JP4720236B2 - Image processing device - Google Patents

Description

  The present invention relates to a technique for processing digital data.

  With the increase in the broadband of computer networks and the increase in hard disk capacity of computers, image data having a large amount of data exceeding several Mbytes is being exchanged between computers and image processing is being performed by computers. For example, an image forming apparatus such as a full-color scanner or printer transmits / receives image data having a large amount of data to / from a personal computer or performs image processing on transmitted / received image data. Also, in personal computers and the like, image processing is performed on image data such as still images and video images with a large amount of data, and images are displayed.

  If the amount of image data handled by an image processing computer (hereinafter referred to as an image processing device) such as an image forming apparatus or a personal computer is enormous, the processing time becomes longer as the amount of data increases. A problem occurs.

For the purpose of increasing the processing speed of image processing, in the conventional image processing apparatus, the priority of the image processing process is set higher than that of the other processes, thereby delaying the image processing process due to the influence of other applications. A method is used to prevent this from happening.
From another point of view, the image processing apparatus is provided with a processor for image processing such as a DSP (Digital Signal Processor) separately from the CPU (Central Processing Unit), and the processor performs a part of the image processing process described above. By doing so, the image processing speed is increased.

For example, a technique disclosed in Patent Document 1 is disclosed for the purpose of maximizing the processing capability of an image processing apparatus using a multiprocessor using a plurality of processors. The technique described in Patent Document 1 can correctly evaluate the load of each processor including processing requests currently in the queue by estimating the processing load prior to the actual operation of image processing. ing. As a result, processing can be distributed to each processor based on appropriate load distribution, and load distribution to individual processors can be equalized.
Japanese Patent Laid-Open No. 06-274608

  Incidentally, when image processing is performed on image data such as a raster image, there is a format in which the entire image data is processed by repeatedly performing predetermined processing on each pixel constituting the image data. For example, in the case of negative / positive inversion processing, processing for replacing each component of R (red), G (green), and B (blue) with a difference value from a predetermined value (for example, 255) for each pixel constituting the image data. Do. By performing this process for each pixel constituting the image data, a negative / positive inversion process is performed.

  When image processing that repeats the same processing for each pixel, such as the negative / positive inversion processing described above, is performed on image data with a large amount of data, the image data is divided into fixed unit amounts, and unit amount images A method is used in which an image processing apparatus performs an image processing process by processing data in unit time. For example, when an image processing apparatus such as a scanner or a printer performs image processing, in order to follow the operation of the image output apparatus, image data processing for one page is performed for each conveyance time with the conveyance time of the paper as a unit time. Do. For this processing speed, a unit of ppm (page per minute) is generally used. For example, in the case of 60 ppm, the speed at which scanning processing and printing processing of one page per second is performed. A video image is also displayed by performing image processing of a unit amount of frames (images) per unit time. Generally, a video image is displayed by displaying 20 to 30 frames per second.

  When performing image processing for each unit time using the image processing processor as described above, the CPU passes the unit amount of data to the image processing processor, and the image processing processor passes the unit amount of data to the image processing. To do. A series of image processing is performed by the image processing processor performing unit processing continuously. In this case, the CPU generally controls the image processing processor by interruption. Specifically, the image processing processor transmits an interrupt signal to the CPU when the unit processing of the image ends. When the CPU receives this interrupt signal from the image processing processor, the CPU passes the unit amount of data to be processed next to the image processing processor via the buffer memory. The image processing processor performs image processing on the transferred unit amount data. By repeating this, the image processing process is executed.

  CPU interrupt processing has a large overhead (indirectly required processing and time required for processing), so if interrupt processing occurs frequently, the CPU is burdened, and others The problem occurs that the execution of the application of the application becomes extremely slow. This also causes a problem that processing requests from the CPU to the processor are delayed, the idle time of the processor is increased, and the processing time of the entire image processing is delayed. If the amount of buffer memory is increased, the amount of data that can be processed by the image processing processor per unit time is increased. Therefore, the number of interrupts to the CPU can be reduced correspondingly, and the processing speed can be improved. However, there is a problem that the larger the buffer memory amount, the higher the cost.

  The technique described in Patent Document 1 is intended to optimize the processing load shared by each processor in an image processing apparatus using a plurality of processors, but the processing load on the processor itself cannot be reduced. . Also, the amount of buffer memory is not taken into consideration, and when the amount of buffer memory is small, as described above, there is a problem that interrupt processing frequently occurs and execution of other applications is delayed.

  In view of the above-described conventional problems, the present invention reduces the load of the image processing process on the CPU while minimizing the amount of hardware buffer memory that executes a part of the image processing process. It is an object of the present invention to provide a software process scheduling technique that can reduce the influence.

The invention according to claim 1 performs image processing for each predetermined processing unit and outputs an interrupt signal at a predetermined timing and how to process the image data to be processed. Processing type information receiving means for receiving the processing type information for each processing unit, and a polling processing procedure and an interrupt processing procedure for controlling the image processing means are preset, and one of the processing procedures is selected. A control unit that executes, a determination unit that determines that the image processing time of the image processing unit is identifiable when the processing type information is information indicating predetermined image processing, and the determination unit If it is determined that the image processing time can be specified, the control means is made to select the polling processing procedure, and the determination means determines the processing time. If it is determined that the impossible to provide an image processing apparatus characterized by comprising a switching means for selecting the interrupt processing procedure for the control means.

According to a second aspect of the present invention, in the image processing apparatus according to the first aspect, the image data is raster image data.

According to a third aspect of the present invention, in the image processing apparatus according to the first aspect, the processing type information is information indicating whether or not the image processing is a filter processing, and the determination means includes the image processing type. When the information is information indicating that it is the filtering process, it is determined that the image processing time can be specified.
According to a fourth aspect of the present invention, in the image processing apparatus according to the first aspect, the processing type information is information indicating whether or not the image processing is color conversion processing, and the determination means includes the image processing When the type information is information indicating the color conversion process, it is determined that the image processing time can be specified.
According to a fifth aspect of the present invention, in the image processing apparatus according to the first aspect, the processing type information is information indicating whether or not the image processing is sub-sampling processing, and the determination means includes the image processing When the type information is information indicating the sub-sampling processing, it is determined that the image processing time can be specified.
According to a sixth aspect of the present invention, in the image processing apparatus according to the first aspect, the processing type information is information indicating whether or not the image processing is a negative / positive inversion processing, and the determination means includes the image processing When the type information is information indicating the negative / positive reversal processing, it is determined that the image processing time can be specified.
According to a seventh aspect of the present invention, in the image processing apparatus according to the first aspect, the processing type information is information indicating whether or not the image processing is a binarization processing, and the determination means includes the image processing device. When the process type information is information indicating the binarization process, it is determined that the image processing time can be specified.

The invention according to claim 8 is the image processing apparatus according to claim 1, wherein a buffer area used as a work area for the image processing, a data amount per unit pixel, a size of the buffer area, and the buffer area A polling interval calculating means for calculating a polling interval using a coefficient for the image processing, a clock cycle number per unit pixel required for the image processing, and a system clock frequency of the image processing means, and the polling processing procedure includes: characterized in that it is a procedure for performing a polling process on the basis of the polling interval calculated by said polling interval calculating unit.
The invention according to claim 9 is the image processing apparatus according to claim 8, wherein the polling interval calculation means includes a data amount N per unit pixel, a size B of the buffer area, a coefficient K for the buffer area, Using the number of clock cycles Cx per unit pixel required for the image processing and the system clock frequency F of the image processing means, the polling interval I is set to
I = (Cx / F) × (K × B / N)
It is characterized by calculating by.
The invention according to claim 10 is the image processing apparatus according to claim 9, wherein the coefficient K is ½.

According to an eleventh aspect of the present invention, in the image processing apparatus according to the ninth aspect, the polling interval calculation means is required for the filter processing of unit pixels as the clock cycle number Cx when the image processing is filter processing. The polling interval is calculated using the clock cycle number Cf.

According to a twelfth aspect of the present invention, in the image processing apparatus according to the ninth aspect, the polling interval calculation means, when the image processing is color conversion processing, uses the color conversion processing of unit pixels as the clock cycle number Cx. The polling interval is calculated using the number of clock cycles Cc required for.

According to a thirteenth aspect of the present invention, in the image processing apparatus according to the ninth aspect, the polling interval calculating means uses the sub-sampling processing of unit pixels as the clock cycle number Cx when the image processing is sub-sampling processing. The polling interval is calculated using the number of clock cycles Cs required for.

According to a fourteenth aspect of the present invention, in the image processing apparatus according to the ninth aspect, the polling interval calculation means, when the image processing is a negative / positive inversion process, the negative / positive inversion process of a unit pixel as the clock cycle number Cx The polling interval is calculated using the number of clock cycles Cn required for.

According to a fifteenth aspect of the present invention, in the image processing apparatus according to the ninth aspect, the polling interval calculation means, when the image processing is binarization processing, uses the binary value of the unit pixel as the clock cycle number Cx. The polling interval is calculated using the number of clock cycles Cb required for the conversion processing.

An embodiment of the present invention will be described below with reference to the drawings.
(1) Configuration (1-1) Overall Configuration of Image Forming Apparatus 1 First, the overall configuration of the image forming apparatus according to the present embodiment will be described.
FIG. 1 is a diagram illustrating an example of a hardware configuration of the image forming apparatus 1. The image forming apparatus 1 is a printer, a scanner, or a complex machine having a plurality of these functions. In the figure, reference numeral 10 denotes a control unit constituted by a CPU or the like, and controls each component described below. Reference numeral 11 denotes an image reading unit including an optical device configured by a CCD (Charge Coupled Device) or the like. The image reading unit 11 generates raster image data by decomposing an original image read by a CCD or the like into R, G, and B color components.

  An image processing unit (image processing apparatus) 12 performs image processing based on raster image data generated by the image reading unit 11. The image processing unit 12 performs image processing based on image data, performs various image processing, and each color of Y (yellow), M (magenta), C (cyan), and K (black) necessary for image formation. YMCK data converted into components is generated.

  An image output unit 13 performs an image forming process based on the YMCK data generated by the image processing unit 12. The image output unit 13 converts the YMCK data into pulse data, irradiates the photosensitive drum with image light based on the pulse data, forms a latent image due to the difference in electrostatic potential on the surface, and converts the latent image into the latent image. Transfer to paper. Reference numeral 14 denotes a user interface for the user to perform various operations. The user interface 14 includes a liquid crystal display that functions as a touch panel, and the user can perform various operations by touching the liquid crystal display.

(1-2) Configuration of Image Processing Unit 12 Next, the configuration of the image processing unit 12 will be described.
FIG. 2 is a diagram illustrating an example of the overall configuration of the image processing unit 12. In the figure, reference numeral 20 denotes an image processing chip, which includes a CPU 21, a processor 22, a local RAM 23, an image input I / F 24, and an image output I / F 25.

  The CPU 21 receives instructions from the control unit 10 and controls the operation of the entire image processing unit 12. The processor 22 receives various instructions from the CPU 21 and executes various image processes. A local RAM 23 is connected to the processor 22 as its own local memory. The image input I / F 24 stores the RGB image data from the image reading unit 11 in the RAM 27 in accordance with an instruction from the CPU 21. The image output I / F 25 reads and outputs CMYK image data stored in the RAM 27 in accordance with an instruction from the CPU 21.

  The ROM 26 stores a buffer amount B, a system clock frequency F, and a clock cycle number table TBL261. These are information referred to when the CPU 21 calculates the polling interval. The buffer amount B is a numerical value (unit: Byte) indicating the number of bytes in the buffer area 271 in the RAM 27 used when the CPU 21 instructs the processor 22 to perform image processing. The system clock frequency F is a numerical value indicating the system clock frequency (unit: Hz) of the processor 22.

  The clock cycle number table TBL 261 stores a numerical value (unit: cycle / pixel) indicating the number of clock cycles required for processing of one pixel for a process whose processing time can be calculated. As shown in FIG. 3, one record constituting the clock cycle number table TBL261 has fields for processing type information and clock cycle number. In the processing type information field, processing type information of image processing capable of calculating the processing time is stored. In the clock cycle number field, a numerical value indicating the number of clock cycles required for processing of one pixel is stored for the processing type information.

  The above-mentioned “image processing that can calculate the processing time” is image processing in which pixel values (three values of 256 gradations that define R, G, and B) of input image data are processed by a predetermined algorithm. Thus, the image processing does not depend on the image data to be processed. For example, image processing such as filter processing, color conversion processing, negative / positive inversion processing, sub-sampling processing, and binarization processing. Specifically, in the case of the filter process, a process of applying a filter having a size of n × m is performed for each pixel constituting the image data. The processing target image is converted in accordance with the characteristics of the filter. In the case of color conversion processing, processing is performed for each pixel constituting the image data in accordance with the color conversion law. For example, conversion from RGB to YMCK and from RGB to YCbCr is performed. In the case of the negative / positive inversion process, a process of replacing the pixel value with a difference value from a predetermined value (for example, 255) is performed for each pixel constituting the image data. By performing this process for each pixel constituting the image data, a negative / positive inversion process is performed. In the case of sub-sampling (thinning) processing, processing is performed in which pixels around the boundary line are thinned out according to a certain rule to extract some points, and intermediate colors of these colors are arranged around the boundary line. The number of pixels to be extracted is the number of input pixels, the number of pixels arranged around the boundary line is the number of output pixels, and the number of output pixels is a constant multiple of the number of input pixels. In addition, a process of calculating a pixel value that is an intermediate color between the extracted pixels based on a predetermined algorithm is performed. In the case of binarization processing, the pixel value of each pixel constituting the image data is compared with a predetermined threshold value (for example, 128), and converted to a binary image (1 bit) having no shading depending on the magnitude.

  A buffer area 271 is provided in the RAM 27. The image processing unit 12 executes various image processing processes such as sub-sampling processing and negative / positive inversion processing according to instructions from the control unit 10. In each unit process, the processor 22 extracts the processing target data in the buffer area 271 of the RAM 27 instructed by the CPU 21 and stores the processing result data in the processing result storage area in the buffer area 271 also instructed by the CPU 21. In this way, data transfer for each unit process is performed through the buffer area 271 including data input from the image reading unit 11 and data output to the image processing unit 12, and the data is buffered until the processing is completed. It stays on the region 271.

(2) Operation Next, the operation of the image forming apparatus 1 according to the present embodiment will be described.
When the user of the image forming apparatus 1 inputs an instruction to perform image processing using the user interface 14, the control unit 10 of the image forming apparatus 1 instructs the image processing unit 12 to perform image processing. The CPU 21 of the image processing unit 12 receives an instruction from the control unit 10 and executes an image processing process based on the instruction content.

FIG. 4 is a flowchart showing processing performed by the CPU 21 of the image processing unit 12. The operation of the image processing unit 12 will be described with reference to this figure.
When the CPU 21 of the image processing unit 12 receives an instruction to instruct image processing from the control unit 10 (step S1; YES), the CPU 21 selects whether to perform interrupt control or polling control for the instructed image processing. Polling determination processing is performed (step S2).

  FIG. 5 is a flowchart showing details of the polling determination process. The polling determination process will be described with reference to this figure. First, the CPU 21 determines whether to perform interrupt control or polling control by determining processing type information of image processing instructed from the control unit 10 (S101). This determination is made based on whether or not a record having the processing type information is stored in the clock cycle number table TBL 261 stored in the ROM 26. If stored (step S101; YES), it is determined that the polling control is to be performed because the processing time can be calculated. If not stored (step S101; NO), the processing time cannot be calculated. Therefore, it is determined that interrupt control is performed. If it is determined that the processing time can be calculated, the polling flag is set to “ON” (step S102). Otherwise, the polling flag is set to “OFF” (S103).

  Returning to the description of FIG. The CPU 21 determines whether or not to perform polling control by determining the polling flag set in the polling determination process of step S2 of FIG. 4 (step S3). If the polling flag is set to “ON” (step S3; YES), it is determined that the polling control is to be performed, and a process of calculating a polling interval is performed (step S4). When the polling flag is set to “OFF” (step S3; NO), it is determined that the interrupt control is performed without performing the polling control, and the polling interval calculation process of step S4 is not performed, and the interrupt of step S5 is performed. / Proceed to the polling switching process.

  The polling interval calculation process performed in step S4 of FIG. 4 will be described. First, the CPU 21 reads the buffer amount B and the system clock frequency F from the ROM 26. Further, the record having the processing type information of the instructed image processing is searched from the clock cycle number table TBL 261, and the clock cycle number Cx corresponding to the searched processing type information is read out. Further, referring to the data amount N (unit: bit / pixel) of the pixel of the input image data, the polling interval is calculated by the equation (6) using these.

When the polling interval is calculated in this way, the CPU 21 performs an interrupt / polling switching process (step S5).
FIG. 6 is a flowchart showing interrupt / polling switching processing. The interrupt / polling switching process will be described with reference to this figure. First, the CPU 21 determines whether or not the polling flag is “ON” (step S201). When the “polling flag” is set to “OFF” (step S201; NO), reception of an interrupt signal is permitted to perform interrupt control (step S202). The CPU 21 knows the end of the unit processing of the processor 22 by receiving the interrupt signal from the processor 22, and when receiving this interrupt signal, stores the next image data in the buffer area 271 and instructs the processor 22 to perform unit processing. To do. By repeating this for each unit process, the image processing process is executed.

  In step S201 of FIG. 6, when the “polling flag” is set to “ON” (step S201; YES), the process proceeds to step S203 and subsequent steps to perform polling control. First, reception of an interrupt signal is prohibited (step S203). In this case, even if an interrupt from the processor 22 occurs, the CPU 21 ignores it. Then, a timer is issued at the polling interval calculated in step S4 in FIG. 4 (step S204). Then, it waits until the set timer times out. When the timer times out (step S205; YES), the next image data is stored in the buffer area 271 and unit processing is instructed to the processor 22 by polling processing. (Step S206). By repeating this for each unit process, the image processing process is executed.

  When comparing each of the interrupt processing and the polling processing once, the load on the CPU 21 is smaller in the polling processing. By controlling the processor 22 not by interrupt processing but by polling processing for processing whose processing time can be calculated, it becomes possible to reduce the interrupt processing of the CPU 21, thereby reducing the load on the CPU 21, It is possible to reduce the influence of image processing on the application. That is, it is possible to reduce the load on the CPU 21 by the image processing process while minimizing the amount of hardware memory that executes a part of the image processing process. This makes it possible to minimize the influence of the image processing process on other applications even when other applications are operating in parallel in addition to the image processing process.

  Further, as shown in the equation (6), the polling interval is set so that the processing time required for the processor 22 to perform unit processing is set. Therefore, when the CPU 21 performs polling processing at the calculated polling interval, the processor The polling process can be performed at an appropriate timing when 22 completes the unit process.

<Modification>
As mentioned above, although embodiment of this invention was described, this invention is not limited to embodiment mentioned above, It can implement with another various form. An example is shown below.
(1)
In the above-described embodiment, an image forming apparatus such as a printer or a scanner is used as the image processing apparatus. However, the image processing apparatus is not limited to this and may be a personal computer or the like, and performs image processing. Any device may be used.

(2)
In the above-described embodiment, the image processing of raster image data is given as an example of the image processing that can calculate the processing time. However, the image processing that can calculate the processing time is limited to the image processing of raster image data. Any other digital data may be used as long as the processing time can be calculated.
In addition, the image processing that can calculate the processing time is image processing that does not depend on the image data to be processed. However, the image processing that can calculate the processing time is not limited to this, and the processing time can be calculated. Any image processing may be used.

  In the above-described embodiment, filter processing, color conversion processing, negative / positive inversion processing, sub-sampling processing, and binarization processing are given as examples of processing for which processing time can be calculated. However, the processing is not limited to this, and any processing may be performed as long as the processing time can be calculated. For example, there is a histogram generation process.

(3)
In the above-described embodiment, one processor 22 is used as a processor that performs image processing. However, the number of processors that perform image processing is not limited to one, and a plurality of processors may be used. Good.
In the above-described embodiment, the apparatus that performs image processing is a processor. However, the apparatus that performs image processing may use a general-purpose processor such as a DSP. For example, an ASIC (Application Specific Integrated Circuit) may be used. An LSI (Large Scale Integration) designed for a specific application may be used.

(4)
In the above-described embodiment, the polling interval is calculated using the equation (6). However, the polling interval calculation method is not limited to this, and any method can be used as long as the polling interval can be suitably calculated. It may be a method. For example, in the case of filter processing, color conversion processing, negative / positive inversion processing, subsampling processing, or binarization processing, formula (1), formula (2), formula (3), formula (4), or formula (5) May be used to calculate the processing time required for processing one pixel and set the polling interval based on the calculated processing time.
Further, when calculating the polling interval using the equation (6), the coefficient K of the buffer amount B is preferably set to ½, but the value of the coefficient K is not limited to this, Any value may be used as long as the polling interval can be suitably calculated.

  In the above-described embodiment, the polling interval is calculated every time the image processing unit 12 performs image processing. However, for each image processing, the polling interval is calculated in advance and stored in a table on the ROM. Alternatively, the polling interval may be referred to from the table when image processing is performed.

1 is a diagram illustrating an overall configuration of an image forming apparatus 1 according to an embodiment of the present invention. It is a figure which shows the whole structure of the image process part 12 of the embodiment. It is a data block diagram of clock cycle number table TBL261 of the embodiment. It is a flowchart which shows the process of the embodiment. It is a flowchart which shows the polling determination process of the embodiment. It is a flowchart which shows the interruption / polling switching process of the embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Image forming apparatus, 10 ... Control part, 11 ... Image reading part, 12 ... Image processing part, 13 ... Image output part, 14 ... User interface, 20 ... Image processing chip, 21 ... CPU, 22 ... Processor, 23 ... Local RAM 24... Image input I / F, 25. Image output I / F, 26... ROM, 27.

Claims (15)

Image processing means for performing image processing for each predetermined processing unit and outputting an interrupt signal at a predetermined timing;
Processing type information receiving means for receiving processing type information indicating how to process image data to be processed for each processing unit;
A control means for presetting a polling processing procedure and an interrupt processing procedure for controlling the image processing means, and selecting and executing any of the processing procedures;
A determination unit that determines that the image processing time of the image processing unit is identifiable when the processing type information is information indicating predetermined image processing ;
When the determination unit determines that the image processing time is identifiable, the control unit selects the polling processing procedure, and the determination unit determines that the processing time cannot be specified. In this case, an image processing apparatus comprising: switching means for causing the control means to select the interrupt processing procedure. The image processing apparatus according to claim 1, wherein the image data is raster image data. The process type information is information indicating whether the image process is a filter process,
The image processing apparatus according to claim 1, wherein the determination unit determines that the image processing time can be specified when the image processing type information is information indicating that the filter processing is performed. . The process type information is information indicating whether the image process is a color conversion process,
The image processing according to claim 1, wherein the determination unit determines that the image processing time is identifiable when the image processing type information is information indicating that the color conversion processing is performed. apparatus. The processing type information is information indicating whether the image processing is sub-sampling processing,
The image processing according to claim 1, wherein the determination unit determines that the image processing time can be specified when the image processing type information is information indicating that the sub-sampling processing is performed. apparatus. The processing type information is information indicating whether the image processing is a negative / positive inversion processing,
The image processing according to claim 1, wherein the determination unit determines that the image processing time can be specified when the image processing type information is information indicating that the negative / positive inversion processing is performed. apparatus. The processing type information is information indicating whether or not the image processing is binarization processing,
The image according to claim 1, wherein the determination unit determines that the image processing time can be specified when the image processing type information is information indicating the binarization processing. Processing equipment. A buffer area used as a work area for the image processing;
A polling interval using the amount of data per unit pixel, the size of the buffer area, the coefficient for the buffer area, the number of clock cycles per unit pixel required for the image processing, and the system clock frequency of the image processing means And a polling interval calculating means for calculating
The polling procedure is an image processing apparatus according to claim 1, characterized in that the procedure for performing a polling process on the basis of the polling interval calculated by said polling interval calculating unit. The polling interval calculating means includes a data amount N per unit pixel , a size B of the buffer area, a coefficient K for the buffer area, a clock cycle number Cx per unit pixel required for the image processing, and the image processing. Using the system clock frequency F of the means, the polling interval I is
I = (Cx / F) × (K × B / N)
Calculate with
The image processing apparatus according to claim 8. The image processing apparatus according to claim 9 , wherein the coefficient K is ½. The polling interval calculating means calculates the polling interval using the clock cycle number Cf required for the filter processing of a unit pixel as the clock cycle number Cx when the image processing is a filter process. The image processing apparatus according to claim 9 . The polling interval calculating means calculates the polling interval using the clock cycle number Cc required for the color conversion processing of a unit pixel as the clock cycle number Cx when the image processing is color conversion processing. The image processing apparatus according to claim 9 . The polling interval calculating means calculates the polling interval using the clock cycle number Cs required for the sub-sampling process of a unit pixel as the clock cycle number Cx when the image processing is a sub-sampling process. The image processing apparatus according to claim 9 . The polling interval calculating means calculates the polling interval using the clock cycle number Cn required for the negative / positive inversion processing of a unit pixel as the clock cycle number Cx when the image processing is negative / positive inversion processing. The image processing apparatus according to claim 9 . The polling interval calculating means calculates the polling interval using the clock cycle number Cb required for the binarization processing of a unit pixel as the clock cycle number Cx when the image processing is binarization processing. The image processing apparatus according to claim 9 .

Images