Operator interactive pattern processing system
First Claim
1. An interactive method for performing a succession of processing functions in relation to an unknown pattern to extract minutiae data therefrom uniquely identifying the pattern for subsequent comparison with minutiae data corresponding extracted from at least one known such pattern to determine a match therebetween, said processing functions being performed selectively in an automatic, continuous succession, and in an interrupted succession with operator interaction requested by the method, as a function of method determination of satisfactory performance of each said processing function, comprising the steps of:
- storing said minutiae data of said at least one known such pattern,comparing the extracted and the stored minutiae data to determine a degree of match therebetween,establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing step to request operator interaction when said required degree of match is not satisfied, and to identify the given pattern as the known pattern for which the required degree of match is satisfied,selectively displaying the given pattern in response to an operator interaction request and for selectively displaying the automatically extracted minutiae data in superposed relationship thereon, andproviding manually operable means for selectively correcting and supplementing the automatically extracted minutiae data to enable said comparing step to automatically compare the selectively corrected and supplemented minutiae data extracted from said given pattern with said stored minutiae data.
4 Assignments
Litigations
0 Petitions
Accused Products
Abstract
An operator interactive pattern processing system is described which combines high speed recognition and processing abilities of an automatic portion with the estimating and recognition abilities of a human operator to extract correct data from patterns, such as poor quality unidentified latent fingerprint patterns and achieve rapid identification thereof. The automatic portion reads the unidentified pattern and extracts specific information therefrom such as ridge contour data describing the epidermal ridge flow and minutial data principally describing ridge endings and bifurcations. Topological data, identifying singularity points such as tri-radii and cores as well as ridge flow line tracings related to those points are automatically extracted from the ridge contour data. The extracted information is then utilized by the automatic portion to perform classification of the unknown fingerprint previously identified fingerprint patterns having the same classification type as they are selectively retrieved from a main file. The automatic portion contains circuitry for making value judgments as to its own functions at intermediate stages of its operation. The value judgment circuitry allows the automatic portion to communicate with an operator through an interactive controller whenever: it doubts the accuracy of its automatically identified singularity points; is unable to classify the unknown fingerprint pattern; obtains no matches to the unknown fingerprint; or obtains too many matches to the unknown fingerprint. At the request of the automatic portion, the operator then analyzes the specific data for which the automatic system determines it is having difficulty and either verifies or corrects the data stored in the automatic portion through the use of the interactive controller. The automatic portion then continues in its processing of the extracted data until identification of the unknown fingerprint is achieved.
80 Citations
37 Claims
-
1. An interactive method for performing a succession of processing functions in relation to an unknown pattern to extract minutiae data therefrom uniquely identifying the pattern for subsequent comparison with minutiae data corresponding extracted from at least one known such pattern to determine a match therebetween, said processing functions being performed selectively in an automatic, continuous succession, and in an interrupted succession with operator interaction requested by the method, as a function of method determination of satisfactory performance of each said processing function, comprising the steps of:
-
storing said minutiae data of said at least one known such pattern, comparing the extracted and the stored minutiae data to determine a degree of match therebetween, establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing step to request operator interaction when said required degree of match is not satisfied, and to identify the given pattern as the known pattern for which the required degree of match is satisfied, selectively displaying the given pattern in response to an operator interaction request and for selectively displaying the automatically extracted minutiae data in superposed relationship thereon, and providing manually operable means for selectively correcting and supplementing the automatically extracted minutiae data to enable said comparing step to automatically compare the selectively corrected and supplemented minutiae data extracted from said given pattern with said stored minutiae data. - View Dependent Claims (2)
-
-
3. An interactive method for performing a succession of processing functions in relation to an unknown pattern to extract data characterizing said pattern for subsequent comparison with data characterizing at least one of plural pattern types to determine a match therebetween, said processing functions being performed selectively in an automatic, continuous succession, and in an interrupted succession with operator interaction requested by the method, in accordance with method determination of satisfactory performance of successive said processing functions, comprising the steps of:
-
storing data defining preestablished classification types of said patterns, automatically extracting classification defining data from a given pattern, comparing the extracted and the stored classification defining data to determine a degree of match therebetween, establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing steps to identify a preestablished classification type for which the degree of match is satisfied as the classification type of the said given pattern, and to request operator interaction when the said required degree of match is not satisfied, selectively displaying the given pattern in accordance with an operator interaction request, and providing means manually operable by an operator in response to an operator interaction request for extracting classification defining data from the displayed, said given pattern, and enabling said comparing step to perform the function of automatic classification of the pattern by comparing the manually extracted classification defining data for the said given pattern with the stored classification defining data to identify the classification type of the said given pattern. - View Dependent Claims (4)
-
-
5. An interactive method for performing a succession of processing functions in relation to an unknown pattern to extract data characterizing said pattern for subsequent comparison with data characterizing at least one of plural pattern types to determine a match therebetween, said processing functions being performed selectively in an automatic, continous succession, and in an interrupted succession with operator interaction requested by the method, in accordance with method determination of satisfactory performance of successive said processing functions, comprising the steps of:
-
storing data defining preestablished classification types of said patterns, automatically extracting classification defining data from a given pattern, comparing the extracted and the stored classification defining data to determine a degree of match therebetween, establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing steps to identify a preestablished classification type for which the degree of match is satisfied as the classification type of the said given pattern, and to request operator interaction when the the said required degree of match is not satisfied, selectively displaying the given pattern in accordance with an operator interaction request, and providing means manually operable by an operator in response to an operator interaction request for extracting classification defining data from the displayed, said given pattern, and enabling said comparing step to perform the function of automatic classification of the pattern by comparing the manually extracted classification defining data for the said given pattern with the stored classification defining data to identify the classification type of the said given pattern, said selective method selectively displaying the manually extracted classification defining data and, simultaneously and in superposed relationship, the stored classification defining data for a given classification type, and said manually operable means selectively displaying said stored classification defining data corresponding to plural different preestablished classification types to enable manual comparison of the manually extracted classification defining data with the stored data defining the plural preestablished classification types.
-
-
6. An interactive method for performing a succession of processing functions in relation to an unknown pattern to extract data characterizing said pattern for subsequent comparison with data characterizing at least one of plural pattern types to determine a match therebetween, said processing functions being performed selectively in an automatic, continuous succession, and in an interrupted succession with operator interaction requested by the method, in accordance with method determination of satisfactory performance of successive said processing functions, comprising the steps of:
-
storing data defining preestablished classification types of said patterns, automatically extracting classification defining data from a given pattern, comparing the extracted and the stored classification defining data to determine a degree of match therebetween, establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said compring steps to identify a preestabished classification type for which the degree of match is satisfied as the classification type of the said given pattern, and to request operator interaction when the said required degree of match is not satisfied, selectively displaying the given pattern in accordance with an operator interaction request, and providing means manually operable by an operator in response to an operator interaction request for extracting classification defining data from the displayed, said given pattern, and enabling said comparing step to perform the function of automatic classification of the pattern by comparing the manually extracted classification defining data for the said given pattern with the stored classification defining data to identify the classification type of the said given pattern, said classification defining data including triradii points, core points, and contour line and wherein said preestablished classification types include predetermined numbers and combinations of respective ones of said triradii points and core points and wherein there is further provided the step of responding selectively to the number and combinations of respective ones of said triradii and core points extracted from a given pattern which do not correspond to those of preestablished classification types of patterns to determine an unsatisfactory performance of the classification function and thereby to request operator interaction - View Dependent Claims (7)
-
-
8. An interactive method for identifying an unknown pattern by comparison with stored patterns, each such pattern being characterized uniquely by a minutiae pattern and a configuration of contour lines, wherein an automatic portion of said method comprises the steps of:
-
scanning an unknown pattern; automatically extracting minutiae data describing said minutiae pattern from said scanned pattern; storing said extracted minutiae data; storing the minutiae data of each of a plurality of previously identified patterns in addressable locations; selectively addressing and retrieving said stored minutiae date; automatically comparing said extracted minutiae data with retrieved minutiae data corresponding to selected ones of said plurality of patterns in succession and producing a match signal when said compared data matches within predetermined limits; indicating the identity of said corresponding pattern for each match signal; generating a first output signal when no match signals are produced; and generating a second output signal when more than a predetermined number of match signals are produced; said interactive system further comprises the steps of; providing interactive communication between said automatic portion of said method and a human operator, wherein said step of interactive communication includes the step of requesting operator verification of said automatically extracted minutiae data when said first or second output signals are generated; selectively displaying said automatically extracted minutiae data, said unknown pattern, said retrieved minutiae data corresponding to said selected ones of said plurality of patterns for which a match signal is produced; and entering correct minutiae data and deleting incorrect extracted minutiae data in storage; and instructing said automatic portion of said method to automatically compare said corrected extracted minutiae data with said retrieved minutiae data corresponding to said selected ones of said plurality of patterns. - View Dependent Claims (9, 11)
-
-
10. said step of comparing includes the steps of automatically converting said extracted minutiae data and said retrieved minutiae data into an RIV format, wherein each minutia is represented in terms of its surrounding minutiae in a surrounding neighborhood of a predetermined size;
- and
said steps of comparing includes the steps of matching each minutia of said unknown pattern represented in an RIV format with each minutia of a selected previously identified pattern represented in an RIV format and producing a pluraliy of neighborhood comparison signals indicating the relative closeness of match and relative coordinate displacement between minutia neighborhoods of the compared patterns, and developing output signals indicative of the relative closeness of match and the relative coordinate displacement of the compared patterns. - View Dependent Claims (12, 15)
- and
-
13. said method further includes the step of window scanning said binary bit stream for producing a window scan address;
-
said step of automatically extracting minutiae data includes the steps of providing preprogrammed means responsive to said window scan address for detecting the occurrence of minutiae in said represented pattern, and providing means responsive to said preprogrammed means for determining the location of said detected minutiae with respect to said defined coordinate system; and said step of storing said extracted minutiae data stores the location coordinate values for each of the extracted minutiae.
-
-
14. An interactive system for performing a succession of processing functions in relation to an unknown pattern to extract minutiae data therefrom uniquely identifying the pattern for subsequent comparison with minutiae data corresponding extracted from at least one known such pattern to determine a match therebetween, said processing functions being performed selectively in an automatic, continuous succession, and in an interrupted succession with operator interaction requested by the system, as a function of system determination of satisfactory performance of each said processing function, comprising:
-
means for storing said minutiae data of said at least one known such pattern, means for comparing the extracted and the stored minutiae data to determine a degree of match therebetween, means establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing means to request operator interaction when said required degree of match is not satisfied, and to identify the given pattern as the known pattern for which the required degree of match is satisfied, means for selectively displaying the given pattern in response to an operator interaction request and for selectively displaying the automatically extracted minutiae data in superposed relationship thereon, and manually operable means for selectively correcting and supplementing the automatically extracted minutiae data to enable said comparing means to automatically compare the selectively corrected and supplemented minutiae data extracted from said given pattern with said stored minutiae data. - View Dependent Claims (17)
-
-
16. An interactive system for performing a succession of processing functions in relation to an unknown pattern to extract data characterizing said pattern for subsequent comparison with data characterizing at least one of plural pattern types to determine a match therebetween, said processing functions being performed selectively in an automatic, continuous succession, and in an interrupted succession with operator interaction requested by the system, in accordance with system determination of satisfactory performance of successive said processing functions, comprising:
-
means for storing data defining preestablished classification types of said patterns, means for automatically extracting classification defining data from a given pattern, means for comparing the extracted and the stored classification defining data to determine a degree of match therebetween, means establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing means to identify a preestabilished classification type for which the degree of match is satisfied as the classification type of the said given pattern, and to request operator interaction when the said required degree of match is not satisfied, means for selectively displaying the given pattern in accordance with an operator interaction request, and means manually operable by an operator in response to an operator interaction request for extracting classification defining data from the displayed, said given pattern, said enabling said comparing means to perform the function of automatic classification of the pattern by comparing the manually extracted classification defining data for the said given pattern with the stored classification defining data to identify the classification type of the said given pattern.
-
-
18. An interactive system for performing a succession of processing functions in relation to an unknown pattern to determine the classification type thereof as one of plural, known classification types, and to identify the unknown pattern as a known, stored pattern of the same, determined classification type, said processing functions being performed selectively in an automatic, continuous succession and in an interrupted succession with operator interaction requested by the system, in accordance with system determination of satisfactory performance or unsatisfactory performance, respectively, of each said processing function, comprising:
-
means for storing data defining preestablished classification types of said patterns, means for automatically extracting classification defining data from a given pattern, means for comparing the extracted and the stored classification defining data to determine a degree of match therebetween, means establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing means to identify a preestablished classification type for which the degree of match is satisfied as the classification type of the said given pattern, and to request operator interaction when the said required degree of match is not satisfied, means for selectively displaying the given pattern in accordance with an operator interaction request, means manually operable by an operator in response to an operator interaction request for extracting classification defining data from the displayed, said given pattern, and enabling said comparing means to perform the function of automatic classification of the pattern by comparing the manually extracted classification defining data for the said given pattern with the stored classification defining data to identify the classification type of the said given pattern, means for storing minutiae data of known said patterns of different classification types, means responsive to the identified classification type of the unknown pattern for selecting the stored minutiae data of known said patterns of the said identified classification type from said storing means, means for comparing the extracted minutiae data and the stored minutiae data for each said pattern of the said selected, identified classification type to determine the corresponding degrees of match therebetween, means establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing means to request operator interaction when said required degree of match is not satisfied, and to identify the given pattern as the known pattern for which the required degree of match is satisfied, means for selectively displaying the given pattern in response to an operator interaction request and for selectively displaying the automatically extracted minutiae data in superposed relationship thereon, and manually operable means for selectively correcting and supplementing the automatically extracted minutiae data to enable said comparing means to automatically compare the selectively corrected and supplemented minutiae data extracted from said given pattern with said stored minutiae data. - View Dependent Claims (21, 24)
-
-
19. An interactive system for performing a succession of processing functions in relation to an unknown pattern to extract data characterizing said pattern for subsequent comparison with data characterizing at least one of plural pattern types to determine a match therebetween, said processing functions being performed selectively in an automatic continuous succession, and in an interrupted succession with operator interaction requested by the system, in accordance with system determination of satisfactory performance of successive said processing functions, comprising:
-
means for storing data defining preestablished classification types of said patterns, means for automatically extracting classification defining data from a given pattern, means for comparing the extracted and the stored classification defining data to determine a degree of match therebetween, means establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing means to identify a preestablished classification type for which the degree of match is satisfied as the classification type of the said given pattern, and to request operator interaction when the said required degree of match is not satisfied, means for selectively displaying the given pattern in accordance with an operator interaction request, and means manually operable by an operator in response to an operator interaction request for extracting classification defining data from the displayed, said given pattern, and enabling said comparing means to perform the function of automatic classification of the pattern by comparing the manually extracted classification defining data for the said given pattern with the stored classification defining data to identify the classification type of the said given pattern, said selective displaying means selectively displaying the manually extracted classification defining data and, simultaneously and in superposed relationship, the stored classification defining data for a given classification type, and said manually operable means including means for selectively displaying said stored classification defining data corresponding to plural different preestablished classification types to enable manual comparison of the manually extracted classification defining data with the stored data defining the plural preestablished classification types.
-
-
20. An interactive system for performing a succession of processing functions in relation to an unknown pattern to extract data characterizing said pattern for subsequent comparison with data characterizing at least one of plural pattern types to determine a match therebetween, said processing functions being performed selectively in an automatic, continuous succession, and in an interrupted succession with operator interaction requested by the system, in accordance with system determination of satisfactory performance of successive said processing functions, comprising:
-
means for storing data defining preestablished classification types of said patterns, means for automatically extracting classification defining data from a given pattern, means for comparing the extracted and the stored classification defining data to determine a degree of match therebetween, means establishing a required degree of match to determine satisfactory performance of said matching function and responsive to the degree of match determined by said comparing means to identify a preestablished classification type for which the degree of match is satisfied as the classification type of the said given pattern, and to request operator interaction when the said required degree of match is not satisfied, means for selectively displaying the given pattern in accordance with an operator interaction request, and means manually operable by an operator in response to an operator interaction request for extracting classification defining data from the displayed, said given pattern, and enabling said comparing means to perform the function of automatic classification of the pattern by comparing the manually extracted classification defining data for the said given pattern with the stored classification defining data to identify the classification type of the said given pattern, said classification defining data including triradii points, core points, and contour lines and wherein said preestablished classification types include predetermined numbers and combinations of respective ones of said triradii points and core points, and wherein there is further provided means responsive selectively to the number and combinations of respective ones of said triradii and core points extracted from a given pattern which do not correspond to those of preestablished classification types of patterns to determine an unsatisfactory performance of the classification function and thereby to request operator interaction. - View Dependent Claims (23, 26, 27, 29, 32, 35)
-
-
22. An operator interactive system for identifying an unknown pattern by comparison with stored patterns, each such pattern being characterized uniquely by a minutiae pattern and a configuration of contour lines, wherein an automatic portion of said system comprises:
-
means for scanning an unknown pattern; means for automatically extracting minutiae data describing said minutiae pattern from said scanned pattern; first means for storing said extracted minutiae data; second means for storing the minutiae data of each of a plurality of previously identified patterns in addressable locations; means for selectively addressing and retrieving said minutiae data stored in said second storing means; means for automatically comparing said extracted minutiae data stored in said first storing means with retrieved minutiae data corresponding to selected ones of said plurality of patterns in succession and producing a match signal when said compared data matches within predetermined limits; means responsive to said comparing means for indicating the identity of said corresponding pattern for each match signal; and means responsive to said comparing means and said addressing means for generating a first output signal when no match signals are produced and generating a second output signal when more than a predetermined number of match signals are produced; said system also includes means selectively connected to said scanning means, said first storing means, said second storing means and to said first and second output signal generating means, and interfacing said automatic portion and a human operator for providing interactive communication between said automatic portion and said operator; said interactive means being responsive to said first and second output signals for requesting operator verification of said automatically extracted minutiae data; said interactive means including means for displaying images and means manually operable by said operator to command said system to selectively display said automatically extracted minutiae data on said display means, to display said unknown pattern, to display said retrieved minutiae data corresponding to said selected ones of said plurality of patterns for which a match signal is produced by said comparing means, to enter correct minutiae data and delete incorrect minutiae data in said first storing means as determined by said operator, and to instruct said automatic comparison means to compare said corrected extracted minutiae data with said retrieved minutiae data corresponding to said selected ones of said plurality of patterns. - View Dependent Claims (25, 28, 30, 31, 33, 34, 36, 37)
-
Specification