Classifications

• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
  • G06F21/60—Protecting data
  • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
  • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
  • G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
  • G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/10—File systems; File servers
  • G06F16/17—Details of further file system functions
  • G06F16/178—Techniques for file synchronisation in file systems
  • G06F16/1794—Details of file format conversion
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
  • G06F16/21—Design, administration or maintenance of databases
  • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
  • G06F16/23—Updating
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
  • G06F16/43—Querying
  • G06F16/435—Filtering based on additional data, e.g. user or group profiles
  • G06F16/436—Filtering based on additional data, e.g. user or group profiles using biological or physiological data of a human being, e.g. blood pressure, facial expression, gestures
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
  • G06F17/10—Complex mathematical operations
  • G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
  • G06F17/175—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method of multidimensional data
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
  • G06F21/60—Protecting data
  • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
  • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
  • G06F21/6227—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database where protection concerns the structure of data, e.g. records, types, queries
• • 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
  • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
  • G06V40/172—Classification, e.g. identification
• • 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
  • G06V40/20—Movements or behaviour, e.g. gesture recognition
  • G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
• • 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
  • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
  • G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Definitions

• the invention relates to the verification of the content of a database in which data relating to persons, such as their name, age, date of birth, sex, portrait, fingerprint and / or other biometric data, are stored. for the purpose of identifying data entry errors and / or fraud attempts at this data stored in this database.
• the subject of the invention is a method for automatically verifying certain data of a database relating to a set of persons, and comprising for each person several data such as age, first name, gender , this method integrating:
• the invention also relates to a method as defined above, in which the data stored for each person comprises on the one hand the gender as well as the date of birth, and on the other hand a portrait and a fingerprint, and in which method implements for each person correlations of gender and age with the portrait and with the fingerprint.
• the invention also relates to a method as defined above, in which the data stored for
• each person includes the first name, and in which this method implements for each person a correlation corresponding to a statistic derived from national data and representative of the frequency of the first name of this person for the year in which it was born.
• the invention also relates to a method as defined above, implementing a correlation value corresponding to a statistical data from national data representative of the frequency of the name of the person in question for the year she was born and for the kind of this person.
• FIG. 1 is a graph with a scatter plot representing a population of men represented by triangles and women represented by circles which gives for each individual age by year on the abscissa and the width of the ribs of his fingerprint in millimeters on the ordinates;
• FIG. 2 is the graph of Figure 1 in which there is shown a middle region and a lower region which respectively constitute a zone of confidence and a zone of suspicion for the masculine gender;
• FIG. 3 is the graph of FIG. 1 in which there is shown an upper region and a middle region which respectively constitute a suspicion zone and a confidence zone for the feminine gender;
• FIG. 4 is the graph of FIG. 1 in which there is shown a middle region constituting a zone of confidence for age as well as an upper zone and a lower zone which constitute zones of suspicion for age;
• FIG. 5 is a representative graph of the frequency per year of the first name Jacob for boys born in the United States in which the years of birth are represented on the abscissa in which the frequency by thousand of individuals appear on the ordinate.
• the idea underlying the invention is to determine for each person several correlations each linking some of the data of this person, and to combine these correlations to identify individually and directly each data appearing inconsistent, instead of limiting themselves to identify only those individuals whose data would appear to be inconsistent.
• the score of each data to be verified is then compared with a threshold value to determine whether the verified data should be considered valid, or as doubtful, to establish a warning message in case of doubtful data.
• the invention is implemented to check the sex, age and first name of a set of persons or individuals stored in a database with additional data including in particular a fingerprint and a fingerprint. portrait for each of these people.
• the width of fingerprint ribs in a population is generally larger in men than in women, and it increases with the age of individuals in this population.
• the confidence zone for the male gender corresponds to a band encompassing the majority of men (represented by triangles), and the area of suspicion for the male gender is a region below the zone of confidence of the male. male, and with almost no male.
• the zone of confidence for the masculine gender which is indicated in Figure 2 by a male acronym surrounded, can be defined by first defining an average value curve for the masculine gender, corresponding to the high curve of Figure 1, and defining on either side of this average curve two envelopes curves to encompass for example 95% of the male population.
• the area of suspicion for the male gender which is identified in Figure 2 by the male symbol crossed out, can be defined by defining a high curve below the average curve of the masculine gender, but above only 2% male individuals.
• the zone of suspicion for the masculine gender is then constituted by the whole region situated under the curve thus defined.
• a possibility consists in determining if the point defines by the age of this person and by the thickness of the veins of its fingerprint is located in the zone of confidence for the masculine gender, or on the contrary in the zone of suspicion.
• a value of 1 can then be assigned to Cge if this point falls within the confidence zone for the masculine gender, and a value of 0 can be attributed to this correlation if the point falls within the suspicion zone.
• An intermediate value for example 0.5, is assigned if the point is outside the confidence zone and outside the suspicion zone.
• Another solution may be to calculate the distance between the age-defined point and the impression rib thickness, the average curve for the male gender (high curve in Figure 1), and to attribute to Cge a value between 0 and 1 all the higher as this distance is small.
• a zone of trust and a zone of suspicion for the female gender can be similarly defined.
• the zone of confidence for the feminine gender which is identified by the female acronym circled, is a band situated in the median position in the graph, and which surrounds the average curve. for women, namely the low curve in Figure 1, encompassing a high proportion, such as 95% of female individuals.
• the zone of suspicion for the female gender which is marked by the female symbol with a crossed out symbol, is an upper region situated above the zone of confidence, so as to include a very small proportion of female individuals, such as for example 2%. .
• Another possibility may be to determine, for a given individual registered as a woman, the distance between the point corresponding to the age and width of the ribs of her fingerprints, and the average curve for women that is the low curve of Figure 1. The value of Cge, between 0 and 1, is then even higher than the distance in question is low.
• the area of confidence for age which is indicated by the letter A circled in Figure 4, is a median band that encompasses the majority of individuals (men and women) in the population considered.
• This median band can be defined by first calculating the average curve for all individuals, which corresponds to the average between the high and low curves of Figure 1, then determining two envelope curves above and below this average curve to encompass for example 95% of individuals.
• the two age suspicion zones correspond to two regions above and below the median age confidence zone, respectively. areas of suspicion covering a very small proportion of individuals in the population, corresponding for example to 2% of the population.
• the determination of the value of the Cae correlation of age with the fingerprint for a given individual can again be ensured by determining whether the point corresponding to the individual in question falls within the zone of confidence or in a zone of suspicion for age, in order to assign the value 1 or 0 to Cae.
• Another solution is also to determine the distance separating the point representing the individual considered from the average curve of all the individuals, to give a correlation value Cae, between 0 and 1, which is even higher than this distance. is weak.
• the graph of FIGS. 1 to 4 whose data result for example from statistics made on a given population sample, makes it possible to determine, for each person registered in the database, a correlation Cge of his kind with his fingerprint, and a Cae correlation of his age with his fingerprint.
• a correlation of age with the portrait can be established by first providing a system, a series of portraits with each of them the actual age. When the system is then given an unknown portrait, it is compared to the series of portraits available to it, which is its reference space for determining the most similar portraits, possibly calculating a degree of resemblance. The age is then determined by calculating an average, weighted by the degrees of similarity, of the ages of the likeness portraits.
• a correlation, noted Cgp, of the kind with the portrait is established analogously.
• external statistics can be used to establish one or more correlations for each person stored in the database.
• Cpa linking the first name and the age of a given individual.
• the correlation value in question can be determined by considering that it is weak, and is worth, for example, 0, if the proportion of birth for the given first name and the year of birth in question is less than a threshold value, this threshold value being for example 1 or 2 per 1000 birth.
• the Cpa correlation of the first name with age is low for a person named Jacob who was born in 1956 in the United States, which suggests that there would be an error of seizure for example on his year of birth to the extent that the same first name, namely Jacob, for the boys born in 1976 in the United States represents more than 1 or 2 per thousandths of the births of boys.
• Another way to determine the correlation value Cpa may be to compute a numerical value that is all the smaller as the given name was infrequent for the year in question.
• these first name statistics also make it possible to determine a correlation value between the first name and the gender, noted Cpg, because these statistics are generally available for boys and girls. by years of birth.
• Cap age-portrait
• Cae age-imprint
• Cgp gender-portrait
• Cge impression-type
• Cpa first name
• Cpg first name-gender, which are all between 0 and 1.
• Correlations can be combined directly to define each score, from which a score of confidence and a suspicion threshold are then defined for each score. The data is then considered valid if its score is higher than the confidence threshold, and doubtful if its score is below the threshold of suspicion, which then leads to establish an alert. It can be decided that the data having a score between these two thresholds are either doubtful or valid.
• the score associated with a given data can be everything simply the sum of the correlations involving this data, possibly divided by the number of correlations added to bring the result back to a value necessarily between 0 and 1.
• the suspicion threshold and the confidence threshold can be determined empirically.
• Another possibility may be to calculate the scores of each data after converting each correlation value into a so-called suspicion value that can be either 0 or 1, or 2, depending on whether the correlation in question has a score respectively greater than a threshold of confidence, between the confidence threshold and a threshold of suspicion, or well below the threshold of suspicion.
• the data age score is then 1
• the invention is implemented at the level of a computer system comprising processor, memory and other means for operating a computer program in order to process the contents of a database.
• the program then analyzes the contents of a database that is submitted to it to return, after processing this database, a list of data that appears dubious. Once the correlation statistics are established on a representative enchantment, the invention also makes it possible to evaluate on the fly the confidence in the manual entry of identity data.
• the database includes the date of acquisition of the portrait and / or em ⁇ digital preinte of each person, and age is taken into account is the person's age at the date of acqui ⁇ sition of his portrait and / or his fingerprint.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Databases & Information Systems (AREA)
• General Engineering & Computer Science (AREA)
• Data Mining & Analysis (AREA)
• General Health & Medical Sciences (AREA)
• Health & Medical Sciences (AREA)
• Bioethics (AREA)
• Software Systems (AREA)
• Multimedia (AREA)
• Quality & Reliability (AREA)
• Human Computer Interaction (AREA)
• Computer Security & Cryptography (AREA)
• Computer Hardware Design (AREA)
• Computational Mathematics (AREA)
• Mathematical Analysis (AREA)
• Mathematical Optimization (AREA)
• Pure & Applied Mathematics (AREA)
• Mathematical Physics (AREA)
• Medical Informatics (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Life Sciences & Earth Sciences (AREA)
• Biomedical Technology (AREA)
• Biophysics (AREA)
• Molecular Biology (AREA)
• Physiology (AREA)
• Algebra (AREA)
• Oral & Maxillofacial Surgery (AREA)
• Social Psychology (AREA)
• Psychiatry (AREA)
• Collating Specific Patterns (AREA)
• Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
• Complex Calculations (AREA)
• Image Analysis (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=46963791

Family Applications (1)

Country Status (15)

Families Citing this family (2)

Family Cites Families (15)

• 2012
  • 2012-05-09 FR FR1254220A patent/FR2990537B1/fr not_active Expired - Fee Related
• 2013
  • 2013-04-25 CN CN201380024452.7A patent/CN104520846B/zh not_active Expired - Fee Related
  • 2013-04-25 AU AU2013258296A patent/AU2013258296A1/en not_active Abandoned
  • 2013-04-25 WO PCT/EP2013/058588 patent/WO2013167388A1/fr active Application Filing
  • 2013-04-25 BR BR112014027747A patent/BR112014027747A2/pt not_active Application Discontinuation
  • 2013-04-25 RU RU2014149344/08A patent/RU2604988C2/ru not_active IP Right Cessation
  • 2013-04-25 KR KR1020147034424A patent/KR101709765B1/ko active IP Right Grant
  • 2013-04-25 EP EP13719807.3A patent/EP2847690A1/fr not_active Ceased
  • 2013-04-25 JP JP2015510715A patent/JP6113270B2/ja not_active Expired - Fee Related
  • 2013-04-25 CA CA2872095A patent/CA2872095A1/fr not_active Abandoned
  • 2013-04-25 US US14/400,244 patent/US20150100603A1/en not_active Abandoned
  • 2013-04-25 MX MX2014013479A patent/MX357138B/es active IP Right Grant
• 2014
  • 2014-11-05 IL IL235513A patent/IL235513B/en active IP Right Grant
  • 2014-11-28 ZA ZA2014/08751A patent/ZA201408751B/en unknown
• 2015
  • 2015-07-07 HK HK15106493.2A patent/HK1206120A1/xx not_active IP Right Cessation
• 2018
  • 2018-07-06 AU AU2018204929A patent/AU2018204929A1/en not_active Abandoned
  • 2018-09-26 US US16/142,989 patent/US20190026495A1/en not_active Abandoned

Non-Patent Citations (2)

Also Published As

Similar Documents

Legal Events