JP2009033448A - Image processing system and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing system constituted so that deterioration of reproducibility is suppressed even when binarization processing is performed to an image area in which density in an image is not uniform. <P>SOLUTION: The detection means of the image processing system detects a value regarding a state that the density of the image area does not become uniform by performing a plurality of binarization processing to the image area, and a density correction means performs density correction of the image area on the basis of the value regarding the state that the density of the image area detected by the detection means does not become uniform. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

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

  A person may add a pencil to a document printed using a printer. Furthermore, there is a technique in which a document added with a pencil is read by a scanner and printed using a printer. Note that the image region added with a pencil is an example of an image region in which the density in the image is not uniform (a so-called uneven image region). As an image area having unevenness, there is an image area such as a seal impression in addition to an image area written with a pencil.

  As a technique related to this, for example, Patent Document 1 discloses that, in a color copying machine or the like, it is an object to improve reproduction image quality of low-contrast characters such as pencil-written characters, characters on light colors, and the like. The judgment circuit separates the black character edge area, the color character edge area, and the pattern area, and the contrast judgment circuit detects the low contrast area. The image data processing circuit system performs processing corresponding to the type of each separated image area. However, even if the region is a black character edge region by image region separation, the remaining color removal processing is not applied to the region determined by the contrast determination circuit as the low contrast region, and the input C, M, Y, K By applying color character edge area processing that inputs data as it is, the connection of low-contrast character lines becomes smoother. It is disclosed that enables reproduction image with less.

  Further, for example, Patent Document 2 has an object to provide an image processing technique capable of appropriately binarizing each object in a multi-valued image, and binarizes the binarization processing of the multi-valued image. An image processing apparatus including a binarization unit including a plurality of binarization functions, wherein the pixel-of-interest data is an edge pixel constituting an edge portion of an object included in the multi-valued image or a pixel in the object A binarization processing determination unit that determines whether the pixel is an in-edge pixel or a background pixel that constitutes a background region, and the selector unit includes the plurality of 2's depending on which pixel the pixel-of-interest data is. It is disclosed that the valuation function is switched and used.

Further, for example, Patent Document 3 aims to increase the detection rate of light and thin characters in a character image and to obtain a printed matter with good image quality. The first feature amount of a pixel of interest in the character image Density enhancement processing for a pixel of interest whose second feature value is larger than a mountain determination threshold value, first calculation means for calculating the first feature value, second calculation means for calculating a second feature value from the first feature value, An image processing apparatus including a character image processing unit having density emphasizing means for performing image processing, background density calculation means for setting a mountain determination threshold corresponding to the background density of the document, and mountain determination threshold setting means is disclosed. ing.
JP 2001-223912 A JP 2005-311991 A JP 2003-051948 A

Incidentally, when binarization is performed after density adjustment called uniform density addition is performed on an image area in which the density in the image is not uniform, particularly an image area in which there is an excessive difference in density, that 2 When a valuated image is printed, information on a light portion in the image is lost.
In the present invention, when binarization is performed on an image area in which the density in the image is not uniform, the pixel value of the light portion in the image is so low that the density adjustment such as uniform density addition cannot be handled. Even so, an object of the present invention is to provide an image processing system and an image processing program capable of suppressing the loss of information.

The gist of the present invention for achieving the object lies in the inventions of the following items.
According to the first aspect of the present invention, a plurality of binarization processes are performed on an image area, thereby detecting a value related to a state in which the density of the image area is not uniform, and the detection means. An image processing system comprising: density correction means for correcting the density of the image area based on a value relating to a state where the density of the detected image area is not uniform.

  The invention according to claim 2 of the present application is characterized in that the detection means detects a value related to a state in which the density of the image area is not uniform, according to the difference in the number of areas generated by the binarization processing. The image processing system according to claim 1.

  The invention according to claim 3 of the present application is characterized in that the detecting means detects a value relating to a state in which the density of the image area is not uniform, according to the difference in the number of black pixels generated by the binarization processing. The image processing system according to claim 1.

  In the invention according to claim 4 of the present application, the detection means determines a value relating to a state in which the density of the image area is not uniform according to the difference in the number of areas and the difference in the number of black pixels generated by the binarization process. The image processing system according to claim 1, wherein the image processing system is detected.

  In the invention according to claim 5, the shading correction unit applies a filter in which a parameter is adjusted based on a value relating to a state where the shading of the image region detected by the detecting unit is not uniform to the image region. The image processing system according to claim 1, wherein shading correction is performed.

  The invention according to claim 6 is characterized in that the density correction means prepares a plurality of types of density correction according to the purpose, and can select the density correction according to the operation of the operator. The image processing system according to claim 1.

  The invention according to claim 7 of the present application provides a detection means for detecting a value relating to a state in which the density of the image area is not uniform by performing a plurality of binarization processes on the image area, and An image processing program that functions as a density correction unit that performs density correction of an image area based on a value related to a state in which the density of the image area detected by the detection unit is not uniform.

  According to the image processing system of claim 1, when binarization is performed on an image area in which the density in the image is not uniform, the pixel value of the light portion in the image is subjected to density adjustment in which uniform density addition is performed. Even if it is so low that it is impossible to cope with, it is possible to suppress the loss of information.

  According to the image processing system of the second aspect, it is possible to use the increase / decrease in the number of areas generated by a plurality of binarization processes suitable as an index relating to a state where the density of the image area is not uniform.

  According to the image processing system of the third aspect, it is possible to use the increase / decrease in the number of black pixels caused by a plurality of binarization processes suitable as an index relating to a state where the density of the image area is not uniform.

  According to the image processing system of claim 4, in the case where the present embodiment does not have a configuration for detecting a value relating to a state in which the density of the image area is not uniform in order to suppress the lack of information of the light portion in the image. In comparison, it can be performed more precisely.

  According to the image processing system of the fifth aspect, it is possible to perform light / dark correction suitable for suppressing deterioration in reproducibility.

  According to the image processing system of the sixth aspect, it is possible to reproduce the image area according to the intention of the operator.

  According to the image processing program of claim 7, when binarization is performed on an image area in which the density in the image is not uniform, the pixel value of the light portion in the image is subjected to density adjustment in which uniform density addition is performed. Even if it is so low that it is impossible to cope with, it is possible to suppress the loss of information.

Hereinafter, an example of a preferred embodiment for realizing the present invention will be described with reference to the drawings.
First, an outline of the present embodiment will be described. When a multi-valued image is binarized, “a chip” is generated due to the influence of an image region with uneven shading, in which a portion that would otherwise be reproduced is lost. The degree of “missing” is calculated as a “state value” obtained by quantification. Then, the shading of the uneven image region is corrected according to the state value.

FIG. 1 shows a conceptual module configuration diagram of a configuration example of the present embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment also serves as an explanation of a computer program, a system, and a method. However, for convenience of explanation, the words “store”, “store”, and the equivalent are used. However, when the embodiment is a computer program, these words are controlled to be stored in the storage device. Is to do. In addition, the modules correspond almost one-to-one with the functions. However, in mounting, one module may be composed of one program, or a plurality of modules may be composed of one program. A plurality of programs may be used. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. In the following, “connection” includes not only physical connection but also logical connection (data exchange, instruction, reference relationship between data, etc.).
In addition, the system or device is configured by connecting a plurality of computers, hardware, devices, and the like by communication means such as a network (including one-to-one correspondence communication connection), etc., and one computer, hardware, device. The case where it implement | achieves by etc. is also included.

As shown in FIG. 1, the present embodiment includes an object separation module 110, a state value detection module 120, a density correction module 130, and a binarization module 140. In addition, although there exists a state value or flatness as a value regarding a state value, in the following embodiment, it demonstrates using a state value mainly.
The object separation module 110 is connected to the state value detection module 120, extracts a target image area (hereinafter also referred to as an object) from the received image, and passes the extracted image area to the state value detection module 120. . Here, accepting an image means reading out an image stored in a hard disk (including those connected to the computer in addition to those built in the computer) or the like, or inputting by a scanner or the like Received images, receiving images by fax, and the like. The image here is a digital multi-valued image, and includes a single color (including only black) and a color image. The image area (object) refers to an image area in which the density in the image is not uniform, for example, an image area written in pencil, an image area of an imprint, and the like. As a method of extracting the target area, a character area is extracted by layout recognition (a technique for recognizing a character area, a photographic area, a graphic area, etc. from an image, regardless of the technique), or by a user operation. Depending on the embodiment, an area to be processed may be extracted. A plurality of objects may be extracted.

The state value detection module 120 is connected to the object separation module 110 and the density correction module 130, and includes a multiple threshold value determination module 121, a region number difference calculation module 122, a black pixel number difference calculation module 123, and a state value calculation module 124. is doing.
The state value detection module 120 receives an object from the object separation module 110, detects a state value representing a state in which the density of the image area is not uniform for each object, and detects the detected state value as a density correction module 130. To pass.
The state value detection module 120 performs a plurality of binarization processes on the image to detect a state value representing a state where the density of the image is not uniform. Furthermore, the state value may be detected according to the difference in the number of areas generated by the binarization process. The state value may be detected according to the difference in the number of black pixels generated by the binarization process. The state value may be detected according to the difference in the number of regions and the difference in the number of black pixels generated by the binarization process.

More specifically, the multiple threshold determination module 121 determines a plurality of thresholds for binarizing the image. Then, the image is binarized using the plurality of threshold values.
The area number difference calculation module 122 counts the number of areas from the binarized image by the multiple threshold value determination module 121, and calculates the difference in the number of areas.
The black pixel number difference calculation module 123 counts the number of black pixels from the binarized image by the multiple threshold value determination module 121, and calculates the difference in the number of black pixels.
The state value calculation module 124 calculates the state value of the image using the difference in the number of regions calculated by the region number difference calculation module 122 and the difference in the number of black pixels calculated by the black pixel number difference calculation module 123. .

The density correction module 130 is connected to the state value detection module 120 and the binarization module 140, and includes a morphological filter module 131, a simple smoothing module 132, and a selection module 133.
The gradation correction module 130 receives the state value from the state value detection module 120, performs gradation correction of the image based on the state value, and passes the density corrected image to the binarization module 140. Further, a morphological filter based on the state value detected by the state value detection module 120 may be applied to the image to perform density correction. The shading correction module 130 may prepare a plurality of types of shading correction, and may select the type of shading correction according to the operation of the operator.

More specifically, the morphological filter module 131 determines the parameters of the morphological filter for performing image density correction according to the state value. For example, processing that fills in unevenness in the density of an image is performed using three-dimensional expansion and contraction. If the state value is large, the range of expansion and contraction of the morphological filter is increased, and if the state value is small, the range of expansion and contraction is decreased. In other words, if the state value is greater than or equal to a certain threshold, the parameter is adjusted so as to increase the influence range of the filter. If the state value is less than the certain threshold, the parameter is set so that the influence range of the filter is further reduced. Adjust.
The simple smoothing module 132 performs image shading correction by simple smoothing processing according to the state value.
The selection module 133 can select density correction by the morphological filter module 131 and density correction by the simple smoothing module 132 according to the purpose of the desired image quality in accordance with the operation of the operator.

  The binarization module 140 is connected to the shading correction module 130, receives the shading corrected image from the shading correction module 130, and performs binarization processing. That is, binarization is performed using a grayscale image in which unevenness of grayscale of the image is filled. By filling the shading unevenness, the binarized image is in a state where the lines that must be connected are cut even if the image area has shading unevenness (an image area having a so-called sensation) The image area becomes a single connected line. In addition, the existing method is used for the binarization method here.

A processing example according to this exemplary embodiment will be described with reference to the flowchart shown in FIG.
In step S201, the object separation module 110 extracts an object from the received image.
In step S202, the state value detection module 120 receives the object extracted in step S201 and detects the state value of the object. Details will be described with reference to FIG.
In step S203, the shading correction module 130 receives the state value detected in step S202, and performs shading correction of the object according to the state value.
In step S204, the binarization module 140 receives the object whose density has been corrected in step S203, and binarizes the image.
Then, the binarized image is stored in a storage device, compressed, character recognition, displayed on a display, printed, and the like.

With reference to the flowchart shown in FIG. 3 and FIG. 4, the processing example of step S202 in the flowchart of FIG. 2 will be described in more detail.
In step S301, the multiple threshold value determination module 121 determines a threshold value for binarization. The threshold value here may be a unique threshold value for an image determined from the statistics (average, variance, etc.) of the image of the object, or may be a binarization threshold value that differs for each pixel such as floating binarization. In the latter case, a binarization threshold value is stored for each pixel.
FIG. 4A shows an example of the density value of one line of the image in the object. The horizontal axis represents the pixel position, and the vertical axis represents the density value. The maximum density value is max, and the minimum density value is min.

隣接する閾値の差分を一定としてもよいし、ある規則に基づいた差分としてもよい。また、ＴＨＤ_０の上下に同数の閾値としたが、異なる数であってもよい。
図４（Ａ）は、数１の閾値列を記入したものである。つまり、基準閾値であるＴＨＤ_０の上下にＮ個の閾値を記入している。 In step S302, the multiple threshold determination module 121 determines a plurality of binarization thresholds in a predetermined range up and down with the threshold determined in step S301 as a reference. For example, if the reference threshold value is THD ₀ , 2N threshold values are determined. That is, a threshold string as shown in Equation 1 is created.

The difference between adjacent threshold values may be constant, or may be a difference based on a certain rule. Further, although the same number of threshold values are set above and below THD ₀ , they may be different numbers.
FIG. 4 (A) is the one in which the threshold string of Formula 1 is entered. That is, fill in the N threshold and below the THD ₀ is the reference threshold.

図４（Ｂ）は、それぞれの閾値で２値化した画像をそれぞれ表したものである。例えば、Ｂ_０の画像は、図４（Ａ）のＴＨＤ_０以上の部分を黒画素としたものである（図４（Ａ）と図４（Ｂ）をつなぐ点線参照）。 In step S303, the multiple threshold determination module 121 creates a plurality of binarized images using the multiple thresholds determined in step S302.
In the case where the threshold value is a threshold value sequence as shown in Equation 1, the binarized image corresponding to each is assumed to be Equation 2. B is an acronym for Binary (binary image).

FIG. 4B shows images binarized with respective threshold values. For example, the image of B ₀ is a black pixel in the portion of THD ₀ or higher in FIG. 4A (see the dotted line connecting FIG. 4A and FIG. 4B).

図４（Ｂ）の例では、小領域数は、Ｂ_Ｎでは３個、Ｂ_０では８個、Ｂ_−Ｎでは４個である。 In step S304, the region number difference calculation module 122 counts the number of connected small regions from the plurality of binarized images created in step S303. For this counting, a labeling method may be used.
For example, when the binarized image is Equation 2, the number of small regions corresponding to each is Equation 3. Note that L is an acronym for Label (label image).

In the example of FIG. 4 (B), the small number of regions, the _{B N} 3 pieces, _B 8 pieces in _0, is four in _{B -N.}

そして、差分の列は、数５のようになる。

In step S305, the number-of-regions difference calculation module 122 calculates a difference between adjacent binarized images of the plurality of small regions counted in step S304. That is, the difference LD is calculated using Equation 4.

The difference column is as shown in Equation 5.

In step S306, the black pixel number difference calculation module 123 counts black pixels in the image from the plurality of binarized images created in step S303.
For example, when the binarized image is represented by Equation 2, the number of black pixels corresponding to each is represented by Equation 6. Note that P is an acronym for Pixel (pixel).

そして、差分の列は、数８のようになる。

In step S307, the black pixel number difference calculation module 123 calculates a difference between adjacent binarized images of the plurality of black pixels counted in step S306. That is, the difference LD is calculated using Equation 7.

The difference column is as shown in Equation 8.

  In step S308, the state value calculation module 124 calculates the state value using Equations 4 and 7. Here, as the state value, (1) a state value LL using the difference in the number of regions and (2) a state value PL representing unevenness in the density direction are obtained.

つまり、ＬＡが大きいということは、閾値に応じて２値化した領域の増減が激しいことを意味する。すなわち、ムラがあることになり、状態値は大きい。
ここで、劣化が一番大きい状態となるのは、ｉ＝１〜Ｎの間で、領域が無い状態から、隣の閾値にしたことによって複数の領域が急激に出現して、逆に、隣の閾値にしたことによってその領域が急激に消滅してしまう場合である。つまり、１画素おきに１画素の領域が急激に出現し、急激に消滅する場合である。すなわち、全画素数の１／４の数の領域が急激に出現し、急激に消滅する場合である。したがって、状態値ＬＬの取り得る最大値ＬＡ_ｍａｘは、数１１のようになる。

なお、ここでの全画素数とは、オブジェクト内の全ての画素数である。
数１１より、状態値ＬＬは、数１２によって求められる。なお、状態値ＬＬは、０．０より大であり、１．０未満の値となる。

ここで、状態値ＬＬとは逆の意を表す平坦度ＬＳは、数１３のように表すことができる。なお、平坦度ＬＳは、０．０より大であり、１．０未満の値となる。以下、状態値ＬＬの代わりに平坦度ＬＳを用いてもよい。ただし、その場合、状態値ＬＬが大であることを平坦度ＬＳが小であると読み替えるものとする。

(1) State value LL using the difference in the number of regions
Equation 4 is used. Then, LA (average value of differences in the number of small areas) is calculated using Equation 9.

That is, a large LA means that the increase / decrease of the binarized region according to the threshold is severe. That is, there will be unevenness and the state value is large.
Here, the state with the greatest deterioration is between i = 1 to N, a plurality of regions suddenly appear when the adjacent threshold value is set from a state where there is no region, and conversely, This is a case where the region disappears rapidly due to the threshold value of. That is, this is a case where a region of one pixel appears suddenly and disappears rapidly every other pixel. That is, a region that is 1/4 of the total number of pixels suddenly appears and disappears rapidly. Therefore, the maximum value LA _max that can be taken by the state value LL is expressed by Equation 11.

Here, the total number of pixels is the total number of pixels in the object.
From Equation 11, the state value LL is obtained by Equation 12. Note that the state value LL is greater than 0.0 and less than 1.0.

Here, the flatness LS representing the opposite of the state value LL can be expressed as in Expression 13. The flatness LS is greater than 0.0 and less than 1.0. Hereinafter, the flatness LS may be used instead of the state value LL. However, in that case, the state value LL being large is read as the flatness LS being small.

つまり、ＰＡが大きいということは、閾値に応じて黒画素の増加又は減少が激しいことを意味しており、閾値に応じて２値化画像がばたついていないこととなる。すなわち、濃度方向のムラがないことであり、状態値は小さい。
ここで、黒画素の変動が一番大きい状態となるのは、ｉ＝１〜Ｎの間で、全てが白画素の状態から、全画素が急激に黒画素になる場合、逆に、全てが黒画素の状態から、全画素が白画素になる場合である。したがって、平坦度ＰＳの取り得る最大値ＰＳ_ｍａｘは、数１４のようになる。

数１４より、平坦度ＰＳは、数１５によって求められる。なお、平坦度ＰＳは、０．０より大であり、１．０未満の値となる。

ここで、濃度方向の状態値ＰＬは、数１６のように定義できる。なお、状態値ＰＬは、０．０より大であり、１．０未満の値となる。

(2) State value PL representing unevenness in density direction
First, before obtaining the state value PL, a flatness PS representing the flatness in the density direction is calculated.
Equation 7 is used. Then, PA (average value of the difference in the number of black pixels) is calculated using Equation 10.

That is, a large PA means that the increase or decrease of black pixels is intense according to the threshold value, and the binarized image does not flutter according to the threshold value. That is, there is no unevenness in the density direction, and the state value is small.
Here, the fluctuation of the black pixel is the largest when i = 1 to N, and when all the pixels suddenly become black pixels from the state of all white pixels, conversely, This is a case where all pixels are white pixels from the black pixel state. Therefore, the maximum value PS _max that the flatness PS can take is as shown in Equation 14.

From Equation 14, the flatness PS is obtained by Equation 15. The flatness PS is greater than 0.0 and less than 1.0.

Here, the state value PL in the density direction can be defined as in Expression 16. Note that the state value PL is greater than 0.0 and less than 1.0.

Two types of processing examples in step S203 in the flowchart of FIG. 2 will be described in more detail with reference to FIGS.
FIG. 5 is a conceptual diagram for explaining a first processing example of density correction. This is used to obtain a binarized image that reproduces the original image as faithfully as possible. A morphological filter is applied to the density correction here.
First, the constituent elements of the morphological filter as a base are determined.
The image B ₀ when binarization is performed with the reference threshold THD ₀ is used. Specifically, the original signal 501 in FIG. 5A is a graph of the density value of one line in the object, as in FIG. 4, and is an image when binarization is performed with the reference threshold value THD _0. B ₀ is illustrated below. The number of areas here is eight.

A label having the largest area in the image B ₀ is referred to, and a circumscribed rectangle including the label is calculated. Specifically, this is the third region from the left in FIG.
The radius r0 of the largest circle that can be taken in the circumscribed rectangle is set as the adaptive range r of the constituent elements of the morphological filter. Alternatively, the adaptive range may be similarly obtained in an unlabeled region, or an average value of both may be used.
The initial weight w of the morphological filter components is set to r0. Here, the shape of the basic component is assumed to be a dome shape as shown in FIG.

ただし、αは、操作者が指定する、又はある規則に従って算出するようにしてもよい。例えば、近傍の領域までの距離の平均等を利用して算出するようにしてもよい。 When the state value LL is small, the adaptive range of the component is narrowed, and when the state value LL is large, the adaptive range of the component may be widened. That is, as shown in Equation 17, the adaptive range r is determined according to the state value LL. Conceptually, as shown in FIG. 5C, the radius of the lower surface of the dome is adjusted.

However, α may be specified by an operator or calculated according to a certain rule. For example, the calculation may be performed using an average of distances to nearby regions.

ただし、βは、操作者が指定する、又はある規則に従って算出するようにしてもよい。例えば、対象領域内での最大値とＴＨＤ_０との差分を利用して算出するようにしてもよい。 When the state value PL in the density direction is small, the weight of the component is increased, and when the state value PL is large, the weight of the component is decreased. That is, as shown in Equation 18, the adaptive range r is determined according to the state value PL. Conceptually, as shown in FIG. 5C, the height of the dome is adjusted.

However, β may be specified by an operator or calculated according to a certain rule. For example, the difference between the maximum value in the target area and THD ₀ may be used for calculation.

  The shape of the morphological filter is a dome-shaped component, but this is not particular. Moreover, although the deformation | transformation of the component was performed linearly, it does not stick to this.

  Next, based on the deformed component, density correction is performed by performing a closing process, which is a morphological filter process. Further, an opening process may be used instead of the closing process. The closing process is a process for connecting the upper ends of the graph (so-called filling process) as shown in the corrected signal 502 in FIG. 5A, and the opening process is the reverse of FIG. ) To connect the lower end of the graph of the original signal 501.

  FIG. 6 is a second processing example of the light / dark correction, and is a conceptual diagram for explaining a plurality of light / dark correction examples. This is also intended to reflect the operator's intention. For example, depending on the operator, there are purposes (including requests) such as “I want you to correct shading while leaving the pencil like,” and “I want you to make the shading uniform.” This is to cope with these.

The following two types of shading correction are performed, and they are combined (blended) according to the operator's request.
(1) Light / dark correction 1: Light / dark correction by the above-described morphological filter This is light / dark correction for a request that “a light / dark correction should be made while retaining the pencil likeness”. Specifically, the original signal 601 is changed to a correction 1 signal 602 as shown in FIG.
(2) Light / dark correction 2: Light / dark correction by simple smoothing This is a light / dark correction for the desire to “make sure the light and dark are uniform”. You may calculate the average value of all the pixels which have a density value. Alternatively, the smoothing filter range may be calculated from the state value LL and partially smoothed, such as the adaptive range of the components used in the density correction of the morphological filter. Specifically, the original signal 601 is changed to a correction 2 signal 603 as shown in FIG.
Next, in accordance with the operation of the operator, for example, a preference is specified with a UI slide bar or the like, and the signals (1) and (2) (the correction 1 signal 602 and the correction 2 signal 603) are blended. . What is blended 50 to 50 is a blend signal 604 shown in FIG.
Furthermore, a TRC (Tone Reproduction Curve: tone reproduction curve) that raises the shading may be applied to the signal after blending. Specifically, the signal is changed to a signal 605 after TRC shown in FIG.

  A hardware configuration example of the present embodiment will be described with reference to FIG. The configuration shown in FIG. 7 is configured by a personal computer (PC), for example, and shows a hardware configuration example including a data reading unit 717 such as a scanner and a data output unit 718 such as a printer.

  A CPU (Central Processing Unit) 701 executes various modules described in the above-described embodiments, that is, the modules such as the object separation module 110, the state value detection module 120, the density correction module 130, and the binarization module 140. It is a control part which performs the process according to the computer program which described the sequence.

  A ROM (Read Only Memory) 702 stores programs, calculation parameters, and the like used by the CPU 701. A RAM (Random Access Memory) 703 stores programs used in the execution of the CPU 701, parameters that change as appropriate during the execution, and the like. These are connected to each other via a host bus 704 including a CPU bus.

  The host bus 704 is connected to an external bus 706 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 705.

  A keyboard 708 and a pointing device 709 such as a mouse are input devices operated by an operator. The display 710 includes a liquid crystal display device, a CRT (Cathode Ray Tube), or the like, and displays various types of information as text or image information.

  An HDD (Hard Disk Drive) 711 includes a hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 701 and information. The hard disk stores an image received by the object separation module 110, an image obtained as a result of density correction by the density correction module 130, and the like. Further, various computer programs such as various other data processing programs are stored.

  The drive 712 reads data or a program recorded in a removable recording medium 713 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and the data or program is read from the interface 707 and the external bus 706. , The bridge 705, and the RAM 703 connected via the host bus 704. The removable recording medium 713 can also be used as a data recording area similar to a hard disk.

  The connection port 714 is a port for connecting an external connection device 715, and has a connection unit such as USB, IEEE1394. The connection port 714 is connected to the CPU 701 and the like via the interface 707, the external bus 706, the bridge 705, the host bus 704, and the like. The communication unit 716 is connected to a network and executes data communication processing with the outside. The data reading unit 717 is a scanner, for example, and executes document reading processing. The data output unit 718 is, for example, a printer, and executes document data output processing.

  Note that the hardware configuration illustrated in FIG. 7 illustrates one configuration example, and the present embodiment is not limited to the configuration illustrated in FIG. 7, and is a configuration capable of executing the modules described in the present embodiment. I just need it. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line In addition, a plurality of systems shown in FIG. 7 may be connected to each other via a communication line so as to cooperate with each other. Further, it may be incorporated in a copying machine, a fax machine, a scanner, a printer, a multifunction machine (an image processing apparatus having any two or more functions of a scanner, a printer, a copying machine, a fax machine, etc.).

  In the above-described embodiment, the morphological filter is used. However, various filters may be used instead of the morphological filter.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standards such as “DVD + R, DVD + RW, etc.”, compact discs (CDs), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), etc. MO), flexible disk (FD), magnetic tape, hard disk, read only memory (ROM), electrically erasable and rewritable read only memory (EEPROM), flash memory, random access memory (RAM), etc. It is.
The program or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

It is a conceptual module block diagram about the structural example of this Embodiment. It is a flowchart which shows the process example by this Embodiment. It is a flowchart which shows the process example of the state value detection by this Embodiment. It is a conceptual diagram for demonstrating the example of a some binarization process. It is a conceptual diagram for demonstrating the example of a density correction. It is a conceptual diagram for demonstrating the example of several density corrections. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 110 ... Object separation module 120 ... State value detection module 121 ... Multiple threshold value determination module 122 ... Area number difference calculation module 123 ... Black pixel number difference calculation module 124 ... State value calculation module 130 ... Shading correction module 131 ... Morphological filter module 132 ... Simple smoothing module 133 ... Selection module 140 ... Binarization module

Claims (7)

Detecting means for detecting a value relating to a state in which the density of the image area is not uniform by performing a plurality of binarization processes on the image area;
An image processing system comprising: density correction means for correcting density of the image area based on a value relating to a state where the density of the image area detected by the detection means is not uniform. The image processing according to claim 1, wherein the detection unit detects a value related to a state in which the density of the image region is not uniform, according to a difference in the number of regions generated by the binarization processing. system. 2. The image according to claim 1, wherein the detection unit detects a value relating to a state in which the density of the image region is not uniform, according to a difference in the number of black pixels generated by the binarization processing. Processing system. The said detection means detects the value regarding the state where the density of the image area is not uniform according to the difference of the number of areas and the difference of the number of black pixels which were produced by the said binarization process. 2. The image processing system according to 1. The shading correction unit performs shading correction by applying a filter in which a parameter is adjusted based on a value relating to a state where the shading of the image region detected by the detection unit is not uniform to the image region. The image processing system according to claim 1. The image processing system according to claim 5, wherein the density correction unit prepares a plurality of types of density correction according to the purpose, and can select the density correction according to an operation of the operator. Computer
Detecting means for detecting a value relating to a state in which the density of the image area is not uniform by performing a plurality of binarization processes on the image area;
An image processing program that functions as a density correction unit that performs density correction of the image area based on a value relating to a state in which the density of the image area detected by the detection unit is not uniform.

Images