JP4793409B2 - Image evaluation apparatus and program - Google Patents

Description

  The present invention relates to a technique for evaluating an image to be evaluated.

In an image forming apparatus such as a color printer or a multi-function peripheral, an image to be evaluated such as a color patch is formed on a sheet, read by a scanner, and the quality of the image to be evaluated is evaluated based on the read image. Some have the function of checking the state of the device. In such an image forming apparatus, in order to obtain an objective evaluation result, generally, the color space of the read image data is converted into a device-independent color space such as a CIELAB color space, and then the color values thereof are converted. Use to evaluate. However, in the color conversion parameters used for converting the color space, the color values of both color spaces are associated with each other for a number of colors distributed throughout the color space. For example, a plurality of colors in the image to be evaluated Depending on the degree of color material (toner) overlap and the order of the color, the conversion accuracy may deteriorate, and the evaluation result of the image to be evaluated may be unreliable. Therefore, Patent Document 1 discloses that a correction parameter corresponding to the color of the color material is provided to perform color conversion of each color image to improve the evaluation accuracy of the evaluated image for various colors.
JP-A-9-163168

However, in the technique of Patent Document 1, since it is necessary for the apparatus to recognize the color of the image to be evaluated, the user must perform an operation to specify the color, which imposes a burden on the user and causes an operation error. There is a problem that an accurate evaluation result cannot be obtained. In addition, the accuracy of the evaluation result may be reduced due to the color and density of the image to be evaluated, flare caused by external light entering the scanner, and the like.
The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a technique for evaluating the quality of an image to be evaluated with high accuracy without imposing a burden on the user.

To solve the problems described above, the present invention reads a target evaluation image, and generating means for generating image data representing the object to be evaluated image represented by the color in the first color space, said generating means generates The first color conversion means for converting the color space of the image data from the first color space to the second color space using the first color conversion parameter, and the first color conversion means First specifying means for specifying a color of an image corresponding to the image to be evaluated represented by the image data generated by the generating means based on the image data in which the space is converted; and a color in the second color space; , A correspondence relationship storage means for storing correspondence relationships between a plurality of predetermined colors, the correspondence relationship stored in the correspondence relationship storage means, and the second color by the first color conversion means. Image data converted to color space Based on, specified by the second specifying means and said first and second specifying means for specifying the color of the object to be evaluated image representing image data to which the generating means is generated by any of the color of the plurality of colors Second color conversion means for converting the color space of the image data generated by the generation means from the first color space to the second color space using a second color conversion parameter corresponding to the selected color. , before SL on the basis of the image data is color space converted by the second color conversion means, wherein evaluates the evaluation image, the image evaluation device, characterized in that it comprises an evaluation unit for outputting the evaluation result provide.

In the image evaluation device of the present invention, the second color space is a color space defined by a component related to lightness and a component related to hue and saturation. In this case,
The first color space is a color space defined by red, green, and blue color components, and the first specifying means determines the color of the image to be evaluated whose saturation is equal to or greater than a threshold value. It may be specified as any one of cyan, magenta, and yellow, which are colors of the color material expressing the color of the image to be evaluated, and red, green, and blue corresponding to the color components in the first color space. preferable.

Further, in the image evaluation apparatus of the present invention, the correspondence storage means stores a color conversion parameter storage for storing a conversion parameter for each color for converting each color in the first color space to a color in the second color space. And a color value storage means for storing the color in the second color space and each color of the plurality of colors in association with each other, and the second specifying means is stored in the color conversion parameter storage means Using the converted conversion parameters for each color, the color of the image to be evaluated represented by the image data generated by the generation unit is converted into a color in the second color space, and is stored in the color value storage unit. among the plurality of colors with the color difference is not the most small and the color of the converted, it is preferable to identify the color of the object to be evaluated image. The first color space is a color space defined by red, green and blue color components, and the color of the image represented by the image data generated by the generating means is black by a black color material. Is a first color obtained by reading the image to be evaluated, or a second color obtained by reading the image to be evaluated in which black is expressed by a combination of cyan, magenta and yellow color materials. In this case, when the ratio of the color values of the color components of red, green, and blue in the first color space matches, the second specifying means sets the color of the image to be evaluated as the first color. It is preferable to specify the color of the image to be evaluated as the second color when the ratio of the color values of the red, green and blue color components does not match.

In the image evaluation apparatus of the present invention, the second specifying unit examines colors at a plurality of positions in the image to be evaluated, and includes the same color that occupies a ratio equal to or greater than a threshold value at the plurality of positions. In this case , it is preferable that the same color is specified as the entire color of the image to be evaluated. The first color space is a color space defined by red, green, and blue color components, and the second color conversion means determines that the color of the image to be evaluated is the color of the image to be evaluated. For the image data specified by the first or second specifying means as the color of a single color material to be expressed, only a single color component of the color components in the first color space is used. It is preferable to express the color in the first color space by changing the color value, and then convert the color space of the image data to the second color space.

According to another aspect of the present invention, a computer reads an image to be evaluated and generates image data representing the image to be evaluated expressed in a color in the first color space, and image data generated by the generator The first color conversion means for converting the first color space from the first color space to the second color space using the first color conversion parameter, and the color space is converted by the first color conversion means. A first specifying unit that specifies a color of an image corresponding to the image to be evaluated represented by the image data generated by the generating unit, a color in the second color space, and a predetermined color based on the generated image data; wherein the corresponding relationship to the corresponding relationship stored hand stage is stored for storing a correspondence relationship between each of a plurality of colors which are, with the first image data converted into the second color space by the color conversion means Based on the generation means And a second specifying unit that the identified by any color of said plurality of colors of color of the evaluation image represented by the image data, the second corresponding to the identified color by the first and second identification means using the color conversion parameter, a second color conversion means for converting the color space of the image data to which the generating means has generated from the first color space into the second color space, before Symbol second color conversion A program for functioning as an evaluation means for evaluating the image to be evaluated based on the image data whose color space has been converted by the means and outputting the evaluation result is provided.

  According to the present invention, it is possible to evaluate the quality of an image to be evaluated with high accuracy without imposing a burden on the user.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. The image forming apparatus 1 described below has a function of an image evaluation apparatus that evaluates the quality of an image to be evaluated such as a color patch and inspects the state of the apparatus itself.
(A) Configuration FIG. 1 is a block diagram illustrating a hardware configuration of the image forming apparatus 1.
The control unit 10 includes a CPU (Central Processing Unit) that controls the entire apparatus, a RAM (Random Access Memory) that provides a work area, and a ROM (Read Only Memory) that stores various control programs, and is described in the control program. The calculation process is performed according to the procedure. The image reading unit 20 is a so-called scanner, and includes an unshown platen glass, a light source, an imaging lens, and a line sensor, and is an image reading unit that optically reads an image. The light source irradiates light on the sheet set on the platen glass. The imaging lens images the reflected light from the sheet at the position of the line sensor. The line sensor receives the imaged light, and generates and outputs an image signal corresponding to the light. The line sensor includes an image sensor that can image in three colors of R (red, red), G (green, green), and B (blue, blue), and generates image signals of these three colors. Then, the image reading unit 20 performs processing such as A / D conversion and shading correction on the image signal, and generates image data composed of pixel data of 8 bits (256 gradations). The image reading unit 20 reads an image such as an image to be evaluated, generates image data representing an image of a color in the RGB color space which is the first color space, and outputs this.

  The image forming unit 30 includes an image forming unit provided for each color (toner) of cyan (C), magenta (M), yellow (Y), and black (K), each of which is a photoconductor. A drum, a charging unit, an exposure unit, a developing unit, and a transfer unit are included. The photosensitive drum is a drum-shaped member that rotates around a shaft at a predetermined speed, and is charged to a predetermined potential by a charging unit. The exposure unit irradiates the charged photosensitive drum with laser light to form an electrostatic latent image. The developing unit develops a toner image by attaching toner to the electrostatic latent image formed on the photosensitive drum. The transfer unit transfers each color toner image developed on the photosensitive drum onto a sheet such as paper. Further, the image forming unit 30 includes a fixing unit, and fixes the toner image transferred to the sheet by each image forming unit. The storage unit 40 is a storage device such as an HDD (Hard Disk Drive), and stores various data such as image data for forming an image to be evaluated.

The image processing unit 50 stores a plurality of types of color conversion parameters for converting a plurality of image processing circuits such as ASIC (Application Specific Integrated Circuit) and LSI (Large Scale Integration), and a color space that defines the color of the image. And a variety of image processing is executed by each image processing circuit. Specifically, the image processing unit 50 applies color conversion parameters to image data whose color is represented by the color values in the RGB color space, and uses the color values in the CIELAB color space, which is the second color space. Image data representing a color is generated. The CIELAB color space is a color space defined by components related to lightness L * and components a * and b * related to hue and saturation. For example, CIE (Commission Internationale de l'Eclairage: International Lighting Commission) There is a color system recommended in 1976. In the color conversion parameter, for example, among the color values in the RGB color space of the color chart and the color values in the CIELAB color space, a method of measuring an unknown color value and associating each color value with each other, It is generated in advance using a method using a color prediction model that estimates and calculates the correspondence between the color values in the two color spaces according to a predetermined algorithm, and this is stored in the memory as a lookup table (LUT) or an arithmetic expression. Has been.
The UI unit 60 is a user interface such as a touch panel in which operation input is performed by the user and notification including display for the user is possible. The communication unit 70 is an interface device for performing communication via a network such as a LAN (Local Area Network), and receives image data from an external terminal such as a computer (not shown) and outputs various types of information. .

Here, an evaluation image used by the image forming apparatus 1 will be described.
The image to be evaluated is generally a square image to be evaluated (patch-like image) in which the density gradually changes in a predetermined direction of the sheet for evaluating the color reproduction characteristics of the image, In order to evaluate in-plane unevenness in which the density is non-uniform, an image to be evaluated in which images of the same color and the same density are distributed on almost the entire surface of the sheet is used. The color of the image to be evaluated formed by the image forming apparatus 1 is expressed by combining Y, M, C, K, which are the colors (primary colors) of a single color material, and two color materials. There are colors (secondary colors) that are expressed by combining three color materials R, G, B, and C, M, and Y corresponding to color components in the RGB color space. . In the secondary color, R (red) is expressed by a combination of yellow and magenta color materials, G (green) is expressed by a combination of magenta and yellow color materials, and B (blue) is cyan and magenta. It is expressed by a combination of color materials. Also, the tertiary color is not subjected to so-called under color removal (UCR), and is expressed by a combination of C, M, and Y toners (hereinafter referred to as “process black” or “Pk”). .) In such an image to be evaluated, the type of color and the density pattern are limited, unlike images handled by the user in printout or copy. In the image forming apparatus 1, an image to be evaluated of any one of C, M, Y, K, R, G, B, and Pk is used. In the density of the image to be evaluated, the density pattern is limited such that C is 80% and other colors are 0%. For example, the density of yellow (Y) is 80% and cyan (C). An image to be evaluated that contains a very small amount of another color for a color that occupies a large proportion, such as a density of 2%, is usually not used. Further, it is not required to accurately evaluate the density of the slightly contained color.

(B) Operation Next, the operation of the image forming apparatus 1 will be described.
The image forming apparatus 1 forms an image such as a printout that forms an image according to a user's request on a sheet based on image data representing an image read by the image reading unit 20 or image data received by the communication unit 70. In addition to the processing, at a certain timing such as maintenance, “evaluation processing” is performed to evaluate the image to be evaluated and inspect the state of the apparatus itself. Hereinafter, “inspection processing” will be described.
First, when the user operates the UI unit 60 to instruct execution of the inspection process, the control unit 10 causes the image forming unit 30 to form a predetermined image to be evaluated on the sheet according to the operation content. Here, the image to be evaluated formed on the sheet is determined based on the contents set in advance for the image forming apparatus 1 or the operation contents of the user. Subsequently, when the sheet on which the image to be evaluated is formed is set on the image reading unit 20 by the user and the reading is instructed by the operation of the UI unit 60, the image reading unit 20 represents the read image obtained by reading the sheet. Read image data is generated. This read image data is image data representing the color of the image by the color values in the RGB color space.

Next, FIG. 2 is a flowchart showing a procedure of processing for evaluating the evaluation image based on the read image data, which is executed by the image forming apparatus 1.
First, when acquiring read image data from the image reading unit 20, the control unit 10 causes the image processing unit 50 to convert the color space of the read image data from the RGB color space to the CIELAB color space. "Is executed (step S1). In the first color conversion process, the image processing unit 50 reads the color conversion parameter P_ALL (first color conversion parameter) stored in the memory, and applies the color conversion parameter P_ALL to the acquired read image data to perform color conversion. Transform space. Then, the control unit 10 stores the image data generated by performing the first color conversion process by the image processing unit 50 in the storage unit 40 as “color specifying image data”.
In this color conversion parameter P_ALL, the color values of the R, G, B color components in the RGB color space and the L *, a *, b * in the CIELAB color space for many colors distributed throughout the CIELAB color space. The correspondence relationship with the color value of each color component is defined. That is, in this step S1, the image processing unit 50 performs color conversion for all colors in the CIELAB color space using a common color conversion parameter.

Subsequently, the control unit 10 executes a “first color region specifying process” for specifying the color of the image to be evaluated represented by the read image data, based on the color specifying image data stored in the storage unit 40 (Step 1). S2). In the first color region specifying process, the control unit 10 refers to the color values L *, a *, and b * of each pixel of the color specifying image data, and reads the image (pixel) of the corresponding read image data. ) Color.
Next, the first color area specifying process will be specifically described.

FIG. 3 is a flowchart showing the procedure of the first color area specifying process executed by the control unit 10.
First, the control unit 10 determines whether or not the saturation COL of the image represented by the color specifying image data is greater than or equal to the threshold value T1 (step S21). The threshold T1 is “20”, for example, and is defined by an arithmetic expression of saturation COL = (a * + b *) ^1/2 .
Here, when it is determined that the saturation COL is equal to or greater than the threshold value T1 (step S21; YES), the control unit 10 specifies the color of the image to be evaluated based on the color value (step S23). The correspondence relationship between the color values in the CIELAB color space and the color of the predetermined image to be evaluated is stored in the storage unit 40 in advance, and the control unit 10 determines the correspondence relationship and the color values L *, a *, b. Based on *, the color of the image to be evaluated is specified as one of C, M, Y, R, G, and B.

  Here, in the first color region specifying process, the reason for specifying the color of the image to be evaluated for pixels whose saturation COL is equal to or higher than the threshold T1 will be described with reference to FIG. FIG. 4 is a diagram for explaining color coordinates of a predetermined color on an a * b * plane composed of components related to hue and saturation in the CIELAB color space. In the figure, the horizontal axis in the a * b * plane indicates the value of the a * component, and the vertical axis indicates the value of the b * component. That is, this figure is a diagram schematically showing the correspondence between the color values in the CIELAB color space and the color of a predetermined image to be evaluated. Further, in the a * b * plane of the figure, (a *, b *) = (0, 0) is the origin O, and the magnitude of the distance from the origin O corresponds to “saturation”. The boundary of the color coordinate range A represents the threshold value T1, the outer color coordinate is a saturation exceeding the threshold value T1, and the inner color coordinate is a saturation less than the threshold value T1.

  The color coordinates on the locus of each color of yellow (Y), magenta (M), and cyan (C) on the a * b * plane are as shown in FIG. These three color trajectories intersect at the origin O, and the color tone is determined by the position on the trajectory of each color. The control unit 10 specifies the color of the image to be evaluated based on the color value of each pixel and the locus of each color as shown in FIG. For example, with respect to magenta (M), the control unit 10 includes the color coordinates (a *, b *) of the pixel on the locus of magenta M and within the color coordinate range TM surrounded by the solid line around it. The color of the image to be evaluated is identified as magenta. For red (R), which is a combination of yellow (Y) and magenta (M), the control unit 10 determines that the color coordinate range TR surrounded by the dotted line is “red”. For other colors, color coordinates in the a * b * plane are determined in advance. The color with high saturation above the threshold value T1 is either a primary color of C, M, or Y, or a secondary color of R, G, or B, and conversely, such as K or Pk of the primary color. The saturation of the tertiary color is very low because the saturation is below the threshold value. For this reason, in the first color region specifying process, the control unit 10 determines the color of the image to be evaluated based on the color specifying image data whose saturation COL is equal to or greater than the threshold (outside the color coordinate range A). It is specified as any one of C, M, Y, R, G, and B.

  By the way, on the a * b * plane shown in FIG. 4, the color coordinates of a position far away from the origin O, that is, the color coordinates having a saturation COL higher than the threshold value T1, are overlapped with each other. In addition, the color of the image to be evaluated can be identified relatively easily and with high accuracy based on the color values. On the other hand, as for the position close to the origin O as in the color coordinate range A, the trajectories (and color coordinates) of the colors are close to each other, and from the color specification value of the color specifying image data, It is not easy to specify the color accurately, and there is a possibility of specifying the wrong color. This is because the color values may be shifted due to the conversion accuracy of the color conversion parameter P_ALL. Therefore, for a pixel whose saturation COL is lower than the threshold value T1, the control unit 10 specifies the color of the image to be evaluated as follows.

When the control unit 10 determines that the saturation COL of the image represented by the color specifying image data is lower than the threshold value T1 (step S21; NO), the image processing unit 50 separates the color conversion parameter P_ALL from the color conversion parameter P_ALL. The color conversion of the read image data is converted using the color conversion parameter P_HIGH (step S22). In the color conversion parameter P_HIGH, the color components L *, a *, b * and R, G, B color components in the CIELAB color space only for colors distributed within the color coordinate range A of the CIELAB color space. The correspondence relationship with the color value of is defined. In other words, since the color chart based on the creation of the color conversion parameter P_HIGH is also selected based on the color coordinate range A, the conversion accuracy of the color space within the color coordinate range A is higher than that of the color conversion parameter P_ALL. high. That is, the color coordinates in the color coordinate range A can be obtained with higher accuracy by converting the color space using the color conversion parameter P_HIGH. Then, the control unit 10 changes the color of the image to be evaluated to C, M, Y, R, G, and B based on the color specification value of the color specifying image data obtained by converting the color space using the color conversion parameter P_HIGH. Any one is specified (step S23).
The above is the description of the first color area specifying process.

Returning to FIG.
Subsequently, the control unit 10 executes a second color area specifying process (step S3). In the second color region specifying process, the control unit 10 specifies the color of the image to be evaluated of the pixel with extremely low saturation. In this case, “saturation is extremely low” means black (K) that is an achromatic color, process black (Pk), and chromatic colors of C, M, Y, R, G, and B that are almost similar to black. It is. In the a * b * plane shown in FIG. 2, the color coordinates in the immediate vicinity of the origin O are assumed. Here, it is assumed that the saturation COL is determined to be “3” or less in advance in the design stage.
The second color area specifying process will be specifically described.

FIG. 5 is a flowchart showing the procedure of the second color area specifying process executed by the control unit 10.
In the second color area specifying process, first, the control unit 10 sets color conversion parameters (hereinafter referred to as “conversion parameters for each color”) provided for each C, M, Y, K (single color) corresponding to the color of each toner. The color space of the read image data is converted from the RGB color space to the CIELAB color space by using the image processing unit 50 (step S31). Each color conversion parameter is a parameter for converting each color in the RGB color space to each color in the CIELAB color space. That is, in each color conversion parameter, for each corresponding color, the color values L *, a *, b * in the CIELAB color space and the color values of the R, G, B color components in the RGB color space The corresponding relationship is defined. Each color conversion parameter is stored in the memory of the image processing unit 50 in advance.
Subsequently, the control unit 10 compares the color specification values in the color specifying image data obtained by converting the color space using the color conversion parameters corresponding to the colors C, M, Y, and K with the predicted color specification values. (Step S32). The “predictive color specification value” is a color specification value L in the CIELAB color space when image data representing C, M, Y, and K images are color space converted using conversion parameters for corresponding colors. *, A *, b * are represented. The predicted color value is obtained experimentally and stored in advance in the storage unit 40 in association with the color of each predetermined image to be evaluated.

  And the control part 10 selects a color with the smallest color difference based on the result each compared by step S32 (step S33). The color selected here is identified by the control unit 10 as a color candidate of the read image. This is because when the color space of the read image data is converted using the conversion parameters for each color corresponding to the color of the read image, the difference between the color value and the predicted color value should be the smallest.

Subsequently, the control unit 10 determines whether or not the color difference between the color specification value of the color specifying image data and the predicted color specification value of the color selected in step S33 is equal to or less than a threshold value (for example, “1”). (Step S34). If the control unit 10 determines that the color difference exceeds the threshold (step S34; NO), the control unit 10 determines that the color of the image to be evaluated is not any of C, M, Y, and K, and proceeds to step S35. .
Then, the control unit 10 uses the color conversion parameters corresponding to each of R, G, B, and Pk, which are multiple colors, to change the color space of the read image data by the image processing unit 50 in the same manner as in step S31. Conversion is performed (step S35). Each color conversion parameter corresponding to each of R, G, B, and Pk is also stored in the memory of the image processing unit 50 in advance. Then, the control unit 10 selects a color having the smallest color difference between the color value of the CIELAB color space of the color specifying image data and the predicted color value corresponding to each of R, G, B, and Pk. The color of the evaluation image is specified as that color (step S36). Here, the reason why the color having the smallest color difference is specified is based on the same reason as the case where the candidate color is selected in step S33. Then, the control unit 10 ends the second color area specifying process.

On the other hand, when the control unit 10 determines that the color difference between the color specification value of the CIELAB color space of the color specifying image data and the predicted color specification value of the selected color is equal to or less than a threshold value (for example, “1”). (Step S34; YES), the selected color is specified as the color of the image to be evaluated (that is, one of C, M, Y, and K) (Step S37).
Subsequently, the control unit 10 determines whether or not the color of the image to be evaluated specified in step S37 is “K” (step S38). Here, when the control unit 10 determines that the specified color is not “K” (that is, any one of C, M, and Y) (step S38; NO), the control unit 10 sets the color of the image to be evaluated to step S37. In step S39, the second color area specifying process is terminated. On the other hand, when the control unit 10 determines that the specified color is K (step S38; YES), the color of the image to be evaluated is “K” or process black (Pk). A “black area determination process” is performed to determine whether or not (step S40).

Here, the reason for executing the “black area determination process” will be described.
The black expressed in the evaluated image may be expressed by black expressed by K toner or by process black (Pk) by a combination of cyan, magenta and yellow toners. It is not easy for the user to visually distinguish these colors, and even in the color values of the CIELAB color space, the color difference between them is considerably small. Therefore, the control unit 10 uses only the color values of the CIELAB color space. It is difficult to accurately determine whether the color of the image to be evaluated is “K” or process black (Pk). Therefore, the control unit 10 executes “black area determination processing” for accurately determining which one is the case.

FIG. 6 is a flowchart showing a procedure of black region determination processing executed by the control unit 10.
The controller 10 refers to the color values in the RGB color space for the read image identified as “K”, and calculates the ratio of the color values of the R, G, and B components (step S41). Then, the control unit 10 determines whether or not the image to be evaluated is “K” based on the calculated ratio of the colorimetric values of the R, G, and B components (step S42). Specifically, the control unit 10 has a ratio of the color values of the R, G, and B color components of 1: 1: 1 (including a case that is very close to the ratio, for example, within an error range that is equal to or less than a threshold). If there is, the read image is determined to be the first color obtained by reading the evaluation image in which black is expressed by K toner, and the evaluation image is determined as a candidate for “K”. As shown in FIG. 7, when the read image obtained by reading the “K” image is represented by the color values in the RGB color space, the RGB ratio of the color values is approximately 1: 1: 1.

When the control unit 10 determines that the image to be evaluated is “K” (step S42; YES), the control unit 10 proceeds to step S43. Then, the control unit 10 divides the image area of the read image corresponding to the “K” evaluation image into four, and performs the same determination as step S42 for each area (step S43). Here, for example, the average of the ratios of the RGB values of each area is set as the RGB ratio of the image area. Then, the control unit 10 determines whether or not the color of the image to be evaluated is determined to be “K” in all regions (step S44). When the control unit 10 determines “YES”, the color of the image to be evaluated is specified as “K” (step S45). The determination is performed a plurality of times because the RGB ratio of the color values may be 1: 1: 1 even in process black. Note that although four divisions are used here, it is sufficient to determine at least a plurality of regions.
On the other hand, when the control unit 10 determines that the ratio of the color values is not 1: 1: 1 even in one area (including the case where the error range is exceeded from 1: 1: 1) (step S44; NO), reading is performed. The image is determined to be the second color obtained by reading the evaluated image in which black is expressed by a combination of C, M, and Y toners, and the color of the evaluated image is specified as process black (Pk) (step S46). ).
If the controller 10 determines in step S42 that the color of the image to be evaluated is not “K”, it is immediately identified as process black (step S46).
Thereby, the control part 10 specified the color of the to-be-evaluated image in any one of C, M, Y, K, R, G, B, and Pk about all the color coordinates in a * b * plane.

Returning again to FIG.
The control unit 10 executes “second color conversion process” for converting the color space of the read image data from the RGB color space to the CIELAB color space based on the color of each image in the specified read image (step S4). ). In the second color conversion process, the control unit 10 uses the color conversion parameter (second color conversion parameter) corresponding to the color of each image specified in steps S2 and S3 to read the read image. Convert the color space of the data. Specifically, the image processing unit 50 performs color space conversion using color conversion parameters corresponding to each color of C, M, Y, K, R, G, B, and Pk. This color conversion parameter is obtained by reading each color image (color chart) of C, M, Y, K, R, G, B, and Pk, and changing the color space of the image data representing the read image from the RGB color space to CIELAB color. It is a parameter for converting to space. In these color conversion parameters, unlike the conversion parameters for each color, conversion parameters are defined over the entire CIELAB color space, but the effect of improving the conversion accuracy by using the color conversion parameters for each color is obtained. be able to.

  The control unit 10 evaluates the image to be evaluated based on the image data obtained by converting the color space using the color conversion parameter corresponding to each specified color, and outputs the evaluation result (step S5). At this time, for example, the control unit 10 uses the color specification value and the target color specification value of each pixel of the image data obtained in step S4 based on a predetermined evaluation algorithm stored in advance in the storage unit 40 or the ROM. Evaluate the image to be evaluated by determining the size of the difference between the image and the distribution of the pixels with the large difference in the image data, etc. A message such as “It has occurred” is displayed on the UI unit 60 and notified to the user. The evaluation result is used for maintenance (calibration or the like) of the image forming apparatus 1. Note that the contents of the evaluation algorithm and the output mode of the evaluation results are not limited to the contents described above.

FIG. 8 shows a comparison (color difference dE) between the color values obtained by performing the above-described inspection processing by the image forming apparatus 1 and color-converted, and the measured values of the color values obtained by measuring the image to be evaluated using a colorimeter. The experimental result which shows is shown. FIG. 8 corresponds to the first color conversion process, and shows an experimental result (color conversion common to all colors) when color conversion is performed using a common color conversion parameter in the entire color space as in the prior art. In addition, an experiment result (color conversion for each color) when the color of the image is designated by the user and color conversion is performed using the color conversion parameter corresponding to each color in the same manner as the image forming apparatus 1 is shown.
In this experiment, the number of samples is “5184”, and the “average color difference”, which is the average of the color difference between the colorimetric value obtained by reading and color-converting the image and the actual measurement value, matches at 95% or more. The “de_95% color difference” that is the average of the color differences between the color specification value and the actual measurement value, and the “maximum color difference” that is the maximum color difference between the color specification value and the actual measurement value, were obtained. As shown in FIG. 8, in “all color common color conversion”, the average color difference is “4.1”, the de_95% color difference is “11.9”, and the maximum color difference is “18.5”. The color difference from the measured value is large and the conversion accuracy is poor. On the other hand, in “color-to-color conversion” in which the color of the image is manually specified by the user, the average color difference is “0.4”, the de_95% color difference is “0.7”, and the maximum color difference is “2.0”. On the other hand, in the “image forming apparatus 1” in which the apparatus itself specifies the color of the image, the average color difference is “0.4”, the de_95% color difference is “0.8”, and the maximum color difference is “2.4”. The color difference between them was almost the same in all experimental results. As a result, even if the user himself / herself does not specify the color of the image and the image forming apparatus 1 specifies the color of the image and performs color space conversion using the color conversion parameter corresponding to the color, It was found that there was almost no difference in conversion accuracy from the case of “color conversion”. As a result, in the evaluation of the quality of the image to be evaluated, there is almost no difference between the evaluation results of both.

  According to the embodiment described above, in the inspection process, the image forming apparatus 1 changes the color space of the read image data from the RGB color space to the CIELAB color space using the common color conversion parameter (P_ALL) in the entire color space. The first color conversion processing to be converted is executed, and the color of the image corresponding to the image to be evaluated is specified in the read image based on the color specification values L *, a *, and b *. Then, the image forming apparatus 1 performs a second color conversion process for converting the color space of the read image data using different color conversion parameters for each specified color, and evaluates the image to be evaluated. According to this configuration, as can be seen from FIG. 8, the color conversion accuracy is improved and the evaluation result is further enhanced as compared with the case where a common color conversion parameter is used for all color coordinates. Also, the same conversion accuracy can be ensured as when color conversion is performed using different color conversion parameters for each color as specified by the user, and the same high accuracy can be obtained in the evaluation of the quality of the image to be evaluated. Can do. Further, since the image forming apparatus 1 itself specifies the color of the image, it is not necessary for the user to perform the operation of specifying the color of the image to be evaluated, the user is not burdened, and an operation error is caused. It is also possible to prevent errors in evaluation results and waste of toner and sheets.

(C) Modification The above embodiment may be modified as follows. These modifications can be appropriately combined with each other.
(C-1) Modification 1
In order to increase the conversion accuracy in the second color conversion process of the above-described embodiment, the following configuration may be adopted. In a general image forming apparatus, when an image to be evaluated is read to generate read image data in which colors are represented by color values in the RGB color space, toner images of C, M, Y, and K colors are generated. Based on the density, the color values of the R, G, and B color components are defined. However, for example, when obtaining the density distribution of yellow, if this is read by a sensor having sensitivity to R, B, and G, the color value of B (blue) greatly depends on the expression of the color, and R (red ) And G (green) color values are used as parameters, there is a problem that the change of the parameter hardly affects the change of yellow color and acts as noise. As a result, this noise also affects the color conversion, which adversely affects the evaluation result of the image to be evaluated. For an image representing only a single color material such as magenta or cyan, the color value of one of the color components of R, G, and B greatly affects its color, and the other color components Has little effect.
Therefore, in the first modification, the control unit 10 determines a color tone determined by the image processing unit 50 for an image region identified as a single color material color such as C, M, and Y. Only the color values of one color component are changed to express the color, and the color values of the other color components are fixed to generate read image data. On the other hand, for an image region expressed by colors of two or more color materials, the control unit 10 expresses each color by changing the respective color values of the three color components (or two color components). In this way, it is possible to suppress the influence of noise generated when the color image area of the single color material is specified on the evaluation result, and particularly effective when the image to be evaluated is yellow (Y). Is.

(C-2) Modification 2
In the first and second color region specifying processes of the above-described embodiment, the following configuration may be adopted in order to increase the conversion accuracy.
An image to be evaluated of a halftone of a certain color may be formed over the entire surface of the sheet, and the image forming apparatus 1 may evaluate the degree of in-plane unevenness and streaks from the variation in color values in the read image. When such an image to be evaluated is formed without in-plane unevenness and streaks, the read image data generated by the image reading unit 20 should have the same color values in the RGB color space for all regions. is there. However, in an optical image reading apparatus such as a scanner, there is a problem of flare in which light other than the light emitted from the light source enters the apparatus, and the same color values may not be obtained in all areas even under normal conditions. . Therefore, the control unit 10 may execute an algorithm as shown in FIG. 9 in the first and second color conversion processes.

  First, the control unit 10 selects 280 pixels from arbitrary positions in the read image, and acquires R, G, and B color values for each selected pixel (step S51). At this time, it is preferable that the control part 10 selects a pixel at random using a random number etc. so that the position of each pixel may not be biased. And the control part 10 investigates the color (C, M, Y, K, R, G, B, Pk) of the selected pixel using the same method as embodiment (step S52). Subsequently, the control unit 10 determines whether or not the number of pixels equal to or greater than the threshold value among the selected 280 pixels (275 when the threshold value is 98%) is identified as the same color (step S53). .

When the control unit 10 determines that the same color is specified for a number of pixels equal to or greater than the threshold (step S53; YES), the control unit 10 proceeds to step S55 and determines whether the color difference between the different colors is equal to or less than the threshold. (Step S55). Here, the control unit 10 obtains the average of the color specification values of the pixels identified as the same color, and makes a determination using the color difference between the average values. Here, when the color difference is larger than the threshold value (step S55; NO) and the two colors are not visually close, the control unit 10 proceeds to step S56. In this case, it means an image that has a dominant color that occupies most of the area with respect to the area of the sheet surface, and that slightly includes another color having a different color. Since such an image to be evaluated is not usually used, it is determined that the apparatus is out of order, and the control unit 10 notifies the user by displaying the fact on the UI unit 60 or the like.
On the other hand, when the color difference is smaller than the threshold value and the two colors are close (step S55; YES), the control unit 10 proceeds to step S57. Then, the control unit 10 identifies the entire area of the read image as the same dominant color (step S57). Even if a flare or the like occurs due to the processing in step S57, the control unit 10 corrects the read image data so that the entire surface has the same color image, so that the accuracy of in-plane unevenness and streak evaluation can be improved. .

On the other hand, if “NO” is determined in step S53, and the control unit 10 does not specify the same color for 98% or more pixels, the control unit 10 proceeds to step S54 and specifies the color of each pixel. For example, when a patch image for improving color reproduction characteristics is formed on a sheet, an image to be evaluated is only formed on a certain portion of the sheet. In this case, an image of the same color is formed on almost the entire surface of the sheet. There is nothing. Therefore, in such a case, the control unit 10 proceeds from step S53; NO to step S54, and thus the inspection process is not adversely affected. Further, in view of this, the control unit 10 specifies the mode from the read result of the image to be evaluated, and performs any type of inspection (inspection of color reproduction characteristics or in-plane unevenness inspection). It can be easily determined by the device itself. In step S51, the control unit 10 may select any number of pixels.
When the above processing is executed, the control unit 10 executes the second color conversion processing in step S4.

(C-3) Modification 3
In the above-described embodiment, in the first color region specifying process, the control unit 10 performs color conversion using the color conversion parameter P_HIGH on the color specifying image data whose saturation COL is equal to or less than the threshold, Increased accuracy. On the other hand, color conversion may also be performed using the color conversion parameter P_HIGH for color specifying image data having a high lightness L *. A read image with a high lightness L * can be a case where a sheet portion on which no image is formed is read, or a case where an evaluation image having a very low density is read. In the latter case, depending on the density and the color of the sheet, the image forming apparatus 1 may not be able to accurately specify the color of the image to be evaluated. For this reason, it is preferable to increase the conversion accuracy even for an image having a lightness L * that is somewhat high (above a threshold value) in order to increase the accuracy of the evaluation result.

(C-4) Modification 4
In the above-described embodiment, in the second color area conversion process, the control unit 10 determines the RGB values at a plurality of positions in the image area when determining whether the color of the image to be evaluated is K or Pk. Judgment based on the ratio. Instead of this, the control unit 10 changes the aperture size of the image reading unit 20 to read the image to be evaluated a plurality of times, calculates the ratio of the RGB values, and calculates the K value based on each reading result. You may determine whether it is Pk. When RGB is obtained with a certain aperture size, even if the R, G, and B color values of the process black reading result satisfy 1: 1: 1, the reading range can be changed by changing the aperture size. This is because the relationship is shifted in the case of process black. On the other hand, if the color of the image to be evaluated is K, this relationship is maintained even if the aperture size is changed.

In the above-described embodiment, the RGB color space is converted from the RGB color space to the CIELAB color space in the first color conversion process. Color space color values may be used. In short, the color of the image to be evaluated represented by the read image data by the control unit 10 based on the correspondence between the color specification value in the space converted by the first color conversion process and the color of the predetermined image to be evaluated. And the second color conversion process may be executed using the color conversion parameter corresponding to each color. In addition, the line sensor of the image reading unit 20 includes an image sensor that can capture images in three colors of R, G, and B, and the image reading unit 20 reads a color that is represented by a color value in the RGB color space. Although data has been generated, an image sensor capable of imaging still another color such as blue green may be provided, and the color space of the read image data is not limited to the RGB color space.
In the above-described embodiment, the case where the present invention is applied to the image forming apparatus 1 that uses toner as a color material has been described. However, the present invention is applied to an image forming apparatus that employs another method such as an inkjet method. Also good. If at least a function realized by the cooperation of the control unit 10 and the image processing unit 50 is realized, it functions as the image evaluation apparatus of the present invention.
Further, the image to be evaluated handled by the image forming apparatus 1 is not limited to that described in the embodiment, and the purpose of use and the type and number of colors are matters to be appropriately designed as necessary. Also in the first and second color area specifying processes, if K and Pk are not used as the colors of the image to be evaluated (color material colors), the image forming apparatus does not perform the black area determination process. The contents of the first and second color area specifying processes may be appropriately changed in design according to the color of the image to be evaluated used by the image forming apparatus.
The control program executed by the control unit 10 or the image processing unit 50 described above is provided in a state of being recorded on a recording medium such as a magnetic tape, a magnetic disk, a flexible disk, an optical recording medium, a magneto-optical recording medium, a CD, a DVD, or a RAM. Can do.

2 is a block diagram illustrating a hardware configuration of the image forming apparatus. FIG. 6 is a flowchart illustrating a procedure of processing executed by the image forming apparatus. It is the flowchart which showed the procedure of the 1st color area specific process which a control part performs. It is a figure explaining the color coordinate of the predetermined color in the a * b * plane which shows the component relevant to a hue and saturation among CIELAB color spaces. It is the flowchart which showed the procedure of the 2nd color area specific process which a control part performs. It is the flowchart which showed the procedure of the black area determination process which a control part performs. It is a graph which shows the relationship of the color value of each color component of R, G, B when a black (K) image is read. It is a figure showing the experimental result which shows the comparison with the colorimetric value calculated | required by performing color conversion, and the actual value of the colorimetric value which measured the to-be-evaluated image using the colorimeter. 10 is a flowchart illustrating a procedure of processing executed by a control unit in second color conversion processing according to Modification 2;

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Image forming apparatus, 10 ... Control part, 20 ... Image reading part, 30 ... Image forming part, 40 ... Memory | storage part, 50 ... Image processing part, 60 ... UI part, 70 ... Communication part.

Claims (8)

Generating means for reading the image to be evaluated and generating image data representing the image to be evaluated expressed in colors in the first color space;
First color conversion means for converting the color space of the image data generated by the generation means from the first color space to the second color space using a first color conversion parameter;
A first specifying means for color space based on the converted image data to identify the color of the image corresponding the to be evaluated image said generating means represented generated image data by the first color conversion means,
Correspondence storage means for storing the correspondence between the colors in the second color space and each of a plurality of predetermined colors ;
The image data generated by the generation unit represents the correspondence relationship stored in the correspondence relationship storage unit and the image data converted into the second color space by the first color conversion unit. Second specifying means for specifying the color of the image to be evaluated by any one of the plurality of colors ;
Using the second color conversion parameter corresponding to the color specified by the first and second specifying means, the color space of the image data generated by the generating means is changed from the first color space to the second color data. Second color conversion means for converting to a color space;
Before SL on the basis of the image data is color space converted by the second color conversion means, wherein evaluates the evaluation image, the image evaluation apparatus, characterized in that it comprises an evaluation unit for outputting the evaluation result.   The image evaluation apparatus according to claim 1, wherein the second color space is a color space defined by a component related to lightness and a component related to hue and saturation. The first color space is a color space defined by red, green and blue color components;
The first specifying means sets the color of the image to be evaluated whose saturation is equal to or greater than a threshold, cyan, magenta and yellow as colors of the color material expressing the color of the image to be evaluated, and the first color. The image evaluation apparatus according to claim 2, wherein the image evaluation apparatus specifies any one of red, green, and blue corresponding to a color component in the space. The correspondence storage means
Color conversion parameter storage means for storing conversion parameters for each color for converting each color in the first color space to a color in the second color space;
Color value storage means for storing the colors in the second color space and the colors of the plurality of colors in association with each other ;
The second specifying means includes:
Using the conversion parameters for each color stored in the color conversion parameter storage unit, the color of the evaluation image represented by the image data generated by the generation unit is converted into a color in the second color space,
Among the plurality of colors stored in the color specification value storage means, wherein the color difference is not the most small and the color of the converted, the in claim 1, wherein the identifying the color of the evaluation image Image evaluation device. The first color space is a color space defined by red, green and blue color components;
The color of the image represented by the image data generated by the generation unit is the first color obtained by reading the image to be evaluated in which black is expressed by the black color material, or the color materials of cyan, magenta, and yellow. When it is one of the second colors obtained by reading the evaluated image in which black is expressed by a combination,
The second specifying means specifies the color of the image to be evaluated as the first color when the ratios of the color values of the color components of red, green and blue in the first color space match, The image evaluation apparatus according to claim 1, wherein when the ratio of the color values of the color components of red, green, and blue does not match, the color of the image to be evaluated is specified as the second color. Said second specifying means, said examining the color of the plurality of positions in the evaluation image, when the same color in a proportion of more than the threshold value in the plurality of positions is included, the same color, the target The image evaluation device according to claim 1, wherein the image evaluation device is specified as an overall color of the evaluation image. The first color space is a color space defined by red, green and blue color components;
The second color conversion means is the image data specified by the first or second specifying means that the color of the evaluated image is a color of a single color material expressing the color of the evaluated image. In contrast, the color value of only a single color component of the color components in the first color space is changed to express the color in the first color space, and then the image data The image evaluation apparatus according to claim 1, wherein a color space is converted into the second color space. Computer
Generating means for reading the image to be evaluated and generating image data representing the image to be evaluated expressed in colors in the first color space;
First color conversion means for converting the color space of the image data generated by the generation means from the first color space to the second color space using a first color conversion parameter;
A first specifying means for color space based on the converted image data to identify the color of the image corresponding the to be evaluated image said generating means represented generated image data by the first color conversion means,
A color in the second color space, wherein the corresponding relationship stored in the correspondence relationship storing hand stage and for storing a correspondence relationship between each of a plurality of colors previously determined, the by the first color conversion means Second specifying means for specifying the color of the image to be evaluated represented by the image data generated by the generating means based on any one of the plurality of colors based on the image data converted into the second color space; ,
Using the second color conversion parameter corresponding to the color specified by the first and second specifying means, the color space of the image data generated by the generating means is changed from the first color space to the second color data. Second color conversion means for converting to a color space;
Based on the image data is color space converted by the pre-Symbol second color conversion means, wherein evaluates the evaluation image, the program to function as an evaluation means for outputting the evaluation result.

Images