JP2010093673A - Image processing apparatus, program and system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus, program and system capable of correcting position deviation of an input document with respect to an original document even if there is eccentricity in distribution of comparison targets in the document. <P>SOLUTION: An image processing apparatus 1 includes: a reference region extraction means 30 for extracting reference regions respectively from an original document 20 and an input document 40; a reference region selection means 32 for selecting the reference region to be used on the basis of distribution of the reference regions extracted from the original document 20 and the input document 40; a reference region corresponding means 33 for letting the reference region selected form the original document 20 corresponding to the reference region selected from the input document 40; a correction coefficient calculation means 34 for calculating a correction coefficient of a correction operation expression to be applied for correcting a position of the input document 40 by comparing a position of the reference region selected from the original document 20 with a position of the reference region selected form the input document 40; and a conversion means 35 for performing correction conversion on the position of the input document on the basis of the correction coefficient and the correction operation expression. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, a program, and a system.

  There is known an image processing apparatus that performs pattern matching between an original document and an input document, and detects a positional deviation from a density density centroid to be compared (for example, see Patent Document 1).

The image processing apparatus of Patent Document 1 detects a comparison target such as a character or a figure from an original document and an input document read by optical scanning or the like, selects a corresponding comparison target, and then compares the density of each comparison target. By calculating the center of gravity, detecting the deviation of the center of gravity, and obtaining a correction formula corresponding to the deviation of the center of gravity, generating a corrected document from the input document by the correction formula, and correcting the positional deviation of the input document with respect to the original document Can do.
Japanese Patent Laid-Open No. 9-245173

  An object of the present invention is to provide an image processing apparatus, a program, and a system that can correct a positional deviation of an input document even when the distribution of comparison targets in the document is biased.

  In order to achieve the above object, one embodiment of the present invention provides the following image processing apparatus, program, and system.

[1] Comparison target extraction means for extracting a comparison target from the original document and the input document, and a comparison target to be used is selected based on the distribution of the positions of the comparison target extracted from the original document and the input document. A comparison object selection means, a corresponding comparison object correspondence means for associating the comparison object selected from the original document with the comparison object selected from the input document, and a position of the comparison object selected from the original document And a correction coefficient calculating means for calculating a correction coefficient of a correction calculation formula to be applied to position correction of the input document by comparing the comparison target position selected from the input document and the correction document and the correction calculation An image processing apparatus comprising: conversion means for performing correction conversion of the position of the input document based on an expression.

[2] Comparison object extraction means for extracting comparison objects from the original document and the input document, correspondence comparison object handling means for associating the comparison object of the original document with the comparison object of the input document, and the original document And comparison object selection means for selecting a comparison object to be used based on the distribution of the comparison object position associated with the input document, the comparison object position selected from the original document, and the input document A correction coefficient calculating means for comparing the selected position to be compared and calculating a correction coefficient of a correction calculation formula to be applied to position correction of the input document; and based on the correction coefficient and the correction calculation formula An image processing apparatus having conversion means for performing correction conversion of the position of an input document.

[3] Comparison object extraction means for extracting comparison objects from the original document and the input document, correspondence comparison object correspondence means for associating the comparison object of the original document with the comparison object of the input document, and the original document And comparing the position of the comparison object associated with the original document and the input document based on the distribution of the position of the comparison object associated with the input document, and applying the comparison to the position of the input document An image processing apparatus comprising: a correction coefficient calculation unit that calculates a correction coefficient of a correction calculation formula to be performed; and a conversion unit that executes correction conversion of the position of the input document based on the correction coefficient and the correction calculation formula.

[4] The comparison target selecting unit divides the original document and the input document into a plurality of divided regions, and uses the comparison document so that the number of the comparison targets included in each divided region is equal to or less than a predetermined number. The image processing apparatus according to [1] or [2], wherein a comparison target to be selected is selected.

[5] The comparison target selecting unit divides the original document and the input document into a plurality of divided regions, and the number of the comparison targets included in each divided region matches the predetermined distribution function. The image processing apparatus according to [1] or [2], wherein a comparison target to be used is selected.

[6] A comparison target extraction step for extracting a comparison target from the original document and the input document, and a comparison target for selecting a comparison target to be used based on the distribution of the comparison target extracted from the original document and the input document A selection step, a comparison object correspondence step for associating the comparison object selected from the original document with the comparison object selected from the input document, the position of the comparison object selected from the original document and the input A correction coefficient calculating step of comparing the position of the comparison target selected from the document and calculating a correction coefficient of a correction calculation expression applied to position correction of the input document; and based on the correction coefficient and the correction calculation expression A conversion step of performing correction conversion of the position of the input document.

[7] A terminal device provided with image information input means for inputting an input document by optically scanning and reading a paper document, and an original document corresponding to the input document and a comparison object for extracting comparison objects from the input document, respectively Extraction means; comparison object selection means for selecting a comparison object to be used based on a distribution of positions of the comparison objects extracted from the original document and the input document; and the comparison object selected from the original document A comparison object corresponding means for associating the comparison object selected from the input document with the position of the comparison object selected from the original document and the position of the comparison object selected from the input document; Correction coefficient calculation means for calculating a correction coefficient of a correction calculation formula applied to position correction of the second document, and the input document based on the correction coefficient and the correction calculation formula The image processing system and a conversion means for performing a correction conversion position.

  According to the first, sixth, or seventh aspect of the invention, it is possible to correct the positional deviation of the input document relative to the original document even when the comparison target distribution in the document is biased.

  According to the second aspect of the present invention, more accurate document misalignment correction can be performed.

  According to the third aspect of the present invention, it is possible to correct the positional deviation of the input document with respect to the original document even when the comparison target distribution in the document is biased.

  According to the invention which concerns on Claim 4, the comparison object used can be selected so that distribution of the comparison object in a document may become uniform.

  According to the invention which concerns on Claim 5, the comparison object used can be selected so that distribution of the comparison object in a document may correspond to a predetermined distribution function.

(Configuration of image processing apparatus)
FIG. 1 is a block diagram showing a configuration example of an image processing apparatus according to the first embodiment of the present invention.

  The image processing apparatus 1 includes a storage unit 2 that is a nonvolatile memory such as an HDD (Hard Disc Drive), a control unit 3 that includes information processing means such as a CPU (Central Processing Unit), an interface circuit, and the like, and optically converts a paper document. The image information input means 4 for inputting the input document 40 by scanning and reading, and the image information output means 5 for outputting the output document by printing on paper or outputting the output document by displaying on the display. And have. The software of the image processing apparatus 1 is operated by a user in an operation unit (not shown). Here, the original document 20 is a document that is an original of the input document 40. Here, the document is information including characters and images such as drawings, image information such as natural images and figures, spreadsheet sheets, word processor documents, and the like, and is in the state of bitmap data. The image processing apparatus 1 and the terminal device may constitute an image processing system by providing the image information input means 4 and the image information output means 5 in a terminal device connected to the image processing device 1 via a network. . The storage unit 2 may be provided in another server device, and a plurality of terminal devices may be installed.

  The storage unit 2 compares the positions of the image processing program 2A for associating the original document 20 with the input document 40, the original document 20 that is the original document of the input document 40, and the original document 20 and the input document 40. And a reference point list 21 that is a list of reference points as one of the comparison targets used in the process. The original document 20 is output as an output document printed on paper by the image information output unit 5. For example, after the user writes characters, graphics, and the like, the original document 20 is read by the image information input unit 4 and the input document 40. Become.

  The control unit 3 extracts a reference area as a comparison target from the original document 20 and the input document 40, and calculates a feature amount of the reference area extracted by the reference area extraction means 30. A reference area that matches between the original document 20 and the input document 40, a quantity calculation means 31, a reference area selection means 32 for selecting a reference area to be used by selecting the reference area extracted by the reference area extraction means 30 A reference area correspondence means 33, a correction coefficient calculation means 34 for calculating a positional deviation of the reference area between the original document 20 and the input document 40, and a correction coefficient based on the reference area, and a correction coefficient calculation means 34. A conversion unit 35 that performs position correction conversion of the input document 40 using the calculated correction coefficient, and a difference extraction unit 36 that extracts a difference between the original document 20 and the input document 40 are included.The control unit 3 functions as the above means by executing the image processing program 2A stored in the storage unit.

  FIG. 2 is a block diagram showing a configuration example of the image processing apparatus according to the first embodiment of the present invention.

  The reference region selection unit 32 extracts a reference point as one of comparison targets such as an intersection or an independent point from the reference region and generates a list, and a reference point list generation unit 32A and a reference in the original document 20 and the input document 40. Reference point distribution calculation means 32B for calculating the distribution of points, reference point number calculation means 32C for calculating the number of reference points used in the divided areas described later, and reference point selection means 32D for selecting the reference points to be used Have.

  FIG. 3 is a schematic diagram showing an example of the contents of a reference point list according to the first embodiment of the present invention.

  The reference point list 21 </ b> A includes a reference point indicated by a symbol, a number, or the like for identifying the reference point, and a position indicated by the coordinates of the reference point.

  FIG. 4 is a schematic diagram showing a configuration example of an original document and an input document according to the first embodiment of the present invention.

  The original document 20 has character strings 21a and 21b arranged on the original document 20, respectively. The input document 40 includes character strings 41a and 41b corresponding to the character strings 21a and 21b, and writing 42 such as characters and figures written by the user.

  FIGS. 5A to 5C are schematic diagrams showing an example of the configuration of an original document according to the first embodiment of the present invention. Here, since the original document and the input document have substantially the same configuration, the original document will be described as a representative.

  As shown in FIG. 5A, the original document 20 has a plurality of divided areas 200 a to 200 f divided by the reference area extracting unit 30.

  As shown in FIG. 5B, the divided area h includes reference areas 201a to 201f extracted by the reference area extracting unit 30 so as to include characters 210a to 210f, for example. The divided regions 200a to 200g have the same configuration.

  As shown in FIG. 5C, the reference area 201a includes connected areas 202a to 202c that include a connected group obtained by further dividing the character 210a. Moreover, each connection area | region 202a-202c has reference points 203a-203c, such as an intersection and an independent point.

(Operation)
The operations of the image processing apparatus and the image processing program according to the embodiment of the present invention will be described below with reference to the drawings.

  FIG. 6 is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention.

  First, the reference area extracting unit 30 converts each of the original document 20 and the input document 40 into, for example, a gray scale and binarizes into white and black (S101). Next, reference regions including characters, graphics, etc. are extracted from the original document 20 and the input document 40 (S102). It is assumed that the operations are executed for the original document 20 and the input document 40 until S105 below.

  Next, the reference area selection unit 32 selects a reference area to be used based on the distribution of the reference area (S103). Details of the operation of S103 will be described later.

  Next, the feature amount calculation means 31 calculates the feature amount of the reference area to be used (S104). As the feature amount, the center of gravity and area of the connected region included in the reference region, the line length obtained by thinning the connected region, the width and height of the circumscribed rectangle of the connected region, and the like are calculated.

  Next, the reference area correspondence unit 33 associates the reference area of the original document 20 with the reference area of the input document 40 based on the calculated feature amount (S105). When associating, the one in which the difference between the feature amounts of the respective reference areas is a certain value or less is selected.

  Next, the correction coefficient calculation unit 34 calculates a correction coefficient that minimizes the positional deviation of the associated reference area (S106), and affine-transforms the input document 40 based on the calculated correction coefficient (S107). ).

The affine transformation is a process for converting the coordinates (x, y) of the input document 40 into the coordinates (X, Y) of the original document 20,
X = ax + by + c
Y = dx + ey + f
Where a to f are affine transformation coefficients, which are the correction coefficients described above.

と表されて、これらをそれぞれａ〜ｆで偏微分して得られた式は誤差の勾配を表すので、それらが０となる場合が誤差の最小値となる。これらの連立一次方程式を解いてアフィン変換係数ａ〜ｆを求める。 For the reference points (x ₁ , y ₁ ), (x ₂ , y ₂ ),... (X _n , y _n ), the reference points (X ₁ , Y ₁ ), (X ₂ , Y ₂ ),. X _n , Y _n ), the sum of the squares of the respective errors is

Since the equations obtained by partial differentiation of these with a to f represent the gradient of the error, the minimum value of the error is when they are zero. These simultaneous linear equations are solved to obtain affine transformation coefficients a to f.

  FIG. 7 is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention, which describes step S103 in FIG. 6 in detail.

  The reference point list creation means 32A of the reference area selection means 32 extracts the reference point coordinates from each reference area and creates the reference point list 21A (S301). Next, the reference point distribution calculating unit 32B calculates the distribution of the reference points based on the reference point list 21A (S302), and determines the number of reference points to be used in each divided region according to the distribution (S303). Next, as many reference points as the determined reference points are selected (S304).

  FIG. 8A is a flowchart showing an example of the operation of the image processing apparatus according to the first embodiment of the present invention, and describes step S302 of FIG. 7 in detail.

  The reference point distribution calculating unit 32B divides each divided area into m × n block areas (S401), and calculates the distribution by counting the number of reference points for each block area (S402).

  FIG. 8B is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention, which is another example in which step S302 of FIG. 7 is described in detail.

  The reference point distribution calculation unit 32B projects the reference points in the X direction and the Y direction (S403), and calculates the distribution by counting the number of reference points for each predetermined section (S404).

  FIG. 9A is a flowchart showing an example of the operation of the image processing apparatus according to the first embodiment of the present invention, and describes step S303 in FIG. 7 in detail.

  The reference point number calculation means 32C determines a fixed value determined in advance according to the distribution calculated in step S302 as the reference point number (S501), and selects the reference point so as to be equal to or less than the fixed value in step S304.

  FIG. 9B is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention, which is another example in which step S303 in FIG. 7 is described in detail.

  The reference point number calculation means 32C calculates statistics such as the maximum value, minimum value, average value, median value, and deviation of the reference points from the number of reference points for each divided region (S502). A predetermined distribution such as Gaussian is determined, and the number of reference points of each divided region is determined based on the distribution (S503).

  FIG. 9C is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention, which is another example illustrating step S303 in FIG. 7 in detail.

  When the minimum value of the number of reference points per divided area is smaller than a predetermined value (S504; No), the reference point number calculating means 32C uses the method shown in FIG. 9A (S505). When the minimum value of the number of reference points is equal to or greater than a predetermined value (S504; Yes), the method shown in FIG. 9B is used (S506).

  FIG. 10A is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention, and is an example in which step S304 of FIG. 7 is described in detail.

  When the number of reference points in the divided area is smaller than the predetermined number determined in step S303 (S601; No), the reference point selection unit 32D sets all the reference points as reference points and uses the predetermined number. When the number of reference points in the divided area is large (S601; Yes), the reference points are deleted from the reference point lists of both the original document 20 and the input document 40 (reference points that do not correspond to each other are deleted from one reference point list. The reference point is deleted) (S602).

  FIG. 10B is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention, which is another example in which step S304 of FIG. 7 is described in detail.

  The reference point sorting and selection unit 32D further divides the divided area into block areas (S603), and calculates the allocation reference number for each block area so that, for example, the reference points are uniformly distributed for each block area. (S604).

  Next, when the number of reference points in the block area is smaller than the predetermined number determined in step S604 (S605; No), the reference point selection means 32D is determined in advance as a reference point that uses all the reference points. If the number of reference points in the block area is larger than the determined number (S605; Yes), the reference points are deleted from the reference point lists of both the original document 20 and the input document 40 (one of the reference points that do not correspond to each other) The reference point is deleted from the point list) (S606).

[Second Embodiment]
FIG. 11 is a schematic diagram showing an example of the contents of a reference point list according to the second embodiment of the present invention.

  The reference point list 21B includes a reference point indicated by a symbol or a number to identify the reference point, a center of gravity of the connected area including the reference point, an area, a line length obtained by thinning the connected area, and a circumscribed rectangle of the connected area. A feature amount such as a width and a height, and a position indicated by coordinates of the position of the reference point are configured.

  FIG. 12 is a flowchart showing an operation example of the image processing apparatus according to the second embodiment of the present invention.

  First, the reference area extracting unit 30 converts each of the original document 20 and the input document 40 into, for example, a gray scale and binarizes into white and black (S201). Next, reference regions including characters, graphics, etc. are extracted from the original document 20 and the input document 40 (S202). It is assumed that the operations are executed on the original document 20 and the input document 40 until S205 below.

  Next, the feature amount calculation means 31 calculates the feature amount of the reference area (S203). Next, the reference area correspondence unit 33 associates the reference area of the original document 20 with the reference area of the input document 40 based on the calculated feature amount (S204). When associating, the one in which the difference between the feature amounts of the respective reference areas is a certain value or less is selected.

  Next, the reference area selection unit 32 selects the reference area based on the distribution of the reference area (S205). Note that the details of the operation of S205 apply the operations of FIGS. 7 to 10B described above.

  Next, the correction coefficient calculation unit 34 calculates a correction coefficient that minimizes the positional deviation of the associated reference area (S206), and affine-transforms the input document 40 based on the calculated correction coefficient (S207). ).

[Third Embodiment]
FIG. 13 is a schematic diagram showing an example of the contents of a reference point list according to the third embodiment of the present invention.

  The reference point list 21 </ b> C includes the reference points described in the reference point list 21 </ b> B, feature amounts, and positions, and weighting coefficients that are multiplied by correction coefficients used for affine transformation.

  FIG. 14 is a flowchart showing an operation example of the image processing apparatus according to the third embodiment of the present invention.

  First, the reference area extracting unit 30 converts each of the original document 20 and the input document 40 into, for example, a gray scale and binarizes into white and black (S701). Next, reference regions including characters, figures, etc. are extracted from the original document 20 and the input document 40 (S702). It is assumed that the operations are executed for the original document 20 and the input document 40 until S704 below.

  Next, the feature amount calculation unit 31 calculates the feature amount of the reference region (S703). Next, the reference area correspondence unit 33 associates the reference area of the original document 20 with the reference area of the input document 40 based on the calculated feature amount (S704). When associating, the one in which the difference between the feature amounts of the respective reference areas is a certain value or less is selected.

  Next, the correction coefficient calculation unit 34 calculates a weighting coefficient for the reference area based on the distribution of the reference area (S705). Details of the operation in S705 will be described later.

から対応づけられた基準領域の位置ずれが最小となるような補正係数を算出し（Ｓ７０６）、得られた補正係数に基づいて入力文書４０をアフィン変換する（Ｓ７０７）。なお、ここで、重み付け係数ｗ_ｉを０又は１のいずれかから選択し、第１の実施の形態又は第２の実施の形態における方法と同一の方法を実施してもよい。 Next, the correction coefficient calculation means 34 is an affine transformation formula obtained by multiplying the calculated weighting coefficient w _i .

A correction coefficient that minimizes the positional deviation of the reference region associated with the input document 40 is calculated (S706), and the input document 40 is affine transformed based on the obtained correction coefficient (S707). Here, the weighting coefficient w _i may be selected from either 0 or 1, and the same method as the method in the first embodiment or the second embodiment may be performed.

  FIG. 15 is a flowchart showing an operation example of the image processing apparatus according to the third embodiment of the present invention, and describes step S705 in FIG. 14 in detail.

  The correction coefficient calculation unit 34 creates a reference point list for each divided region (S801), and calculates a distribution of reference points (S802). For the reference points included in the divided areas with a large number of reference points, the weighting coefficient to be multiplied by the correction coefficient is reduced, and for the reference points included in the divided areas with a small number of reference points, the weighting coefficient to be multiplied by the correction coefficient is increased. As described above, a weight is assigned to the square of the positional deviation between the original document 20 and the input document 40 at each reference point (S803). The weighting calculates a coefficient that makes the distribution uniform by multiplying the distribution, and a coefficient that makes the distribution become a predetermined distribution by multiplying the distribution.

  FIG. 16 is a flowchart showing an operation example of the image processing apparatus according to the third embodiment of the present invention, and describes step S803 in FIG. 15 in detail.

  The correction coefficient calculation means 34 calculates a weighting coefficient from the number of reference points in the divided area as described above (S901), and adds the weighting coefficient to the reference point list 21C (S902). When a weighting coefficient is added to all the reference points in the reference point list, the process ends (S903).

[Other embodiments]
The present invention is not limited to the above embodiment, and various modifications can be made without departing from the spirit of the present invention.

  In addition, the reference area extraction means 30, the feature amount calculation means 31, the reference area selection means 32, the reference area correspondence means 33, the correction coefficient calculation means 34, the conversion means 35, and the difference extraction means 36 used in the above embodiment are: It may be read from a storage medium such as a CD-ROM into a storage unit in the apparatus, or may be downloaded from a server apparatus connected to a network such as the Internet to the storage unit in the apparatus. Moreover, you may implement | achieve part or all of the means used by the said embodiment by hardware, such as ASIC.

1 is a block diagram illustrating a configuration example of an image processing device according to a first embodiment of the present invention. 1 is a block diagram illustrating a configuration example of an image processing device according to a first embodiment of the present invention. It is the schematic which shows the example of the content of the reference point list which concerns on the 1st Embodiment of this invention. It is the schematic which shows the structural example of the original document and input document which concern on the 1st Embodiment of this invention. (A)-(c) is the schematic which shows the structural example of the original document in the 1st Embodiment of this invention. 3 is a flowchart showing an operation example of the image processing apparatus according to the first embodiment of the present invention. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 1st Embodiment of this invention, and demonstrated step S103 of FIG. 6 in detail. 7 is a flowchart illustrating an operation example of the image processing apparatus according to the first exemplary embodiment of the present invention, and illustrates step S302 in FIG. 7 in detail. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 1st Embodiment of this invention, and is the other example which demonstrated step S302 of FIG. 7 in detail. 7 is a flowchart illustrating an operation example of the image processing apparatus according to the first exemplary embodiment of the present invention, and illustrates step S303 in FIG. 7 in detail. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 1st Embodiment of this invention, and is the other example which demonstrated step S303 of FIG. 7 in detail. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 1st Embodiment of this invention, and is the other example which demonstrated step S303 of FIG. 7 in detail. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 1st Embodiment of this invention, and is an example which demonstrated step S304 of FIG. 7 in detail. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 1st Embodiment of this invention, and is the other example which demonstrated step S304 of FIG. 7 in detail. It is the schematic which shows the example of the content of the reference point list which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 2nd Embodiment of this invention. It is the schematic which shows the example of the content of the reference point list which concerns on the 3rd Embodiment of this invention. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 3rd Embodiment of this invention. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 3rd Embodiment of this invention, and demonstrated step S705 of FIG. 14 in detail. It is a flowchart which shows the operation example of the image processing apparatus which concerns on the 3rd Embodiment of this invention, and demonstrated step S803 of FIG. 15 in detail.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Image processing apparatus, 2 ... Memory | storage part, 2A ... Image processing program, 3 ... Control part, 4 ... Image information input means, 5 ... Image information output means, 20 ... Original document, 21a, 21b ... Character string, 21 ... Reference point list, 21A to 21C ... reference point list, 30 ... reference area extraction means, 31 ... feature amount calculation means, 32 ... reference area selection means, 32A ... reference point list creation means, 32B ... reference point distribution calculation means, 32C ... Reference point calculation means, 32D... Reference point selection and selection means, 33... Reference area correspondence means, 34... Correction coefficient calculation means, 35... Conversion means, 36 ... Difference extraction means, 40 ... Input document, 41a, 41b. , 42 ... write, 200a-200f ... divided area, 201a-201f ... reference area, 202a-202c ... connected area, 203a-203c ... reference point, 210a-210f ... character

Claims (7)

Comparison object extraction means for extracting comparison objects from the original document and the input document,
Comparison target selection means for selecting a comparison target to be used based on the distribution of the position of the comparison target extracted from the original document and the input document;
A comparison object corresponding means for associating the comparison object selected from the original document with the comparison object selected from the input document;
The comparison target position selected from the original document is compared with the comparison target position selected from the input document, and a correction coefficient of a correction calculation formula applied to position correction of the second document is calculated. Correction coefficient calculation means for
An image processing apparatus comprising: conversion means for performing correction conversion of the position of the input document based on the correction coefficient and the correction calculation formula. Comparison object extraction means for extracting comparison objects from the original document and the input document,
A comparison object corresponding means for associating the comparison object of the original document with the comparison object of the input document;
Comparison target selection means for selecting a comparison target to be used based on the distribution of the position of the comparison target associated in the original document and the input document;
The comparison target position selected from the original document is compared with the comparison target position selected from the input document, and a correction coefficient of a correction calculation formula applied to position correction of the second document is calculated. Correction coefficient calculation means for
An image processing apparatus comprising: conversion means for executing position correction conversion of the input document based on the correction coefficient and the correction calculation formula. Comparison object extraction means for extracting comparison objects from the original document and the input document,
A comparison object corresponding means for associating the comparison object of the original document with the comparison object of the input document;
Based on the distribution of the comparison target associated with the original document and the input document, the position of the second document is compared by comparing the position of the comparison target associated with the original document and the input document. Correction coefficient calculating means for calculating a correction coefficient of a correction arithmetic expression applied to correction;
An image processing apparatus comprising: conversion means for executing position correction conversion of the input document based on the correction coefficient and the correction calculation formula.   The comparison target selection unit divides the original document and the input document into a plurality of divided areas, and uses the comparison target to be used so that the number of comparison targets included in each divided area is equal to or less than a predetermined number. The image processing apparatus according to claim 1, wherein the image processing apparatus is selected.   The comparison target selecting unit divides the original document and the input document into a plurality of divided regions, and uses the comparison so that the number of the comparison targets included in each divided region matches a predetermined distribution function. The image processing apparatus according to claim 1, wherein a target is selected. A comparison object extraction step for extracting a comparison object from the original document and the input document,
A comparison target selection step of selecting a comparison target to be used based on the distribution of the comparison target extracted from the original document and the input document;
A comparison object corresponding step for associating the comparison object selected from the original document with the comparison object selected from the input document;
Correction for calculating a correction coefficient of a correction arithmetic expression applied to position correction of the input document by comparing the position of the comparison target selected from the original document and the position of the comparison target selected from the input document A coefficient calculation step;
An image processing program comprising: a conversion step of executing position correction conversion of the input document based on the correction coefficient and the correction calculation formula. A terminal device provided with image information input means for inputting an input document by optically scanning and reading a paper document;
A comparison object extracting means for extracting a comparison object from each of the original document corresponding to the input document and the input document;
Comparison target selection means for selecting a comparison target to be used based on the distribution of the position of the comparison target extracted from the original document and the input document;
A comparison object corresponding means for associating the comparison object selected from the original document with the comparison object selected from the input document;
The comparison target position selected from the original document is compared with the comparison target position selected from the input document, and a correction coefficient of a correction calculation formula applied to position correction of the second document is calculated. Correction coefficient calculation means for
An image processing system comprising: conversion means for executing correction conversion of the position of the input document based on the correction coefficient and the correction calculation formula.

Images