JP2012205129A - Image processing device, image forming device and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent the occurrence of stripe-shaped density unevenness generated in a region of substantially constant pixel values when geometric conversion processing is performed on image data.SOLUTION: When rotation processing is indicated to an original image, a sub-pixel coordinate value calculation unit 34 calculates coordinate values of a sub-pixel in the original image corresponding to each pixel of an image after rotation processing. A determination unit 33 determines a degree of dispersion in the pixel values of 16 pixels in a determination region of 4 pixels×4 pixels including the sub-pixel (virtual pixel) of which coordinate values are calculated by the sub-pixel coordinate value calculation unit 34. Based on the degree of dispersion in the pixel values of the plurality of pixels in the determination region determined by the determination unit 33, a pixel value determination unit 35 switches to determine whether the pixel value of each pixel in the image after the rotation processing is to be calculated from the pixel values of the 16 pixels in the determination region of the original image, or the pixel value of a particular one pixel in the determination region is to be selected.

Description

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

  In Patent Document 1, interpolation data output from a plurality of interpolation calculation circuits having different interpolation characteristics is evaluated, an interpolation calculation circuit that is estimated to have the smallest interpolation error is specified, and the interpolation data of the interpolation calculation circuit is finalized. A pixel interpolation method is disclosed that is output as typical interpolation data.

JP 2005-117291 A

  An object of the present invention is to provide an image processing apparatus and an image forming apparatus capable of preventing the occurrence of streak-like density unevenness that occurs in an area where pixel values are almost constant when geometric transformation processing is performed on image data. And to provide a program.

[Image processing device]
According to a first aspect of the present invention, there is provided calculation means for calculating the coordinate value in the original image of the virtual pixel corresponding to each pixel of the image after the geometric transformation processing when the geometric transformation processing is instructed for the original image. ,
Determination means for determining a degree of variation in pixel values of a plurality of pixels of an original image in a determination area in a predetermined range including a virtual pixel whose coordinate value is calculated by the calculation means;
Based on the degree of variation of the pixel values of the plurality of pixels in the determination region determined by the determination unit, the pixel values of the pixels in the image after the geometric transformation process are converted into the pixels of the plurality of pixels in the determination region of the original image. An image processing apparatus comprising: a determination unit that switches between determining whether to calculate from a value or to select a pixel value of a specific pixel in the determination region.

  According to a second aspect of the present invention, the determination means determines whether the difference between the maximum value and the minimum value of the plurality of pixels in the determination region is equal to or greater than a preset threshold value. The image processing apparatus according to claim 1, wherein the degree of variation in pixel values of a plurality of pixels in the determination area is determined.

According to a third aspect of the present invention, there is provided image determination means for determining whether an original image is a natural image or a document image;
When the image determination unit determines that the original image is a natural image, the threshold value is set to a first value. When the image determination unit determines that the original image is a document image, the threshold value is set to the first value. 3. The image processing apparatus according to claim 2, further comprising setting means for setting a second value larger than the value.

  According to the fourth aspect of the present invention, the determination means determines whether the pixel values of all the plurality of pixels in the determination region are equal to or greater than a preset threshold value or less than the threshold value. The image processing apparatus according to claim 1, wherein the degree of variation of the pixel values of the plurality of pixels in the determination region is determined based on whether or not.

  The present invention according to claim 5 is directed to a method in which, when the determination unit has pixel values of all the plurality of pixels in the determination region within a preset range including the threshold value, The image processing apparatus according to claim 4, wherein the degree of variation in pixel values of the plurality of pixels is determined to be small.

  According to a sixth aspect of the present invention, when the determining unit determines that the degree of variation of the pixel values of the plurality of pixels in the determination region is small by the determining unit, the pixel of the pixel in the image after the geometric transformation process A value is determined based on a pixel value of a specific pixel in the determination region, and when the determination unit determines that the degree of variation in the pixel values of the plurality of pixels in the determination region is large, geometric conversion 6. The image processing apparatus according to claim 1, wherein pixel values of pixels in the processed image are determined by calculating from pixel values of a plurality of pixels in the determination region.

The present invention according to claim 7 further comprises detection means for detecting the contents of halftone processing in the original image before geometric transformation processing,
The determination unit determines the pixel value of the pixel in the image after the geometric transformation process when the state of the pixel value of the plurality of pixels in the determination region matches the content of the halftone processing detected by the detection unit. The image processing device according to any one of 1 to 6, wherein the image processing device is determined based on a pixel value of a specific pixel in the determination region.

[Image forming equipment]
According to an eighth aspect of the present invention, there is provided calculation means for calculating the coordinate value in the original image of the virtual pixel corresponding to each pixel of the image after the geometric conversion process when the geometric conversion process is instructed to the original image. ,
Determination means for determining a degree of variation in pixel values of a plurality of pixels of an original image in a determination area in a predetermined range including a virtual pixel whose coordinate value is calculated by the calculation means;
Based on the degree of variation of the pixel values of the plurality of pixels in the determination region determined by the determination unit, the pixel values of the pixels in the image after the geometric transformation process are converted into the pixels of the plurality of pixels in the determination region of the original image. Determining means for switching to determine whether to calculate from a value or to select a pixel value of a specific pixel within the determination region;
And an image output unit that outputs an image after the geometric transformation process in which the pixel value of each pixel is determined by the determination unit.

[program]
The present invention according to claim 9 is a step of calculating coordinate values in the original image of virtual pixels corresponding to each pixel of the image after the geometric transformation process when the geometric transformation process is instructed on the original image;
Determining a variation degree of pixel values of a plurality of pixels of an original image in a determination region in a predetermined range including a virtual pixel whose coordinate value is calculated;
Based on the degree of variation in the pixel values of the plurality of pixels in the determined determination region, the pixel value of each pixel in the image after the geometric transformation process is calculated from the pixel values of the plurality of pixels in the determination region of the original image. Or a step of switching and determining whether to select a pixel value of one specific pixel in the determination region.

  According to the first aspect of the present invention, when geometric transformation processing is performed on image data, image processing that can prevent the occurrence of streaky density unevenness that occurs in an area where pixel values are substantially constant. An apparatus can be provided.

  According to the second aspect of the present invention, in addition to the effect obtained by the first aspect of the invention, it is possible to determine variations in pixel values of a plurality of pixels only by calculating a difference between the maximum value and the minimum value. An image processing apparatus that can be provided can be provided.

  According to the third aspect of the present invention, in addition to the effect obtained by the second aspect of the present invention, when the original image is a natural image, it is difficult to perform pixel interpolation during the geometric transformation process. It is possible to provide an image processing apparatus that can

  According to the fourth aspect of the present invention, in addition to the effect obtained by the first aspect of the present invention, there is provided an image processing apparatus capable of determining variations in pixel values of a plurality of pixels by a simple method. Can do.

  According to the fifth aspect of the present invention, in addition to the effect obtained by the fourth aspect of the present invention, even for an original image in which an image region that fluctuates across a threshold exists. It is possible to provide an image processing apparatus capable of preventing the occurrence of uneven density.

  According to the present invention of claim 6, in addition to the effect obtained by the invention of any one of claims 1 to 5, pixel interpolation is not performed when the variation in pixel values of a plurality of pixels is small. When the pixel value of the image after rotation processing is determined based on the pixel value of one specific pixel in the determination area, and the pixel values of the plurality of pixels vary greatly, the pixels of the plurality of pixels in the determination area It is possible to provide an image processing device capable of determining pixel values of pixels of an image after rotation processing by performing pixel interpolation using values.

  According to the seventh aspect of the present invention, in addition to the effect obtained by the invention according to any one of the first to sixth aspects, an original image in which there is an image region where halftone processing is performed exists. In contrast, it is possible to provide an image processing apparatus capable of preventing the occurrence of streaky density unevenness.

  According to the eighth aspect of the present invention, when geometric transformation processing is performed on image data, image formation that can prevent the occurrence of streak-like density unevenness that occurs in an area where pixel values are substantially constant. An apparatus can be provided.

  According to the ninth aspect of the present invention, there is provided a program capable of preventing the occurrence of streaky density unevenness that occurs in an area where pixel values are substantially constant when geometric transformation processing is performed on image data. Can be provided.

It is a figure for demonstrating an example of the rotation process of an image. It is a figure for demonstrating the method for determining the pixel value of the image after rotation, when performing the rotation process of an image. It is a figure for demonstrating the relationship between a sub pixel and the pixel of an original image, when performing the rotation process of an image. It is a figure which shows an example of the stripe-shaped nonuniformity which generate | occur | produces in a uniform density | concentration area | region. 1 is a diagram illustrating a configuration of an image forming system according to an embodiment of the present invention. 1 is a block diagram illustrating a hardware configuration of an image forming apparatus 10 according to an embodiment of the present invention. 1 is a block diagram illustrating a functional configuration of an image forming apparatus 10 according to an embodiment of the present invention. It is a figure which shows an example of the content of halftone processing, such as a halftone dot period (pattern) of a halftone processing, and a halftone density. It is a block diagram which shows the structure of the pixel value determination part 35 shown in FIG. It is a figure which shows an example of the pixel value of 16 pixels of the determination area | region which determines the dispersion | variation degree of a pixel value. It is a figure which shows the other example of the pixel value of 16 pixels of the determination area | region which determines the dispersion | variation degree of a pixel value.

[background]
First, in order to help understanding of the present invention, its background and outline will be described.

  Here, a general image rotation process will be described first.

  When an original is read obliquely by the image reading apparatus, the read image may be inclined (skew). In such a case, as shown in FIG. 1, rotation processing is performed on the read image to correct the inclination of the document, and an image without inclination is obtained.

  When such a rotation process is performed, as shown in FIG. 2, a process for determining the pixel value of each pixel of the rotated image after the rotation process as the pixel value of the original image before the rotation process is performed. Is done. However, when the rotation processing angle is other than a specific angle such as 90 degrees, 180 degrees, and 270 degrees, the coordinate value of the pixel in the original image corresponding to each pixel of the rotated image is not an integer, but a decimal number, etc. Real value. However, since the pixel having such coordinates represented by decimal numbers does not exist on the original image, it is necessary to perform processing for determining the pixel value from the surrounding pixels.

As such processing, the following three methods are known.
(1) Nearest neighbor method (2) Bilinear interpolation method (bilinear interpolation method)
(3) Bicubic interpolation (bicubic interpolation)

  Next, these three pixel value determination methods will be described with reference to FIG. In the example shown in FIG. 3, a 4 × 4 pixel window including a virtual pixel (sub pixel) on the original image corresponding to the pixel in the rotated image is shown, and 16 pixels included in this window are represented by A11. Expressed as ~ A44.

  In the nearest neighbor method of these three pixel value determination methods, the pixel value of the pixel A22 closest to the coordinate position of the subpixel is selected as the pixel value of the image after the rotation process. In other words, in this nearest neighbor method, pixel interpolation calculation is not performed, and only pixel value selection is performed.

  In addition, in the bilinear interpolation method, pixel interpolation calculation is performed in which calculation is performed using the pixel values of the four pixels A22, A23, A32, and A33 around the coordinate position of the subpixel to calculate the pixel value of the image after rotation processing. Done.

  Furthermore, in the bicubic interpolation method, pixel interpolation is performed to calculate the pixel value of the image after rotation processing by performing a product-sum operation using the pixel values of 16 pixels A11 to A44 of a 4 × 4 pixel window including subpixels. An operation is performed.

  Of these pixel value determination methods, the nearest neighbor method requires the least amount of computation, but jaggies and the like occur in the image after the rotation process. And in the method of performing pixel interpolation using pixel values of a plurality of pixels, such as bilinear interpolation and bicubic interpolation, calculation processing is required for each pixel of the image after rotation processing. Later images can be obtained with higher quality than the nearest neighbor method. In particular, the bicubic interpolation method has a feature that an image having the highest image quality can be obtained although it is necessary to perform calculation using pixel values of 16 pixels.

  However, when calculating the pixel value of the rotated image by performing a product-sum operation based on the pixel values of a plurality of pixels as in the bicubic interpolation method, if there is a uniform density region in the original image, the image May deteriorate.

  When pixel interpolation is performed by the bicubic interpolation method described above, a calculation error having a specific period corresponding to the rotation angle occurs. In addition, accumulation of errors generated during the product-sum operation of the interpolation coefficient for performing the product-sum operation and the coordinate value of the sub-pixel results in continuous linear density unevenness as shown in FIG. , Streaky density unevenness occurs.

  Such streak-like density unevenness should not be a problem when the original image has a dispersed density value such as a natural image, but it is noticeable in a solid area where the density value is constant. It will be perceived as image degradation.

[Embodiment]
Next, embodiments of the present invention will be described in detail with reference to the drawings.
FIG. 5 is a block diagram showing a configuration of an image forming system according to an embodiment of the present invention.

  As shown in FIG. 5, the image forming system according to the embodiment of the present invention includes an image forming apparatus 10 and a terminal device 20 connected to each other via a network 30. The terminal device 20 generates print data and transmits the print data generated via the network 30 to the image forming apparatus 10. The image forming apparatus 10 receives the print data transmitted from the terminal device 20 and outputs an image corresponding to the print data on a sheet. The image forming apparatus 10 is an apparatus called a so-called multi-function machine having a plurality of functions such as a print function, a scan function, a copy function, and a facsimile function.

  Next, FIG. 6 shows a hardware configuration of the image forming apparatus 10 in the image forming system of the present embodiment.

  As shown in FIG. 6, the image forming apparatus 10 transmits and receives data to and from an external device or the like via a CPU 11, a memory 12, a storage device 13 such as a hard disk drive (HDD), and a network 30. It has a communication interface (IF) 14, a user interface (UI) device 15 including a touch panel or a liquid crystal display and a keyboard, a scanner 16, and a printer 17. These components are connected to each other via a control bus 18.

  The CPU 11 executes predetermined processing based on a control program stored in the memory 12 or the storage device 13 and controls the operation of the image forming apparatus 10. In the present embodiment, the CPU 11 has been described as reading and executing a control program stored in the memory 12 or the storage device 13, but the program is stored in a storage medium such as a CD-ROM and stored in the CPU 11. It is also possible to provide.

  FIG. 7 is a block diagram illustrating a functional configuration of the image forming apparatus 10 realized by executing the control program.

  As shown in FIG. 7, the image forming apparatus 10 according to the present exemplary embodiment includes an image processing apparatus 40 and an image output unit 50. In the present embodiment, in order to simplify the description, the description of the configuration related to the control of the printing process is omitted.

  In addition, as shown in FIG. 7, the image processing device 40 includes an image determination unit 31, a threshold setting unit 32, a determination unit 33, a subpixel coordinate value calculation unit 34, and a pixel value determination unit 35. And a halftone dot processing detection unit 36.

  When the rotation process is instructed for the original image, the sub-pixel coordinate value calculation unit 34 calculates the coordinate value in the original image of the sub-pixel (virtual pixel) corresponding to each pixel of the image after the rotation process.

  The determination unit 33 is a variation degree of pixel values of 16 pixels in a determination region (window) of 4 pixels × 4 pixels including the sub pixel (virtual pixel) whose coordinate value is calculated by the sub pixel coordinate value calculation unit 34. Determine. Specifically, the determination unit 33 determines whether or not the difference between the maximum value and the minimum value of the 16 pixels in the determination region of 4 × 4 pixels is equal to or greater than a preset threshold value. The variation degree of the pixel values of the 16 pixels in the determination area is determined.

  For example, when the pixel value of each pixel takes a range of 0 to 256, the determination unit 33 determines that the degree of variation is large when the difference between the maximum value and the minimum value of the pixel value is 10 or more, and the pixel When the difference between the maximum value and the minimum value is less than 10, it is determined that the degree of variation is small.

  The pixel value determination unit 35 determines the pixel value of each pixel in the rotated image based on the degree of variation of the pixel values of the plurality of pixels in the determination region determined by the determination unit 33 in the determination region of the original image. Whether to calculate from the pixel values of the 16 pixels or to select the pixel value of one specific pixel in the determination region.

  For example, when the determination unit 33 determines that the degree of variation of the pixel values of 16 pixels in a certain determination region is small, the pixel value determination unit 35 determines the pixel value of the pixel in the image after the rotation process as the determination region. The pixel value of one pixel closest to the sub-pixel among the plurality of pixels is determined. Then, when the determination unit 33 determines that the degree of variation of the pixel values of the 16 pixels in a certain determination region is large, the pixel value determination unit 35 determines the pixel value of the pixel in the image after the rotation process as the determination region. It is calculated by the product-sum operation using the pixel values of the 16 pixels. In this case, the pixel value determination unit 35 switches between the pixel value determination method based on the nearest neighbor method and the pixel value determination method based on the bicubic interpolation method as described above based on the determination result in the determination unit 33. Thus, the pixel value of each pixel in the rotated image is determined.

  Further, the image determination unit 31 determines whether the original image is a natural image or a document image. Specifically, the image determination unit 31 acquires a histogram (density distribution) of the image data of the original image, and evaluates a plurality of peak density values obtained from the acquired histogram and density values around the plurality of peaks. If the distribution around each peak density value is wide (distributed), it is determined that the original image is a natural image such as a photograph. Otherwise, it is a document image such as a character or a line drawing. judge.

  Then, the threshold value setting unit 32 sets a threshold value for determining the degree of variation of the pixel value in the determination unit 33 based on the determination result by the image determination unit 31. For example, the threshold setting unit 32 sets the threshold to 10 when the image determination unit 31 determines that the original image is a natural image, and determines that the original image is a document image. Set the threshold to 15.

  The halftone processing detection unit 36 detects the content of halftone processing in the original image before the rotation processing. Specifically, the halftone dot processing detection unit 36 performs halftone dots such as a halftone dot period (pattern) of halftone dot processing in the original image, a halftone dot density, and the like as shown in FIGS. 8 (A) and 8 (B). Detect the contents of the process.

  If the pixel value state of the 16 pixels in the determination area matches the content of the halftone processing detected by the halftone processing detection unit 36, the pixel value determination unit 35 displays the determination result in the determination unit 33. Regardless, the pixel value of the pixel in the image after the rotation processing is set as the pixel value of a specific pixel in the determination region (4 × 4 window). For example, the pixel value of the upper left pixel A11 in the 4 × 4 window as shown in FIG. 3 is set as the pixel value of the pixel in the image after the rotation process.

  The image output unit 50 outputs the image after the rotation process in which the pixel value of each pixel is determined by the pixel value determination unit 35 on a predetermined sheet.

Next, the configuration of the pixel value determination unit 35 shown in FIG. 7 will be described with reference to FIG.
As illustrated in FIG. 9, the pixel value determination unit 35 includes a line buffer 41, a product-sum calculator 42, a switch 43, and an image data memory 44.

  The line buffer 41 is a buffer memory for storing, for example, image data for six lines in the input original image.

  The product-sum operation unit 42 specifies a window including the sub-pixel calculated by the sub-pixel coordinate value calculation unit 34 among the windows (determination areas) divided every 16 pixels of 4 × 4 pixels, and the window The pixel value of the pixel after the rotation process is calculated by performing a pixel-interpolation by performing a product-sum operation using 16 pixels included in. Since a general method can be used for the specific contents of the product-sum operation, the description thereof is omitted here.

  The switch 43 selects either the pixel value subjected to pixel interpolation from the product-sum calculator 42 or the pixel value of the pixel closest to the sub-pixel (nearest neighbor pixel) based on the determination result by the determination unit 33. It should be noted that the switching unit 43 does not relate to the determination result from the determination unit 33 when the content of the halftone processing detected by the halftone processing detection unit 36 matches the pixel arrangement of the 4 × 4 pixel window. A pixel value of a specific pixel in a 4 × 4 pixel window is selected and output.

  The image data memory 44 is a memory for sequentially storing the pixel values selected by the switch 43. The image data stored in the image data memory 44 is output to the image output unit 50 as a rotated image after the rotation process.

  Next, operations in the image processing apparatus 40 of the present embodiment will be described in detail with reference to the drawings.

  For example, it is assumed that the pixel values of 16 pixels in the determination region in which the determination unit 33 determines the degree of variation in pixel values are values as illustrated in FIGS. 10 and 11.

  In the case shown in FIG. 10, the maximum value of the pixel value in the determination area is 202, and the minimum value is 199. Therefore, the difference between the maximum value and the minimum value is 3, which is smaller than the threshold value 10 for determining the degree of variation. For this reason, the determination unit 33 determines that the variation degree of the pixel values of 16 pixels as illustrated in FIG. 10 is small.

  In the case as shown in FIG. 10, the pixel value determination unit 35 determines a pixel value of one pixel closest to the sub-pixel among the 16 pixels, for example, 201 as the pixel value in the image after the rotation process.

  In the case as shown in FIG. 11, the maximum value of the pixel values in the determination area is 202, and the minimum value is 20. Therefore, the difference between the maximum value and the minimum value is 182 and is larger than the threshold value 10 for determining the degree of variation. For this reason, the determination unit 33 determines that the variation degree of the pixel values of 16 pixels as illustrated in FIG. 11 is large.

  In the case shown in FIG. 11, the pixel value determination unit 35 calculates a pixel value in the image after the rotation process by performing a product-sum operation using the pixel values of 16 pixels and performing a pixel interpolation process.

[Modification]
In the above embodiment, the determination unit 33 determines the degree of pixel value variation based on the difference between the maximum and minimum pixel values of the 16 pixels in the determination region. The degree determination method is not limited to such a method. For example, the determination unit 33 uses a 4 × 4 pixel window as a determination region, and all the pixel values of 16 pixels in the determination region are equal to or greater than a preset threshold value or less than the threshold value. You may make it determine the dispersion | variation degree of the pixel value of 16 pixels in this determination area | region depending on whether there exists.

  For example, the determination unit 33 may determine that the degree of variation in pixel values is small when the pixel values of 16 pixels in the determination region are all 128 or more or less than 128.

  When such a determination method is used, the determination unit 33 further determines the determination region when the pixel values of all 16 pixels in the determination region are within a preset range including 128. You may make it determine with the variation degree of the pixel value of 16 pixels of them being small. Specifically, the determination unit 33 also displays the pixel value when all the upper 3 bits when the 16 pixel values are expressed in binary numbers are “100” or when the upper 3 bits are all “011”. You may make it determine with the dispersion | variation in being small.

  Here, the upper 3 bits are “100” means that the pixel value is in the range of 128 (10000000) to 159 (10011111), and the upper 3 bits are “011”. Is in the range of 96 (01100000) to 127 (01111111). That is, all the upper 3 bits of the pixel value are “100” or all the upper 3 bits are “011” means that the pixel value is in the range of 96 to 159.

  In the above-described embodiment, the pixel value determination unit 35 determines the pixel value determination method by the nearest neighbor method and the pixel value determination method by the bicubic interpolation method as described above based on the determination result in the determination unit 33. It was explained as switching. However, the pixel value determination unit 35 is switched between the pixel value determination method based on the nearest neighbor method and the pixel value determination method based on the bilinear interpolation method as described above based on the determination result in the determination unit 33. Is also possible.

  Furthermore, in the above-described embodiment, the case where the input original image is rotated has been described. However, the present invention is not limited to this, and the image enlargement / reduction process, the deformation process, and the like are performed. The present invention can be similarly applied even when other geometric transformation (affine transformation) processing is performed.

10 Image forming apparatus 11 CPU
12 Memory 13 Storage Device 14 Communication Interface (IF)
DESCRIPTION OF SYMBOLS 15 User interface (UI) apparatus 16 Scanner 17 Printer 18 Control bus 20 Terminal apparatus 30 Network 31 Image determination part 32 Threshold setting part 33 Determination part 34 Sub pixel coordinate value calculation part 35 Pixel value determination part 36 Halftone process detection part 40 Image Processing Device 41 Line Buffer 42 Multiply-Accumulator 43 Switch 44 Image Data Memory 50 Image Output Unit

Claims (9)

Calculating means for calculating coordinate values in the original image of virtual pixels corresponding to the respective pixels of the image after the geometric conversion processing when the geometric conversion processing is instructed on the original image;
Determination means for determining a degree of variation in pixel values of a plurality of pixels of an original image in a determination area in a predetermined range including a virtual pixel whose coordinate value is calculated by the calculation means;
Based on the degree of variation of the pixel values of the plurality of pixels in the determination region determined by the determination unit, the pixel values of the pixels in the image after the geometric transformation process are converted into the pixels of the plurality of pixels in the determination region of the original image. Determining means for switching to determine whether to calculate from a value or to select a pixel value of a specific pixel within the determination region;
An image processing apparatus.   The determination means determines whether or not the plurality of pixels in the determination region are different depending on whether or not the difference between the maximum value and the minimum value of the pixel values of the plurality of pixels in the determination region is greater than or equal to a preset threshold value. The image processing apparatus according to claim 1, wherein the degree of variation in pixel values is determined. Image determination means for determining whether the original image is a natural image or a document image;
When the image determination unit determines that the original image is a natural image, the threshold value is set to a first value. When the image determination unit determines that the original image is a document image, the threshold value is set to the first value. Setting means for setting a second value larger than the value;
The image processing apparatus according to claim 2, further comprising:   The determination means determines whether or not the pixel values of all the plurality of pixels in the determination area are greater than or equal to a preset threshold value or less than the threshold value. The image processing apparatus according to claim 1, wherein a degree of variation in pixel values of the pixels is determined.   When the pixel values of all of the plurality of pixels in the determination region are within a preset range including the threshold value, the determination unit varies the pixel values of the plurality of pixels in the determination region. The image processing apparatus according to claim 4, wherein the degree is determined to be small.   The determination unit determines the pixel value of the pixel in the image after the geometric transformation process in the determination region when the determination unit determines that the degree of variation of the pixel values of the plurality of pixels in the determination region is small. Pixel value of the pixel in the image after the geometric transformation process, when the determination unit determines that the degree of variation of the pixel value of the plurality of pixels in the determination region is large The image processing apparatus according to claim 1, wherein the image processing device is determined by calculating from pixel values of a plurality of pixels in the determination region. It further comprises detection means for detecting the contents of halftone dot processing in the original image before geometric transformation processing,
The determination unit determines the pixel value of the pixel in the image after the geometric transformation process when the state of the pixel value of the plurality of pixels in the determination region matches the content of the halftone processing detected by the detection unit. The image processing device according to any one of 1 to 6, wherein the image processing device is determined based on a pixel value of a specific pixel in the determination region. Calculating means for calculating coordinate values in the original image of virtual pixels corresponding to the respective pixels of the image after the geometric conversion processing when the geometric conversion processing is instructed on the original image;
Determination means for determining a degree of variation in pixel values of a plurality of pixels of an original image in a determination area in a predetermined range including a virtual pixel whose coordinate value is calculated by the calculation means;
Based on the degree of variation of the pixel values of the plurality of pixels in the determination region determined by the determination unit, the pixel values of the pixels in the image after the geometric transformation process are converted into the pixels of the plurality of pixels in the determination region of the original image. Determining means for switching to determine whether to calculate from a value or to select a pixel value of a specific pixel within the determination region;
Image output means for outputting an image after geometric transformation processing in which the pixel value of each pixel is determined by the determining means;
An image forming apparatus. Calculating a coordinate value in the original image of the virtual pixel corresponding to each pixel of the image after the geometric transformation process when the geometric transformation process is instructed on the original image;
Determining a variation degree of pixel values of a plurality of pixels of an original image in a determination region in a predetermined range including a virtual pixel whose coordinate value is calculated;
Based on the degree of variation in the pixel values of the plurality of pixels in the determined determination region, the pixel value of each pixel in the image after the geometric transformation process is calculated from the pixel values of the plurality of pixels in the determination region of the original image. Or a step of switching and determining whether to select a pixel value of a specific pixel in the determination region.

Images