JP3733686B2 - Image processing method and apparatus - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention is an image processing apparatus capable of performing appropriate image processing in accordance with the attributes of a document image having various attributes such as a character image, a halftone dot image, or a grayscale image (photo image). For example, it is used for a digital copying machine.
[0002]
[Prior art]
As a document used in a copying machine or the like, a document containing only a character image, a document containing only a photographic image, a document containing only a halftone image, and a document in which they are mixed are often used. The image processing for these various images is preferably processing adapted to each characteristic.
[0003]
For this purpose, it is necessary to accurately perform area determination for dividing an original image into areas corresponding to attributes such as characters / photos / halftone dots.
In conventional area discrimination, for each pixel in the document image, the density difference between the target pixel and its surrounding pixels, the difference between the maximum and minimum values in the area including the target pixel, or density information such as a histogram Based on the above, a method of determining the attribute of the target pixel is often used. There is also known a method for discriminating attributes in a region from frequency components in the region including the target pixel. Neural nets are often used to discriminate these areas.
[0004]
[Problems to be solved by the invention]
However, in the above-described conventional area determination method, the attribute of each pixel in the document image or the attribute of a narrow area including peripheral pixels is determined. Therefore, misidentification often occurs in the attribute in each area.
[0005]
Therefore, there is a possibility that a plurality of attribute areas erroneously determined to be different attributes are scattered in one actual attribute area in the document image. As a result, a plurality of types of image processing corresponding to the misclassified attribute are executed even though the region has the same attribute, and there is a problem in that image quality deterioration due to misclassification occurs. It was.
[0006]
The present invention has been made in view of the above-described problems. Even when there are a plurality of types of images in a document image, the region determination is accurately performed by extracting the boundary line of the image, and each region is determined. An object of the present invention is to provide an image processing method and apparatus capable of performing appropriate image processing according to attributes.
[0007]
[Means for Solving the Problems]
  BookA method according to the invention extracts a feature amount for each pixel of an input image, determines attribute for each pixel based on the feature amount, generates pixel attribute information, and creates a photographic region based on the pixel attribute information Or for halftone areas, For pixels located at attribute boundariesApply the Hough transformA straight line parallel or perpendicular to the axis is detected in the Cartesian coordinate plane, and the image is divided into a plurality of rectangular shapes by the detected straight lineDivided into local regions,And the divided local regionThe attribute having the largest number of pixels having the same attribute among the pixels included in each local area is determined as the attribute of each pixel in each local areaThe pixel attribute information is corrected by,CorrectedPixelBased on the attribute information, image processing corresponding to each attribute is performed on each area.
  Preferably, for the character area, the pixel attribute information of each pixel is corrected by applying a closing process to the pixels included in the area.
[0008]
  BookAn apparatus according to the invention is located at a boundary between attributes, means for extracting a feature amount for each pixel of an input image, means for discriminating an attribute for each pixel based on the feature amount, and generating pixel attribute information Apply the Hough transform to the pixelsParallel or perpendicular to the axis in the Cartesian planeA straight line is detected, and the image is divided into a plurality of images by the detected straight line.RectangularDivided into local regions,andAbout each divided local regionThe attribute having the largest number of pixels having the same attribute among the pixels included in each local area is determined as the attribute of each pixel in each local areaFirst attribute correcting means for correcting the pixel attribute information, and correctedPixelMeans for performing image processing corresponding to each attribute for each region based on attribute information.
  Preferably, a second attribute correction unit that corrects pixel attribute information of each pixel by applying a closing process to the pixels included in the character area, and the first attribute correction unit based on the pixel attribute information. And switching means for switching between the attribute correction means and the second attribute correction means in accordance with the attribute.
[0009]
  Preferably,The first attribute correction unit extracts a boundary point that is a pixel located at a boundary based on the pixel attribute information, and applies a Hough transform to each boundary point on an orthogonal coordinate plane to display a polar coordinate plane. Means for converting to a curve, means for detecting the intersection of each curve converted to the polar coordinate plane, andOf the intersections at any position of θ = 0, π / 2, πMeans for generating a boundary line by inversely transforming polar coordinates into a straight line on an orthogonal coordinate plane, and surrounded by the boundary lineRectangularMeans for extracting an area as a local area and means for discriminating an attribute for each local area.
[0010]
  AlsoThe second attribute correction means includes means for detecting the maximum value of the target pixel and its peripheral pixels, means for replacing the detected maximum value with the target pixel, and the replacement of the target pixel and its peripheral pixels. Means for detecting the minimum value in the medium, and means for replacing the detected minimum value with the pixel of interest.
[0011]
  AlsoThe switching means selects the first attribute correction means for the photographic area and the halftone dot area, and selects the second attribute correction means for the character area.
[0012]
An example of an image processing method according to the present invention will be described with reference to FIG. 11, and an operation of attribute correction processing by Hough transform will be described with reference to FIGS.
In FIG. 11, attributes are determined for each pixel (# 11), and an attribute map MP is created for each attribute (# 12). That is, the attribute map MP is created for each candidate area of each image of characters, photos, and halftone dots.
[0013]
For the candidate region of the character image, the closing process is performed on the attribute map MP (# 13). In the closing process, a disk filter corresponding to the maximum character size is used, and the image is once thickened and then reduced.
[0014]
For the photograph or halftone dot candidate region, the attribute discrimination processing by Hough transform is performed for each attribute map MP (# 14, 15). After each processing is completed, the respective attribute maps MP are comprehensively determined and synthesized (# 16). In composition, the composition is preferentially performed in order of accuracy of attribute discrimination for each pixel, for example, dot, photograph, and character.
[0015]
When attribute discrimination is performed for each pixel on the original image RF conceptually shown in FIG. 7A, as shown in FIG. 7B, the pixels GA1 and A2 that are determined to be the area A1 are obtained. An attribute map MP1 in which the determined pixel GA2 is mixed is obtained.
[0016]
By applying noise removal to the attribute map MP1 shown in FIG. 7B, an attribute map MP2 shown in FIG. 7C is obtained. FIG. 8D is a boundary map MP3 showing the result of extracting the boundary point GB between the region A2 and the non-region A2 with respect to the attribute map MP2 shown in FIG. 7C.
[0017]
  Applying the Hough transform to the boundary point GBDetect line segments parallel or perpendicular to the axis in the Cartesian coordinate plane; andThe result of detecting line segments LB3 and LB4 having a predetermined length or more is shown in FIG. With line segments LB3 and LB4 as boundaries,RectangularIt is divided into four local areas AL1-4. In each of these local areas AL1 to AL4, attribute discrimination is performed.
[0018]
FIG. 8F shows the result of adopting the attribute of the pixel GA having the larger number of pixels GA1 and the number of pixels GA2 in each of the local areas AL1 to AL4. That is, the local areas AL1 and AL2 are areas A1, and the local areas AL3 and AL4 are areas A2, which are close to the actual areas A1 and A2 of the original image RF.
[0019]
In addition, when dividing into the local area AL, the division into the local area AL can be performed recursively until no segment longer than a predetermined length is detected for the divided local area AL. is there.
[0020]
DETAILED DESCRIPTION OF THE INVENTION
FIG. 1 is a diagram showing the overall configuration of an image reading apparatus 1 incorporating an image processing unit 23 according to the present invention.
[0021]
1, the image reading apparatus 1 includes a main body 10, a document cover 11, a document placement glass 12, an exposure lamp 13, mirrors 14a, b, and c, a lens 15, a CCD sensor 16, a slider drive unit 17, and an operation panel unit 21. , A control unit 22, an image processing unit 23, and the like.
[0022]
The document DR placed on the document placement glass 12 is irradiated by the exposure lamp 13. Reflected light from the document DR is guided to the lens 15 by the mirrors 14 a, b, and c, and an image of the document DR is formed on the CCD sensor 16.
[0023]
The exposure lamp 13 and the mirrors 14a, b, and c are moved at a speed corresponding to the magnification by the slider driving unit 17, and scan the document DR placed on the document placement glass 12 over the entire surface.
[0024]
The reflected light of the document DR that has entered the CCD sensor 16 is converted into an image signal SP that is an electrical signal by the CCD sensor 16 and is input to the image processing unit 23. In the image processing unit 23, various analog signal processing, A / D conversion, and digital image processing are sequentially performed on the image signal SP. The image data DO subjected to the image processing is output to the external device 24, for example, an image memory or a printer unit.
[0025]
FIG. 2 is a block diagram illustrating a configuration of the image processing unit 23.
The image processing unit 23 includes an A / D conversion unit 31, a shading correction unit 32, a LOG correction unit 33, an image storage unit 34, an area determination unit 35, and an image correction unit 36.
[0026]
The image signal SP output from the CCD sensor 16 is converted into image data D1 which is a digital signal by the A / D conversion unit 31, and is stored in the image storage unit 34 through the shading correction unit 32 and the LOG correction unit 33. Based on the image data D3 stored in the image storage unit 34, an attribute for each local region is determined by the region determination unit 35, and attribute information DA2 is output. In the image correction unit 36, parameters are switched according to the determination result in the region determination unit 35, and image processing corresponding to the attribute is performed for each local region on the image data D3.
[0027]
FIG. 3 is a block diagram showing the configuration of the area determination unit 35.
The area determination unit 35 includes a feature amount extraction unit 41, an attribute determination unit 42, a calculation unit 43, an attribute storage unit 44, and a local region attribute storage unit 45.
[0028]
The feature amount extraction unit 41 extracts a feature amount DC for each pixel of the input image data D3. As the feature quantity extraction unit 41, for example, a Laplacian filter is used. The attribute discriminating unit 42 discriminates the attribute for each pixel based on the feature amount DC and outputs attribute information DA1. The attribute information DA1 is stored in the attribute storage unit 44. The attribute information DA1 corresponds to the pixel attribute information in the present invention.
[0029]
Based on the attribute information DA1, the calculation unit 43 performs an operation for determining the attribute for each local region and outputs the corrected attribute information DA2. That is, the calculation unit 43 corrects the attribute information DA1 by applying the Hough transform to the photographic area or the halftone dot area and dividing the local area, and determining the attribute of the divided local area, thereby obtaining the character area. On the other hand, the attribute information DA1 is corrected by performing a closing process which is a kind of morphology process. The corrected attribute information is combined and output as one piece of attribute information DA2.
[0030]
In the attribute correction process to which the Hough transform is applied, a straight line is detected by applying the Hough transform to the pixels located at the attribute boundary based on the attribute information DA1, and the image data D3 is converted into a plurality of rectangular shapes by the detected straight line. It divides | segments into a local area | region, An attribute is discriminate | determined about each divided | segmented local area | region. The attribute for each local area is attribute information DA2. The local area attribute storage unit 45 stores attribute information DA2. The calculation unit 43 and the attribute storage unit 44 constitute an attribute correction unit AM.
[0031]
Therefore, in the image data D3 read from the image storage unit 34, the feature amount extraction unit 41 extracts the feature amount DC for each pixel, the attribute determination unit 42 determines the attribute for each pixel, and the obtained attribute information. DA1 is stored in the attribute storage unit 44. The attribute information DA1 stored in the attribute storage unit 44 is read by the calculation unit 43, and attribute correction processing is performed by applying a Hough transform or closing process. The corrected attribute information DA2 is stored in the local region attribute storage unit 45. Stored.
[0032]
FIG. 4 is a block diagram functionally showing the configuration of the attribute correction unit AM.
The attribute correction unit AM includes a switching unit 50, a noise removal processing unit 51, a boundary point extraction unit 52, a Hough conversion unit 53, an intersection detection unit 54, an inverse conversion unit 55, a local region extraction unit 56, an attribute determination unit 57, and a closing process. A unit 58 and a synthesis unit 59 are included. Among these, the first attribute correction unit AM1 includes the noise removal processing unit 51, the boundary point extraction unit 52, the Hough conversion unit 53, the intersection detection unit 54, the inverse conversion unit 55, the local region extraction unit 56, and the attribute determination unit 57. And the closing processing unit 58 constitutes a second attribute correction unit AM2.
[0033]
The switching unit 50 switches between the first attribute correction unit AM1 and the second attribute correction unit AM2 based on the attribute information DA1, and performs correction processing of the attribute information DA1 corresponding to the attribute. Usually, when the attribute information DA1 is a character image, the second attribute correction unit AM2 is selected, and when the attribute information DA1 is a photographic image or a halftone image, the first attribute correction unit AM1 is selected.
[0034]
In the first attribute correction unit AM1, the noise removal processing unit 51 performs a process for removing noise included in the attribute information DA1. The noise removal processing unit 51 deletes candidate areas of other images having a small area included in the candidate area from the candidate areas of the photographic image and the halftone dot image. For example, the area area of 14 point character size or less included in the candidate areas of the photographic image and the halftone dot image is removed. Thereby, attribute information DA1a is obtained.
[0035]
The boundary point extraction unit 52 extracts a boundary point PB that is a pixel located at the boundary based on attribute information DA1a that is attribute information determined for each pixel. The Hough transform unit 53 applies Hough transform (Hough transform) to each boundary point PB on the orthogonal coordinate plane to convert it into a curve on the polar coordinate plane. The intersection detection unit 54 detects the intersection PC of each curve converted to the polar coordinate plane. The inverse conversion unit 55 generates the boundary line LB by inversely converting the polar coordinates of the detected intersection point PC into a straight line on the orthogonal coordinate plane. The local area extraction unit 56 extracts the area surrounded by the boundary line LB as the local area AL.
[0036]
The attribute discriminating unit 57 discriminates the attribute for each local area AL and outputs attribute information DA2a that is the discrimination result. In determining the attribute for each local area AL, the attribute determined for each pixel is used. For example, if a pixel having a specific attribute is 50% or more in one local area AL, the attribute of the pixel is set as the attribute of the local area AL. When pixels having three or more types of attributes are mixed in the local area AL, the attribute having the largest number of pixels among them is set as the attribute of the local area AL.
[0037]
  The closing processing unit 58 uses a disk filter corresponding to the maximum character size (14 points), and performs a process of shrinking the image after thickening it once. Although not shown, the closing processing unit 58 includes means for detecting the maximum value of the target pixel and its peripheral pixels, means for replacing the detected maximum value with the target pixel, the replaced target pixel and its peripheral pixels. There are provided means for detecting the minimum value of the pixels and means for replacing the detected minimum value with the pixel of interest. By the closing processing unit 58,Apply the closing process to each pixel in the area, and depending on the result of the processAttribute information DA1ThecorrectionShiThe corrected attribute information DA2b is output.
[0038]
The synthesizer 59 synthesizes the attribute information DA2a output from the first attribute corrector AM1 and the attribute information DA2b output from the closing processor 58 into one attribute information DA2.
[0039]
FIG. 5 is a block diagram showing a configuration of the image correction unit 36.
In FIG. 5, the image correction unit 36 includes a scaling / movement processing unit 61, an MTF correction unit 62, a density correction unit 63, and a binarization processing unit 64. In each of these units, a parameter for each process is set based on the attribute information DA2 output from the region discriminating unit 35. Thus, image processing corresponding to the attribute is performed for each local area AL. For example, edge enhancement processing is performed on a character region, smoothing processing is performed on a photographic image, and filtering processing is performed on a halftone image.
[0040]
Next, the processing operation of the area determination unit 35, particularly the processing operation of the attribute information DA will be described in more detail. First, the Hough transform will be briefly described.
FIG. 6 is a diagram showing the concept of Hough transform. 6A shows the positions of the points A to G in the xy space (orthogonal coordinate plane), and FIG. 6B shows the ρ-θ space (polar coordinates) of the points A to G by Hough transform. (Plane) The curve shown above is shown.
[0041]
The Hough transform is a method for detecting graphics such as straight lines, circles, and ellipses from an image. In particular, a straight line detection method based on the Duda and Hart method is often used, and this method is also used in this embodiment. In this method, a straight line is
ρ = x cos θ + ysin θ (1)
It expresses with. Here, ρ is the length of a perpendicular line drawn from the origin to a straight line, and θ is the angle formed between the perpendicular line and the x axis.
[0042]
A point on the xy space shown in FIG. 6A, for example, point A (x0, y0), according to the equation (1), is one sine in the ρ-θ space shown in FIG. 6B. This corresponds to the locus ρ = x0 cos θ + y0 sin θ of the curve.
[0043]
On the contrary, the locus of one sine curve in the ρ-θ space represents all straight lines passing through (x0, y0) in the xy space. Therefore, when each point on one straight line in the xy space is converted into the ρ-θ space, the locus of each sine curve created in the ρ-θ space from these points intersects at one point. . A straight line is obtained in the xy space by inversely transforming the points where the trajectories intersect. That is, according to this method, it is possible to detect a single straight line based on discrete points, in other words, even when the straight line is broken.
[0044]
In FIG. 6A, points A, B, C, and D on the xy space are points on one straight line LB1. In the straight line LB1, θ is π / 4. When these points are converted into the ρ-θ space by the Hough transform, as shown in FIG. 6B, the trajectories are sinusoidal curves, and the trajectories intersect at the intersection α.
[0045]
Similarly, points E, B, F, and G on the xy space are points on one straight line LB2. In the straight line LB2, θ is π / 2. When these points are converted into the ρ-θ space by the Hough transform, the locus becomes a sinusoidal curve as shown in FIG. 6B, and each locus intersects at the intersection β.
[0046]
  Thus, the straight line parallel or perpendicular to the axis in the xy space has intersections at positions θ = 0, π / 2, and π in the ρ-θ space. Therefore, when there is an intersection at the position of θ = 0, π / 2, π, by inversely transforming the intersection on the xy space,parallel or perpendicular to the axis in xy spaceA straight line (line segment) can be obtained.
[0047]
As a specific method for obtaining a straight line, a pixel position as a straight line element candidate is detected from the original image, and each point of the locus in the ρ-θ space corresponding to the pixel position is obtained. Each obtained point is counted up with respect to the coordinate position in the ρ-θ space. Since a point (maximum value point) having a count value equal to or greater than a certain threshold is an intersection, a straight line on the xy plane is extracted by performing inverse transformation on the maximum value point using equation (1). The
[0048]
  Further, the length of the straight line (line segment) is detected based on the coordinate position on the xy plane corresponding to the trajectory passing through the local maximum point. For example, in FIG.E, B,F,GWhen it is detected that each point is on a straight line, end points E and G among these four points are detected, and the distance between these two points may be measured. Therefore, it is possible to extract only a line segment having a predetermined length or more.
[0049]
Next, the operation of attribute correction processing in the image reading apparatus 1 will be described.
7 and 8 are diagrams for conceptually explaining the operation of attribute correction processing by Hough transform.
[0050]
FIG. 7A shows the boundary between two regions A1 and A2 having different attributes for the original image RF that is an image of the document DR. Note that the region A1 is a region that is not the region A2, that is, the non-region A2. When attribute determination is performed on the original image RF for each pixel, as shown in FIG. 7B, the pixel GA1 determined to be the area A1 and the pixel GA2 determined to be the area A2 are mixed. An attribute map MP1 is obtained. Each pixel GA1 is shown in white, and each pixel GA2 is shown in gray.
[0051]
According to the attribute map MP1 shown in FIG. 7B, one region is in a state where it enters the other region, which is a state in which noise is mixed. By applying noise removal to the attribute map MP1, an attribute map MP2 shown in FIG. 7C is obtained. By performing noise removal, the number of boundary points is reduced, the calculation time is reduced, and erroneous discrimination is also reduced. Note that, as a method of noise removal processing, there are a method of deleting an area region having a predetermined size or less, a method of correcting an attribute map according to an attribute count value in a matrix of a predetermined size, and the like.
[0052]
FIG. 8D is a boundary map MP3 showing the result of extracting the boundary point GB between the region A2 and the non-region A2 with respect to the attribute map MP2 shown in FIG. 7C. Note that the boundary point GB is detected for the pixel GA2, and the boundary portion between the pixel GA2 and the pixel GA1 is extracted as the boundary point GB. Each boundary point GB is shown in black.
[0053]
FIG. 8E shows the result of detecting line segments LB3 and LB4 having a predetermined length or more by applying the Hough transform to the boundary point GB. The line segments LB3 and LB4 are divided into four local regions AL1 to 4 with the boundary line as a boundary line. In each of these local areas AL1 to AL4, attribute discrimination is performed.
[0054]
FIG. 8F shows the result of adopting the attribute of the pixel GA having the larger number of pixels GA1 and the number of pixels GA2 in each of the local areas AL1 to AL4. That is, the local areas AL1 and AL2 are areas A1, and the local areas AL3 and AL4 are areas A2, which are close to the actual areas A1 and A2 of the original image RF. In determining the attribute of each local area AL, the number of the respective pixels GA1, GA2 is counted in each local area AL, and the attribute of the pixel GA having a large count value may be adopted.
[0055]
In the description of FIG. 8, the division into the local area AL is performed only once. However, in the image reading apparatus 1, a predetermined length is applied to the divided local area AL in order to reduce erroneous determination as much as possible. The division into the local areas AL is recursively performed until the above line segment is not detected.
[0056]
Next, a method for dividing the local area AL in the attribute correction process will be described in detail.
FIG. 9 is a diagram conceptually showing a method of division into local areas AL, and FIG. 10 is a diagram showing re-division within the local area AL.
[0057]
An original image RF1 shown in FIG. 9A has a character image area A3 and a photographic image area A4. The Hough transform is applied to the original image RF1 to draw the boundary line LB as described above, and the original image RF1 is divided into a plurality of local areas AL surrounded by the boundary line LB as shown in FIG. 9B. Here, the boundary line LB is obtained by extending the line segment to the entire image when a line segment having a predetermined length LG or more is detected. Further, in the divided local area AL, the Hough transform is applied again in the same manner as described above, and a line segment having a predetermined length LG or more is extracted. The extracted line segment is set as a boundary line LB, and the local area AL is subdivided.
[0058]
FIG. 10A shows one local area AL0 shown in FIG. 9B. The local area AL0 is an area surrounded by the boundary lines LB5-8. By performing re-division within the local area AL0, two boundary lines LB9 and LB10 are extracted, and thereby divided into four local areas AL00, AL01, AL10, and AL11 as shown in FIG.
[0059]
Here, as a specific example of the length of the line segment extracted by application of the Hough transform, in the first division, the predetermined length LG1 is set to 1 cm, for example. This corresponds to about 150 dots at a density of 400 dpi. In this case, in the second division, the predetermined length LG2 is set to be smaller than 1 cm and 30% or more for the vertical and horizontal lengths of the local area AL. The predetermined length LG1 may be set to an appropriate value in the range of several mm to several cm.
[0060]
The attribute is discriminated in each of the divided local areas AL. As is clear from FIG. 10B, only the inside of the local area AL0 is divided by the boundary lines LB9 and LB10 extracted in the local area AL0. Accordingly, useless division is not performed on the local area AL that does not need to be divided, so that the time required for calculation is shortened.
[0061]
According to the above-described embodiment, even when a plurality of types of images such as characters / photos / halftone dots exist in the original image RF, the Hough transform is applied to the photo / halftone images, and the boundaries between the images. By extracting the line LB, it is possible to accurately determine the region. In particular, since the area of the photograph / halftone dot image is often rectangular, accurate area discrimination with less noise can be performed by detecting the rectangular local area AL by Hough transform.
[0062]
In addition, the character image can be subjected to a closing process to reduce misidentification. In particular, since the Hough transform is not performed in the character image area, the amount of calculation is reduced and the processing speed is improved.
[0063]
By synthesizing these corrected attribute information DA2a and b, accurate attribute information DA2 can be obtained as a whole, and appropriate image processing corresponding to each attribute can be performed.
[0064]
Next, attribute correction processing will be described with reference to a flowchart.
11 is a flowchart showing the entire attribute correction process, FIG. 12 is a flowchart showing the attribute determination process by Hough transform, FIG. 13 is a flowchart showing the local region dividing process, and FIG. 14 is a diagram for explaining the concept of the attribute correction process It is.
[0065]
In FIG. 11, attributes are determined for each pixel (# 11), and an attribute map MP is created for each attribute (# 12). That is, the attribute map MP is created for each candidate area of each image of characters, photos, and halftone dots.
[0066]
For the character image candidate area, the closing process is performed on the attribute map MP (# 13). In the closing process, a disk filter corresponding to the maximum character size (14 points) is used, and the image is once thickened and then contracted.
[0067]
For the photograph or halftone dot candidate region, the attribute discrimination process by Hough transform is performed for each attribute map MP (# 14, 15). After each processing is completed, the respective attribute maps MP are comprehensively determined and synthesized (# 16). In composition, the composition is preferentially performed in order of accuracy of attribute discrimination for each pixel, for example, dot, photograph, and character. That is, when areas overlap each other, the areas are secured in the order of halftone dots, photos, and characters.
[0068]
In FIG. 12, noise is removed by removing isolated points (# 21). The isolated point is removed by, for example, removing an area area smaller than the maximum character size (14 points) included in the candidate area. This eliminates most of the noise. Then, the boundary point GB is detected (# 22), local region division processing is performed (# 23), and attributes are determined (# 24).
[0069]
In FIG. 13, the Hough transform is performed (# 31), and the area is recursively divided into local areas AL whose side length is equal to or greater than a predetermined length LG (# 32).
The image of the hair included in the photographic image is often misclassified as a character image or a halftone dot image in the attribute discrimination for each pixel. On the other hand, by applying the Hough transform, such erroneous determination is corrected and it is determined that the image is correct. In addition, a character image may be misclassified as including a halftone dot image or a photographic image. However, by performing a closing process on the character image, the misclassified region is correctly identified as a character image. It is determined that this is an image area.
[0070]
That is, as shown in FIG. 14, first, it is determined for each pixel whether the attribute is a character, a photograph, or a halftone dot, and an attribute map MP is generated for each attribute. . As a result, three attribute maps MPC1, MPP1, and MPM1 of the character image attribute map MPC1, the photographic image attribute map MPP1, and the halftone image attribute map MPM1 are generated.
[0071]
Next, an attribute correction process (# 13) by closing processing and an attribute correction process (# 14, 15) by Hough transform are performed on each attribute map MPC1, MPP1, and MPM1, and the attribute maps corrected thereby are respectively obtained. MPC2, MPP2, and MPM2 are obtained. Then, the corrected attribute maps MPC2, MPP2, and MPM2 are combined to obtain one comprehensive attribute map MPT.
[0072]
FIG. 15 is a diagram showing an example of the attribute map MP. FIG. 15A shows the original image RF2, and FIG. 15B shows an example of the attribute map MPP1 of the photographic image obtained by discriminating the attributes of the original image RF2 for each pixel, and FIG. Shows an example of a corrected attribute map MPP2 based on the attribute map MPP1.
[0073]
In the original image RF2 shown in FIG. 15A, a photographic image FP is arranged at the center, a character image FC is arranged at the periphery, and a plurality of halftone images FM are arranged so as to overlap them.
[0074]
As shown in FIG. 15B, a photographic image area AP1 is extracted at the center by performing attribute discrimination for each pixel on the original image RF2. The outside of the photographic image area AP1 is a non-photographic image area AP2. In the photographic image area AP1 shown in FIG. 15B, there is a missing portion from the original photographic image area shown in FIG. This is because the missing portion of the pixel is erroneously determined to be a pixel having another attribute rather than a pixel of the photographic image.
[0075]
When attribute correction processing by Hough transform is performed on the photographic image area AP1, the missing part is repaired as shown in FIG. 15C, and a photographic image area AP3 that substantially matches the original photographic image area is extracted. The
[0076]
Although illustration is omitted, an area substantially corresponding to the halftone image FM shown in FIG. 15A is extracted as the halftone image attribute map MPM2. A region corresponding to the character image FC shown in FIG. 15A is extracted as the character image attribute map MPC2, but the degree of coincidence is lower than that of other images. Therefore, when these are combined to obtain the attribute map MPT, areas are secured in the order of the halftone dot image area AM and the photographic image area AP, and the character area is determined in the remaining areas.
[0077]
In the above-described embodiment, the configuration, processing content, processing order, and processing timing of the image correction unit 36, the attribute correction unit AM, the first attribute correction unit AM1, the second attribute correction unit AM2, or the local region attribute storage unit 45. In addition, the whole of the image reading apparatus 1 or the configuration of each part can be appropriately changed in accordance with the gist of the present invention.
[0078]
【The invention's effect】
According to the first to fifth aspects of the present invention, the Hough transform is applied to a photo / halftone image even when a plurality of types of images such as characters / photos / halftone dots exist in the original image. By extracting the boundary line of each image, it is possible to accurately determine the region. In addition, it is possible to reduce misidentification by performing a closing process on a character image or the like.
[0079]
Therefore, appropriate image processing corresponding to the attribute can be performed on each region, and image degradation due to erroneous determination can be prevented. In addition, since application of Hough transform and application of processing other than Hough transform are selected according to attributes, it is possible to perform appropriate correction processing according to each attribute, thereby reducing misclassification and improving processing speed. Contribute.
[0080]
According to the invention of claim 5, since the region of the photograph / halftone image is often rectangular, it is possible to perform accurate region determination with little noise by detecting the rectangular local region AL by Hough transform. . In addition, since the Hough transform is not performed in the character image area, the amount of calculation is reduced and the processing speed is improved.
[Brief description of the drawings]
FIG. 1 is a diagram showing the overall configuration of an image reading apparatus incorporating an image processing unit according to the present invention.
FIG. 2 is a block diagram illustrating a configuration of an image processing unit.
FIG. 3 is a block diagram illustrating a configuration of an area determination unit.
FIG. 4 is a block diagram functionally showing the configuration of an attribute correction unit.
FIG. 5 is a block diagram illustrating a configuration of an image correction unit.
FIG. 6 is a diagram illustrating a concept of Hough transform.
FIG. 7 is a diagram for conceptually explaining the operation of attribute correction processing;
FIG. 8 is a diagram for conceptually explaining the operation of attribute correction processing;
FIG. 9 is a diagram conceptually illustrating a method of division into local regions.
FIG. 10 is a diagram showing another division within a local region.
FIG. 11 is a flowchart showing the entire attribute correction process;
FIG. 12 is a flowchart showing attribute determination processing by Hough transform.
FIG. 13 is a flowchart showing local region division processing;
FIG. 14 is a diagram for explaining the concept of attribute correction processing;
FIG. 15 is a diagram illustrating an example of an attribute map.
[Explanation of symbols]
36 Image correction unit (means for performing image processing)
41 feature amount extraction unit (means for extracting feature amount for each pixel)
42 attribute determination unit (means for generating pixel attribute information)
50 switching part (switching means)
51 Noise removal processing unit (means for performing noise removal processing)
52 Boundary point extraction unit (means for extracting boundary points)
53 Hough transform unit (means for transforming into a curve on a polar coordinate plane)
54 Intersection detection unit (means for detecting the intersection)
55 Inverse transformation unit (means for generating boundary line)
56 Local region extraction unit (means for extracting as a local region)
57 Attribute discrimination unit (means for discriminating attributes for each local region)
58 Closing processing unit (second attribute correction means)
AM1 first attribute correction unit (first attribute correction means)
DA1 attribute information (pixel attribute information)
DA2 attribute information (corrected attribute information)

Claims (7)

Extract features for each pixel of the input image,
Generate pixel attribute information by determining attributes for each pixel based on the feature amount,
Based on the pixel attribute information, for a photographic area or a halftone dot area, a Hough transform is applied to a pixel located at the boundary of the attribute to detect a straight line parallel to or perpendicular to the axis in the orthogonal coordinate plane. The image is divided into a plurality of rectangular local areas by the straight line , and the attribute having the largest number of pixels having the same attribute among the pixels included in each local area is attributed to the attribute of each pixel in each local area. the pixel attribute information corrected by determining as,
Perform image processing corresponding to each attribute for each region based on the corrected pixel attribute information,
An image processing method. For the character area, the pixel attribute information of each pixel is corrected by applying a closing process to the pixels included in the area.
The image processing method according to claim 1. Means for extracting feature values for each pixel of the input image;
Means for discriminating attributes for each pixel based on the feature amount and generating pixel attribute information;
Detecting a parallel or perpendicular straight line to the axis in the orthogonal coordinate plane by applying a Hough transform on the pixels positioned on the attributes of the boundaries, the image is divided into a plurality of rectangular local region by the detected straight lines and and divided First attribute correction means for correcting the pixel attribute information for each local area by determining the attribute having the largest number of pixels having the same attribute among the pixels included in each local area as the attribute of each pixel in each local area When,
Means for performing image processing corresponding to each attribute for each region based on the corrected pixel attribute information;
An image processing apparatus comprising: Second attribute correction means for correcting pixel attribute information of each pixel by applying a closing process to the pixels included in the character region;
Switching means for switching the first attribute correction means and the second attribute correction means in accordance with the attribute based on the pixel attribute information;
The image processing apparatus according to claim 3, comprising: The second attribute correction means includes
Means for detecting the maximum value of the pixel of interest and its surrounding pixels;
Means for replacing the detected maximum value with the pixel of interest;
Means for detecting a minimum value in the replaced pixel of interest and its surrounding pixels;
Means for replacing the detected minimum value with the pixel of interest;
The image processing apparatus according to claim 4 , comprising: The switching means is
Selecting the first attribute correction means for a photo area and a halftone dot area, and selecting the second attribute correction means for a character area;
Claim 4 or claim 5 Symbol mounting image processing apparatus. The first attribute correction means includes:
Means for extracting a boundary point that is a pixel located at the boundary based on the pixel attribute information;
Means for applying a Hough transform to each boundary point in the Cartesian coordinate plane to convert it into a curve on the polar coordinate plane;
Means for detecting the intersection of each curve converted to a polar coordinate plane;
Means for generating a boundary line by inversely transforming the polar coordinates of the intersection at any position of θ = 0, π / 2, π among the detected intersections into a straight line on an orthogonal coordinate plane;
Means for extracting a rectangular region surrounded by the boundary line as a local region;
Means for determining an attribute for each local region;
The image processing apparatus according to claim 3 , comprising:

Images