with a point-to-point in focus imaging system preferably a line tracking arrangement for imaging skin profiles particularly of the thumb-top which contains relatively many continuous lines and avoids mental association with criminal finger print actions. Characteristics from skin profiles, preferably mutual line distances progressively measured along a selected skin line are compared with such information stocked in the system in order to discriminate upon authorization. A line tracking system is preferably provided with a servo-mechanism, a control signal of which acting as measuring signal.

Abstract: From an image memory of a fingerprint picture, gradient vectors of the picture are calculated. And from distribution of gradient vectors in a subregion, ridge direction of the subregion are determined, and confidence of the determined direction is also defined.

Abstract: A method for locating minutia in a gray scale image of a fingerprint using a pair of filters, called "Gabor" and "Minutia" filters, includes determining direction and spacing of ridges at regularly spaced pixels, aligning filters by ridge direction, determining outputs of filters where Gabor Filter has high level output when in parallel ridge flow and, due to phase discontinuity at a minutia, low level output when in neighborhood of a minutia. The Minutia filter exhibits opposite phenomenon, having low level output in parallel ridge flow and high output in neighborhood of a minutia. A method for creating a state map of a fingerprint includes determining image quality, identifying minutia locations, determining areas of good quality where minutia are present, areas of good quality where no minutia are present and areas where quality is below a predetermined value to reliably determine presence or absence of minutia.

Abstract: A device for providing a plain image signal indicative of a plain image of surface characteristics of more than one finger on a hand includes an plain platen prism having a flat, rectangular shaped finger receiving surface having a platen aspect ratio greater than 1.33:1. An illumination source internally illuminates the finger receiving surface such that light internally illuminating a bare portion of the finger receiving surface is internally reflected from the finger receiving surface and light internally illuminating a contacted portion of the finger receiving surface in contact with the fingers is not internally reflected from the finger receiving surface. The internally reflected light forms a reflection image of the surface characteristics of the fingers. Optical elements direct the reflection image to a camera. The camera, which has a rectangular receiving surface with an aspect ratio of approximately 1.33:1, receives the reflection image and provides the plain image signal in response.

Abstract: A fingerprint matcher links together minutiae from a search print and minutiae from a file print in a chain to determine if the two prints match. Minutiae are extracted from the images of the search and file prints. Geometric and other relationships between close minutiae in each print are calculated. A table of candidate "steps" is formed. Each step consists of four minutiae, two close search minutiae and two close file minutiae. Each "rung" of the step is a search-file pair, the candidate mating of presumed identical minutiae in the two images. Each "riser" of the step is formed by two close minutiae, search minutiae on the one side and file minutiae on the other. A candidate step is entered into the table if and only if the relationships between search minutiae are similar to those between file minutiae. The number of candidate steps is reduced by requiring that each step adhere to various rules regarding the presence of other steps in the table and the identity of minutiae therein.

Abstract: A fingerprint recognition and retrieval system in which the positions of fingerprint minutiae points and an index number for each minutiae point are recorded in a storage medium. The local ridge flow direction in the vicinity of each minutiae point defined by ridge endings and ridge bifurcations is determined and a generating line is projected at an angle to the local ridge flow direction. The generating line has a length sufficient to span a predetermined number of ridges to each side of each of the minutiae points. Each ridge is traced, in two directions, from the point of crossing of the projected generating line along any crossed ridge line. The first occurring topological event is assigned a type code (T) to the topological event. A topological event code vector is generated for each minutiae comprising an ordered sequence of topological type codes encountered during the tracing and any associated minutiae reference numbers and sets of the vectors are stored in a machine searchable database.

Abstract: An optical device for forming an image of an uneven surface, including a plane-parallel plate with a pair of parallel plane surfaces which is made of a transparent material having a refractive index larger than that of water and transparent to illuminating light. An uneven object (object having an uneven surface) is placed in close contact with one plane surface of the plane-parallel plate. A light source illuminates the uneven object through the plane-parallel plate. Among light rays scattered back into the plane-parallel plate by the uneven object and totally reflected at the other plane surface of the plane-parallel plate, only light that is totally reflected at an angle larger than the critical angle at the boundary between the plane-parallel plate and water is taken in by an image-forming device.

Abstract: An image comparison arrangement uses an electronic computer to compare digitized fingerprint minutia maps of fingerprints of an unknown fingerprint set with corresponding maps of reference fingerprint sets which are stored in memory, in order to identify unknown fingerprints or to match fingerprints. The matching is performed by converting all the fingerprints to attributed relation graphs (ARGs) including nodes and branches, to which attributes are appended. For each fingerprint pair being compared, a distance matrix is generated, the elements of which are the similarities of stars. The highest-ranking star pair is selected as the starting point of a comparison tree, by which attempts are made to fill a match core with elements representing the matching stars. The comparison is of the various attributes of the nodes and branches of each star.

Abstract: A technique for fingerprint classification and/or identification, in which a fingerprint is defined by areas containing patterns of ridges and valleys. At least one local pattern is determined using locations and characterizations of the fingerprint, which are indicated by a rapid change in direction of the ridges and valleys. The fingerprint is classified into types based upon the relative locations and characterizations of said local pattern(s). The fingerprint identification process can utilize minutiae location and angles as well as local pattern characterizations. Neural networks are utilized in determining the local patterns. The amount of data required to store data defining the fingerprints using the local pattern and/or minutiae techniques is significantly reduced.

Abstract: The present invention provides a method of processing an unknown physical fingerprint for use in a data processing system to verify/identify an unknown fingerprint. The method involves obtaining an unknown fingerprint image that includes images of ridges, binarizing the images of ridges in the unknown fingerprint image, generating an image with fused ridges by expanding the images of ridges in the binarized image, shrinking the image with fused ridges to create a scaled-down image, and masking a first portion of the unknown fingerprint image with the scaled-down image so as to create a modified image of the unknown fingerprint.

Abstract: In a fingerprint image processing system for use in processing a fingerprint image prior to identification of a fingerprint, edition or correction is made by adding true minutiae and/or deleting false minutiae from the fingerprint image displayed on an output device to leave only real minutiae and to formulate a minutia list which registers a location of each minutia, a minutia direction, and minutia relations representative of adjacent minutia pairs. Edition of the minutiae may be carried out by handling the minutiae as an image while correction may be made by recognizing the minutiae as data. Ridge numbers between two adjacent ones of the minutiae are included in the minutia relations and may be manually or automatically extracted from the fingerprint image.

Abstract: In fingerprint pattern classification, radial scanning vectors are used. A space between two adjacent ridge lines including a core point is traced by radial scanning. Radial distribution of number of cross points from the core point is a clue to a fingerprint classification.

Abstract: A fingerprint ID system, which compares input fingerprint image data with registered data, with a digital signal processor exclusive for image processing use, indpendently of a central processing unit comprises: a device for scanning the input fingerprint image data for determining the thinning thereof and for extracting minutiae therefrom; a circuit for removing a pseudo minutia from the extracted minutiae; a circuit for registering the minutiae based on positions of branch points and their positional relationships; a circuit for scoring the mismatching degree between branch points in said fingerprint image data and the registered data on the basis of the norm and for judging the examinee to be the person of said registered data when the mean mismatching degree of the branch point of the minimum mimatching degee is under a predetermined value.

Abstract: An automated fingerprint classification and identification system used to determine or verify the identity of an unknown person by comparing one or more of the person's fingerprints (i.e., the unknown fingerprints) to known fingerprints stored in a database. The components of the present invention include: (1) an apparatus and method for automatically classifying and storing the fingerprints in the database according to a lesser known manual 10-fingerprint classification method (the Vucetich classification and subclassification method), and (2) an apparatus and method for limiting the search of the database to only those fingerprints that are of the same classification as the unknown fingerprint(s).

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: A method for minutia extraction from a digitized fingerprint array by twin tracker border line analysis includes scanning the array to detect ridge pixels, setting up a pair of tracker pixels or trackers on opposite borders of the ridge, moving the trackers along the borders of the ridge, periodically calculating the midpoint between the trackers to generate a centerline between the borders, calculating an average slope of the centerline, and periodically testing between the trackers for the presence of valley pixels. When such a valley pixel is detected, a sequence of aberration tests is conducted to identify the type of aberration. If the aberration tests all fail, the aberration is identified as a ridge diversion, the location and slope of which are stored as a minutia in a minutia location table. Ridge endings are detected by comparing the coordinates of the trackers after each move. If a ridge ending is detected, an attempt is made to jump to another ridge within a given proximity to the current ridge.