EP2044712A1 - Procede d'identification d'un individu - Google Patents
Procede d'identification d'un individuInfo
- Publication number
- EP2044712A1 EP2044712A1 EP07785953A EP07785953A EP2044712A1 EP 2044712 A1 EP2044712 A1 EP 2044712A1 EP 07785953 A EP07785953 A EP 07785953A EP 07785953 A EP07785953 A EP 07785953A EP 2044712 A1 EP2044712 A1 EP 2044712A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- image
- encrypted
- identified
- images
- transformation function
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Definitions
- the present invention relates to a method for identifying an individual by superimposing encrypted images, a method of recording, in a database, an image of a biometric data, and a recording device. Encrypt images implementing such a recording method and an identification device implementing such an identification method.
- biometric data fingerprints, iris,
- a biometric data For each individual to be recognized, a biometric data must be previously recorded in a reference biometric database during a registration process.
- biometric data when the individual wishes to be recognized, an image of his biometric data must be captured and compared to all the biometric reference data of the database during an identification process. If the biometric data thus captured is recognized, the individual is identified as an authorized person, whereas if the captured biometric data is not recognized, the individual is considered an unauthorized person.
- the security of the database is very important because an attacker who has access to such a database can modify the risk of reducing the level of safety of the building or the well protected machine.
- An object of the present invention is to propose a method for identifying an individual who does not have the drawbacks of the state of the art, and who, in particular, makes it possible to obtain an identification that is easy to carry out while securing biometric data.
- a method of identifying an individual comprising:
- a obtaining step during which a transformation function and a previously recorded encrypted image corresponding to said identified identity are obtained and which has been obtained by transforming the image of a biometric data item of said individual into at least two images encrypted by the transformation function, the encrypted images being such that the visual recognition of the shapes of said biometric data item requires the superposition of all the encrypted images,
- a capture step during which an image of the biometric data to be identified is captured; a transformation step during which the captured image is transformed into at least one encrypted image to be identified (500, 802); from the transformation function,
- the obtaining step consists, as regards the transformation function, in a recovery of the transformation function corresponding to the identified identity.
- the loopback step consists of a substep of improving the alignment of the encrypted images to identify compared to the encrypted images recorded by geometric manipulation of the image of the biometric data item to be identified and in a loopback on the transformation stage.
- the loopback step consists of a sub-step of displaying the superposition image and a looping of the process on the capture step.
- the verification step consists of an analysis of the sharpness of the superposition image.
- the image of the biometric data item is transformed into its direction matrix.
- the invention also proposes a method of recording an image in a database comprising:
- a step of capturing an image of a biometric data a step of obtaining a transformation function
- the transformation function is generated for each biometric data item and the backup step includes the backup of the transformation function.
- the transformation function relies on a visual cryptographic method.
- the image of the biometric datum is transformed into its direction matrix.
- the invention also proposes an encrypted image recording device which comprises means for implementing a recording method according to one of the preceding variants.
- the invention also proposes an identification device which comprises means for implementing an identification method according to one of the preceding variants.
- FIG. . 1 represents an image of a reference fingerprint
- FIG. 2a, FIG. 2b and FIG. 2c show examples of subdivisions of pixels used in the context of the invention
- FIG. 3a and FIG. 3b represent encrypted images of the reference fingerprint obtained by a first embodiment of the invention
- FIG. 4 represents a first fingerprint to be identified
- FIG. 5 shows an encrypted image of the first fingerprint obtained by the first embodiment of the invention
- FIG. 6c represent, in the context of the first embodiment of the invention, the images obtained by superposition of the encrypted image of the reference fingerprint and the encrypted image of the first fingerprint
- FIG. 7 represents a second fingerprint to be identified
- FIG. 8a and FIG. 8b represent, in the context of the first embodiment of the invention, the images obtained by superposition of the encrypted image of the reference fingerprint and the encrypted image of the second fingerprint
- FIG. 9a, FIG. 9b and FIG. 9c represent encrypted fingerprint images obtained by a second embodiment of the invention
- FIG. 10a, FIG. 10b, FIG. 10c, FIG. Iia and FIG. 11b represent, in the context of the second embodiment of the invention, the images obtained by superposition of the encrypted image of a reference fingerprint and the encrypted fingerprint image to be identified
- FIG. 12 represents an algorithm of an identification method according to the invention
- FIG. 13 is a schematic representation of an encrypted image recording device
- FIG. 14 is a schematic representation of an identification device according to the invention.
- Fig. 1 represents an image 100 of a fingerprint captured using a fingerprint sensor. This fingerprint image 100 is in black and white and is considered, in the remainder of the description, as the image of the reference print 100.
- Fig. 13 shows an encrypted image recording device 1300 which includes such a fingerprint sensor 1302.
- the recording device
- 1300 comprises a database 1314 in which are stored encrypted images of reference prints whose generation is described below.
- the individual wishing to register one of the encrypted images from his fingerprint in the database 1314 places the finger 1304 on the fingerprint sensor 1302 which captures the image of the reference fingerprint 100.
- the image of the reference fingerprint 100 is then transformed so as to obtain two encrypted images which are such that when at least one of these two encrypted images is not known, it is not possible to reconstruct the image.
- the image of the reference fingerprint 100 is then transformed so as to obtain two encrypted images which are such that when at least one of these two encrypted images is not known, it is not possible to reconstruct the image.
- to visually recognize the shapes of the reference footprint 100 as they appear on the image of the reference footprint 100 it is necessary to overlay the image of the reference footprint 100.
- the two encrypted images that come from the transformation. If one of the encrypted images is missing, it is not possible to determine the global information relating to the image of the reference footprint 100.
- the method used to transform the image of the reference fingerprint is then transformed so as to obtain two encrypted images which are such that when at least one of these two encrypted images is not known, it is not possible to reconstruct the image.
- to visually recognize the shapes of the reference footprint 100 as they appear on the image of the reference footprint 100 it is necessary to overlay the image of the reference footprint 100.
- 100 in two encrypted images consists, preferably, in the method called "visual cryptography" which allows to encrypt visual information.
- the image of the reference footprint 100 is an image consisting of black and white pixels.
- the transformation into two encrypted images thus consists in producing two images which, by superposition and by transparency, make it possible to obtain an image which is comparable to that of the reference imprint 100.
- each pixel of the image of the reference print 100 is subdivided into a group of several sub-pixels, preferably four forming a square.
- Fig. 2a, FIG. 2b and FIG. 2c are examples of subdivisions of pixels into four sub-pixels.
- Each subpixel may be opaque (black in Figs.) Or transparent (white in Figs.).
- 202b, 204b, 202c and 204c consists of two opaque subpixels and two transparent subpixels.
- Fig. 2a represents a horizontal subdivision.
- Each group of sub-pixels 202a, 204a is symmetrical to the other 204a, 202a by symmetry with respect to a horizontal line.
- the first group of sub-pixels 202a comprises two transparent sub-pixels arranged horizontally next to each other and two opaque sub-pixels arranged horizontally next to one another and below the two sub-pixels. transparent pixels.
- the second group of sub-pixels 204a is deduced from the first group by an axial symmetry of horizontal axis.
- Fig. 2b represents a vertical subdivision.
- Each group of sub-pixels 202b, 204b is symmetrical to the other 204b, 202b by symmetry with respect to a vertical line.
- the first group of sub-pixels 202b comprises two transparent sub-pixels arranged vertically one above the other and two opaque sub-pixels arranged vertically one above the other and to the right of the two sub-pixels. transparent.
- the second group of sub-pixels 204b is deduced from the first group by axial symmetry of vertical axis.
- Fig. 2c represents a diagonal subdivision.
- the first group of four sub-pixels 202c comprises two transparent sub-pixels arranged diagonally with respect to each other and two opaque sub-pixels arranged diagonally with respect to each other.
- the second group of four sub-pixels 204c has diagonals inverted with respect to the first group of four sub-pixels 202c, that is to say that it is deduced from the first group by an axial
- the transformation of the image of the reference footprint 100 into two encrypted images is carried out according to the following principle.
- the group of sub-pixels of the first encrypted image and the group of sub-pixels of the second encrypted image are different.
- the first encrypted image receives the first group of four sub-pixels 202a and the second encrypted image receives the second group of four sub-pixels 204a, or vice versa.
- the pixel Jc the image of the reference fingerprint 100 is white
- the group of sub-pixels of the first encrypted image and the group of sub-pixels of the second encrypted image are identical.
- the first encrypted image and the second encrypted image receive the first group of four sub-pixels 202a or the second group of four sub-pixels 204a.
- the superposition of the two encrypted images then makes it possible to find, for each black pixel of the image of the reference print 100, a black pixel consisting of four opaque sub-pixels, and for each white pixel of the image of the image reference footprint 100, a gray pixel consisting of two opaque sub-pixels and two transparent sub-pixels.
- each encrypted image is therefore carried out by taking the first pixel of the image of the reference fingerprint 100, by choosing a subdivision (horizontal, vertical, diagonal or other), by choosing a pair of subgroups of subgroups. pixels, by choosing which group of sub-pixels is assigned to which image encrypted according to the black or white color of the pixel of the image of the reference fingerprint 100.
- a subdivision horizontal, vertical, diagonal or other
- a pair of subgroups of subgroups pixels
- group of sub-pixels is assigned to which image encrypted according to the black or white color of the pixel of the image of the reference fingerprint 100.
- the image of the reference print 100 has four pixels distributed according to the following black-white-white-black. Only the horizontal subdivision is used.
- the pair (202a, 204a) is selected and the first encrypted image receives the group 202a and the second encrypted image receives the group 204a.
- the pair (202a, 204a) is selected and each encrypted image receives the group 202a.
- the pair (204a, 202a) is selected and each encrypted image receives the group 204a.
- the one (204a, 202a) is selected and the first encrypted image receives the group 204a and the second encrypted image receives the first group 202a.
- the transformation of the image of the reference fingerprint 100 into two encrypted images is therefore done through a transformation function F which for each pixel of the image of the reference print 100 stores the pair of subgroups. - pixels used (ie (202a, 204a) or (204a, 202a)). Then, the first encrypted image receives the first subpixel group 202a (or 204a) and the second encrypted image receives the second subpixel group which is determined from the black or white color of the pixel of the image. the reference footprint 100.
- Fig. 3a represents the first encrypted image 302a from the image of the reference fingerprint 100 of FIG. 1 and transformation function F as just described.
- Fig. 3b represents the first encrypted image 302b from the image of the reference fingerprint 100 of FIG. 1 and the same transformation function F. Individually, each encrypted image 302a, 302b gives no information about the image of the reference fingerprint 100, but the superimposition of the two encrypted images 302a and 032b gives a fingerprint image in accordance with that of FIG. 1 but on a gray background instead of white.
- the encrypted image recording device 1300 comprises a transformation module 1306 (see Fig. 13).
- the transformation module 1306 is designed to generate the two encrypted images 302a and 302b from a transformation function F which is previously established for all the individuals or for each individual or that the transformation module 1306 establishes itself. for each individual.
- One of the encrypted images 302a or 302b is then saved in a database 1314. If the transformation function F varies according to the individuals, it must also be saved in the database 1314.
- the method of recording an image in the database 1314 comprises: a step of capturing the image of the IUU imprint,
- the advantage of this method is to allow the realization of a secure database by the fact that an intrusion into this database 1314, does not allow to obtain global information on the forms of data. fingerprints that were used to make these encrypted images 302a, 302b. Indeed, an intruder can have access to only one of two encrypted reference images 302a or 302b.
- This recording method applies in the same way to other biometric data such as iris.
- the backup step includes the backup of the transformation function F.
- the transformation function F can be generated globally for all the individuals, the generation step is then replaced by a step of recovering the transformation function F from a generation module of the transformation function F.
- Fig. 14 represents an identification device 1400 which is connected to the database 1314.
- the database 1314 contains, for each individual, only one of the two encrypted images generated previously, as well as the transformation function F if the latter is dependent on the individual .
- This separation of the database is particularly interesting in the case of a remote database 1314 receiving information from a central database containing the two reference encrypted images 302a and 302b. Indeed, only part of the information relating to the image of the reference footprint 100 is present and this information is not usable.
- the encrypted image stored in the database 1314 is called: encrypted reference image.
- the identification device 1400 includes a fingerprint sensor 1302.
- the individual who wishes to be identified poses the finger 1304 on the fingerprint sensor 1302 which captures the image of his fingerprint.
- Fig. 4 represents the image of such a fingerprint 400.
- FIG. 5 represents an encrypted image 500 generated from the image of the fingerprint 400 to be identified and the transformation function T.
- This encrypted image is denominated: encrypted image to be identified 500.
- the encrypted reference image corresponds to the first (respectively second) encrypted image 302a (respectively 302b) generated by the transformation function T
- the encrypted image to identify 500 corresponds to the second (respectively first) encrypted image generated from the image of the fingerprint to identify 400 and the transformation function F.
- the encrypted reference image and the encrypted image to be identified 500 are superimposed and the analysis then relates to the result of this superposition.
- the identification is then easy to carry out since an analysis of the sharpness of the superposition image is sufficient and because of the particular structure of the encrypted images, the biometric data are secured.
- FIG. 6a, FIG. 6b and FIG. 6c represent three overlays of the encrypted reference image and the encrypted image to be identified 500.
- Fig. 6a represents an overlay image 602a consisting of the encrypted reference image 604 and the encrypted image to be identified 500. Due to the shift of the image of the fingerprint to be identified 400 with respect to the image of the reference footprint 100, the overlay image 602a is blurred and the individual to be identified can not be recognized.
- the superimposition image 602a shows that the encrypted reference image 604 and the encrypted image to be identified 500 are offset with respect to each other. It is then possible for the individual to identify, by viewing the superposition image 602a, to move the finger 1304 so that the encrypted image to be identified 500 is superimposed correctly with the encrypted reference image 604.
- Fig. 6b represents an overlay image 602b whose superposition is improved over the overlay image 602a, but there are still fuzzy areas and the individual can not be considered to have been recognized.
- Fig. 6c represents an overlapping image 602c whose superposition is perfect, there are no more fuzzy areas and the individual can be considered to have been recognized.
- the sharpness of the superposition is verified by the sharpness of the opaque forms that appear and which vary according to the alignment of the encrypted image to identify 500 with the encrypted reference image 604. This alignment can be performed manually or automatically.
- the manual alignment may be performed by a controller who knows the identity of the individual to be identified and who can manipulate the encrypted image to be identified 500 to coincide with the encrypted reference image 604 corresponding to that individual.
- the manual alignment can be performed by the individual to identify himself who identifies with the encrypted image alignment device 1400 so that it displays the corresponding encrypted reference image 604.
- the display of the overlay images allows the individual to identify to correctly position the finger 1304 in order to match the encrypted image to identify 500 with the encrypted reference image 604.
- the validation of the identification can be done by a controller viewing the final overlay image or an automatic system that measures the sharpness of the final overlay image.
- the individual to be identified identifies with the encrypted image alignment device
- the automatic system attempts to align the encrypted image to identify 500 with the encrypted reference image 604 by manipulating the encrypted image to be identified 500.
- the misalignment of the encrypted image to identify 500 and the encrypted reference image 604 generally stems from a misposition of the finger 1304 on the fingerprint sensor 1302 and / or a finger pressure 1304 on the fingerprint sensor 1302 different from that which was exercised when recording the encrypted image reference 604.
- a wrong positioning of the finger 1304 can be solved by translations and rotations of the finger 1304 or the encrypted image to be identified.
- a different pressure can be solved by a different pressure of the finger 1304 or by a homothety of the encrypted image to be identified.
- the center of the homothety is located near the center of the footprint, namely, the point referenced 402 in FIG. 4.
- FIG. 7 represents the image 700 of a fingerprint which is different from the reference fingerprint.
- the image of the fingerprint to be identified 700 is transformed into two encrypted images to be identified, including the encrypted image referenced 802.
- FIG. 7a and FIG. 7b show two superimpositions of the encrypted reference image 604 and the encrypted image to be identified 802. Each of these superposition images has fuzzy areas even after translation and alignment of the central areas of the imprints (Fig. 8b).
- the individual having the imprint corresponding to image 700 can not therefore be validly recognized as an authorized person.
- Fig. 12 represents an algorithm of the method of identifying an individual whose encrypted reference image 302a or 302b has been recorded according to the recording method described above.
- the identification method comprises: an identification step 1201 in the course of which the identity of the individual to be identified is noted,
- a obtaining step 1203 during which the transformation function F and the previously recorded encrypted image 302a, 302b corresponding to said identified identity and obtained by transforming the image of a biometric data are obtained; 100 of the individual in at least two encrypted images 302a, 302b by the transformation function F, the encrypted images 302a, 302b being such that the visual recognition of the forms of said biometric data requires the superposition of all the encrypted images 302a, 302b ,
- a capture step 1202 in which the image of the fingerprint to be identified 400, 700 is captured
- a transformation step 1204 in the course of which the image thus captured is transformed into an encrypted image to be identified 500, 802 from the transformation function F, an overlay step 1206 during which a superimposition image resulting from the superposition of the recorded encrypted image 302 ⁇ a, 302b and the encrypted image to be identified 500, 802 is formed,
- an identification step 1210 in which a decision as to the identification of the individual is taken on the basis of said verification step 1208 and,
- a looping step 1214 This identification method makes it possible to verify the identity of an individual by visual alignment of two encrypted images which are such that the knowledge of only one of these two images does not provide information on the biometric data considered, thus allowing increased security in case of intrusion into the database.
- the looping step 1214 consists of a sub-step of improving the aligning the encrypted image to identify 500, 802 with respect to the encrypted reference image 302a, 302b by geometric manipulation (translation, rotation, homothety) of the image of the fingerprint to be identified 400, 700 and in a loopback of the process on the transformation step 1204.
- geometric manipulation transformation, rotation, homothety
- the transformation of the image of the fingerprint to be identified 400, 700 depends on the position of the finger 1304 (the transformation function F applies differently depending on the position of the pixel to which it applies).
- the looping step 1214 consists of a substep of displaying the overlay image and looping the process over the 1202. Indeed, after the display of the superposition image, the individual is able to deduce the new position of the finger 1304 and / or the new pressure to be exerted on the fingerprint sensor 1302. The individual then modifies the position of his finger 1304 and / or the pressure he exerts before the new capture step 1202.
- the identification step 1201 may comprise, for example, a phase of entering a code or reading a smart card, to identify the individual wishing to be identified.
- the obtaining step 1203 may consist, as regards the transformation function F, by reading an internal memory of the identification device 1400 or in a recovery from the database 1314.
- the transformation function F is individual, the step of obtaining
- the verification step 1208 may consist of an analysis of the sharpness of the overlay image. Verification is positive when the sharpness achieved is the best possible. For example, the process checks the iteration sharpness, i.e., the sharpness of each overlay image is analyzed with respect to the overlay image that has previously been analyzed as having the best sharpness. Thus, when the best sharpness is reached, the process proceeds to the identification step 1210.
- the sharpness of the overlay image it is possible to use a known method of analyzing the sharpness of an image. For example, it is possible to consider a part of the superimposition image, to translate one of the two encrypted images with a relatively coarse pitch and to check if the same part of the resulting superimposition image is more or less fuzzy. If the resulting superimposition image is fuzzier, the translation is canceled and translation is carried out in another direction. If the resulting superimposition image is less blurred, we start from this new base and start the process again, refining step by step in different directions in order to find the best position.
- the fuzzier the analyzed part is, the more the signal level of a pixel is close to the signal level of its neighbors, whereas when the analyzed part is sharp, the signal level of a pixel is very different from the signal level of the signal. some of his neighbors. In other words, when the image is sharp, a white pixel and a black pixel are neighbors, while when the image is blurred, the two pixels are more or less gray.
- the identification step 1210 can base its decision on the sharpness that is obtained at the output of the verification step 1208. If the sharpness of the final superposition image is greater than a certain threshold, the individual to be identified is recognized as an authorized person, if not, the individual is recognized as not being an authorized person.
- the image of the fingerprint to be identified 400, 700 is transformed into two encrypted images to be identified 500, 802 on the basis of the transformation function F.
- the first pixel (said first pixel to be identified) of the image of the fingerprint to be identified 400, 700 is selected, as well as the pair of subpixel groups used
- the first encrypted image to identify receives the first group of sub-pixels 202a (respectively 204a) and the second encrypted image to be identified receives the first group of sub-pixels 202a (respectively 204a). If the first pixel to be identified is black, the first encrypted image to be identified receives the first group of sub-pixels 202a (respectively 204a) and the second encrypted image to be identified receives the second group of sub-pixels 204a (respectively 202a).
- the identification device 1400 comprises:
- a transformation module 1406 designed to transform the captured image into an encrypted image to be identified 500, 802 from the transformation function F,
- an overlay module 1408 provided for recovering the recorded encrypted image 302a, 302b from the database 1314 and superimposing it on the encrypted image to be identified 500, 802 in order to form the superposition image
- a verification module 1410 designed to check the superposition image formed
- an identification module 1412 intended to take a decision as to the identification of the individual.
- the image of the captured biometric data undergoes a first transformation prior to the step of transforming the image of the biometric data into two encrypted images and this as well in the method of only in the identification process.
- the first transformation consists of converting the image of the biometric data into its direction matrix.
- the direction matrix of a fingerprint is a matrix representing the local orientation of the peak lines of the fingerprint at a given number of points of the image of the fingerprint.
- a graphical representation can then be obtained by assigning each possible orientation a gray level. The image is then represented in gray level and no longer in black and white.
- Fig. 9a represents the direction matrix 902 of the reference fingerprint 100 of FIG. 1.
- Fig. 9b represents the direction matrix 904 of the fingerprint to be identified 400 of FIG. 4.
- FIG. 9c represents the direction matrix 906 of the fingerprint to be identified 700 of FIG. 7.
- the dark areas represent the points where the directions of the tangents at these points have a positive angle in the trigonometric direction. Between a dark zone and a clear zone, the angle of the tangents varies from 0 to ⁇ .
- the step of transforming the image into two encrypted images then applies to the biometric data image in the form of its direction matrix.
- FIG. 10a, FIG. 10b and FIG. 10c represent the overlay images
- 1002a, 1002b and 1002c obtained by superimposing the encrypted image of the direction matrix 902 of the reference fingerprint and the encrypted image of the direction matrix 904 of the fingerprint to be identified 400, that is to say when the impression to be verified corresponds to the reference impression.
- Figs. 10a, 10b and 10c respectively correspond to the positions of Figs. 6a, 6b and 6c, that is to say when the alignment of the two images is bad, then when it is improved, then when it is perfect. Note that in FIG. 10a, there are significant areas of parasites that fade in FIG. 10c.
- FIG. Iia and FIG. 1 1b represent the superposition images 1 102a and
- Figs. 1a and 11b respectively correspond to the positions of Figs. 8a and 8b, that is to say when the alignment of the two images is bad, then when it is improved but not concordant
- the step of transforming the image of the biometric data into two encrypted images has more particularly been described within the framework of an OR function, but it can also be based on an XOR function associated with a mask which also constitutes a method visual cryptography.
- Each image of a captured biometric data is divided into two intermediate images. Each of these intermediate images is then combined with the mask through an XOR function. The result of each combination produces an encrypted image that can be used later in the registration process or identification process.
- the transformation function F is then the combination of this division into two intermediate images and the application of the XOR function.
- the intermediate images may, for example, consist respectively of even pixels and odd pixels of the image of the captured biometric data.
- the invention has been more particularly described in the case where the image of the biometric data is transformed into two encrypted images, but it applies in the same way if the image of the biometric data is transformed into more than two images. encrypted.
- the step of transforming the image of the imprint 100 into two images encrypted by the transformation function T must then be understood as a step of processing i'image of ia IUU biometric data into at least two image encrypted by the transform function T i s e s encrypted images being such that the visual pattern recognition of said biometric data requires the superimposition of all the encrypted images.
- the backup step, in the database 1314 is then understood as a step of saving, in the database 1314, only a part of the images thus encrypted.
- the transformation step 1204 then means the transformation of the captured image into at least one encrypted image to be identified from the transformation function T.
- the superposition step 1206 then is understood as a superposition step during which a superposition image resulting from the superposition of the encrypted images recorded and the encrypted images to be identified is formed.
- the loopback step 1214 consisting of a substep of improving the alignment of the encrypted image to identify 500, 802 with respect to the encrypted image recorded 302a, 302b by manipulation of the image of the biometric data to identify, is understood as a loopback step consisting of a substep of improving the alignment of the encrypted images to be identified with respect to the encrypted images recorded by manipulation of the image of the biometric data to be identified.
- the invention has been more particularly described in the case of an image captured in black and white, but it can be applied in the same way to a grayscale image as is applied in the case of the direction matrix .
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR0606290A FR2903513B1 (fr) | 2006-07-10 | 2006-07-10 | Procede d'identification d'un individu utilisant une fonctio n de transformation et dispositif d'identification associe |
| PCT/EP2007/006082 WO2008006537A1 (fr) | 2006-07-10 | 2007-07-09 | Procédé d'identification d'un individu |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP2044712A1 true EP2044712A1 (fr) | 2009-04-08 |
Family
ID=37672278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP07785953A Withdrawn EP2044712A1 (fr) | 2006-07-10 | 2007-07-09 | Procede d'identification d'un individu |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US8233680B2 (fr) |
| EP (1) | EP2044712A1 (fr) |
| CA (1) | CA2657216C (fr) |
| FR (1) | FR2903513B1 (fr) |
| WO (1) | WO2008006537A1 (fr) |
Families Citing this family (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8260008B2 (en) | 2005-11-11 | 2012-09-04 | Eyelock, Inc. | Methods for performing biometric recognition of a human eye and corroboration of same |
| US8364646B2 (en) | 2006-03-03 | 2013-01-29 | Eyelock, Inc. | Scalable searching of biometric databases using dynamic selection of data subsets |
| US8604901B2 (en) * | 2006-06-27 | 2013-12-10 | Eyelock, Inc. | Ensuring the provenance of passengers at a transportation facility |
| EP2076871A4 (fr) | 2006-09-22 | 2015-09-16 | Eyelock Inc | Dispositif compact et procédé d'acquisition de données biométriques |
| WO2008042879A1 (fr) | 2006-10-02 | 2008-04-10 | Global Rainmakers, Inc. | Système et procédé de transaction financière biométrique résistant à la fraude |
| WO2008131201A1 (fr) | 2007-04-19 | 2008-10-30 | Global Rainmakers, Inc. | Procédé et système de reconnaissance biométrique |
| US8953849B2 (en) | 2007-04-19 | 2015-02-10 | Eyelock, Inc. | Method and system for biometric recognition |
| US9002073B2 (en) | 2007-09-01 | 2015-04-07 | Eyelock, Inc. | Mobile identity platform |
| US8212870B2 (en) | 2007-09-01 | 2012-07-03 | Hanna Keith J | Mirror system and method for acquiring biometric data |
| US8553948B2 (en) | 2007-09-01 | 2013-10-08 | Eyelock, Inc. | System and method for iris data acquisition for biometric identification |
| US9036871B2 (en) | 2007-09-01 | 2015-05-19 | Eyelock, Inc. | Mobility identity platform |
| US9117119B2 (en) | 2007-09-01 | 2015-08-25 | Eyelock, Inc. | Mobile identity platform |
| WO2009158662A2 (fr) | 2008-06-26 | 2009-12-30 | Global Rainmakers, Inc. | Procédé de réduction de visibilité d'éclairement tout en acquérant une imagerie de haute qualité |
| WO2010063318A1 (fr) * | 2008-12-03 | 2010-06-10 | Novelty Group Limited | Système de signature et procédé de production d'un dispositif d'identification, système d'authentification, procédé d'authentification d'un utilisateur |
| US8195044B2 (en) | 2009-03-30 | 2012-06-05 | Eyelock Inc. | Biometric camera mount system |
| EP2282284A3 (fr) * | 2009-07-30 | 2012-08-15 | Universität Duisburg-Essen | Codage des informations biométriques |
| US10043229B2 (en) | 2011-01-26 | 2018-08-07 | Eyelock Llc | Method for confirming the identity of an individual while shielding that individual's personal data |
| RU2589859C2 (ru) | 2011-02-17 | 2016-07-10 | АЙЛОК ЭлЭлСи | Эффективный способ и система для получения данных изображения сцены и изображения радужной оболочки с использованием одного датчика |
| WO2012124115A1 (fr) * | 2011-03-17 | 2012-09-20 | 富士通株式会社 | Dispositif d'acquisition de données biologiques, dispositif de comparaison de données biologiques et programme |
| US20120268241A1 (en) | 2011-04-19 | 2012-10-25 | Eyelock Inc. | Biometric chain of provenance |
| RU2623795C2 (ru) | 2011-08-22 | 2017-06-29 | АЙЛОК ЭлЭлСи | Системы и способы для захвата безартефактных изображений |
| US9280697B2 (en) * | 2011-11-16 | 2016-03-08 | Apple Inc. | Authentication device including template validation and related methods |
| US9495526B2 (en) | 2013-03-15 | 2016-11-15 | Eyelock Llc | Efficient prevention of fraud |
| EP3087533A4 (fr) | 2013-12-23 | 2017-09-20 | Eyelock Llc | Procédés et appareil pour une reconnaissance de l'iris à faible consommation d'énergie |
| CN105981047A (zh) | 2014-01-06 | 2016-09-28 | 眼锁有限责任公司 | 用于重复虹膜识别的方法和设备 |
| EP3192009A4 (fr) | 2014-09-12 | 2018-04-25 | Eyelock Llc | Procédés et appareil permettant de diriger le regard d'un utilisateur dans un système de reconnaissance d'iris |
| US10332113B2 (en) | 2014-11-19 | 2019-06-25 | Eyelock Llc | Model-based prediction of an optimal convenience metric for authorizing transactions |
| US10074011B2 (en) | 2015-01-20 | 2018-09-11 | Eyelock Llc | Lens system for high quality visible image acquisition and infra-red iris image acquisition |
| CN107580767B (zh) | 2015-03-12 | 2020-12-29 | 眼锁有限责任公司 | 使用生物特征来管理网络活动的方法和系统 |
| KR102460069B1 (ko) * | 2015-09-30 | 2022-10-28 | 삼성전자주식회사 | 보안 인증 장치 및 보안 인증 방법 |
| US10311299B2 (en) | 2015-12-21 | 2019-06-04 | Eyelock Llc | Reflected optic camera module for iris recognition in a computing device |
| WO2017201147A2 (fr) | 2016-05-18 | 2017-11-23 | Eyelock, Llc | Procédés et systèmes de reconnaissance d'iris basés sur un modèle de texture stochastique d'iris |
| WO2018156726A1 (fr) | 2017-02-24 | 2018-08-30 | Eyelock, Llc | Systèmes et procédés de fourniture d'éclairage pour acquisition biométrique d'iris |
| CA3015802C (fr) | 2017-08-31 | 2021-06-22 | Eyelock, Llc | Systemes et methodes d'acquisition biometrique au moyen de distorsion optique |
| EP3971797B1 (fr) * | 2020-09-22 | 2025-08-13 | Grazper Technologies ApS | Concept pour une réidentification anonyme |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2122919A1 (fr) * | 1991-11-05 | 1993-05-13 | Richard Steenblik | Methodes optiques de cryptage et de decryptage d'images |
| US5825482A (en) * | 1995-09-29 | 1998-10-20 | Kla-Tencor Corporation | Surface inspection system with misregistration error correction and adaptive illumination |
| US6343150B1 (en) * | 1997-11-25 | 2002-01-29 | Interval Research Corporation | Detection of image correspondence using radial cumulative similarity |
| JP4303410B2 (ja) * | 2000-09-29 | 2009-07-29 | 富士通株式会社 | 紋様中心決定装置および紋様方向決定装置並びに紋様位置合わせ装置および紋様照合装置 |
| CN1826798A (zh) * | 2003-07-21 | 2006-08-30 | 皇家飞利浦电子股份有限公司 | 图像对准 |
| US7667871B1 (en) * | 2004-01-30 | 2010-02-23 | Roskind James A | Visual cryptography and voting technology using a pair of enhanced contrast glyphs in overlay |
-
2006
- 2006-07-10 FR FR0606290A patent/FR2903513B1/fr not_active Expired - Fee Related
-
2007
- 2007-07-09 CA CA2657216A patent/CA2657216C/fr not_active Expired - Fee Related
- 2007-07-09 EP EP07785953A patent/EP2044712A1/fr not_active Withdrawn
- 2007-07-09 US US12/373,156 patent/US8233680B2/en not_active Expired - Fee Related
- 2007-07-09 WO PCT/EP2007/006082 patent/WO2008006537A1/fr not_active Ceased
Non-Patent Citations (2)
| Title |
|---|
| None * |
| See also references of WO2008006537A1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| US8233680B2 (en) | 2012-07-31 |
| WO2008006537A1 (fr) | 2008-01-17 |
| CA2657216A1 (fr) | 2008-01-17 |
| FR2903513B1 (fr) | 2008-12-05 |
| FR2903513A1 (fr) | 2008-01-11 |
| CA2657216C (fr) | 2015-01-27 |
| US20090274344A1 (en) | 2009-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2044712A1 (fr) | Procede d'identification d'un individu | |
| US11250285B2 (en) | Detecting characteristics of identification documents | |
| Piva | An overview on image forensics | |
| CA2957774C (fr) | Procede de securisation et de verification d'un document | |
| FR2952738A1 (fr) | Procede et systeme de controle automatique et d'authenticite d'un document d'identite | |
| EP3459013B1 (fr) | Procédé d'authentification augmentée d'un sujet matériel | |
| WO2017089736A1 (fr) | Procede d'authentification et/ou de controle d'integrite d'un sujet | |
| Abdulrahman et al. | Color images steganalysis using RGB channel geometric transformation measures | |
| FR3053500B1 (fr) | Procede de detection de fraude d'un systeme de reconnaissance d'iris | |
| CA2982878C (fr) | Procede de verification d'un dispositif de securite comportant une signature | |
| Li et al. | A robust approach to detect digital forgeries by exploring correlation patterns | |
| Hussain et al. | Evaluation of deep learning and conventional approaches for image recaptured detection in multimedia forensics | |
| WO2021123209A1 (fr) | Procédé de segmentation d'une image d'entrée représentant un document comportant des informations structurées | |
| EP2713315B1 (fr) | Procédé et dispositif de lecture d'un document | |
| EP4328874A1 (fr) | Procédé de vérification de l authenticité d'une empreinte digitale | |
| EP3782060B1 (fr) | Procédé pour authentifier un document securisé | |
| WO2021255069A1 (fr) | Procédé d'authentification d'un élément optiquement variable. | |
| EP3367304B1 (fr) | Procédé et dispositif de reconnaissance d'un individu par signature biométrique | |
| EP4015228B1 (fr) | Procédé de fabrication d'un dispositif de sécurité et dispositif de sécurité associé | |
| FR3044451A3 (fr) | Procede d'authentification par motif de glass | |
| Anderson | Digital Image analysis: analytical framework for authenticating digital images | |
| FR3048106A1 (fr) | Procede visuel d'authentification | |
| EP3910537A1 (fr) | Procédé de reconnaissance et d'identification de clés aux fins de leur duplication | |
| WO2026033103A1 (fr) | Procede d'authentification de sujets materiels par motif de glass au moyen d'un reseau de neurones artificiels | |
| FR3136076A3 (fr) | Image à description simplifiée |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| 17P | Request for examination filed |
Effective date: 20090203 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC MT NL PL PT RO SE SI SK TR |
|
| AX | Request for extension of the european patent |
Extension state: AL BA HR MK RS |
|
| 17Q | First examination report despatched |
Effective date: 20090617 |
|
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: SAGEM SECURITE |
|
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: MORPHO |
|
| DAX | Request for extension of the european patent (deleted) | ||
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: MORPHO |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
| GRAJ | Information related to disapproval of communication of intention to grant by the applicant or resumption of examination proceedings by the epo deleted |
Free format text: ORIGINAL CODE: EPIDOSDIGR1 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
| INTG | Intention to grant announced |
Effective date: 20210628 |
|
| INTC | Intention to grant announced (deleted) | ||
| INTG | Intention to grant announced |
Effective date: 20210722 |
|
| RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: CHABANNE HERVE Inventor name: BRINGER, JULIEN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20211202 |