JP2001014458A - Image data processing device - Google Patents

Abstract

(57) [Summary] [Problem] When performing a plurality of image processing based on a certain feature amount, the feature amount is corrected to an optimal form for each process, and
An image data processing apparatus capable of forming a higher quality image is provided. An image data processing apparatus that acquires a feature amount of image data generated based on an image and performs a plurality of processes on the image data based on the feature amount, corrects the acquired feature amount. A correction unit is provided, and a correction amount by the feature amount correction unit is changed according to processing performed on the image data.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image data processing apparatus, and more particularly to an image data processing apparatus for performing a plurality of types of processing on image data.

[0002]

2. Description of the Related Art There is an image data processing apparatus for processing information (image data) obtained by converting an image into a digital signal to form an image. At present, such an image data processing apparatus is applied to a copier, a facsimile, a printer that prints out image data received via a network, or the like.

In such an image data processing apparatus, an original image is divided into a plurality of areas on image data,
Processing (image area separation) is performed to separate the divided area into a character area representing a character and a picture area representing a picture. In the character area and picture area separated by image area, characters,
Alternatively, a process suitable for the pattern is performed to reproduce the image. As a result, the image data processing device can reproduce the entire image including characters and pictures with high image quality.

The above-mentioned image data processing apparatus includes, for example, an invention described in Japanese Patent Application Laid-Open No. 3-89677. In the invention described in Japanese Patent Application Laid-Open No. 3-89677, as a result of image area separation, image data is divided into regions such as non-character edges, color character edges, intermediate saturation character edges, and black character edges. Then, for each divided area,
The contents of the spatial filter processing, γ conversion processing, and screen processing are switched. According to this switching, for characters (particularly black characters), the contrast between the character region and the non-character region is enhanced, and the character is reproduced sharply.

However, in the invention described in Japanese Patent Application Laid-Open No. 3-89677, the processing content is switched only by the character or background, so that the difference in the processing content between the character area and the non-character area is limited. Relatively large. For this reason,
If the text area and the non-text area are separated by mistake,
Sudden texture changes occur in the reproduced image,
There is a possibility that the image quality is reduced.

[0006] As an invention made to avoid such a fear, for example, there is an invention described in Japanese Patent Publication No. 7-108019. According to the present invention, the edge amount of an image is detected as a multi-level signal, and processing is switched in multiple stages according to the edge amount. According to such a technique, a difference in gradation at a boundary where processing is switched is reduced, and a more natural image can be obtained. However, a response (response) when the edge portion and the background portion are signalized changes in a very narrow range. Further, since a filter of about 5 × 5 is used for calculating the edge amount, it was not possible to sufficiently eliminate the sense of discomfort at the boundary due to the switching of the processing.

[0007] The sense of discomfort at the boundary due to the switching of the process becomes more remarkable as the change in the content of the process switched according to the edge amount becomes larger. Generally, under color removal (Under
Color Removal)
It is said that such a problem is relatively likely to occur.

On the other hand, an image in which a character is present on a halftone dot as shown in FIG. 11, that is, an image in which a character and a halftone dot are immediately adjacent to each other, is subjected to edge enhancement for the character, and In some cases, non-edge enhancement (or smoothing) is desired. In such a case, as in Japanese Patent Publication No. 6-5885, it is possible to switch the filter for edge detection in multiple stages and control the response from the edge to the background in a narrow range as necessary. It is effective for suppressing discomfort.

[0009]

As described above, a method of extracting an optimum feature amount (for example, an edge amount) in spatial filter processing such as undercolor removal, edge enhancement, and smoothing differs depending on the processing. For this reason, in the case where the under color removal and the spatial filter processing are performed stepwise according to the feature amount of the image, if a plurality of processes are performed based on the extracted feature amount in the same manner, a failure may occur in any of the processes. There is.

The present invention has been made in view of the above points, and when performing a plurality of image processings based on a certain characteristic amount, the characteristic amount is corrected to an optimal form for each processing.
It is an object of the present invention to provide an image data processing device capable of forming a higher quality image.

[0011]

The above-mentioned problems can be solved by the following means. That is, the invention according to claim 1 is an image data processing apparatus that acquires a feature amount of image data generated based on an image and performs a plurality of processes on the image data based on the feature amount. The image processing apparatus further includes a characteristic amount correcting unit that corrects the amount, and a correction amount by the characteristic amount correcting unit is changed according to a process performed on the image data.

With this configuration, when a plurality of processes are performed, the feature amount can be corrected independently for each process.

According to a second aspect of the present invention, the characteristic amount correcting means corrects the characteristic amount of the image data by a primary conversion.

With such a configuration, it is possible to relatively easily execute the correction of the characteristic amount.

According to a third aspect of the present invention, there is provided an image data processing apparatus for acquiring a characteristic amount of image data generated based on an image and performing a plurality of processes on the image data based on the characteristic amount. The image processing apparatus further includes a characteristic amount expanding unit that expands the characteristic amount, and an amount of expansion by the characteristic amount expanding unit is changed according to a process performed on the image data.

With this configuration, when a plurality of processes are performed, the feature amount can be expanded independently for each process.

According to a fourth aspect of the present invention, the characteristic amount is an edge amount which is multi-valued information or binary information which represents the edge amount in a binary manner.

With such a configuration, the image data processing apparatus of the present invention can be configured with any of multi-valued and binary-valued features as required.

According to a fifth aspect of the present invention, the image data is area image data representing an image of a predetermined area.

With this configuration, the spatial filter processing for correcting specific image data based on a plurality of image data can be corrected for each processing in accordance with the feature amount.

[0021]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments 1 and 2 of the present invention will be described below. (Embodiment 1) FIG. 1 is a block diagram showing a configuration of an image data processing apparatus according to Embodiment 1. The configuration shown in the figure reads an image to read R (red), G (green),
CCD (Char) that generates image signals of three colors B (blue)
ged Coupled Device) Color input device 1 using elements
And a smoothing filter 2 for processing image data generated by the color input device 1, a γ conversion unit 3, and an adaptive edge enhancement unit 4. In the above configuration, the image data of three colors is processed for each color, and the smoothing filter 2, the γ conversion unit 3, and the adaptive edge enhancement unit 4
Are provided one by one.

The configuration shown in the figure includes a color correction / black generation unit 5 for inputting all three color image data processed by the adaptive edge enhancement unit 4 and performing color correction and black generation processing on the image data. An adaptive undercolor removal unit 6 for adjusting the undercolor removal amount based on the characteristic amount of the printer, a printer γ conversion unit 7 for converting a signal based on image data according to the characteristics of the printer, and a halftone processing unit 8 for performing dither processing and the like And a color output device 9 that is a printer that prints out image data that has undergone the above processing.

Further, as shown in the figure, the image data processing apparatus according to the first embodiment includes an edge amount calculating section 10 for calculating an edge amount used for controlling the adaptive edge enhancing section 4 and the adaptive undercolor removing section 6; A first correction unit 11 that corrects a control signal k output from the edge amount calculation unit 10 into a control signal m based on the calculated edge amount and outputs the control signal m to the adaptive edge enhancement unit 4
And a second correction unit 12 that corrects the control signal k to the control signal n and outputs the corrected signal to the adaptive undercolor removal unit 6. Note that the first correction unit 11 and the second correction unit 12 are configured to function as a feature value correction unit that corrects the feature value of the first embodiment.

In the configuration described above, a color image is formed in a frame sequence, and the image data is input to the color correction / black generation unit 5 as three signals of R, G, and B. Then, the image data of K (black) and R, G,
Two signals of any one of the colors B are input to the printer γ conversion unit 7, and thereafter, the image data to be printed out at one time flows one signal at a time.

In the above configuration, the adaptive edge emphasis unit 4
Is a configuration in which image data is processed by a spatial filter, and controls the degree of edge enhancement based on a predetermined feature amount when performing edge enhancement processing on image data. With this control, the image data is processed as image data (region image data) representing an image of a predetermined region.

The adaptive edge emphasis unit 4 has an edge emphasis filter 21 and a mixer 22 as shown in FIG. The mixer 22 inputs the image data γ-converted by the γ converter 3 directly or as signals s1 and s2 through the edge emphasizing filter 21, respectively, and adjusts the mixing ratio between the two based on a control signal m described later. And the signal s
3 is output.

The adaptive under color removing section 6 controls the amount of under color removal based on a predetermined characteristic amount when performing under color removal processing on image data. In the embodiment of the present invention, it is assumed that the predetermined feature amount is an edge amount.

The control signal m and the control signal n output from the first correction unit 11 and the second correction unit 12 have different correction amounts of the signal k depending on whether the correction is an edge enhancement process or an undercolor removal process. It is a signal generated by That is, the control signal m output from the first correction unit 11 to the adaptive edge enhancement unit 4
Is a control signal for correcting the control signal k such that the edge amount changes sharply in a narrow range, and the control signal n output from the second correction unit 12 to the undercolor removal unit 6 is This is a control signal for correcting the control signal k so as to change smoothly.

FIG. 3 is a block diagram for explaining the configuration of the edge amount calculator 10. The edge amount calculation unit 10
It has a character pixel detector 18 and a distance calculator 19. The character pixel detector 18 binarizes the image data G on which the edge enhancement has been performed at a predetermined level. Then, black pixels are subjected to pattern matching from the image data G using, for example, the patterns (a) to (d) shown in FIG.
Detects bar-shaped black lump.

Subsequently, the distance calculation unit 19 calculates, as a value V, the distance between the detected pixel of interest in the black block and the character pixel (active pixel) in the mask that is the shortest distance from the pixel of interest. According to this processing, the value V of the target pixel (（) shown in FIG. 5 is obtained by the following equation, where the coordinates of the active pixel black (〇) in the mask are (x, y). In addition,
In this formula, the response is attenuated concentrically from the center pixel in the mask toward the outer periphery with the maximum value being 255. Then, in the 9 × 9 mask shown in FIG. 5, the response is made almost zero at the outermost periphery. V = 255-255 × dis / 6, where dis = (x ² + y ² ) ^1/2 ,

The distance calculating section 19 calculates a signal indicating a response that becomes smaller as the distance from the target pixel increases as described above, and determines the degree of the edge of the target pixel. Then, the control signal k is output to the first correction unit 11 and the second correction unit 12 based on the determination result. Note that the distance calculation unit 19 according to the first embodiment is configured to calculate the value V by a calculation formula. You may make it contrast with this table.

Each of the first correction unit 11 and the second correction unit is configured as a table conversion unit. FIG. 6 is a diagram illustrating a graph for explaining the correction performed by the first correction unit 11 and the second correction unit 12. The horizontal axis indicates the input to the first correction unit 11 and the second correction unit 12. The control signal (the control signal based on the distance calculation result by the distance calculation unit 19) to be performed, and the vertical axis indicates the control signals m and n corrected and output by the first correction unit 11 and the second correction unit 12.
In FIG. 6, a straight line A indicated by a broken line is a straight line indicating a state where the control signal is output without correction for comparison. In FIG. 6, signals input to and output from the first correction unit 11 and the second correction unit 12 are [0,
1] is described as analogized. However, this signal is actually a signal obtained as a digital sampling signal corresponding to the required number of bits.

According to FIG. 6, the first correction unit 1
First, it can be seen that the correction by the second correction unit 12 is performed by linearly converting the straight line A into a straight line m or a straight line n, that is, correcting the feature amount of the image data by the primary conversion. Further, the control signal m output from the first correction unit 11 to the adaptive edge enhancement unit 4 is a control signal for correcting the edge amount to change sharply in a narrow range, and the control signal m from the second correction unit 12 to the under color removal unit. The control signal n output to 6 is a control signal for correcting the edge amount to change smoothly in a wide range, so that in the processing of the edge emphasizing unit, the edge amount changes sharply in a narrow range. It can be seen that, in the undercolor removal processing, the edge amount is controlled so as to change smoothly over a wide range.

Next, the operation of the above-described configuration will be described. The color input device 1 reads an image of a document and performs A / D conversion, and then outputs 8-bit image data that is substantially linear in reflectance for each pixel read. All of the image data are input to the smoothing filter 2 as three signals of R, G, and B, and at least one of them is input to the edge amount calculation unit 10. The image data input to the edge amount calculation unit 10 includes a first correction unit 11 and a second correction unit 1
2 to generate a control signal m and a control signal n, respectively.

The image data input to the smoothing filter 2 is filtered by a filter shown in FIG. 7, for example. By this filtering, it is possible to prevent moiré and texture from occurring in an image to be printed out. The image data filtered by the smoothing filter 2 is further input to the γ conversion unit 3. The γ conversion unit 3 linearly converts the attribute of the image data, which has been linear in reflectance, into density. With this conversion,
In the conversion of the density signal to the printer drive signal in the color correction / black generation unit 5 at the subsequent stage, the relationship between the two is made closer to linear, and the conversion accuracy at the time of color correction can be improved.

The γ-converted image data is further input to the adaptive edge emphasizing unit 4. This image data is branched inside the adaptive edge enhancement unit 4, one of which is directly divided into the mixer 22.
2 is input as a signal s1 and the other is input as a signal s2 to a mixer 22 via an edge enhancement filter 21. The image data that has passed through the edge enhancement filter 21 is filtered by, for example, the edge enhancement filter shown in FIG. 8 to perform edge enhancement.

At this time, the control signal m generated by the first correction unit 11 is also input to the mixer 21. The mixer 21 mixes the signal s1 and the signal s2 based on the control signal m, and outputs the signal s3 to the color correction / black generation unit 5. The mixing ratio of the signal s1 and the signal s2 based on the control signal m (mixing ratio for generating the signal s3) is obtained by the following equation. s3 = m × s2 + (1-m) × s1

According to such processing, even for an image having a character on a halftone dot as shown in FIG. 11, the influence of the feature amount whose edge is to be emphasized is suppressed from affecting the surroundings. While edge enhancement is performed, moire and texture can be suppressed without performing edge enhancement on the background portion.

The image data processed by the adaptive edge enhancement unit 4 is input to a color correction / black generation unit 5. The color correction of the color correction / black generation unit 5 is a process of removing a color separation filter and a turbid component of ink in the color input device 1 (scanner), and includes a masking method, a memory map method (interpolation) in a general method. Method). In the first embodiment, an example in which linear conversion is performed using the former masking method will be described.

According to the masking method, R, G, and B image data are replaced with C (cyan), M (magenta), Y (yellow), and K (black) color data according to the following equations. That is, C = k11 × R + k12 × G + k13 × B + k14 M = k21 × R + k22 × G + k23 × B + k24 Y = k31 × R + k32 × G + k33 × B + k34 Here, k11 to k34 are constants determined by experiments.

In the black generation process, K color data is created from the C, M, and Y color data determined according to the above equation, according to the following equation. K = min (C, M, Y)

The C, M, Y, K color data obtained in this way is further inputted to the adaptive under color removing section 6 and changed. The adaptive under color removing unit 6 changes the color data of C, M, Y, and K using the following formula. K1 = α × K C1 = C−K1 M1 = M−K1 Y1 = Y−K1 In the above equation, α is a coefficient reflecting the feature amount of the image, and C1, M1, Y1, and K1 are respectively These are the C, M, Y, and K color data after the change.

At this time, the control signal n generated by the second correction unit 12 is input to the adaptive under color removal unit 6 together with the color data. In the first embodiment, by reflecting the control signal n to α, processing is performed so that the edge changes smoothly when the undercolor is removed.

FIG. 9 is a graph for explaining the relationship between the control signal n and the coefficient α. The control signal n ([0, 1 standardized) input to the adaptive undercolor removal unit 6 is plotted on the horizontal axis. ]), And the vertical axis indicates the value of the coefficient α. According to FIG. 9, the coefficient α is made closer to 1.0 as the control signal n increases (the probability of being a character portion is high). Further, as the control signal n becomes smaller (the probability of being a picture portion is higher).
It can be seen that the coefficient α approaches 0.6 which is a coefficient used for processing generally performed on a picture area.

The control signal n according to the first embodiment is corrected by the second correction unit 12 so as to change smoothly over a wide range of the image. For this reason, the change of the coefficient α also becomes gentle, and a phenomenon that occurs when the undercolor removal amount changes in a relatively narrow range of the image, a difference in color turbidity, a difference in gray balance disappears, The image to be printed can have high image quality.

The image data subjected to the undercolor removal processing as described above is converted into a table by the printer γ conversion unit 7 in accordance with the characteristics of the printer. At this time, a process of removing background and a process of positively adding contrast may be performed on this table.

The halftone processing section 8 processes the image data so as to reproduce the halftone of the image by dither processing or error diffusion. In a second embodiment to be described later, processing for reproducing halftone by dither processing will be described in detail. The halftone processing unit 8 outputs a control signal for controlling the color output device 9 so as to reproduce the image data subjected to the above processing. The color output device 9 is driven according to the control signal, and prints out an image in a frame-sequential manner.

According to the first embodiment described above, when the edge amount extracted as the feature amount of the image is used for the edge enhancement processing, it is corrected so as to change relatively steeply. It can be corrected so as to change relatively gently. Therefore, in the first embodiment, edge enhancement,
Problems that occur in the undercolor removal processing (character edge emphasis on halftone dots, turbidity change is conspicuous, etc.) can be solved, and a high-quality image can be formed.

The present invention relates to the first embodiment described above.
However, the present invention is not limited to this. For example, the first correction unit 11,
The correction of the control signal performed by the second correction unit 12 is not limited to the example illustrated in FIG. 6, and may be corrected in another form. Further, the correction may be made by a change method other than the primary conversion as needed. Such other corrections can be relatively easily performed by changing the shape of the conversion table used in the first correction unit 11 and the second correction unit 12.

In the first embodiment, an example has been described in which the spatial filter processing is controlled with the edge enhancement being adaptive edge enhancement. However, a similar effect can be obtained by controlling the smoothing filter.

(Embodiment 2) Next, Embodiment 2 of the present invention will be described. In the processing described in the second embodiment, the coefficient α is fixed (for example, 0.6) by the undercolor removing unit 6.
However, when the adaptive intermediate gradation unit 8 performs a process of mixing signals generated by dither processing with different dither sizes at a mixing ratio based on the feature amount, a phenomenon called hollowness occurs in characters having a certain width. This is suitable for preventing such a situation.

FIG. 10 is a block diagram for explaining the configuration of the image data processing apparatus according to the second embodiment of the present invention. In FIG. 10, the same components as those shown in FIG. 1 are denoted by the same reference numerals, and the description thereof will be partially omitted.

The image data processing apparatus according to the second embodiment obtains a feature amount of image data in the same manner as the image data processing apparatus according to the first embodiment, and performs image processing on the image data based on the feature amount. It is a data processing device. For this reason,
The image data processing apparatus according to the second embodiment includes a color input device 1 using a CCD element, three smoothing filters 2 for processing image data generated by the color input device 1, a γ conversion unit 3, an adaptive edge enhancement. Unit 4 and color correction / black generation unit 5
The adaptive undercolor removal unit 6, the printer γ conversion unit 7, the adaptive halftone processing unit 80, the color output device 9, the edge amount calculation unit 10, and the edge amount calculated by the edge amount calculation unit 10. A first correction unit 11 that outputs a control signal m to the adaptive edge emphasis unit 4 and a third correction unit 13 that outputs a control signal o to the adaptive halftone processing unit 80.

Of the above configuration, in the second embodiment, the third correction unit 13 functions as a feature amount expanding unit. The expansion amount of the edge amount expanded by the third correction unit 13 is configured to be changed according to the processing performed on the image data.

The edge amount calculation unit 10 includes a first correction unit 11,
The control signal is input to the third correction unit 13. This control signal is corrected by the first correction unit 11 to a control signal m similar to that of the first embodiment, and is corrected by the third correction unit 13 to a control signal o. The third correction unit 13 corrects the control signal o by, for example, 3
A × 3 mask is provided, and the control signal for the central pixel is replaced with the maximum value in the mask.

According to such processing of the third correction unit 13, control is performed such that the center pixel is always processed with the maximum value in the mask. For this reason, the pixel after the processing is expressed (expanded) so as to be represented as a pixel slightly larger than that before the processing.
No white spots occur. On the other hand, when such processing is not desired in the edge enhancement, the correction signal m described in the first embodiment is used, so that the expansion processing is not naturally performed.

Therefore, according to the second embodiment, the edge amount is expanded only when the edge amount extracted as the feature amount of the image is used for the halftone processing, the white spot is solved, and the high quality image is obtained. Can be formed.

The expansion amount (expansion size) of the expansion performed by the third correction unit 13 can be made by changing the mask size. Therefore, it is possible to appropriately change the mask size according to the quality of the image to be processed, and select an appropriate expansion amount for the processing. Further, the expanded control signal may be further converted into a table as shown in FIG.

The present invention is not limited to the first and second embodiments described above. For example,
In each of the first and second embodiments, the feature amount is an edge amount which is multi-valued information. However, the edge amount which is the feature amount is binarized with an appropriate threshold value, and the processing is performed on a 0/1 basis. You may make it control. Further, the image may be divided by a known image area separation process, and the process may be controlled based on the result. In this case, the area indicated by the control signal changes with the processing such as the spatial filter and the halftone processing.

Furthermore, in the first and second embodiments, both printers function as a single unit as an example. However, the image data processing apparatus of the present invention is connected to a network to perform image data processing. May be configured as a printer that performs the following. In such a configuration, the color input device is not required. Further, it is also possible to input the edge amount which is the feature amount together with the image data. In this case, the feature amount calculating unit is not required.

[0061]

According to the first aspect of the present invention, among a plurality of processes, the feature amount can be independently corrected according to each process, and each process can be optimally controlled. Therefore, the quality of the formed image can be further improved.

According to the second aspect of the invention, the correction of the characteristic amount can be performed relatively easily, and the image data processing apparatus of the present invention can be realized with a relatively simple configuration. In addition, the processing time can be reduced, and the size of the apparatus can be reduced.

According to the third aspect of the present invention, of a plurality of processes, the feature amount can be expanded independently, and each process can be optimally controlled. Therefore, the quality of the formed image can be further improved.

According to the invention described in claim 4, the feature quantity can be multi-valued or binary as required, and the usability of the image data processing apparatus of the present invention can be further enhanced.

According to the fifth aspect of the present invention, the spatial filter processing can be corrected for each processing according to the characteristic amount, and the usability of the image data processing apparatus of the present invention can be further improved.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration according to a first embodiment of the present invention.

FIG. 2 is a block diagram for explaining an adaptive edge emphasis unit common to the embodiments of the present invention.

FIG. 3 is a block diagram illustrating a configuration of an edge amount calculation unit common to the embodiment of the present invention;

FIG. 4 is a diagram illustrating a pattern used for calculating an edge amount shown in FIG. 3;

FIG. 5 is a diagram for explaining a process of a distance calculation unit shown in FIG. 3;

FIG. 6 is a diagram illustrating a graph for explaining correction performed by a first correction unit and a second correction unit illustrated in FIG. 1;

FIG. 7 is a diagram for explaining a filter used in the smoothing filter shown in FIG. 1;

FIG. 8 is a diagram for explaining a filter used in the edge enhancement unit shown in FIG. 2;

FIG. 9 is a diagram for explaining a specific method of correction performed by a second correction unit illustrated in FIG. 1;

FIG. 10 is a block diagram for describing a configuration according to a second embodiment of the present invention.

FIG. 11 is a diagram illustrating an image in which a character exists on a halftone dot;

[Explanation of symbols]

 Reference Signs List 1 color input device 2 smoothing filter 3 γ conversion unit 4 adaptive edge enhancement unit 5 color correction / black generation unit 6 adaptive under color removal unit 7 printer γ conversion unit 8 halftone processing unit 9 color output device 10 edge amount calculation unit 11 First correction unit 12 Second correction unit 13 Third correction unit 18 Character pixel detection unit 19 Distance calculation unit 21 Edge enhancement unit 22 Mixer 80 Adaptive halftone processing unit

 ──────────────────────────────────────────────────続 き Continued on the front page (72) Inventor Tokiko Miyagi 1-3-6 Nakamagome, Ota-ku, Tokyo F-term in Ricoh Co., Ltd. 5B057 CA01 CA08 CA12 CA16 CB01 CB08 CB12 CB16 CC03 CE03 CE06 CE11 CE17 CH09 DB02 DB06 DB09 DC16 5C077 LL19 MP08 PP02 PP15 PP37 PP38 PP47 PP68 TT02 TT06

Claims (5)

[Claims] An image data processing apparatus for acquiring a feature amount of image data generated based on an image and performing a plurality of processes on the image data based on the feature amount, wherein the acquired feature amount is corrected. An image data processing apparatus, comprising: a feature amount correcting unit, wherein a correction amount by the feature amount correcting unit is changed according to a process performed on image data. 2. An image data processing apparatus according to claim 1, wherein said characteristic amount correcting means corrects the characteristic amount of the image data by a primary conversion. 3. An image data processing apparatus for acquiring a feature amount of image data generated based on an image and performing a plurality of processes on the image data based on the feature amount, wherein the acquired feature amount is expanded. An image data processing apparatus, comprising a feature amount expanding unit, wherein an amount of expansion by the feature amount expanding unit is changed in accordance with processing performed on image data. 4. The image data processing apparatus according to claim 1, wherein the feature amount is an edge amount that is multi-valued information or binary information that represents the edge amount in a binary manner. 5. The image processing apparatus according to claim 1, wherein the image data is area image data representing an image of a predetermined area.
5. The image data processing device according to any one of 4.