CA2262300A1 - Method and apparatus for the automated identification of fingerprints - Google Patents
Method and apparatus for the automated identification of fingerprints Download PDFInfo
- Publication number
- CA2262300A1 CA2262300A1 CA002262300A CA2262300A CA2262300A1 CA 2262300 A1 CA2262300 A1 CA 2262300A1 CA 002262300 A CA002262300 A CA 002262300A CA 2262300 A CA2262300 A CA 2262300A CA 2262300 A1 CA2262300 A1 CA 2262300A1
- Authority
- CA
- Canada
- Prior art keywords
- fingerprint
- values
- pixel map
- epidermal ridges
- characterizing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
Abstract
A method for the automated identification of a fingerprint consists in, first creating a pixel map of the fingerprint. The pixel map is then thinned to ease the finding of the coordinates of the points forming the epidermal ridges of the fingerprint. These epidermal ridges are then tracked and characterized mathematically. The mathematical characterization produces a set of values that can be compared to other sets of values characterizing pre-identified fingerprints and stored in a database. The apparatus adapted to carry out the method includes an input device to create a pixel map of a fingertip, a controller to execute all the computations on the pixel map and a storage device to store the resulting values characterizing the epidermal ridges on the fingertip.
Description
TITLE OF THE INVENTION
METHOD AND APPARATUS FOR THE AUTOMATED
IDENTIFICATION OF FINGERPRINTS.
FIELD OF THE INVENTION
The present invention relates to a method and an apparatus for automatically identifying fingerprints through a mathematical characterization of their ridge patterns.
BACKGROUND OF THE INVENTION
The intricate pattern of skin ridges in fingerprints has long been considered the most reliable physical feature by which an individual is identified. Fingerprints are accepted as evidence in courts of law, and police authorities maintain extensive files of fingerprints for known reasons. Many governments discuss, at present, if and how fingerprinting could help to identify and authenticate the legitimate users of their social services. The control of immigration and the influx of aliens as temporary workers is also of the greatest concern, and the use of fingerprint technology is presently the more reliable answer to this problem. Business also sees a need to use fingerprints in order to grant or deny access to confidential data banks through communication networks, and to authenticate the source of decisions transmitted through such links. No other physical feature characterizes an individual as reliably as fingerprints.
METHOD AND APPARATUS FOR THE AUTOMATED
IDENTIFICATION OF FINGERPRINTS.
FIELD OF THE INVENTION
The present invention relates to a method and an apparatus for automatically identifying fingerprints through a mathematical characterization of their ridge patterns.
BACKGROUND OF THE INVENTION
The intricate pattern of skin ridges in fingerprints has long been considered the most reliable physical feature by which an individual is identified. Fingerprints are accepted as evidence in courts of law, and police authorities maintain extensive files of fingerprints for known reasons. Many governments discuss, at present, if and how fingerprinting could help to identify and authenticate the legitimate users of their social services. The control of immigration and the influx of aliens as temporary workers is also of the greatest concern, and the use of fingerprint technology is presently the more reliable answer to this problem. Business also sees a need to use fingerprints in order to grant or deny access to confidential data banks through communication networks, and to authenticate the source of decisions transmitted through such links. No other physical feature characterizes an individual as reliably as fingerprints.
The use of fingerprints in any of the above applications is hampered by the fact that the characteristic pattern of skin ridges is not easily analysed by computer. Present police computers dedicated to this task are among the biggest and most expensive of such machines in the public service; their capital cost is typically in excess of 4 mil. US$, to which amount must be added the considerable expense of highly specialized personnel. Even these machines with all their associated manpower perform at a relatively slow rate, mainly because they are based on a method of analysis that has not kept pace with the latest advance in technology.
Current method of characterization and identification of fingerprints are usually based on identification of the pattern of so-called "minutiae" in the skin ridges. Minutiae are ridge endings, bi- and trifurcations, "eyelets" or islands, and other details. The minutiae found are typically mapped by triangulation to give a characteristic pattern to which is added, in some methods, a count of the number of ridges on the lines joining them. False minutiae (e.g. due to over-inking when the print is taken) will interfere with this analysis and can easily render it meaningless since the presence of just a few of them, or the absence of some important ones, seriously falsifies the entire network of triangles thus established. Therefore, all analyses under these methods must be supervised and eventually corrected by the work of trained and experienced specialists who must make the decision, among others, which of the apparent minutiae in a print are true and which are artefactuaf.
False minutiae can be produced in many ways: bridges between adjacent epidermal ridges are seen, for instance, if a print is over-inked or when the fingertip is dirty, or simply if an excess of pressure is applied at the time the print is taken, etc. True minutiae are lost through oversight, or by under-inking, or if the fingertip is wet. The loss of a few minutiae can be critical in the analysis of certain types of fingerprint patterns such as the simple arch and the tented arch which do not contain many minutiae to begin with.
OBJECTS OF THE INVENTION
An object of the present invention is therefore to provide an improved method and apparatus to identify a fingerprint.
It is another object of the present invention to provide a method and an apparatus to identify a fingerprint through a mathematical characterization of its ridge patterns.
SUMMARY OF THE INVENTION
More specifically, in accordance with the present invention, there is provided a method for identifying a fingerprint defined by its epidermal ridges. The method comprises the steps of:
creating a pixel map of the fingerprint;
thinning the pixel map;
tracking the epidermal ridges on the thinned pixel map;
using a mathematical model to characterize the tracked epidermal ridges on the thinned pixel map, the characterization of the epidermal ridges producing a first set of values; and comparing the first set of values to other sets of values present in a database and characterizing pre-identified fingerprints.
According to another aspect of the present invention, there is provided an apparatus for the automated identification of a fingerprint identified by its epidermal ridges. The apparatus comprises a first input device to create a pixel map of the fingerprint;
a controller for thinning the pixel map, for tracking the epidermal ridges on the thinned pixel map, and for using a mathematical model to characterize the tracked epidermal ridges on the thinned pixel map thereby producing a first set of values; and a second input device to provide the controller with other sets of values characterizing pre-identified fingerprints;
the controller comparing the first set of values to other sets of values.
BRIEF DESCRIPTION OF THE DRAWINGS
Figure 1 is a block diagram of an apparatus for the automated identification of a fingerprint according to an embodiment of the present invention;
Figure 2 is a simplified block diagram of a method to identify a fingerprint according to an embodiment of the present invention;
Figure 3 is a pixel map of a fingerprint;
Figure 4 is a pixel map of the fingerprint of Figure 3 after thinning; Figure 4 also illustrates a diagonal used in the tracking step;
Figure 5 is a pixel map of the fingerprint of Figure 4, after tracking of the epidermal ridges; and Figure 6 shows two pixel maps of the same fingerprint) 5 one through a rotation of 90~ of the other, illustrating the utility of a hashing table.
DESCRIPTION OF PREFERRED EMBODIMENTS
Turning now to Figure 1 of the appended drawings, an apparatus 10 for the automated identification of a fingerprint) according a preferred embodiment of the present invention, includes a controller 12, in the form of a microcomputer, an input device 14 and a storage device 16.
The controller 12 performs automatically all the calculations necessary, first to model a fingerprint and, second to compare this fingerprint to fingerprints pre-identified using the same mathematical model, as will be described hereinbelow.
The input device 14 can be any device that can take a picture of a fingerprint and convert it in the form of a pixel map 20; a CCD
camera is a good example of such device. There are also known fingertip scanners which work under the same principle as that of a photocopier and which are used to obtain a pixel map 20 of an individual's fingerprints. The input device 14 must be so configured as to preserve the actual size of the ridges 22 forming the fingerprint and not distort them.
Current method of characterization and identification of fingerprints are usually based on identification of the pattern of so-called "minutiae" in the skin ridges. Minutiae are ridge endings, bi- and trifurcations, "eyelets" or islands, and other details. The minutiae found are typically mapped by triangulation to give a characteristic pattern to which is added, in some methods, a count of the number of ridges on the lines joining them. False minutiae (e.g. due to over-inking when the print is taken) will interfere with this analysis and can easily render it meaningless since the presence of just a few of them, or the absence of some important ones, seriously falsifies the entire network of triangles thus established. Therefore, all analyses under these methods must be supervised and eventually corrected by the work of trained and experienced specialists who must make the decision, among others, which of the apparent minutiae in a print are true and which are artefactuaf.
False minutiae can be produced in many ways: bridges between adjacent epidermal ridges are seen, for instance, if a print is over-inked or when the fingertip is dirty, or simply if an excess of pressure is applied at the time the print is taken, etc. True minutiae are lost through oversight, or by under-inking, or if the fingertip is wet. The loss of a few minutiae can be critical in the analysis of certain types of fingerprint patterns such as the simple arch and the tented arch which do not contain many minutiae to begin with.
OBJECTS OF THE INVENTION
An object of the present invention is therefore to provide an improved method and apparatus to identify a fingerprint.
It is another object of the present invention to provide a method and an apparatus to identify a fingerprint through a mathematical characterization of its ridge patterns.
SUMMARY OF THE INVENTION
More specifically, in accordance with the present invention, there is provided a method for identifying a fingerprint defined by its epidermal ridges. The method comprises the steps of:
creating a pixel map of the fingerprint;
thinning the pixel map;
tracking the epidermal ridges on the thinned pixel map;
using a mathematical model to characterize the tracked epidermal ridges on the thinned pixel map, the characterization of the epidermal ridges producing a first set of values; and comparing the first set of values to other sets of values present in a database and characterizing pre-identified fingerprints.
According to another aspect of the present invention, there is provided an apparatus for the automated identification of a fingerprint identified by its epidermal ridges. The apparatus comprises a first input device to create a pixel map of the fingerprint;
a controller for thinning the pixel map, for tracking the epidermal ridges on the thinned pixel map, and for using a mathematical model to characterize the tracked epidermal ridges on the thinned pixel map thereby producing a first set of values; and a second input device to provide the controller with other sets of values characterizing pre-identified fingerprints;
the controller comparing the first set of values to other sets of values.
BRIEF DESCRIPTION OF THE DRAWINGS
Figure 1 is a block diagram of an apparatus for the automated identification of a fingerprint according to an embodiment of the present invention;
Figure 2 is a simplified block diagram of a method to identify a fingerprint according to an embodiment of the present invention;
Figure 3 is a pixel map of a fingerprint;
Figure 4 is a pixel map of the fingerprint of Figure 3 after thinning; Figure 4 also illustrates a diagonal used in the tracking step;
Figure 5 is a pixel map of the fingerprint of Figure 4, after tracking of the epidermal ridges; and Figure 6 shows two pixel maps of the same fingerprint) 5 one through a rotation of 90~ of the other, illustrating the utility of a hashing table.
DESCRIPTION OF PREFERRED EMBODIMENTS
Turning now to Figure 1 of the appended drawings, an apparatus 10 for the automated identification of a fingerprint) according a preferred embodiment of the present invention, includes a controller 12, in the form of a microcomputer, an input device 14 and a storage device 16.
The controller 12 performs automatically all the calculations necessary, first to model a fingerprint and, second to compare this fingerprint to fingerprints pre-identified using the same mathematical model, as will be described hereinbelow.
The input device 14 can be any device that can take a picture of a fingerprint and convert it in the form of a pixel map 20; a CCD
camera is a good example of such device. There are also known fingertip scanners which work under the same principle as that of a photocopier and which are used to obtain a pixel map 20 of an individual's fingerprints. The input device 14 must be so configured as to preserve the actual size of the ridges 22 forming the fingerprint and not distort them.
The input device 14 can either be connected to the controller 12 through conventional cables 24 to transfer directly the pixel map 20 to the controller 12 or the pixel map 20 can be stored on a computer disk or other conventional binary data storing means (not shown). In such case, the controller 12 must be equipped with a reading device (not shown) to read the pixel map 20 on the storing means.
The storage device 16 is used to store the values characterizing the mathematical model of the fingerprint obtained with a method according to a preferred embodiment of the present invention, and that will be described hereinbelow.
The storage device 16 can be any conventional device to store binary data such as a RAM (Random Access Memory), disk drives, cd-rom drives, etc. The output device 16 can also either be directly connected to the controller via conventional cables 26 or remotely via a computer network, such as for example, the Internet.
Turning now to Figure 2 of the appended drawings, the method for the automated identification of a fingerprint , according to one aspect of the present invention, will be described.
Generally stated) the method of the present invention consists in performing the following steps in sequence:
100 - starting the apparatus 10;
102 - digitization of the fingerprint using the input device 14 to produce a pixel map 20;
The storage device 16 is used to store the values characterizing the mathematical model of the fingerprint obtained with a method according to a preferred embodiment of the present invention, and that will be described hereinbelow.
The storage device 16 can be any conventional device to store binary data such as a RAM (Random Access Memory), disk drives, cd-rom drives, etc. The output device 16 can also either be directly connected to the controller via conventional cables 26 or remotely via a computer network, such as for example, the Internet.
Turning now to Figure 2 of the appended drawings, the method for the automated identification of a fingerprint , according to one aspect of the present invention, will be described.
Generally stated) the method of the present invention consists in performing the following steps in sequence:
100 - starting the apparatus 10;
102 - digitization of the fingerprint using the input device 14 to produce a pixel map 20;
104 - optionally, cleanup of the pixel map 20;
106 - thinning of the epidermal ridges 22 on the pixel map 20 to produce a thinned pixel map 28;
108 - tracking of the epidermal ridges 30 of the thinned pixel map 28;
110 - mathematical modelling of the epidermal ridges;
112 - geometric hashing of the mathematical model;
114 - comparison with existing models of pre-identified fingerprints; and 116 - stopping the apparatus 10.
These general steps will now be further described.
The digitization of the fingerprint (step 102) consists in using the input device 14 of the apparatus 10 to produce a pixel map 20 forming an image of the fingerprint (see Figure 3). The pixel map 20 is stored in the memory of the controller 12 or in the input device for later processing. The pixel map 20 can be stored under any well known computer images format such as, for example, .BMP, .JPG, etc.
A cleanup of the pixel map 20 is then performed at step 104. This step is optional and serves to establish optimal conditions and, to increase the speed and reliability of the method. Step 104 can include, for example, the substeps of contrast enhancement, contrast expansion and levelling of image brightness. Those substeps will not be described further since they are believed well known to one versed in the art.
The controller 12 then executes step 106 that consists in the thinning of the epidermal ridges 22 in the original pixel map 20 as obtained by the input device 14 or optionally, after the cleanup step 104.
106 - thinning of the epidermal ridges 22 on the pixel map 20 to produce a thinned pixel map 28;
108 - tracking of the epidermal ridges 30 of the thinned pixel map 28;
110 - mathematical modelling of the epidermal ridges;
112 - geometric hashing of the mathematical model;
114 - comparison with existing models of pre-identified fingerprints; and 116 - stopping the apparatus 10.
These general steps will now be further described.
The digitization of the fingerprint (step 102) consists in using the input device 14 of the apparatus 10 to produce a pixel map 20 forming an image of the fingerprint (see Figure 3). The pixel map 20 is stored in the memory of the controller 12 or in the input device for later processing. The pixel map 20 can be stored under any well known computer images format such as, for example, .BMP, .JPG, etc.
A cleanup of the pixel map 20 is then performed at step 104. This step is optional and serves to establish optimal conditions and, to increase the speed and reliability of the method. Step 104 can include, for example, the substeps of contrast enhancement, contrast expansion and levelling of image brightness. Those substeps will not be described further since they are believed well known to one versed in the art.
The controller 12 then executes step 106 that consists in the thinning of the epidermal ridges 22 in the original pixel map 20 as obtained by the input device 14 or optionally, after the cleanup step 104.
In step 106, each line representing an epidermal ridge 22 in the pixel map 20 (see Figure 3) is first localized. Then, only the center of each line is retained to form lines of only one pixel wide. The resulting images is a thinned pixel map 28 (see the example of Figure 4) with thinned epidermal ridges 30. The purpose of step 106 is to established the exact coordinates of the ridges 22 and the ridge intercepts 32.
It is to be noted that, since the purpose of step 106 is to establish the coordinates of the ridges 22, a person skilled in the art can conceive a method, according to the present invention, wherein the thinning step 106 is replaced by another step that provides with the same desired coordinates.
The thinned epidermal ridges 30 are then tracked (step 108) according to the following algorithm. The thinned epidermal ridges 30 are followed, starting from the diagonal 34 of the thinned pixel map 28, and going in a first direction until they end at any of the four map borders 36 of the thinned pixel map, or at one of the ridge intercepts 32. At such intercept 32, the tracking continues along the ridge that follows the smaller angle with the segment of ridge preceding (it is to be noted that the line 34 is only a representation of the diagonal of the thinned pixel map 28, and is not part of the thinned pixel map). This process is then repeated, starting from the diagonal 34 and going in a second direction opposite the first direction. As can be better seen from Figure 5, this tracking algorithm retains all the ridges intersecting the diagonals, such as, for example, ridges 30, all others are discarded.
It is to be noted that, since the purpose of step 106 is to establish the coordinates of the ridges 22, a person skilled in the art can conceive a method, according to the present invention, wherein the thinning step 106 is replaced by another step that provides with the same desired coordinates.
The thinned epidermal ridges 30 are then tracked (step 108) according to the following algorithm. The thinned epidermal ridges 30 are followed, starting from the diagonal 34 of the thinned pixel map 28, and going in a first direction until they end at any of the four map borders 36 of the thinned pixel map, or at one of the ridge intercepts 32. At such intercept 32, the tracking continues along the ridge that follows the smaller angle with the segment of ridge preceding (it is to be noted that the line 34 is only a representation of the diagonal of the thinned pixel map 28, and is not part of the thinned pixel map). This process is then repeated, starting from the diagonal 34 and going in a second direction opposite the first direction. As can be better seen from Figure 5, this tracking algorithm retains all the ridges intersecting the diagonals, such as, for example, ridges 30, all others are discarded.
In step 110, each of the ridges 33, retained by the tracking step 108, are modelled mathematically. In a preferred embodiment, a cubic spline representation of each ridge 33 is computed by the controller 12, using the pixel coordinates of selected points along the ridges 33. This representation is combined with a least-square fit.
The coefficients of the spline functions representing each ridge 33 are tabulated in matrix form and stored in the output device 16.
Alternatively, the values representing the derivatives of the spline functions can be tabulated instead of the coefficients of the spline functions. It is to be noted that other representations of the ridges can be used, such as for example, a statistical modelling, without departing from the spirit of the present invention.
Preferably, step 110 also includes the use of the mathematical modelling of each ridge to compute their maxima, minima and points of inflection. As will be explained later, these values help to speed the search in databases comprising numerous values representing pre-identified fingerprints.
Together, the coordinates of the points selected along the ridges, the coefficients of the spline representation and the mathematical model form a set of values characterizing the epidermal ridges of the fingerprint.
In step 112, the resulting values from step 110 are correlated geometrically in the form of a hashing table. The distances between each and every point and value to the others are measured and retained.
This approach has the particular advantage that the 5 points are not positioned with respect to the coordinate axes of the window and that therefore the same correlations are found even if the fingerprint is oriented differently as can be seen in Figure 6 of the appended drawings. Figure 6 illustrates that, although the orientation of a pixel map of a fingerprint changes, the relative position of, for example, 10 points 38 and 38' and 40 and 40', chosen to model the ridges, does not change.
The geometric hashing performed at step 112 prevents the complications due to translations or rotations that can arise in the digitization step 102.
In step 114, the set of values are compared to other values representing pre-identified fingerprints. These other sets of values can be part of a database of mathematically characterized known fingerprints. Preferably, the search is conducted in two parts. A quick search is first performed by comparing only some of the values, such as, for example, the maxima and minima of the mathematical representations of the fingerprints. Since only some values are checked) the search can be done rapidly. It results a limited number of pre-identified fingerprints that share the same values of maxima and minima.
A more precise search can then be performed in the remaining set of values. This second search is executed by comparing several sets of values characterizing the epidermal ridges of pre-identified fingerprints to the corresponding values characterising in the database.
Evidently, pre-determined matching criteria must be used to compare the numerical values. These criteria can be chosen) for example, by setting the precision of the values before comparison.
Also, it is well known in the art that the set of values characterizing the fingerprint to be identified can first be stored in the storage device 16 for later identification.
Both, the matrix of spline coefficients for all epidermic ridges in a fingerprint and the hashing table can be stored in the storage device 16 and transmitted rapidly and economically. The values identifying a fingerprint can also be used for purposes of encryption: for example) selected data points derived from an individual's fingerprint can serve as a cipher to send confidential messages. The great quantity of information in a single fingerprint makes it possible to use such ciphers only once, and thus render the code virtually unbreakable. This application will be of interest in particular in the field of business who are looking for a fast, reliable and inexpensive method to transmit confidential data over unprotected phone lines.
Since the epidermal ridges are defined in a fingerprint and not only their minutiae, the total volume of data utilized by the present method is considerably greater than that of current techniques) although the volume of data retained after the tracking step 108 and mathematical modelling step 110 is smaller. As a consequence, this method is much more robust, less subject to errors due to the loss of data or the appearance of unreliable or false features. Secondly, fingerprints processed by this method will only rarely require the services of trained personnel. The complete process of analysis, including the cleanup, the thinning, the tracking, and the mathematical characterization are performed rapidly and automatically on currently available, inexpensive PC-type microcomputers.
Although the invention has been described above with respect with one specific form, it will be evident to a person skilled in the art that it may be modified and refined in various ways.
For example, the fingerprint ridges as defined by this method contain a wealth of information on their relative positions, distances, and curvatures. This information may be helpful to identify also partial (incomplete) fingerprints.
It is therefore wished to have it understood that the present invention should not be limited in scope, except by the terms of the following claims.
The coefficients of the spline functions representing each ridge 33 are tabulated in matrix form and stored in the output device 16.
Alternatively, the values representing the derivatives of the spline functions can be tabulated instead of the coefficients of the spline functions. It is to be noted that other representations of the ridges can be used, such as for example, a statistical modelling, without departing from the spirit of the present invention.
Preferably, step 110 also includes the use of the mathematical modelling of each ridge to compute their maxima, minima and points of inflection. As will be explained later, these values help to speed the search in databases comprising numerous values representing pre-identified fingerprints.
Together, the coordinates of the points selected along the ridges, the coefficients of the spline representation and the mathematical model form a set of values characterizing the epidermal ridges of the fingerprint.
In step 112, the resulting values from step 110 are correlated geometrically in the form of a hashing table. The distances between each and every point and value to the others are measured and retained.
This approach has the particular advantage that the 5 points are not positioned with respect to the coordinate axes of the window and that therefore the same correlations are found even if the fingerprint is oriented differently as can be seen in Figure 6 of the appended drawings. Figure 6 illustrates that, although the orientation of a pixel map of a fingerprint changes, the relative position of, for example, 10 points 38 and 38' and 40 and 40', chosen to model the ridges, does not change.
The geometric hashing performed at step 112 prevents the complications due to translations or rotations that can arise in the digitization step 102.
In step 114, the set of values are compared to other values representing pre-identified fingerprints. These other sets of values can be part of a database of mathematically characterized known fingerprints. Preferably, the search is conducted in two parts. A quick search is first performed by comparing only some of the values, such as, for example, the maxima and minima of the mathematical representations of the fingerprints. Since only some values are checked) the search can be done rapidly. It results a limited number of pre-identified fingerprints that share the same values of maxima and minima.
A more precise search can then be performed in the remaining set of values. This second search is executed by comparing several sets of values characterizing the epidermal ridges of pre-identified fingerprints to the corresponding values characterising in the database.
Evidently, pre-determined matching criteria must be used to compare the numerical values. These criteria can be chosen) for example, by setting the precision of the values before comparison.
Also, it is well known in the art that the set of values characterizing the fingerprint to be identified can first be stored in the storage device 16 for later identification.
Both, the matrix of spline coefficients for all epidermic ridges in a fingerprint and the hashing table can be stored in the storage device 16 and transmitted rapidly and economically. The values identifying a fingerprint can also be used for purposes of encryption: for example) selected data points derived from an individual's fingerprint can serve as a cipher to send confidential messages. The great quantity of information in a single fingerprint makes it possible to use such ciphers only once, and thus render the code virtually unbreakable. This application will be of interest in particular in the field of business who are looking for a fast, reliable and inexpensive method to transmit confidential data over unprotected phone lines.
Since the epidermal ridges are defined in a fingerprint and not only their minutiae, the total volume of data utilized by the present method is considerably greater than that of current techniques) although the volume of data retained after the tracking step 108 and mathematical modelling step 110 is smaller. As a consequence, this method is much more robust, less subject to errors due to the loss of data or the appearance of unreliable or false features. Secondly, fingerprints processed by this method will only rarely require the services of trained personnel. The complete process of analysis, including the cleanup, the thinning, the tracking, and the mathematical characterization are performed rapidly and automatically on currently available, inexpensive PC-type microcomputers.
Although the invention has been described above with respect with one specific form, it will be evident to a person skilled in the art that it may be modified and refined in various ways.
For example, the fingerprint ridges as defined by this method contain a wealth of information on their relative positions, distances, and curvatures. This information may be helpful to identify also partial (incomplete) fingerprints.
It is therefore wished to have it understood that the present invention should not be limited in scope, except by the terms of the following claims.
Claims (9)
1. A method for characterizing the epidermal ridges of a fingerprint comprising the steps of:
creating a pixel map of the fingerprint;
thinning said pixel map;
tracking the epidermal ridges on the thinned pixel map;
and creating a mathematical model of the tracked epidermal ridges on said thinned pixel map so as to produce a set of values characterizing the epidermal ridges of the fingerprint.
creating a pixel map of the fingerprint;
thinning said pixel map;
tracking the epidermal ridges on the thinned pixel map;
and creating a mathematical model of the tracked epidermal ridges on said thinned pixel map so as to produce a set of values characterizing the epidermal ridges of the fingerprint.
2. A method for characterizing the epidermal ridges of a fingerprint as recited in claim 1, further comprising the step of performing a cleanup of said pixel map before said thinning step.
3. A method for characterizing the epidermal ridges of a fingerprint as recited in claim 2, wherein the step of performing a cleanup of said pixel map consists of at least one substep taken from the group including contrast enhancement, contrast expansion and levelling of image brightness.
4. A method for characterizing the epidermal ridges of a fingerprint as recited in claim 1, wherein said mathematical model includes spline functions.
5. A method for characterizing the epidermal ridges of a fingerprint as recited in claim 1, wherein said mathematical model includes a least-square fit.
6. A method for characterizing the epidermal ridges of a fingerprint as recited in claim 1, wherein a statistical model is used in said mathematical model.
7. A method for characterizing the epidermal ridges of a fingerprint as recited in claim 1, wherein said set of values includes at least one of maximum, minimum and points of inflection of said mathematical model.
8. A method for characterizing the epidermal ridges of a fingerprint as recited in claim 1, wherein said set of values is correlated geometrically in the form of a hashing table.
9. A method for identifying a fingerprint defined by its epidermal ridges; said method comprising the steps of:
characterizing the epidermal ridges of a fingerprint in accordance with the method of claim 1; and comparing said first set of values to other sets of values present in a database and characterizing pre-identified fingerprints.
11. A method for identifying a fingerprint defined by its epidermal ridges as recited in claim 10, wherein said comparing step includes:
performing a quick search by comparing at least one value of said first set of values to at least one value of at least one of said other sets of values to create a subassembly of said database; and performing a search by comparing a number of values of said first set of values to values of said other sets of values from said subassembly of said database.
12. A method for identifying a fingerprint defined by its epidermal ridges; said method comprising the steps of:
creating a pixel map of the fingerprint;
thinning said pixel map;
tracking the epidermal ridges on the thinned pixel map;
using a mathematical model to characterize the tracked epidermal ridges on said thinned pixel map; said characterization of the epidermal ridges producing a first set of values; and comparing said first set of values to other sets of values present in a database; said other sets of values characterizing pre-identified fingerprints.
13. An apparatus for the automated identification of a fingerprint identified by its epidermal ridges, said apparatus comprising:
a first input device to create a pixel map of the fingerprint;
a controller for thinning said pixel map, for tracking the epidermal ridges on the thinned pixel map, and for using a mathematical model to characterize the tracked epidermal ridges on said thinned pixel map thereby producing a first set of values; and a second input device to provide said controller with other sets of values characterizing pre-identified fingerprints;
said controller comparing said first set of values to other sets of values.
14. An apparatus for the automated identification of a fingerprint as recited in claim 13, wherein said controller is a microcomputer.
15. An apparatus for the automated identification of a fingerprint as recited in claim 13, wherein said input device is selected form a group consisting of a camera, a CCD camera and a fingertip scanner.
16. An apparatus for the automated identification of a fingerprint as recited in claim 13, further comprising a storage device to store at least one of said first set of values and other sets of values.
17. An apparatus for the automated identification of a fingerprint as recited in claim 16, wherein said storage device is selected form a group consisting of a RAM, a disk drive and a CD-ROM drive.
18. An apparatus for the automated identification of a fingerprint as recited in claim 16, wherein said storage device is remotely connected to said controller via a computer network.
characterizing the epidermal ridges of a fingerprint in accordance with the method of claim 1; and comparing said first set of values to other sets of values present in a database and characterizing pre-identified fingerprints.
11. A method for identifying a fingerprint defined by its epidermal ridges as recited in claim 10, wherein said comparing step includes:
performing a quick search by comparing at least one value of said first set of values to at least one value of at least one of said other sets of values to create a subassembly of said database; and performing a search by comparing a number of values of said first set of values to values of said other sets of values from said subassembly of said database.
12. A method for identifying a fingerprint defined by its epidermal ridges; said method comprising the steps of:
creating a pixel map of the fingerprint;
thinning said pixel map;
tracking the epidermal ridges on the thinned pixel map;
using a mathematical model to characterize the tracked epidermal ridges on said thinned pixel map; said characterization of the epidermal ridges producing a first set of values; and comparing said first set of values to other sets of values present in a database; said other sets of values characterizing pre-identified fingerprints.
13. An apparatus for the automated identification of a fingerprint identified by its epidermal ridges, said apparatus comprising:
a first input device to create a pixel map of the fingerprint;
a controller for thinning said pixel map, for tracking the epidermal ridges on the thinned pixel map, and for using a mathematical model to characterize the tracked epidermal ridges on said thinned pixel map thereby producing a first set of values; and a second input device to provide said controller with other sets of values characterizing pre-identified fingerprints;
said controller comparing said first set of values to other sets of values.
14. An apparatus for the automated identification of a fingerprint as recited in claim 13, wherein said controller is a microcomputer.
15. An apparatus for the automated identification of a fingerprint as recited in claim 13, wherein said input device is selected form a group consisting of a camera, a CCD camera and a fingertip scanner.
16. An apparatus for the automated identification of a fingerprint as recited in claim 13, further comprising a storage device to store at least one of said first set of values and other sets of values.
17. An apparatus for the automated identification of a fingerprint as recited in claim 16, wherein said storage device is selected form a group consisting of a RAM, a disk drive and a CD-ROM drive.
18. An apparatus for the automated identification of a fingerprint as recited in claim 16, wherein said storage device is remotely connected to said controller via a computer network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CA002262300A CA2262300A1 (en) | 1998-02-24 | 1999-02-22 | Method and apparatus for the automated identification of fingerprints |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CA2,230,386 | 1998-02-24 | ||
| CA002230386A CA2230386A1 (en) | 1998-02-24 | 1998-02-24 | Automated indentification and analysis of fingerprints |
| CA002262300A CA2262300A1 (en) | 1998-02-24 | 1999-02-22 | Method and apparatus for the automated identification of fingerprints |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA2262300A1 true CA2262300A1 (en) | 1999-08-24 |
Family
ID=29585085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002262300A Abandoned CA2262300A1 (en) | 1998-02-24 | 1999-02-22 | Method and apparatus for the automated identification of fingerprints |
Country Status (1)
| Country | Link |
|---|---|
| CA (1) | CA2262300A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014059205A1 (en) * | 2012-10-12 | 2014-04-17 | Microsoft Corporation | Touchless input for a user interface |
-
1999
- 1999-02-22 CA CA002262300A patent/CA2262300A1/en not_active Abandoned
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014059205A1 (en) * | 2012-10-12 | 2014-04-17 | Microsoft Corporation | Touchless input for a user interface |
| CN104838337A (en) * | 2012-10-12 | 2015-08-12 | 微软技术许可有限责任公司 | Touchless input for a user interface |
| US9310895B2 (en) | 2012-10-12 | 2016-04-12 | Microsoft Technology Licensing, Llc | Touchless input |
| CN104838337B (en) * | 2012-10-12 | 2018-05-25 | 微软技术许可有限责任公司 | It is inputted for the no touch of user interface |
| US10019074B2 (en) | 2012-10-12 | 2018-07-10 | Microsoft Technology Licensing, Llc | Touchless input |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1467308B1 (en) | Image identification system | |
| Xu et al. | Virtual u: Defeating face liveness detection by building virtual models from your public photos | |
| EP3849130B1 (en) | Method and system for biometric verification | |
| EP1423821B1 (en) | Method and apparatus for checking a person's identity, where a system of coordinates, constant to the fingerprint, is the reference | |
| JP4678883B2 (en) | Apparatus, method, program storage device, and computer program (fingerprint biometric machine) for representing biometrics | |
| US6487662B1 (en) | Biometric system for biometric input, comparison, authentication and access control and method therefor | |
| US8358336B2 (en) | Frontal hand capture of fingerprints, palm prints and hand geometry using contactless photography | |
| KR102137329B1 (en) | Face Recognition System for Extracting Feature Vector Using Face Recognition Model Based on Deep Learning | |
| EP1476846B1 (en) | Method and device for recognizing fingerprint data | |
| US8260060B2 (en) | Comparison method, comparison system, computer, and program | |
| KR20150079583A (en) | Biometric authentication in connection with camera-equipped devices | |
| CN102439604A (en) | A method for fingerprint template synthesis and fingerprint mosaicing using a point matching algorithm | |
| JP2004506253A (en) | Biometric identity check | |
| JP2000011176A (en) | Certifying device and storage medium | |
| KR102294574B1 (en) | Face Recognition System For Real Image Judgment Using Face Recognition Model Based on Deep Learning | |
| Leng et al. | Palmprint recognition system on mobile devices with double-line-single-point assistance | |
| CN111027404B (en) | Fingerprint identification method based on fingerprint protection template | |
| CN111091075A (en) | Face recognition method and device, electronic equipment and storage medium | |
| Ilankumaran et al. | Multi-biometric authentication system using finger vein and iris in cloud computing | |
| US20120020535A1 (en) | Unique, repeatable, and compact biometric identifier | |
| CN108111709A (en) | A kind of primary photo identification method and system | |
| Grother et al. | Biometric specifications for personal identity verification | |
| US20230246839A1 (en) | System and method for complex confirmation of biometric information without stored biometric data | |
| CA3104384A1 (en) | Cluster-based security for network devices | |
| CN110956468B (en) | Fingerprint payment system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FZDE | Discontinued |