JP2005079940A - Image processing apparatus and copying machine with same - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor capable of increasing image types to be classified on the basis of a feature amount of image data and flexibly classifying the image types with high accuracy, and a copying machine provided with the image processor. <P>SOLUTION: An image type is determined (S13 and S15) on the basis of a feature amount detected (S12) from input image data obtained by reading an image on a medium to be read (S11). If there is no corresponding image type (S15: NO), a new image type can be registered as user definition (S20 to S28). Also, even when there is a corresponding image type (S13: YES or S15: YES), a new image type can be registered arbitrarily (S18: NO, and S20 to S28). Then, image processing that fits an optimum image type determined in accordance with an original image is applied to the input image data (S16 or S21), and an image based on the input image data can be formed on a medium to be recorded (S31). <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to an image processing apparatus capable of performing image processing based on an image type determined from a feature amount of image data on the image data, and a copying machine including the image processing apparatus.

  Conventionally, in an image processing apparatus mounted on a printer, a facsimile machine, a copier, etc., image data input for printing or the like is analyzed, and whether the image type of the original document from which the image data is based is a document It is determined whether the image is a photograph or another image type. Then, image processing is performed in accordance with the determined image type (for example, processing for emphasizing the edges of characters in the case of a document, etc.) Etc.). If the image data subjected to such image processing is printed, a better printing result can be obtained.

For example, in Patent Document 1, based on a plurality of feature amounts obtained by analyzing characteristic elements of image data, the distribution is made according to whether or not a predetermined condition is satisfied in the order of predetermined feature amounts, and a preset image type ( The document is classified so that it is classified as one of the document types.
JP 2000-295468 A (see FIG. 3)

  However, in Patent Document 1, whether or not a predetermined condition is satisfied in the order of the predetermined feature amount is assigned to the feature amount of the image data. For example, the feature amount 2 is similar to a document having different image types. When there are two pieces of image data, both of them may be classified as the same image type depending on the feature amount previously classified. In addition, the image type can be classified only into a preset type and may not necessarily be classified as the image type desired by the user.

  The present invention has been made to solve the above-described problems, and can increase the number of image types to be classified based on the feature amount of image data, and can perform image type classification that is flexible and accurate. An object of the present invention is to provide an apparatus and a copying machine including the apparatus.

  In order to achieve the above object, an image processing apparatus according to a first aspect of the present invention associates and stores a feature amount of image data and a predetermined image type whose type is classified according to the difference in the feature amount. A new image type information storage means, a feature quantity detection means for detecting the feature quantity of the input image data input, and a new image type not stored in the image type information storage means for the input image data Image type designation means for performing registration, a registered image type information storage means for storing the feature quantity of the input image data and the image type newly designated by the image type designation means, and the feature quantity detection Determining means for determining whether or not an image type corresponding to the feature amount of the input image data detected by the means is stored in the image type information storage means; Therefore, when it is determined that the image type is stored in the image type information storage unit, the image type information storage unit is referred to, and the image type is not stored in the image type information storage unit If it is determined, the reference means for referring to the registered image type information storage means, and the image type information stored in the image type information storage means or the registered image type information storage means referred to by the reference means. An image type determining unit for determining an image type corresponding to the feature amount of the input image data, and an image for the input image data based on the image type of the input image data determined by the image type determining unit Image processing means for performing processing.

  According to a second aspect of the present invention, in addition to the configuration of the first aspect of the invention, the image type is at least one of a document, a graphic chart, a natural image, a portrait, and a night view. The image type specifying unit causes the image processing unit to perform image processing for each image type on the input image data, and from the result, an arbitrary image type can be specified. It is characterized by.

  According to a third aspect of the present invention, in addition to the configuration of the first or second aspect of the present invention, the image processing unit performs at least an edge processing based on the image type of the input image data. The method includes any one of enhancement, smoothing, white balance adjustment, and saturation adjustment.

  According to a fourth aspect of the present invention, in addition to the configuration of the first aspect of the present invention, the image processing apparatus is determined after the image type determination unit determines the image type of the input image data. An image type creation unit for creating a new image type different from the image type, and the registered image type information storage unit is newly created by the feature amount of the input image data and the image type creation unit. The stored image type is stored in association with each other.

  According to a fifth aspect of the present invention, in addition to the configuration of the fourth aspect of the invention, the image type creation unit is configured to determine parameters for image processing performed on the input image data. Parameter determining means, image processing control means for controlling the image processing means to perform image processing based on the parameters determined by the parameter determining means for the input image data, and the image processing control means Processing image data storage means for storing the results of image processing performed on the input image data, and image processing based on all parameters within a range of parameters that can be determined by the parameter determination means. All parameter range image processing end judging means for judging whether or not the image processing control means has performed; When it is determined by the end determination means that the image processing control means does not perform image processing based on all parameters, the parameter determination means determines a parameter different from the determined parameter, and the image processing control means Image processing continuation control means for controlling image processing performed based on the different parameters in the processed image data storage means, and performing image processing based on the determined different parameters. When it is determined by the all parameter range image processing end determination means that the image processing control means has performed image processing based on all parameters, the results of the image processing stored in the processed image data storage means are listed as processed images. Displayed by the processed image list display means to be displayed and the processed image list display means. Image processing performed on the arbitrary processed image selected by the arbitrary image selecting means, and an arbitrary image selecting means for making it possible to select an arbitrary processed image from the processed images. It is created as a new image type to be associated with the feature amount of the input image data.

  According to a sixth aspect of the present invention, in addition to the configuration of the first aspect of the present invention, the image type determining means refers to the registered image type information storage means, and If the image type corresponding to the feature amount of the input image data is not stored, the image type information storage unit is referred to determine the image type corresponding to the feature amount of the input image data.

  According to a seventh aspect of the present invention, there is provided a copying machine comprising: an image reading means for reading an image formed on a read medium; and image data of the read medium read by the image reading means as input image data. 7. An image processing apparatus according to claim 1, which performs image processing on the input image data, and on the recording medium based on the image data of the read medium processed by the image processing apparatus. And image forming means for forming an image.

  In the image processing apparatus according to the first aspect, when the image type corresponding to the feature amount of the input image data is not in the predetermined image type, a new image type can be specified. Thus, it is possible to classify image types with higher accuracy.

  Further, in the image processing apparatus of the invention according to claim 2, in addition to the effect of the invention of claim 1, since general image types are stored in advance, it is necessary to newly designate these image types. Absent.

  Further, in the image processing apparatus of the invention according to claim 3, in addition to the effect of the invention according to claim 1 or 2, since various image processing can be performed according to the image type, a more suitable image processing result can be obtained. Can be obtained.

  Further, in the image processing apparatus according to the fourth aspect of the invention, in addition to the effect of the invention according to any one of the first to third aspects, the image type corresponding to the feature amount of the input image data is set to a predetermined image type. Even in such a case, since a new image type can be designated, the image type can be classified more finely and with higher accuracy.

  Further, in the image processing apparatus according to the fifth aspect, in addition to the effect of the invention according to the fourth aspect, an arbitrary process is selected from a plurality of processed images obtained by performing image processing with different parameters on the input image data. Since a new image type can be created by selecting an image, a new image type can be easily created, which is highly convenient.

  Further, in the image processing apparatus according to the sixth aspect of the invention, in addition to the effect of the invention according to any of the first to fifth aspects, the feature amount of the input image data is classified into a predetermined image type. However, since classification can be performed with priority over the newly designated image type, it is possible to classify the image type more finely and with higher accuracy.

  Further, since the copying machine of the invention according to claim 7 includes the image processing apparatus according to any one of claims 1 to 6, the image processing according to the image type of the image read from the read medium is performed. Thus, the image can be formed on the recording medium.

  An embodiment of an image processing apparatus embodying the present invention and a copying machine including the same will be described below with reference to the drawings, taking as an example a copying machine 1 equipped with the image processing apparatus according to the present invention. First, the overall configuration of the copying machine 1 will be described with reference to FIG. FIG. 1 is a perspective view showing the appearance of the copying machine 1.

  As shown in FIG. 1, the copying machine 1 includes a substantially rectangular parallelepiped housing 10 that is configured to be slightly wider in the left-right direction. The copying machine 1 discharges ink and optically reads the read medium on which the image is formed on the upper part of the printer unit 181 that forms an image based on the image data on the recording medium, and converts it into digital data. The scanner unit 171 is arranged.

  The printer unit 181 of the housing 10 of the copying machine 1 includes a paper feed tray 11 for supplying paper as a recording medium from the paper feed port 14 provided on the back surface of the housing 10 to the inside of the housing 10. A paper discharge tray 12 is provided for stacking and holding sheets on which images discharged from a paper discharge port 13 provided on the front surface of the housing 10 are formed. The printer unit 181 is a known ink jet printer, and ejects, for example, four colors of ink of yellow (Y), magenta (M), cyan (C), and black (K) from an ink jet head (not shown) to form paper. Perform color printing on The paper set in the paper feed tray 11 when printing is carried is conveyed from the paper feed port 14 on the back surface of the housing 10 to the inside of the printer unit 181, and after printing is performed, the paper discharge port 13 on the front surface. And are held in a stacked manner on the paper discharge tray 12. In FIG. 1, the paper discharge tray 12 can be stored at the bottom of the housing 10, and is used by being pulled forward when in use.

  On the front surface of the housing 10, there is provided an operation unit 17 that extends along the left-right direction of the housing 10 and has an operation surface directed obliquely upward and forward. On the operation surface of the operation unit 17, an operation panel unit 15 including a plurality of keys and switches for a user to give an instruction by key input to the copier 1, and an input subjected to image processing described later. A display panel unit 16 including a liquid crystal display or the like that displays image data or displays a message to the user when an operation or an error occurs is provided.

  On the upper surface of the housing 10, an upper lid portion 18 that can be opened and closed by using the back side of the housing 10 as a support shaft and lifting up the handle 18 a provided above the operation portion 17 on the front surface side. Is provided. A glass plate (not shown) that covers the inner upper surface of the housing 10 in a substantially horizontal direction is fixed to the inside where the upper lid portion 18 is lifted. A line CCD image sensor (not shown) for reading an image of a document as a read medium placed on the glass plate with a photodiode and converting it into digital data is provided below the glass plate surface. Yes. The scanner unit 171 is a so-called FB (Flat Bed) type scanner, and the CCD image sensor has a longitudinal direction of the housing 10 (main scanning direction) as a line direction in which the photodiodes are arranged in the horizontal direction. The document placed on the glass plate is scanned while moving the lower surface of the glass plate in the (sub-scanning direction).

  Further, the upper lid portion 18 is provided with an automatic document feeder (hereinafter referred to as “ADF (Automatic Document Feeder)”) 19. The ADF 19 is loaded with originals so that the originals can be read by passing over the CCD image sensor fixed by moving to the left end of the glass plate, and the ADFs 19 are drawn one by one from the supply port 20. A supply tray 21 is provided, and a discharge tray 23 is provided for loading and holding documents that have been read and discharged from the discharge port 22. The original passes from the supply port 20 toward the left end of the glass plate, passes through a U-turn-shaped conveyance path that goes U-turns on the CCD image sensor to the discharge port 22, and the horizontal direction of the casing 10 is the conveyance direction. Yes.

  Next, the electrical configuration of the copying machine 1 will be described with reference to FIGS. FIG. 2 is a block diagram illustrating a configuration of the control unit 100 of the copying machine 1. FIG. 3 is a conceptual diagram showing the storage area of the ROM 120. FIG. 4 is a conceptual diagram showing a storage area of the RAM 130. FIG. 5 is a conceptual diagram showing a storage area of the flash ROM 140.

  As shown in FIG. 2, a control unit 100 is provided inside the copying machine 1 to control each part of the copying machine 1. The control unit 100 is provided with a CPU 110 that controls the entire copying machine 1. A ROM 120 that stores various programs executed by the CPU 110 and the like are temporarily stored in the CPU 110 via a bus 115. The RAM 130 is connected to a flash ROM 140 that can read and write data and can store stored data even when the power is turned off.

  The CPU 110 also includes a circuit for driving a driving motor (not shown) of the ADF 19 of the scanner unit 171 and a CCD image sensor (not shown), and analog data read by the CCD image sensor. A scanner driving unit 170 including a / D converter (not shown) or the like is connected via a bus 115. Further, a circuit for driving an ink jet head (not shown) for ejecting ink onto the paper in the printer unit 181 and a drive motor (not shown) for transporting the paper are driven. A printer driving unit 180 provided with a circuit is connected to the CPU 110 via a bus 115.

  The CPU 110 further includes a screen drive unit 150 that controls display of an image on the display panel unit 16 provided in the operation unit 17, and an input that detects input of each key and switch of the operation panel unit 15 of the operation unit 17. The detection unit 160 is connected via the bus 115.

  Next, as shown in FIG. 3, the ROM 120 stores a program storage area 121 that stores various programs executed by the CPU 110, and an initial setting storage area that stores initial setting values set at the start of program execution. 122 and a table storage area 123 that stores an image type table (see FIG. 6) described later. Further, the ROM 120 is provided with various storage areas not shown.

  Next, as shown in FIG. 4, the RAM 130 has a work area 131 for storing temporary data during execution of the program, and input image data storage for storing an image read by the CCD image sensor as input image data. Area 132, processed image data storage area 133 capable of storing a plurality of input image data subjected to image processing, and output image data for converting input image data subjected to image processing for printing and storing as print data A storage area 134 is provided. Further, the RAM 130 is provided with various storage areas not shown.

  Also, as shown in FIG. 5, the flash ROM 140 is provided with a registration table storage area 141 that stores a registered image type table (see FIG. 7) described later. Further, the flash ROM 140 is provided with various storage areas not shown.

  Next, with reference to FIGS. 6 and 7, a table referred to in a copy program executed at the time of copying will be described. FIG. 6 is a conceptual diagram showing an image type table stored in the table storage area 123 of the ROM 120. FIG. 7 is a conceptual diagram showing a registered image type table stored in the registration table storage area 141 of the flash ROM 140.

  In the copying machine 1 according to the present embodiment, image processing is performed on image data of a document read by the scanner unit 171 and then printing on a sheet is performed by the printer unit 181. The image processing performed on the image data is known image processing such as edge enhancement, smoothing, white balance adjustment, and saturation adjustment. These image processes are performed on the read image data of the original document, that is, input image data. In the copying machine 1, the original image type (document, graphic chart, natural image, portrait image, night scene) is processed. Etc.), each process is applied to a different degree. Therefore, the feature amount of the input image data is detected, and the image type to which the input image data corresponds is classified based on the feature amount. The image type table and registered image type table indicate to which image type the input image data is classified from the feature amount detected from the input image data. Each element of the feature amount (edge amount, edge strength, number of colors) , Color distribution, person matching amount, fine dose) value range. Further, image processing performed on input image data according to the classified image type (HPF processing for performing edge enhancement, LPF processing for performing smoothing, and saturation enhancement processing for performing saturation adjustment) These parameter values are also associated with each other.

入力画像データの全画素についてこの値を求め、それぞれ実験等により決められた所定のしきい値と比較する。そして、そのしきい値よりも大きい値をとる画素をエッジを構成するエッジ画素とし、全画素に対するエッジ画素の割合を求めることによってエッジ量が求められる。また、エッジ強度は、エッジ画素の一次微分の大きさの平均値を求めることによって得ることができる。 Hereinafter, each element of the feature amount will be described. The edge amount is a value indicating the ratio of pixels in the boundary between the region configured by pixels similar to an arbitrary pixel in the input image data and the region configured by dissimilar pixels to all the pixels. It is. When the input image data is converted to gray scale, and the gradation value of an arbitrary pixel in the input image data is f (i, j), the horizontal primary spatial differential filter is expressed by the following equation.
g _h (i, j) = (-1) ・ f (i-1, j-1) + f (i + 1, j-1) + (-1) ・ f (i-1, j) + f (i + 1, j) + (-1) ・ f (i-1, j + 1) + f (i + 1, j + 1)
The vertical first-order spatial differential filter is expressed by the following equation.
g _v (i, j) = (-1) ・ f (i-1, j-1) + (-1) ・ f (i, j-1) + (-1) ・ f (i + 1, j -1) + f (i-1, j + 1) + f (i, j + 1) + f (i + 1, j + 1)
The magnitude of the first derivative of the arbitrary image is expressed by the following equation.

This value is obtained for all the pixels of the input image data, and each value is compared with a predetermined threshold value determined by experiment or the like. Then, a pixel having a value larger than the threshold value is set as an edge pixel constituting the edge, and the edge amount is obtained by obtaining the ratio of the edge pixel to all the pixels. The edge strength can be obtained by obtaining an average value of the magnitude of the first derivative of the edge pixel.

Next, the number of colors will be described. For example, when the R value, G value, and B value each take a value from 0 to 255 for the RGB value of an arbitrary pixel of the input image data, the color element of that pixel is
C _0,0,0 = 0 ≦ R ≦ 7, 0 ≦ G ≦ 7, 0 ≦ B ≦ 7
C _0,0,1 = 0 ≦ R ≦ 7, 0 ≦ G ≦ 7, 8 ≦ B ≦ 15
C _0,0,2 = 0 ≦ R ≦ 7, 0 ≦ G ≦ 7, 16 ≦ B ≦ 23
...
C _31,31,30 = 248 ≦ R ≦ 255, 248 ≦ G ≦ 255, 240 ≦ B ≦ 247
C _31,31,31 = 248 ≦ R ≦ 255, 248 ≦ G ≦ 255, 248 ≦ B ≦ 255
This area is divided into 32768 areas. Furthermore, each pixel is assigned to one of the regions for all the pixels of the input image data. If the number of color elements to which pixels are assigned is obtained, the number of colors can be obtained. In addition, with respect to the color elements to which the pixels are assigned, adjacent color elements (for example, C _0,0,0 and C _0,0,1 ) are processed as a single cluster. If this process is repeated for a predetermined number of times determined in advance by experiments or the like, the number of clustered clusters can be obtained as a color distribution.

  Next, the person matching amount will be described. As is well known, an image obtained by cutting a face region into a predetermined size from a plurality of human face images is prepared, and the gradation value of each image pixel corresponding to an arbitrary pixel of a certain image is prepared. Find the average. This is performed for all the pixels to create a pattern indicating the graphic features of the human face, that is, a human face template. This template is overlaid on the image indicated by the input image data, and the parameters of the template's coordinates, magnification, and rotation angle are arbitrarily changed. Based on the degree of coincidence between the image and the template, the area as a human face in the image To extract. The number of extractions corresponds to the person matching amount.

  Next, the fine dose will be described. The input image data is binarized with a predetermined threshold value, and the binarized input image data is scanned in the horizontal direction and the vertical direction, respectively. Regarding the change of the pixel at this time, the number of pixels that were the other gradation before the change from one gradation to the other gradation and before the change to one gradation was previously determined by experiments or the like. If it is less than the determined threshold value, it is regarded as a thin line and the number of pixels is counted. Then, if the ratio of the number of pixels regarded as a fine line in the total number of pixels is obtained in both scanning directions and the average is taken, the fine dose can be obtained.

  In the image type table shown in FIG. 6 and the registered image type table shown in FIG. 7, the range of the value of each element of the feature amount is associated with each image type. For example, if the image type is “document”, as shown in FIG. 6, the feature amount is a value between 30 and 50 (%) for the edge amount, and 1 to 5 (color) for the number of colors. It becomes. The amount of person matching is 1 to 6 (pieces), the edge strength is 60 to 80, the fine dose is 70 to 90 (%), and the color distribution is 1 to 5 (pieces). In the present embodiment, when the feature amount of the input image data is detected and each element satisfies all the above ranges, the document that is the basis of the input image data is classified as “document”. That is, in the image type table, if any one of the elements of the feature amount of a certain image type does not match, it is not classified into that image type. In this manner, similarly for other image types, that is, “graphic chart”, “natural image”, “person image”, and “night scene”, the value ranges are associated with each feature element. .

  Further, the image type table stores parameter values for image processing applied to the input image data for each image type. For example, when “document” is classified as the image type, LPF processing is performed. “0” is associated with the parameter value, “50” as the parameter value for HPF processing, and “0” as the parameter value for saturation enhancement processing.

  The LPF process is a process for so-called smoothing, and is a process for attenuating the feeling of roughness by attenuating high-frequency components. Specifically, a known weighted average smoothing process using a mask pattern is performed. For example, a mask of 3 × 3 pixels, 5 × 5 pixels, etc. is prepared, and the center pixel is weighted more than the surrounding pixels to the average value of the gradation of the colors in the mask, and the original pixel of the center pixel Each pixel in the mask is smoothed so as to retain the color. Then, by applying this process to all the pixels of the image, the rough feeling of the entire image is suppressed. The strength at which smoothing is performed is determined by the parameter value of the LPF process.

  The HPF process is a process for so-called edge enhancement, and is a process for enhancing high-frequency components and enhancing edge portions in an image. As in the case of the LPF process, a known sharpening process using a mask pattern is performed. The strength at which edge enhancement is performed is determined by the parameter value of the HPF process.

  The saturation enhancement process is a process for so-called saturation adjustment, and is a process for expressing a vivid hue by increasing the saturation of an image. The color of each pixel of the input image data indicated by the RGB value is converted into a known L * u * v * value. Here, in the u * v * plane, the saturation is enhanced as the distance from the origin increases. Therefore, a process for increasing the distance from the origin in the u * v * plane is performed for each pixel. The degree of distance expansion is determined by the parameter value of the saturation enhancement process.

  In the present embodiment, processing for white balance adjustment is also performed on the input image data. When reading a document, strong light is emitted from a light source (not shown) to illuminate the document, and the light intensity of the reflected light is read by a CCD image sensor (not shown). The light emitted from the light source may have different so-called color temperatures due to individual differences in the light source itself or the influence of changes over time, and the white color of the read image varies. The white balance adjustment process is a known process for correcting the variation due to the influence of the color temperature and whitening the color of the pixel that should be white. The intensity balance of the R value, G value, and B value of the input image data is adjusted.

  Next, the registered image type table shown in FIG. 7 is a table that allows a user to newly create and register an image type when the input image data is not classified by referring to the image type table. is there. User definition 1 to user definition 16 are provided as image types, and for each user definition, as described above, the value range of each element of the feature value and the image processing parameter value are stored in association with each other. Has been. As will be described later, in the present embodiment, the registered image type table is first referred to when classifying image types, and the image type table is referred to when classification is impossible. In some cases, all elements of any user-defined feature quantity in the registered image type table are included within the range of the feature quantity of an image type in the image type table, and by referring to the registered image type table first, User definition as an image type is applied with priority. The table storage area 123 storing the image type table corresponds to the “image type information storage unit” in the present invention, and the registration table storage area 141 storing the registered image type table is the “registered image type information” in the present invention. It corresponds to “memory means”.

  Next, according to the flowchart of the copying program shown in FIGS. 8 and 9, the operation during copying of the copying machine 1 will be described with reference to FIGS. 1 to 7, 10 and 11. FIG. FIG. 8 is a main routine of the copying program of the copying machine 1. FIG. 9 is a subroutine for image processing called from the main routine. FIG. 10 is a diagram illustrating an example of a screen displayed on the display panel unit 16 when selecting an optimal image processing result. FIG. 11 is a diagram illustrating an example of a screen displayed on the display panel unit 16 when selecting an optimal image processing result. Hereinafter, each step of the flowchart is abbreviated as “S”.

  In the copying machine 1 of the present embodiment, when copying is performed based on a user's operation, the copying program stored in the program storage area 121 of the ROM 120 is read into the work area 131 of the RAM 130 and executed. As shown in FIG. 8, when the copy program is executed, first, the initial setting at the time of executing the copy program is read from the initial setting storage area 122 of the ROM 120 and set as a parameter at the time of executing the program (S10).

  Next, an image formed on the upper surface of the original to be copied is read (S11). A document set on a glass plate (not shown) or an image on the upper surface of a document set to be read by the ADF 19 is read by a CCD image sensor (not shown), converted into digital data, and input image data Is stored in the input image data storage area 132 of the RAM 130. Note that the CPU 110 that controls to read the image of the document in the process of S11 corresponds to the “image reading unit” in the present invention.

  Then, the feature amount of the input image data is detected (S12). As described above, each element (edge amount, edge strength, number of colors, color distribution, person matching amount, fine dose) of the feature amount of the input image data is detected, and the result is stored in the work area 131. The Note that the CPU 110 that detects the feature amount of the input image data in the processing of S12 corresponds to the “feature amount detection means” in the present invention.

  Next, it is checked by referring to the registered image type table whether there is any image type (registered image type) defined by the user that matches all elements of the detected feature amount (S13). More specifically, first, for the user definition 1 in the registered image type table, it is confirmed whether each element of the feature amount of the input image data is sequentially within the range of the corresponding feature amount of the user definition 1 Is done. If there is even one out of the range, the same confirmation is performed for the user definition 2 next, assuming that the image type of the document is not the user definition 1. If there is a matching image type for all elements of the feature amount (S13: YES), the image processing parameter value of that image type is read into the work area 131, and the process proceeds to S16.

  If all the registered image types stored in the registered image type table are confirmed and there is no match (S13: NO), then the image type table is referred to and the preset image type (document In the same manner as described above, each of the image types is checked in order as to whether any of the elements of the feature amount matches any of a graphic chart, a natural image, a portrait, a night view, or the like (S15). As described above, if there is a matching image type for all feature amount elements (S15: YES), the image processing parameter value of that image type is read into the work area 131, and the process proceeds to S16. In the process of S15, the CPU 110 that refers to the image type table and confirms whether there is an image type that matches all the elements of the feature amount corresponds to the “determination unit” in the present invention. Further, it is determined that there is an image type in which all elements of the feature amount match in the registered image type table in the process of S13 or in the image type table in the process of S15, and the image type is determined as the image type of the document. The CPU 110 corresponds to “image type determining means” in the present invention.

  In S16, an image processing subroutine shown in FIG. 9 is called. As shown in FIG. 9, in the image processing subroutine, based on the image processing parameter values stored in the work area 131, the aforementioned LPF processing (S50), HPF processing (S51), and saturation enhancement processing (S52). ) Are sequentially applied to the input image data. Further, the input image data is subjected to white balance adjustment processing (S53). In each of these processes, the input image data is copied to the processed image data storage area 133, and the copied input image data is performed. Then, after the end of the image processing, the process returns to the main routine. The CPU 110 executing the image processing subroutine corresponds to the “image processing means” in the present invention.

  As shown in FIG. 8, when returning to the main routine of the copying program, the input image data subjected to the image processing is displayed on the display panel unit 16 (S17). If the user views the result of the image processing performed on the image of the document and instructs the operation panel unit 15 to perform printing, assuming that the image processing has been properly performed (S18: YES). Are stored in the processed image data storage area 133, are currently displayed on the display panel unit 16, and are subjected to color conversion on the input image data subjected to the above-described image processing, and output image data storage area The print data is stored in 134 (S30). As is well known, the input image data is image data indicated by RGB values, and color conversion into print data indicated by YMCK values is performed when printing is performed.

  Then, based on the print data, the printer unit 181 is driven, and, as is well known, four colors of ink are ejected from the ink jet head (not shown), and printing on the paper is performed (S31). In this way, the user can obtain a sheet on which an image subjected to appropriate image processing according to the image type of the document is copied. Note that the CPU 110 that controls to perform printing on a sheet in the processing of S31 corresponds to the “image forming unit” in the present invention.

  By the way, in the determination processing of S13 and S15, when there is no image type that matches the feature amount of the input image data in either the registered image type table or the image type table (S13: NO, S15: NO), they match. If there is an image type to be displayed and the image processing is performed and the image is displayed on the display panel unit 16 but the user does not consider the result of the image processing appropriate (S18: NO), the processing of S20 to S28 described below is performed. By doing so, the user can newly define an image type and register it as a registered image type. The CPU 110 that performs the processing of S20 to S28 and performs control so that a new image type can be defined corresponds to the “image type creation unit” in the present invention.

  The processes of S20 to S23 are processes for allowing the user to select input image data subjected to the most appropriate image processing from input image data subjected to the multiple pattern image processing. . First, based on the initial value of each parameter of image processing set in the initial setting of S10, for example, the parameter value is set as LPF: “0”, HPF: “0”, and saturation enhancement: “0”. (S20). Note that the CPU 110 that sets each parameter value of the image processing in the processing of S20 corresponds to the “parameter determining means” in the present invention.

  Next, an image processing subroutine is called (S21). As described above, the input image data copied to the processed image data storage area 133 is subjected to image processing based on each parameter value. For example, the parameter values for image processing are changed in units of 10 in the range of “0” to “40” for LPF, HPF, and saturation emphasis, respectively. Then, image processing based on all combinations of parameters is performed on the input image data. For this reason, as long as all combinations of parameters for image processing are not set (S22: NO), the process returns to S20, the parameters are changed and set (S20), and the newly set parameters (for example, LPF: “ 10 ”, HPF:“ 0 ”, saturation enhancement:“ 0 ”) is performed on the input image data newly copied to the processed image data storage area 133 (S21). In the processed image data storage area 133, all combinations (for example, LPF: “0”, HPF: “0”, saturation enhancement: “0” to LPF: “40”, HPF: “40”, saturation enhancement: Input image data that has been subjected to image processing of a combination of values that have been changed in units of 10 to “40” is stored. In step S21, the CPU 110 that calls the image processing subroutine and performs image processing on the input image data copied to the processed image data storage area 133 corresponds to the “image processing control means” in the present invention. The processed image data storage area 133 for storing the input image data subjected to the image processing corresponds to “processed image data storage means” in the present invention. Further, the CPU 110 that determines whether or not all the combinations of the parameters of the image processing have been set in the processing of S22 corresponds to the “all parameter range image processing end determination means” in the present invention and is not set. When the determination is made, the CPU 110 that controls to return to S20 corresponds to “image processing continuation control means” in the present invention.

If the input image data is subjected to image processing for all combinations of image processing parameters (S22: YES), it is possible to select input image data that has been subjected to optimal image processing for the user. The result of the image processing is displayed on the display panel unit 16 (S23). For example, as shown in FIG. 10, first, saturation enhancement: “0”, based on each combination of LPF: “0” to “40”, HPF: “0” to “40”. A list of input image data subjected to image processing is displayed. Then, when the user selects the input image data subjected to the optimum image processing for the LPF processing and the HPF processing by inputting the numbers assigned to the respective combinations from the operation panel unit 15 or the like, then FIG. 11, the LPF and HPF parameter values are selected values, and the saturation enhancement is “0”.
A list of input image data that has undergone image processing with different parameter values in the range of “40” to “40” is displayed. Similarly, when the user selects input image data that has undergone optimal image processing, the parameter values of LPF, HPF, and saturation enhancement are determined (S25). In addition, CPU110 which displays the result of an image process on the display panel part 16 by the process of S23 is equivalent to a process image list display means. In addition, the CPU 110 that displays selectable input image data subjected to optimal image processing in the process of S25 corresponds to the “image type designation means” in the present invention, and is optimal from the displayed input image data. The CPU 110 that allows the user to select an image that has undergone image processing corresponds to “arbitrary image selection means” in the present invention.

  If the user is not appropriate for the result of the image processing selected and determined in this manner (S26: NO), the user's operation is performed on the updated values of the LPF, HPF, and saturation emphasis parameter values. The change is made based on the input from the panel unit 15 (S27). For example, in the initial setting, LPF: “0”, HPF: “0”, saturation enhancement: “0” to LPF: “40”, HPF: “40”, saturation enhancement: “40”, 10 units. However, LPF: “30”, HPF: “50”, saturation enhancement: “20”, LPF: “50”, HPF: “50”, saturation enhancement. : Up to “60”, the update value of the parameter value is set so that the LPF is changed to 5 units, the HPF is unchanged, and the saturation enhancement is changed to 10 units. Then, returning to S20, as described above, image processing based on all combinations of parameter values is performed on the input image data, and the user is allowed to select input image data that has been subjected to optimal image processing.

  If the user is appropriate for the selected and determined image processing result (S26: YES), registration in the free storage area of the registered image type table is performed (S28). That is, each element of the feature amount of the input image data and each determined parameter of the image processing are associated with each other as a user definition and stored in the registered image type table. At this time, each element of the feature amount is stored as a predetermined range with the detected value as the center value. This range is preferably narrower than the range of each element of the feature amount of each image type set in the image type table (for example, a range having a value of ± 5 with respect to the center value). For example, an image (such as a photo of a blue sky) should be classified as a “natural image” in S15, but may be classified as a “graphic chart” if the feature values match. In such a case, the image is subjected to image processing different from that desired by the user. However, by applying the user definition to this image having a specific feature amount as described above, even when a similar image is read from the next time, the image processing desired by the user is performed. Can be set as follows.

  After registration of the user definition, as described above, the input image data for which the content of the image processing has been determined is subjected to color conversion processing to generate print data (S30), and printing based on this print data is performed. (S31). In this way, the user can customize the image type of the document and obtain a sheet on which an image subjected to more optimal image processing is copied.

  As described above, the copying machine 1 according to the present embodiment is equipped with an image processing apparatus that can be customized by performing user-defined registration according to user preferences. In this image processing apparatus, a feature amount is detected from input image data obtained by reading an image formed on a document, and an image of the document can be classified into image types that match each element of the feature amount. Then, image processing based on the classified image type can be performed on the input image data. In addition, it is possible to selectably display image processing content that the user thinks is optimal for input image data having a predetermined feature amount, and to store the selected image processing content as a user definition. . Since the user definition is determined as the image type of the document in preference to the preset image type, more appropriate image processing can be performed on the input image data even when feature amounts overlap. Can be applied.

  Needless to say, the present invention can be modified in various ways. For example, in the present embodiment, the result of image processing performed on the input image data is displayed on the display panel unit 16 to create a user definition. However, a personal computer is connected to the copying machine 1 and the personal computer is connected. You may make it create user definition etc. above.

  In addition, although the user-defined storage number of the registered image type table is “16”, it may be more or less. The preset image types stored in the image type table are not limited to documents, graphic charts, natural images, portraits, and night views, and may be classified into various image types. The types of image processing performed on the input image data are HPF processing, LPF processing, saturation enhancement processing, and white balance adjustment processing. However, more types of image processing are performed. May be.

  The image processing apparatus according to the present invention is applied to an image reading apparatus such as a scanner, an image forming apparatus such as a printer, an image transfer apparatus such as a facsimile, and an image display apparatus such as a monitor in addition to the copying machine according to the present invention. Can do.

1 is a perspective view showing an appearance of a copying machine 1. FIG. 2 is a block diagram illustrating a configuration of a control unit 100 of the copying machine 1. FIG. 3 is a conceptual diagram showing a storage area of a ROM 120. FIG. 3 is a conceptual diagram showing a storage area of a RAM 130. FIG. 3 is a conceptual diagram showing a storage area of a flash ROM 140. FIG. 3 is a conceptual diagram showing an image type table stored in a table storage area 123 of a ROM 120. FIG. 4 is a conceptual diagram showing a registered image type table stored in a registration table storage area 141 of the flash ROM 140. FIG. This is a main routine of a copying program of the copying machine 1. This is an image processing subroutine called from the main routine. FIG. 6 is a diagram illustrating an example of a screen displayed on the display panel unit 16 when selecting an optimal image processing result. FIG. 6 is a diagram illustrating an example of a screen displayed on the display panel unit 16 when selecting an optimal image processing result.

Explanation of symbols

1 Copier 100 Control Unit 110 CPU
120 ROM
123 Table storage area 140 Flash ROM
141 Registration table storage area

Claims (7)

Image type information storage means for storing the feature amount of the image data in association with a predetermined image type whose type is classified according to the difference in the feature amount;
Feature quantity detection means for detecting the feature quantity of the input image data input;
For the input image data, an image type designation unit for newly designating an image type that is not stored in the image type information storage unit;
A registered image type information storage unit that stores the feature amount of the input image data in association with the image type newly specified by the image type specifying unit;
A determination unit that determines whether or not an image type corresponding to a feature amount of the input image data detected by the feature amount detection unit is stored in the image type information storage unit;
If the determination means determines that the image type is stored in the image type information storage means, the image type information storage means is referred to and the image type is stored in the image type information storage means. If it is determined that the reference image type information storage means is referred,
Image type determining means for determining an image type corresponding to a feature amount of the input image data from among the image types stored in the image type information storing means or the registered image type information storing means referred to by the referring means. When,
An image processing apparatus comprising: image processing means for performing image processing on the input image data based on the image type of the input image data determined by the image type determining means.   The image type includes at least one of a document, a graphic chart, a natural image, a portrait, and a night view, and the image type designation unit sends the image processing unit to the image processing unit with respect to the input image data. The image processing apparatus according to claim 1, wherein image processing for each type is performed, and an arbitrary image type can be designated based on the result.   2. The image processing performed by the image processing unit based on the image type of the input image data includes at least one of edge enhancement, smoothing, white balance adjustment, and saturation adjustment. Or the image processing apparatus of 2. An image type creating means for creating a new image type different from the determined image type after the determination of the image type of the input image data by the image type determining means;
4. The registered image type information storage unit stores the feature amount of the input image data and the image type newly created by the image type creation unit in association with each other. An image processing apparatus according to claim 1. The image type creation means includes
Parameter determining means for determining parameters of image processing performed on the input image data;
Image processing control means for controlling the image processing means to perform image processing on the input image data based on the parameters determined by the parameter determination means;
Processed image data storage means for storing results of image processing performed on the input image data by the image processing control means;
All parameter range image processing end determination means for determining whether or not the image processing control means has performed image processing based on all parameters within a range of parameters that can be determined by the parameter determination means;
If the image processing control unit determines that the image processing control unit is not performing image processing based on all parameters by the all parameter range image processing end determining unit, the parameter determining unit determines a parameter different from the determined parameter. Image processing for controlling the image processing control means to perform image processing based on the determined different parameters and to store the result of the image processing performed based on the different parameters in the processed image data storage means Continuous control means;
When it is determined by the all parameter range image processing end determination means that the image processing control means has performed image processing based on all parameters, the result of the image processing stored in the processed image data storage means is used as a processed image. Processing image list display means for displaying a list;
Arbitrary image selection means for making it possible to select an arbitrary processed image from the processed images displayed by the processed image list display means,
5. The content of the image processing performed on the arbitrary processed image selected by the arbitrary image selecting unit is created as a new image type for associating with the feature amount of the input image data. An image processing apparatus according to 1.   The image type determining unit refers to the registered image type information storage unit, and if the image type corresponding to the feature amount of the input image data is not stored, refers to the image type information storage unit and the input image 6. The image processing apparatus according to claim 1, wherein an image type corresponding to a feature amount of data is determined. Image reading means for reading an image formed on the read medium;
The image processing apparatus according to claim 1, wherein the image data of the read medium read by the image reading unit is set as input image data, and image processing is performed on the input image data.
An image forming unit configured to form an image on a recording medium based on image data of the medium to be read processed by the image processing apparatus.

Images