EP0551086A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method of smoothing a ridge direction pattern and equipment used therefor
Assignee: NEC Corp
•
Filing: 1993-01-05
•
Granted: —
•
Expires: 2013-01-05
Abstract
Abstract An energy function is defined as a linear sum of a discrepancy evaluation function and a dispersion evaluation function. Direction variables of all the subregions of a ridge direction pattern are variables of both evaluation functions. Direction variables are successively renovated along a line on which the energy function becomes minimum for a change of a concerned variable keeping all other variables unchanged. Reliabilities of initial directions in all the subregions are included as coefficients in the discrepancy evaluation function, and a higher reliability of an initial direction constrains the directional difference between the initial direction and the corresponding direction variable in a smaller amount. A set of variables which makes the energy function minimum is taken as a set of smoothed ridge direction pattern.
Inventors
- 👤 Toshio C/O Nec Corporation Kamei
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 12:57
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/10; G06V40/12; G06V40/1347
Claims Analysis
Total Claims: 6
Claim 1
Independent Claim
266 words
Method of smoothing a ridge direction pattern comprising: a step of dividing a ridge line image picture into an array of plural subregions, a step of determining for all the subregions, an initial direction Θ(m,n) of ridge line image and an initial probability R(m,n) representing the reliability of said initial direction of a subregion whose position in said array of subregions is denoted by (m,n), a step of determining an initial value of a direction variable ϑ(m,n) of a subregion for all the subregions, a step of calculating, for each subregion, a product of the initial probability R(m,n) of said subregion multiplied by direction difference δ{ϑ(m,n),Θ(m,n)} between the direction variable and the initial direction of said subregion, a step of integrating said product R(m,n)δ{ϑ(m,n),Θ(m,n)} for all the subregions for determining a discrepancy evaluation function E₁, a step of calculating, for each concerned subregion, a product of weight of influence from a neighboring subregion multiplied by the direction difference δ{ϑ(m,n),ϑ(m+1,n)} between the direction variables of said concerned and said neighboring subregion. a step of integrating, for each said concerned subregion, said product of weight and the direction difference on all neighboring subregions for determining a component of a dispersion evaluation function of said concerned subregion, a step of integrating said component of dispersion evaluation function on all the subregions for determining a dispersion evaluation function E₂, a step of calculating an energy function E which is represented as a linear function E=E₁+λE₂ of said discrepancy evaluation function E₁ and said dispersion evaluation function, and a step of renovating direction variable along lines of decreasing said energy function.
Claim 2
Dependent Claim
46 words
Method of smoothing a ridge direction pattern according to claim 1, wherein said direction difference δ(ϑ₂,ϑ₁) between two directions ϑ₁ and ϑ₂ is defined as a square of magnitude of a vector representing a difference vector between two unit vectors having directions ϑ₁ and ϑ₂ respectively.
Claim 3
Dependent Claim
78 words
Method of smoothing a ridge direction pattern according to claim 1 or 2, wherein said step of renovating said direction variables comprises: calculation step for determining a new direction variable ϑ₁ by equations ∂E/∂ϑ₁,=0 , and ∂²E/∂ϑ₁²>0 where ϑ₁ is the direction variable of an arbitrary subregion, renovation step for substituting said direction variable of said arbitrary subregion by said new direction variable, and steps of repeating said calculation steps and said renovation steps for all other subregions.
Claim 4
Dependent Claim
119 words
Method of smoothing a ridge direction pattern comprising: a step of dividing a ridge line image picture into an array of plural subregions, a step of determining an initial direction of ridge line image and an initial probability representing the reliability of said initial direction for each subregion, a step of determining an initial value of a direction variable for each subregion, ridge direction pattern renovating step in which a step of calculating a new direction variable and a step of renovating the direction variable by the calculated value is repeated for all the subregions, a step of calculating said energy function for renovated direction variables, and judgement step for determining iteration of said ridge direction pattern renovating step.
Claim 5
Dependent Claim
45 words
Method of smoothing a ridge direction pattern according to claim 4, wherein said judgement step comprises: a step of calculating decrement of said energy function by said ridge direction pattern renovating step, and a step of comparing said calculated decrement to a predetermined threshold value.
Claim 6
Dependent Claim
139 words
An equipment used for smoothing a ridge direction pattern comprising: an image memory 11 for storing a fingerprint ridge line picture, ridge direction pattern extraction means 12 for converting the contents of said image memory to direction patterns of all subregions and reliabilities of the directional patterns, an initial pattern memory 13 for storing said direction patterns produced by said ridge line pattern extraction means, a reliability pattern memory 14 for storing said reliabilities of the direction patterns produced by said ridge direction pattern extraction means, variable direction memory 15 for storing all the direction variables, ridge direction pattern renovation means 16 for renovating the contents of said variable direction memory, and, judgement means 17 including means of calculating said energy function E and means of deciding the termination of renovation of the contents of said variable direction memory.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.