JP5090881B2 - Image processing apparatus and image processing program - Google Patents

Description

  The present invention relates to image processing, and more particularly, to an image processing apparatus and an image processing program having a function of removing unnecessary information from image data.

  Image data obtained by reading a document with an image reading apparatus such as a scanner includes information unnecessary for the user, such as noise and shadows. In particular, the image data obtained by scanning a ruled manuscript in which characters or the like are written on a report paper or campus note cannot read all the information because the density of the ruled line is low, and the ruled line is unnecessary for the user. May be included as information.

  FIG. 2A is an explanatory diagram of a ruled document with characters or the like written therein, and FIG. 2B is an explanatory diagram of image data obtained by reading the ruled document shown in FIG. It is. From these figures, in addition to information such as clear ruled lines 1001, noise 1002, and shadows 1003, ruled lines that are actually continuous lines are dotted lines or innumerable lines that are irregular in the read image data. It can be seen that it is included as point information. Such a ruled line 1004 is unnecessary information for the user, like noise (hereinafter, the ruled line that becomes the dotted line information or the point information is referred to as “unclear ruled line information”).

  Therefore, Patent Document 1 and Patent Document 2 below disclose that ruled line information is extracted from image data obtained by reading with a scanner, and the ruled line information is collectively removed.

Further, in Patent Document 3 below, rectangles circumscribing each of characters, noises, and the like are extracted from image data, candidates that can be noise are extracted from these circumscribed rectangles, and the circumscribed rectangle and the surrounding rectangles that are candidates are extracted. It is disclosed that it is determined whether or not the rectangle is a circumscribed rectangle that is considered to be noise from the relationship, and is removed when an affirmative determination is made.
Japanese Patent No. 3079508 JP 2002-366900 A JP 2006-72839 A

  However, the inventions of Patent Documents 1 and 2 both remove information that can be clearly read by a scanner and can be recognized as ruled lines (hereinafter referred to as “clear ruled line information”). Clear ruled line information 1004 is not removed.

  Further, the invention of Patent Document 3 exclusively removes general noise (sesame salt-like isolated point noise or the like), and there is no description that the unclear ruled line information is regarded as noise and removed. Note that if the unclear ruled line is point information that can be regarded as equivalent to noise, it is possible to remove the unclear ruled line information by performing the above-described noise removal processing. The point information cannot be regarded as equivalent to noise.

  In view of the above problems, an object of the present invention is to provide an image processing apparatus and an image processing program capable of leaving clear ruled line information from ruled image data and removing unclear ruled line information.

In the first aspect of the image processing apparatus according to the present invention,
An image processing apparatus for removing unclear ruled line information from image data having N × M pixels obtained by reading a document with ruled lines by an image reading apparatus,
There is no colored pixel having a density equal to or higher than the first threshold in a matrix of X × Y (X << N and Y << M) pixels centered on the target pixel, with one pixel of the image data as the target pixel. The number of pixels having a color difference or density difference with respect to the pixel of interest within a matrix of V × W (X << V << N and Y << W << M) pixels centered on the pixel of interest is equal to or less than a second threshold value. A ruled line removal unit that changes the color value of the pixel of interest to a white value and removes pixels related to the unclear ruled line information when
Where N, M, X, Y, V, and W are each a positive integer.

In the second aspect of the image processing apparatus according to the present invention, in the first aspect,
The image processing apparatus further includes a blur processing unit that performs blur processing on the image data before the ruled line removal unit performs processing on the image data.

In the third aspect of the image processing apparatus according to the present invention, in the first or second aspect,
The image processing apparatus further includes a noise removal unit that performs noise removal processing on the image data before the ruled line removal unit performs processing on the image data.

In the fourth aspect of the image processing apparatus according to the present invention, in the third aspect,
The image processing apparatus further includes a shadow removing unit that removes shadow information from the image data.

In the fifth aspect of the image processing apparatus according to the present invention, in the fourth or fifth aspect,
At the end of the various image processes, a sharpness processing unit for performing a sharpness process on the image data is further provided.

  According to the configuration of the first aspect, with respect to image data having the number of N × M pixels obtained by reading an original with a ruled line by an image reading device, the one pixel is a pixel of interest and the pixel of interest is the center. In the X × Y (X << N and Y << M) pixel matrix, there is no colored pixel having a density equal to or higher than the first threshold, and V × W (X << V << When the number of pixels whose color difference or density difference with the target pixel is less than or equal to the second threshold value in the matrix of N and Y << W << M) is less than the third threshold value, the color value of the target pixel is a white value Therefore, it is possible to leave the pixels related to the clear ruled line and to remove the pixels related to the unclear ruled line information.

  According to the configuration of the second aspect, since the ruled line removal unit performs blurring processing on the image data before processing the image data, unnecessary information can be reduced in the preprocessing stage, The ruled line removal unit only needs to process information that cannot be removed by the pre-processing, and the processing load of the ruled line removal unit can be reduced.

  According to the configuration of the third aspect, since the noise removal processing is performed on the image data before the ruled line removal unit performs processing on the image data, unnecessary information can be reduced at the preprocessing stage. The ruled line removing unit only needs to process information that cannot be removed by the preprocessing, and it is possible to reduce the processing load of the ruled line removing unit.

  According to the configuration of the fourth aspect, the shadow information is removed from the image data. Therefore, unnecessary information can be further removed from the image data as compared with the above aspect, and the printing cost can be reduced. There is an effect.

According to the configuration of the fifth aspect, since the ruled line removal unit performs the sharpness process on the image data after processing the image data, it is possible to improve the image quality compared to the above aspect. .

  Other objects, configurations and effects of the present invention will become apparent from the following description.

[1] Hardware configuration of image forming apparatus

  FIG. 5 is a schematic block diagram showing a hardware configuration of the image forming apparatus 10 according to the first embodiment of the present invention. The image forming apparatus 10 is a digital color image forming apparatus capable of color scanning, color printing, and color copying.

  In this image forming apparatus 10, an EEPROM 13 E 1, EEPROM 13 E 2, DRAM 13 D, HDD 14, operation panel 15, scanner 16 S, printer 16 P, NIC 17, facsimile modem 18, and compression / decompression ASIC 19 are coupled to the MPU 11 via an interface 12. In FIG. 5, a plurality of interfaces are shown as one block for the sake of simplicity.

  The EEPROMs 13E1 and 13E2 are, for example, flash memories. The EEPROM 13E1 stores BIOS (Basic Input Output System). The EEPROM 13E2 stores a later-described image processing program 20 according to the present invention in addition to software included in a normal image forming apparatus such as an OS and an application. The DRAM 13D is for work area, and the HDD 14 is for data storage.

  The operation panel 15 is used for inputting a setting value or an instruction and displaying a setting screen or a state. In the first embodiment, a case where the operation panel 15 is configured by a combination of a touch panel and hardware keys will be described.

  The scanner 16S is used for image input in scanning, copying, and fax transmission. The printer 16P as an image output means includes a print engine, a fixing device, a paper feeding unit, a transport unit, and a paper discharge unit, and generates an electrostatic latent image on the photosensitive drum of the print engine based on the supplied bitmap data. The toner is formed, developed with toner, transferred to a sheet, fixed, and discharged.

  The NIC 17 is coupled to a host computer (not shown) on a network via a cable or a wireless communication medium, and is used for print jobs, e-mail transmission / reception, and Internet facsimile transmission. The facsimile modem 18 is for facsimile transmission / reception.

The compression / decompression ASIC 19 is used as a coprocessor of the MPU 11.
[2] Partial Functional Configuration of Image Forming Apparatus According to the Present Invention FIG. 1 is a diagram showing partial functional blocks of an image forming apparatus 10 according to the first embodiment of the present invention.

  The image forming apparatus 10 includes a scanner 16S for reading an original and acquiring an image signal, an image processing unit 100 that performs various data processing on image data obtained by A / D converting the image signal, and image processing. A printer 16P that mainly outputs a document image on recording paper based on data processed by the unit 100 is mainly provided.

  The scanner 16S optically reads an original and outputs a CCD image element (an example of a color image pickup element) that outputs analog image signals representing the three primary colors R (red), G (green), and B (blue) for each pixel. (Not shown). The output signal of the CCD element is given to the image processing unit 100.

  The image processing unit 100 can be configured by the MPU 11, the EEPROM 13E2, and the image processing program 20 stored in the MPU 11, and the MPU 11 executes the image processing program 20 to realize the function. As functional units of the image processing unit 100, an A / D conversion unit 110, an image data storage unit 111, a CMY conversion unit 112, a blur processing unit 113, a noise removal unit 114, a shadow removal unit 115, and ruled line removal And a sharpness processing unit 117. Note that some of these functions can be realized by an electronic circuit.

  The A / D conversion unit 110 converts each color analog image signal supplied from the scanner 16S into, for example, an 8-bit digital signal, and stores the converted image data in the image data storage unit 111 as image data.

  The image data storage unit 111 is, for example, a DRAM 13D, and stores image data acquired by the scanner 16S. Hereinafter, each functional unit performs respective processing on the image data on the storage unit 111.

  The CMY conversion unit 112 reads the image data of RGB color components after A / D conversion from the image data storage unit 111, and converts the density of the color components of C (cyan), M (magenta), and Y (yellow). Color conversion to image data to represent.

  The blur processing unit 113 reads out the color-converted image data from the image data storage unit 111, extracts a region in the image data that does not form a contour, and extracts, for example, a moving average method and a median filter from the region. A known blurring (smoothing) process is performed. Here, in this embodiment, a density histogram is created, and an area in which the color density is equal to or less than a threshold value (for example, 10% or less) is defined as an “area not forming an outline”.

  In the blurring process, unnecessary information including noise 1002, shadow 1003, and unclear ruled line 1004 can be reduced from the image data. However, since it cannot be completely removed, the subsequent noise removal unit 114 and shadow removal are performed. The removal processing is performed on each piece of unnecessary information in the unit 115 and the ruled line removal unit 116.

  The noise removing unit 114 reads out the image data after the blurring process from the image data storage unit 111 and performs a known noise removing process such as Japanese Patent Application Laid-Open No. 2007-129460 and Patent Document 3 described above. In these noise processes, as described in the background art section, it is possible to remove a part of the ruled line 1004 that is unclear together with noise, but it cannot be completely removed.

  The shadow removal unit 115 reads out the image data after the noise removal from the image data storage unit 111. For example, when there are colored pixels in an area within 99 pixels from the top, bottom, left, and right ends of the image data, The color information (CMY value) is held. An average value (C1, M1, Y1) and standard deviation (σ1, σ2, σ3) of each color component is obtained from the held plurality of CMY values. All the colored pixels having CMY values within the range of ± σ3) are removed (the color value of the colored pixels is changed to a white color value).

  The ruled line removal unit 116 is a functional unit according to the present invention, reads image data after shadow removal from the image data storage unit 111, and is indistinct that cannot be removed by the blurring process, noise removal process, and shadow removal process. The ruled line information 1004 is removed, details of which will be described later.

The sharpness processing unit 117 reads out the image data after removing the unclear ruled lines from the image data storage unit 111, and in order to emphasize the outline of characters and the like, the image data is subjected to sharpness processing by, for example, Laplacian filter or Fourier transform. Apply. The image data after the sharpness processing is given to the printer 16P, and the printer 16P outputs an image based on the input image data on a recording sheet.
[3] Application of the Present Invention to Ruled Documents The case where the ruled document 1000 shown in FIG. 2A is copied by the image forming apparatus 10 having the above configuration will be described with reference to FIG. In the following, the step identification codes in FIG. 1 are shown in parentheses.

  (S1, S2) When the user sets a ruled document 1000 on the document table of the scanner 16S and presses a start button (not shown) on the operation panel 15, the paper 1000 is read by the scanner 16S and obtained by reading. The analog image signals of the respective colors are converted into digital signals by the A / D conversion unit 110 and stored in the image data storage unit 111 as image data.

  (S3) The image data stored in the image data storage unit 111 is subjected to color conversion processing through the CMY conversion unit 112.

  The converted image data includes noise 1002, which is unnecessary information, a shadow 1003, and an unclear ruled line 1004, as shown in FIG. Therefore, in the present invention, the image data after the conversion process is subjected to the following various image processes to remove the unnecessary information.

  (S4 to S6) The converted image data is subjected to various image processing through the blurring processing unit 113, the noise removal unit 114, and the shadow removal unit 115.

  FIG. 2C is an explanatory diagram of the image data after various image processing is performed on the image data illustrated in FIG. 2B through the blurring processing unit 113, the noise removal unit 114, and the shadow removal unit 115. From this figure, it can be seen that the noise 1002 and the shadow 1003 have been removed by the above-described various image processing, but the unclear ruled line 1004 has not been completely removed.

  (S7) The image data that has been subjected to the above-described various processes passes through the ruled line removal unit 116, and unclear ruled lines 1004 are removed.

  FIG. 4 is a detailed flowchart of the image processing of the ruled line removal unit 116. In the following, the step identification codes in FIG. 4 are shown in parentheses.

  (S10) The image data processed by the shadow removal unit 115 is copied in order to separate the reference target and the change target. Hereinafter, the copy source image data is referred to as reference image data, and the image data obtained by copying is referred to as changed image data. These image data have N × M pixels. In this embodiment, the image data is represented by N × M (N and M are both integers and N >> as shown in FIG. 3). 100, M >> 100) A description will be given using a matrix of pixels.

  (S11, S18) The following processes in steps S12 to S17 are repeated from the 100th line to the (N-100) th line in the matrix of reference image data using the variable i.

  (S12, S17) The processes in steps S13 to S16 below are repeated from the 100th column to the (M-100) th column in the matrix of reference image data using the variable j. As a result, the pixels other than the region within 99 pixels from the top, bottom, left, and right ends of the reference image data will be the subject of attention.

  (S13) The pixel at the position (i, j) is set as the pixel of interest Dij.

  (S14) As shown in FIG. 3, whether or not there is a colored pixel having a density of 90% or more in the 5 × 5 pixel matrix centered on the pixel of interest Dij is determined by creating a density histogram. If the determination is affirmative, the process proceeds to step S17. If the determination is negative, the process proceeds to the next step S15. Here, when the pixel related to the character or figure shown in FIG. 2C is the target pixel Dij, an affirmative determination is made, and when the pixel related to the clear ruled line 1001 and the unclear ruled line 1004 is the target pixel Dij, the density thereof is determined. The result is negative because it is thin.

(S15) As shown in FIG. 3, it is determined whether or not the number of pixels having substantially the same color value as the target pixel Dij is, for example, eight or more in the 9 × 9 pixel matrix centered on the target pixel Dij. To do. If the determination is affirmative, the process proceeds to step S17. If the determination is negative, the process proceeds to the next step S16. Here, the color value of one pixel in the 9 × 9 pixel matrix is (C2, M2, Y2), and the color value of the pixel of interest Dij is (C3, M3, Y3). For example, when the following conditional expression is satisfied, the color value (C2, M2, Y2) of the one pixel is set as the “substantially identical color value”.
√ ((C3-C2) ^ 2 + (M3-M2) ^ 2 + (Y3-Y2) ^ 2) ≦ 5
Note that the symbol “^” in the above expression means a power.

  (S16) The coloring of the pixel of the changed image data corresponding to the pixel of interest Dij is removed (the color value of the pixel is changed to a white color value).

  FIG. 2D is an explanatory diagram of the image data after processing by the ruled line removal unit 116. As shown in this figure, by performing the processing of steps S10 to S18 on the image data, the clear ruled line 1001 shown in FIG. 2C is left in the image data, and the unclear ruled line 1004 is removed.

  (S8, S9) Returning to FIG. 1, the pixel data after the ruled line removal (changed image data) is sharpened by the sharpness processing unit 117, and the image is output on the recording paper by the printer 16P.

  According to the first embodiment, with respect to image data having the number of N × M pixels obtained by reading a ruled document with an image reading device, the one pixel is the target pixel Dij, and the target pixel Dij is the center. There is no colored pixel having a density of 90% or more in the 5 × 5 pixel matrix, and the color difference from the target pixel Dij is a second predetermined value in the 9 × 9 pixel matrix centered on the target pixel Dij. When the number of pixels below the condition is less than the eighth, the color value of the pixel of interest is changed to a white value, so that the clear ruled line 1001 can be left from the image data and the unclear ruled line 1004 can be removed. There is an effect.

  In addition, the Example of this invention mentioned above is an illustration for description of this invention, and is not the meaning which limits the scope of the present invention only to those Examples. Various modifications can be made to the present invention without departing from the gist thereof. Hereinafter, some of the modifications will be exemplified.

  In the first embodiment, the document 1000 with ruled lines is read as a color image by the scanner 16S, and processing is performed on the color image data. However, each of the image processing is also applied to processing on monochrome image data. can do.

  Further, in the case of copying a document, an example in which image data obtained by reading with the scanner 16S is input to the image processing unit 100 as an image processing target is exemplified. For example, an image read from a recording file is used. Data may be input to the image processing unit 100 as an image processing target. Further, the image data processed by the image processing unit 100 may be stored in a recording file instead of being input to the printer 16P.

  Furthermore, although the case where the image forming apparatus 10 includes the image processing unit 100 is taken as an example, an image processing apparatus such as a personal computer may include the image processing unit 100.

  Furthermore, in step S15, the case where the determination is made based on the number of pixels whose color difference from the target pixel Dij is equal to or smaller than a predetermined value is taken as an example, but the determination is made based on the number of pixels whose density difference from the target pixel Dij is equal to or smaller than the predetermined. You may make it do.

1 is a diagram illustrating a partial functional block of an image forming apparatus according to Embodiment 1 of the present invention. (A) is an explanatory diagram of a document with ruled lines in which characters and the like are written, and (b) is an explanatory diagram of image data obtained by reading the document with ruled lines shown in (a). (C) is an explanatory diagram of the image data after various image processing is performed on the image data shown in (b) through the blurring processing unit, the noise removal unit, and the shadow removal unit, and (d) is the ruled line removal 6 is an explanatory diagram of image data after ruled line removal processing by a unit; FIG. It is explanatory drawing of the matrix of a NxM pixel. It is a detailed flowchart of the image process of a ruled line removal part. 1 is a schematic block diagram illustrating a hardware configuration of an image forming apparatus according to Embodiment 1 of the present invention.

Explanation of symbols

10 Image forming apparatus 11 MPU
12 interface 13E1 EEPROM
13E2 EEPROM
13D DRAM
14 HDD
15 Operation panel 16S Scanner 16P Printer 17 NIC
18 Facsimile modem 19 Compression / decompression ASIC
20 Image processing program 100 Image processing unit 110 A / D conversion unit 111 Image data storage unit 112 CMY conversion unit 113 Blur processing unit 114 Noise removal unit 115 Shadow removal unit 116 Ruled line removal unit 117 Sharpness processing unit 1000 Ruled line original 1001 Clear Ruled line 1002 Noise 1003 Shadow 1004 Unclear ruled line

Claims (6)

An image processing apparatus for removing unclear ruled line information from image data having N × M pixels obtained by reading a document with ruled lines by an image reading apparatus,
There is no colored pixel having a density equal to or higher than the first threshold in a matrix of X × Y (X << N and Y << M) pixels centered on the target pixel, with one pixel of the image data as the target pixel. The number of pixels having a color difference or density difference with respect to the pixel of interest within a matrix of V × W (X << V << N and Y << W << M) pixels centered on the pixel of interest is equal to or less than a second threshold value. A ruled line removal unit that changes the color value of the pixel of interest to a white value and removes pixels related to the unclear ruled line information when
An image processing apparatus comprising:   The image processing apparatus according to claim 1, further comprising a blur processing unit that performs a blur process on the image data before the ruled line removal unit performs the process on the image data.   The image processing apparatus according to claim 1, further comprising a noise removing unit that removes isolated point noise from the image data before the ruled line removing unit performs processing on the image data. . The image processing apparatus according to any one of claims 1 to 3, characterized by further comprising a shadow removal unit for removing a shadow information from the image data. After treatment with該罫line removing section relative to the image data is performed, according to any one of claims 1 to 4, further comprising a sharpness processing unit for performing sharpness processing on the image data Image processing apparatus. An image processing program for causing a computer processor to remove unclear ruled line information from image data having N × M pixels obtained by reading a ruled document with an image reading device,
With respect to the processor, one pixel of the image data is set as a target pixel, and the density is not less than a first threshold in a matrix of X × Y (X << N and Y << M) pixels centered on the target pixel. There is no color pixel, and the color difference or density difference with the target pixel in the matrix of V × W (X << V << N and Y << W << M) pixels centered on the target pixel is the second threshold value. When the number of the following pixels is less than the third threshold, the pixel related to the unclear ruled line information is removed by changing the color value of the pixel of interest to a white value.
An image processing program characterized by that.

Images