Apparatus and method for nonlinear normalization of image
First Claim
1. An apparatus for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said apparatus comprising:
- means for obtaining a local spatial density function ρ
(Xi, Yj) (i=1-I, j=1-J) from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling said unknown character at a sampling interval γ
. said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;
means for computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;
means for computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;
means for extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively;
means for determining new sampling points (Xi, Yj) at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value; and
means for computing normalized sampled values at said new sampling points (Xi, Yj) by resampling said unknown character or by performing a computation on said two-dimensional pattern f(Xi, Yj),wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is a function of the product of the reciprocals of said line pitches in the X and Y directions.
1 Assignment
0 Petitions
Accused Products
Abstract
A method for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown pattern and a reference pattern. A local spatial density function ρ(Xi, Yj) (i=1-I, j=1-J) is calculated from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling the unknown pattern at a sampling interval γ. The spatial density function ρ(Xi, Yj) is obtained as the product of reciprocals of line pitches in both the X and Y directions. An x-direction cumulative function hx(Xi) and a y-direction cumulative function hy(Yj) are computed by successively adding the space density function ρ(Xi, Yj). New sampling points (Xi, Yj) are computed in such a fashion that new sampling intervals (δi, εj), defined as intervals between two adjacent points of the new sampling points (Xi, Yj), satisfy the condition that a product between the cumulative function hx(Xi) and δi takes a first fixed value, and a product between the cumulative function hy(Yj) and εj takes a second fixed value. The normalized sampled values at the new sampling points (Xi, Yj) are obtained by resampling the unknown pattern or by performing a computation on the two dimensional pattern f(Xi, Yj).
164 Citations
20 Claims
-
1. An apparatus for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said apparatus comprising:
-
means for obtaining a local spatial density function ρ
(Xi, Yj) (i=1-I, j=1-J) from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling said unknown character at a sampling interval γ
. said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;means for computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;means for computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;means for extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; means for determining new sampling points (Xi, Yj) at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value; andmeans for computing normalized sampled values at said new sampling points (Xi, Yj) by resampling said unknown character or by performing a computation on said two-dimensional pattern f(Xi, Yj), wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is a function of the product of the reciprocals of said line pitches in the X and Y directions. - View Dependent Claims (2)
-
-
3. An apparatus for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said apparatus comprising:
-
means for obtaining a local spatial density function ρ
(Xi, Yj) (i=1-I, j=1-J) from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling said unknown character at a sampling interval γ
, said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;means for computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;means for computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;means for extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; means for determining new sampling points (Xi, Yj) at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value; andmeans for computing normalized sampled values at said new sampling points (Xi, Yj) by resampling said unknown character or by performing a computation on said two-dimensional pattern f(Xi, Yj), wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the sum of a term which includes the reciprocal of the line pitch in the X direction and a term which includes the reciprocal of the line pitch in the Y direction. - View Dependent Claims (4)
-
-
5. An apparatus for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said apparatus comprising:
-
means for obtaining a local spatial density function ρ
(Xi, Yj) (i=1-I, j=1-J) from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling said unknown character at a sampling interval γ
, said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;means for computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;means for computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;means for extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; means for determining new sampling points (Xi, Yj) at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value; andmeans for computing normalized sampled values at said new sampling points (Xi, Yj) by resampling said unknown character or by performing a computation on said two-dimensional pattern f(Xi, Yj), wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the reciprocal of the sum of a term which includes the line pitch in the X direction and a term which includes the line pitch in the Y direction.
-
-
6. An apparatus for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said apparatus comprising:
-
means for obtaining a set of feature parameters from a two-dimensional pattern f(Xi, Yj) (i=1-M, j=1-N) which is obtained by sampling said unknown character at a sampling interval γ
;means for computing a local spatial density function ρ
(Xi, Yj) from said two-dimensional pattern f(Xi, Yj), said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line ditch in the X direction and the line pitch in the Y direction;means for computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;means for computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;means for extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx (X) and hy (Y), respectively; means for matching coordinates of said set of feature parameters and coordinates of said spatial density function ρ
(Xi, Yj); andmeans for determining new sampling points (Xi, Yj) of said set of feature parameters at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(yj) and ε
j takes a second fixed value,wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is a function of the product of the reciprocals of said line pitches in the X and Y directions. - View Dependent Claims (7)
-
-
8. An apparatus for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said apparatus comprising:
-
means for obtaining a set of feature parameters from a two-dimensional pattern f(Xi, Yj) (i=1-M, j=1-N) which is obtained by sampling said unknown character at a sampling interval γ
;means for computing a local spatial density function ρ
(Xi, Yj) from said two-dimensional pattern f(Xi, Yj), said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;means for computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;means for computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;means for extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx (X) and hy (Y), respectively; means for matching coordinates of said set of feature parameters and coordinates of said spatial density function ρ
(Xi, Yj); andmeans for determining new sampling points (Xi, Yj) of said set of feature parameters at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value,wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the sum of a term which includes the reciprocal of the line pitch in the X direction and a term which includes the reciprocal of the line pitch in the Y direction. - View Dependent Claims (9)
-
-
10. An apparatus for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said apparatus comprising:
-
means for obtaining a set of feature parameters from a two-dimensional pattern f(Xi, Yj) (i=1-M, j=1-N) which is obtained by sampling said unknown character at a sampling interval γ
;means for computing a local spatial density function ρ
(Xi, Yj) from said two-dimensional pattern f(Xi, Yj), said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;means for computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;means for computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;means for extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx (X) and hy (Y), respectively; means for matching coordinates of said set of feature parameters and coordinates of said spatial density function ρ
(Xi, Yj); andmeans for determining new sampling points (Xi, Yj) of said set of feature parameters at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value,wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the reciprocal of the sum of a term which includes the line pitch in the X direction and a term which includes the line pitch in the Y direction.
-
-
11. A method for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said method comprising the steps of:
-
obtaining a local spatial density function ρ
(Xi, Yj) (i=1-I, j=1-J) from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling said unknown character at a sampling interval γ
, said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; determining new sampling points (Xi, Yj) at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value; andcomputing normalized sampled values at said new sampling points (Xi, Yj) by resampling said unknown character or by performing a computation on said two-dimensional pattern f(Xi, Yj), wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is a function of the product of the reciprocals of said line pitches in the X and Y directions. - View Dependent Claims (12)
-
-
13. A method for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said method comprising the steps of:
-
obtaining a local spatial density function ρ
(Xi, Yj) (i=1-I, j=1-J) from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling said unknown character at a sampling interval γ
, said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; determining new sampling points (Xi, Yj) at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value; andcomputing normalized sampled values at said new sampling points (Xi, Yj) by resampling said unknown character or by performing a computation on said two-dimensional pattern f(Xi, Yj), wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the sum of a term which includes the reciprocal of the line pitch in the X direction and a term which includes the reciprocal of the line pitch in the Y direction.
-
-
14. A method for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said method comprising the steps of:
-
obtaining a local spatial density function ρ
(Xi, Yj) (i=1-I, j=1-J) from a two-dimensional pattern f(Xi, Yj) which is obtained by sampling said unknown character at a sampling interval γ
, said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from Xi to XI and Yj is fixed;extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; determining new sampling points (Xi, Yj) at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value; andcomputing normalized sampled values at said new sampling points (Xi, Yj) by resampling said unknown character or by performing a computation on said two-dimensional pattern f(Xi, Yj), wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the reciprocal of the sum of a term which includes the line pitch in the X direction and a term which includes the line pitch in the Y direction. - View Dependent Claims (15)
-
-
16. A method for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said method comprising the steps of:
-
obtaining a set of feature parameters from a two-dimensional pattern f(Xi, Yj) (i=1-M, j=1-N) which is obtained by sampling said unknown character at a sampling interval γ
;computing a local spatial density function ρ
(Xi, Yj) from said two-dimensional pattern f(Xi, Yj), said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y). respectively; matching coordinates of said set of feature parameters and coordinates of said spatial density function ρ
(Xi, Yj); anddetermining new sampling points (Xi, Yj) of said set of feature parameters at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value,wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is a function of the product of the reciprocals of said line pitches in the X and Y directions. - View Dependent Claims (17)
-
-
18. A method for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said method comprising the steps of:
-
obtaining a set of feature parameters from a two-dimensional pattern f(Xi, Yj) (i=1-M, j=1-N) which is obtained by sampling said unknown character at a sampling interval γ
;computing a local spatial density function ρ
(Xi, Yj) from said two-dimensional pattern f(Xi, Yj), said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; matching coordinates of said set of feature parameters and coordinates of said spatial density function ρ
(Xi, Yj); anddetermining new sampling points (Xi, Yj) of said set of feature parameters at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value,wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the sum of a term which includes the reciprocal of the line pitch in the X direction and a term which includes the reciprocal of the line pitch in the Y direction.
-
-
19. A method for nonlinear normalization of an image, which performs pre-processing for computing the correlation between an unknown character and a reference pattern, the unknown character being formed of lines and having a line pitch in the X direction and a line pitch in the Y direction, said method comprising the steps of:
-
obtaining a set of feature parameters from a two-dimensional pattern f(Xi, Yj) (i=1-M, j=1-N) which is obtained by sampling said unknown character at a sampling interval γ
;computing a local spatial density function ρ
(Xi, Yj) from said two-dimensional pattern f(Xi, Yj), said spatial density function ρ
(Xi, Yj) being obtained as a correlate of both the line pitch in the X direction and the line pitch in the Y direction;computing an X-direction cumulative function hx(Xi) by successively adding said spatial density function ρ
(Xi, Yj) while Yj is varied from Y1 to YJ and Xi is fixed;computing a Y-direction cumulative function hy(Yj) by successively adding said spatial density function ρ
(Xi, Yj) while Xi is varied from X1 to XI and Yj is fixed;extending said cumulative functions hx(Xi) and hy(Yj) into continuous cumulative functions hx(X) and hy(Y), respectively; matching coordinates of said set of feature parameters and coordinates of said spatial density function ρ
(Xi, Yj); anddetermining new sampling points (Xi, Yj) of said set of feature parameters at new sampling intervals (δ
i, ε
j) in the X and Y directions, the new sampling intervals satisfying the condition that the product of said cumulative function hx(Xi) and δ
i takes a first fixed value, and the product of said cumulative function hy(Yj) and ε
j takes a second fixed value,wherein said correlate of both the line pitch in the X direction and the line pitch in the Y direction is the reciprocal of the sum a term which includes the line pitch in the X direction and a term which includes the line pitch in the Y direction. - View Dependent Claims (20)
-
Specification