JP2001150741A - Apparatus and method for image processing and recording medium thereof - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent deterioration of an image, to embed access control information in the image and to precisely read the embedded access control information. SOLUTION: On the basis of a first main component vector 1502 between an objective binary image and a reference pattern, a pattern score average of the objective binary image is obtained. The pattern score average of the objective binary image and a reference pattern score based on the sum of distances between the reference pattern in the main component direction is compared with a criteria vector. A specific small amount vector space 1501 is moved to the first main component vector 1502 in parallel corresponding to the compared result and the access control information to be embedded in the objective binary image and then the image is formed by changing the objective binary image on the basis of the result that the specific small amount vector space 1501 is moved in parallel.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image processing apparatus and method for embedding access control information as watermark information in a document image or the like, and a storage medium for the method.

[0002]

2. Description of the Related Art In recent years, image quality formed by digital image forming apparatuses such as printers and copiers has been remarkably improved, and high quality images can be easily printed using these apparatuses. ing. Further, by reducing the price of high-performance scanners, printers, and copiers, and by performing image processing using computers, anyone can easily obtain desired printed matter. for that reason,
Problems such as unauthorized copying of printed matter (hereinafter, simply referred to as printed matter) such as documents, images, and photographs have been occurring. Therefore, in order to prevent or deter unauthorized use of a printed material due to such unauthorized copying, access control information as watermark information is embedded in the printed material.

[0003] As such an access control function, one that embeds access control information invisibly in a printed matter, and that embeds a bitmap pattern (glyph code, DD code, etc.) corresponding to the access control information in the margin of a document. In general, a document or a document image is subjected to scramble encryption. Among them, those that embed the access control information invisibly are, as general implementation methods, those that embed the access control information by controlling the amount of space in the English character string, those that rotate the characters and rotate the characters There is a method of embedding access control information in accordance with the above, and a method of enlarging or reducing a character and embedding the access control information in accordance with the enlargement or reduction ratio.

FIG. 21 is a diagram for explaining an example of embedding access control information by controlling the amount of space between words in an English character string. Here, reference numeral 1701 denotes a space between words. This space is p ← (1 + p) (p + s) / s s if the watermark bit to be embedded is “0”.
← (1-p) (p + s) / 2, and if the watermark bit is “1”, p ← (1-p) (p + s) / 2 s ←
(1 + p) (p + s).

FIGS. 22 and 23 show that a character is rotated.
FIG. 9 is a diagram illustrating an example of embedding access control information according to the amount of rotation. Here, FIG. 22 shows a state before the characters are rotated, and FIG. 23 shows a state after the characters are rotated. 1901 indicates the rotation angle θ of the character.

FIG. 24 is a diagram showing an example of embedding access control information by enlarging / reducing a character. Reference numeral 2001 denotes an original character width, and 2002 denotes a character width after reduction. Access control information is embedded according to enlargement / reduction.

[0007]

However, according to such an access control information embedding method, the original characters and images are obviously deformed, and the original characters and images are deteriorated. Will be.

Further, according to such an access control information embedding method, in order to accurately detect the embedded access control information, the printed matter is read with high accuracy and, for example, the space amount between words, The rotation angle of the character,
You need to read the size of the characters accurately. for that reason,
When printing is performed with a small character size and high resolution, there is a problem that it is very difficult to detect the access control information embedded in the printed matter.

SUMMARY OF THE INVENTION The present invention has been made in view of the above conventional example, and has as its object to provide an image processing apparatus capable of embedding access control information in an image without deteriorating the image, a method thereof, and a storage medium therefor. Aim.

It is another object of the present invention to provide an image processing apparatus and method capable of reading embedded access control information with high precision, and a storage medium for the method.

[0011]

In order to achieve the above object, an image processing apparatus according to the present invention has the following arrangement.
That is, an image processing apparatus for inputting and processing a binary image, comprising: an arithmetic unit that calculates a pattern score average of the target binary image based on the target binary image and a first principal component value of a reference pattern; Comparing means for comparing the average pattern score of the target binary image with a reference pattern score based on the sum of the distance between the first principal component direction of the reference pattern and the reference vector, and a comparison performed by the comparing means A translation unit that translates the feature vector space of the target binary image according to the result and the access control information embedded in the target binary image; and a translation result of the feature vector space based on the result. Changing means for changing the target binary image.

In order to achieve the above object, an image processing apparatus according to the present invention has the following arrangement. That is, an extraction unit that reads a document image and extracts a contour portion of the image, a unit that obtains an average of pattern scores of an image corresponding to the contour portion, and a unit that determines a first principal component direction of a reference pattern and a reference vector. Difference calculating means for calculating a difference between a reference pattern score based on the sum of distances and the average of the pattern scores, and detecting control information embedded in the document image according to the difference obtained by the difference calculating means And a detecting means.

[0013] To achieve the above object, the image processing method of the present invention comprises the following steps. That is, an image processing method for inputting and processing a binary image, comprising: a calculating step of calculating a pattern score average of the target binary image based on a first principal component value of the target binary image and a reference pattern; A comparison step of comparing the average of the pattern scores of the target binary image with a reference pattern score based on the sum of the distances between the first principal component direction of the reference pattern and the reference vector, and a comparison performed in the comparison step A translation step of translating the feature vector space of the target binary image in accordance with the result and the access control information embedded in the target binary image; and And a changing step of changing the target binary image.

In order to achieve the above object, the image processing method of the present invention comprises the following steps. That is, an original image is read, an extraction step of extracting a contour part of the image, a step of calculating a pattern score average of an image corresponding to the contour part, and a step of determining a first principal component direction of the reference pattern and the reference vector are performed. A difference calculation step for obtaining a difference between a reference pattern score based on the sum of distances and the pattern score average, and detecting control information embedded in the document image according to the difference obtained in the difference calculation step And a detecting step.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In the following embodiment, a monochrome laser beam printer (hereinafter, referred to as monochrome LBP) will be described as an example.

The document image is a binary black-and-white image.
An inexpensive scanner is used as an image reading device for reading printed matter.

[First Embodiment] FIG. 1 is a diagram showing a flow of conversion of monochrome LBP document image data related to embedding of access control information according to a first embodiment of the present invention.
In this figure, the image data of the document is binary image data 10.
1 is passed to the monochrome LBP printer driver. Next, the binary image data 101 is converted to binary data 102 of a device that matches the characteristics of each printer.
The multi-level K image data 103 is binarized into binary K image data 104.

The binary K image data 104 is passed to a printer engine and printed on paper or the like at a high resolution.

FIG. 2 is a diagram showing a flow of conversion of image data related to reading of access control information by the scanner according to the first embodiment of the present invention. In this figure, image data of a read document is transferred to a scanner driver as multi-valued grayscale image data 201.

Next, the observation pattern feature quantity space, reference vector, and reference pattern feature quantity space according to the present embodiment will be described.

FIG. 3 is a diagram showing an example of an image of M × N pixels corresponding to a part of the binary K image data 104.

FIG. 4 shows the outline of the image shown in FIG.
FIG. 4 is a diagram illustrating a contour image in which pixels are thinned.

FIG. 5 is a diagram showing a direction index index for extracting a feature amount of a date-ahead pixel when a target pixel is placed at the center of a 3 × 3 pixel block. In this figure, there are pixels in the t1, t2, t3, and t8 directions of the target pixel, and t4, t5,
The case where there is no pixel in the t6 and t7 directions is shown.

FIG. 6 shows the values of the direction index of the target pixel in FIG. 5 with respect to the feature amounts t1, t2, t3, t4, t5, t6, t7, and t8. Here, “1” indicates that there is a pixel in that direction, and “0” indicates that there is no pixel in that direction.

FIG. 7 shows the target pixel Pij of FIG. 5 shown in FIG.
Is a vectorized version of the direction index feature quantity.

Here, the direction index feature vector Hij is
The vector of the direction index feature amount of the pixel of interest Pij is shown. The number of dimensions of this vector is eight.

The observation pattern feature quantity space is a set of direction index feature quantity vectors for each pixel in the contour image obtained in FIG. The number of dimensions of the observation pattern feature quantity space is eight.

FIG. 8 shows a reference vector pattern. The reference vector of the reference vector pattern is a direction index feature amount of the pattern. FIG. 9 shows a vector DIST indicating the direction index special distribution amount. The number of dimensions of this vector is eight.

FIG. 10 is a diagram showing an example of a reference image of S × T pixels. FIG. 11 shows an outline image of the reference image. The reference pattern feature amount space is a direction index characteristic amount for each pixel in the outline image. It is a set of vectors. The number of dimensions of the reference pattern feature amount space is eight.

Next, a procedure for embedding access control information in a document image will be described.

FIG. 12 is a diagram showing an example of a bit sequence of access control information (watermark information). Here, 1
201 indicates a bit “0”, and 1202 indicates a bit “1”.

FIGS. 13 and 14 are flowcharts showing a process of embedding access control information (watermark information) for accessing the document image in the document image. Hereinafter, the operation will be described with reference to this flowchart.

First, in step S1, a reference pattern score is calculated from the reference vector and the first principal component of the reference pattern. This is obtained based on the following equation (1).

Z1 * = a11 × 1 * + a12 × 2 * +... + A18 × 8 * (1) where z1 * is the reference pattern score, and a11,..., A18 are the first principal component vectors of the reference pattern. Component value, x1 *, ...,
x8 * indicates each component value of the standardized reference vector. Here, a11,..., A18 are reference vectors x1,.
The eigenvector of the x8 correlation matrix is used. When the reference vector and the reference pattern are determined in advance, the reference pattern score may be calculated in advance and stored in a memory or the like.

FIG. 15 shows the first principal component vector obtained from the reference pattern feature vector space, and changes the feature vector space of the document image (observation pattern) into which the watermark information is to be inserted, in accordance with the watermark information. It is a conceptual diagram showing an example. In FIG. 15, reference numeral 1500 denotes a reference pattern feature vector space, and reference numeral 1503 denotes a first principal component vector of the reference pattern. Therefore, the reference pattern score z1 * corresponds to the sum of the linear distances between the first principal component vector and each component of the reference vector.

Then, the process proceeds to a step S2, wherein the binarization K of FIG.
A document image corresponding to the image data 104 is read. Next, the process proceeds to step S3, and as shown in FIG.
The document image read in step 2 is divided. In FIG.
Reference numeral 1601 denotes a block of M × N pixels, and 1602
Indicates the row number index of each block, and 1603 indicates the column number index of each block. In the figure,
The index number is an m × n matrix. Based on the index matrix, an index vector corresponding to each block of m × n dimensions is generated. At this time, the element number of the index vector becomes the index number of each block 1601.

Then, the process proceeds to a step S4, wherein a random number from "1" to "m * n" is generated based on predetermined key information or key information inputted by the user. At this time, the generated random number corresponds to the element number of the index vector generated in step S3. That is, each random value corresponds to the index number of each block.

In step S5, for example, a bit sequence (8-bit data) of the access control information shown in FIG.
Is associated with the index number of each block. At this time, the correspondence is at the end of the bit sequence (in the example of FIG.
Bit), the association with the next block is
It starts from the head (first bit) of the bit sequence. In this way, this bit sequence is repeatedly allocated until each bit of the bit sequence is allocated to all blocks.

FIG. 17 shows a bit sequence 1 as watermark information.
FIG. 701 is a diagram illustrating a correspondence example between a random number sequence 1702 generated in step S4 and an index number of each block.

In FIG. 17, reference numeral 1701 denotes a bit sequence, and 1702 a random number sequence corresponding to the bit sequence. The number of bits of the bit sequence 1701 and the number of random numbers (R1 to Rmn) 1702 which are also index numbers of each block are both set. (M × n). Also, in FIG. 17, the random number R1 corresponds to the block with the index number (I, J) = (1, 1), and the random number R2 is the index number (I, J) =
The last random number Rmn corresponds to the block of (1, 2), and similarly, the last random number Rmn is an index number (I, J) = (m, n)
Corresponds to the block.

Then, the process proceeds to a step S6, wherein the random number sequence 1702
The index number of the block (I, J = (1, 1)) corresponding to the X = 1st (the random number R1 in FIG. 17) and the bit value of the bit sequence 1701 corresponding to the index number (“0” in the example of FIG. 17) )). Then, the process proceeds to step S8, and an M × N document image block corresponding to the obtained index number is obtained. Next, the process proceeds to step S9, in which each component of the observed pattern feature amount space when the obtained M × N document image is used as the observed image, and the first principal component of the reference pattern calculated in step S1 and the reference vector. Calculate the average score. This is obtained by the following equation (2).

Zz1 * = (a11.mu.1 * + a12.mu.2 * +... + A18.mu.8 *) / p Expression (2) where zz1 * is the average of the observation pattern score, a11,.
18 are the first principal component values of the reference pattern, μ1 *,..., Μ8 * are the component values of the standardized observation pattern feature quantity space, and p is the number of observation points in the observation pattern feature quantity space. 3 shows the number of contour points in the contour image.

Then, the flow advances to step S10 to determine whether or not the bit of the bit sequence 1701 corresponding to the block is "0". If the bit is "0", the flow advances to step S11, and zz1 *> z1 * (reference pattern score) The whole feature space of the observation pattern is moved so as to be + defZ.

If it is determined in step S10 that the bit of the bit sequence 1701 corresponding to the block is "1", the flow advances to step S13, and the characteristic amount of the observed pattern is set so that zz1 * <z1 * (reference pattern score) + defZ. Move the whole space. Here, defZ is a predetermined value set in advance.

In FIG. 15, the feature vector space of the observation pattern is indicated by 1501 and 1502.
Indicates the feature space of the observation pattern moved in step S11 or step S13. In this movement, it is assumed that the movement is performed in the direction in which the value of each element of all the feature amount vectors in the observation pattern feature amount space increases, and not in the direction in which the value of each element decreases.

Then, the process proceeds to step S12, where the observation image data is reconstructed based on the feature space of the observation pattern after the movement in the observation pattern feature space. Then, in step S6, until the random number sequence no longer exists, ie, m ×
The process is performed until the process for the n-th random number is completed.

The binary K image data thus obtained is output to the printer engine as binary K image data 104 in FIG. 1 and printed.

FIG. 18 is a block diagram showing a hardware configuration of the image processing apparatus according to the present embodiment.

In the figure, an input unit 110 for inputting image data is, for example, a scanner or a CD-R.
It is provided with a memory device or the like in which a storage medium such as an OM is mounted and image data stored therein is input. The image data may be loaded from an external storage device 115, which will be described later, or may be connected to a line interface (I / F) 11
7, and may be input from another network or the like. 111 is a CPU for controlling the operation of the entire apparatus.
The program executed by the CPU 111 (for example, shown in the flowcharts of FIGS. 13 and 14)
2 is stored. The memory 112 temporarily stores image data in the various processes described above, or stores or stores input / output image data.
It stores the generated random numbers, vector information, index information, and the like, and is also used as a work area for storing various data during the processing of the CPU 111.
An input unit 113 includes a pointing device such as a keyboard and a mouse. The input unit 113 is operated by an operator and used to instruct generation of the above-described random number or to input various control information.

A display (display unit) 114 has, for example, a CRT, a liquid crystal, and the like. Reference numeral 115 denotes an external storage device that includes a storage medium such as a hard disk and an MO, and stores various image data and programs. Reference numeral 116 denotes a printer, which is an LBP in this embodiment as described above. However, the present invention is not limited to this, and may be, for example, a printer using an inkjet method. 11
A line interface unit 7 controls communication with another device or a network via a communication line.

Next, a case where access control information (watermark information) is extracted from an image in which a digital watermark is embedded as described above will be described.

FIGS. 19 and 20 are flowcharts showing a process for extracting the access control information from the printed image. A program for executing this process is stored in the memory 112 and executed under the control of the CPU 111. .

First, in step S21, a reference pattern score is calculated from the reference vector and the first principal component of the reference pattern in the same manner as in step S1 of FIG. Next, in step S22, the printed image is read in the gray scale mode (8 bits / pixel) using the scanner of the image input unit 110. Next, the process proceeds to step S23, in which a contour portion of the read image is extracted, and a contour image in which the contour portion is thinned to one pixel is generated as shown in FIG. 4, for example. Then, the process proceeds to step S24, where the contour image is converted into a size when the access control information is added. The following processing is performed on the converted contour image. Step S26 in FIGS. 19 and 20
The processing in steps S30 to S30 is the same as the processing in steps S4 and S6 to S9 in FIGS.

First, in step S25, as shown in FIG. 16, the contour image is divided into M × N blocks, and an m × n index matrix is generated from the row number index and column number index of each block. Then, an m × n-dimensional index vector is generated from the index matrix. Here, the element number of the index vector becomes the index number of each block.

Then, the process proceeds to a step S26, wherein random numbers of 1 to m × n are generated based on key information determined in advance or input by the user. At this time, the generated random number corresponds to the element number of the index vector generated in step S25. That is, each random value is an index number of each block. In step S27, it is checked whether a random number sequence exists, that is, whether processing for all blocks has been completed. If not completed, the process proceeds to step S28, where the block corresponding to the X = 1st (R1) of the random number sequence Get the index number. And step S29
Then, an M × N contour image corresponding to the obtained block index number is obtained. In step S30,
The average value of each component value of the observed pattern feature space when the obtained M × N document image is used as the observed image and the principal component score of the first principal component of the reference pattern calculated in step S21 is calculated. I do. This can be obtained by the above equation (2).

Next, the process proceeds to step S31, in which the similarity (g) between the reference pattern score (z1 *) thus obtained and the observed pattern score average (zz1 *) is calculated. The similarity (g) at this time is given by the following equation.

G = zz1 * -z1 * In step S32, the calculated similarity (g) is compared with a predetermined value (defZ). If g> defZ, the process proceeds to step S33, where the embedded bit is It is determined to be “0”. If g> defZ is not satisfied in step S32, the process proceeds to step S34, and it is determined that the embedded bit is "1".
After executing step S33 or S34 in this manner, the process returns to step S27, and repeats the processing of steps S28 to S34 until the same processing is performed on the m × n-th random number. A majority decision is made based on the bit sequence extracted in this way, and the bit length at the time of embedding is reproduced.

As described above, according to this embodiment, desired control information can be embedded without deteriorating an image.

Also, there is an effect that control information embedded in an image can be read and detected with high accuracy.

Even if the present invention is applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), a device including one device (for example, a copying machine, a facsimile machine, etc.) ) May be applied.

Another object of the present invention is to supply a storage medium (or a recording medium) in which a program code of software for realizing the functions of the above-described embodiments is recorded to a system or an apparatus, and to provide a computer of the system or the apparatus. (Or CP
U or MPU) reads out and executes the program code stored in the storage medium. in this case,
The program code itself read from the storage medium implements the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention. By executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an operating system (OS) running on the computer based on the instruction of the program code. This also includes a case where some or all of the actual processing is performed and the functions of the above-described embodiments are realized by the processing.

Further, after the program code read from the storage medium is written into the memory provided in the function expansion card inserted into the computer or the function expansion unit connected to the computer, the program code is read based on the instruction of the program code. This also includes the case where the CPU provided in the function expansion card or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

[0063]

As described above, according to the present invention, it is possible to embed access control information in an image without deterioration of the image.

According to the present invention, the embedded access control information can be read with high accuracy.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a flow of conversion of document image data according to the present embodiment.

FIG. 2 is a diagram showing a flow of image data related to reading of access control information of a scanner.

FIG. 3 is a diagram illustrating an example of an observation image (document image) of M × N pixels.

FIG. 4 is a diagram illustrating an example of a contour image in which a contour portion of the observation image in FIG. 3 is indicated by one pixel.

FIG. 5 is a diagram illustrating a direction index feature amount of a pixel of interest.

FIG. 6 is a diagram showing a variation and a value of a direction index feature amount of a pixel of interest in FIG. 5;

7 is a diagram illustrating a variation of the direction index feature amount of FIG. 6 by a direction index feature amount vector.

FIG. 8 is a diagram illustrating an example of an image of a reference vector.

FIG. 9 is a diagram illustrating a direction index feature amount of the reference vector in FIG. 8;

FIG. 10 is a diagram showing an example of a reference image composed of S × T pixels.

11 is a diagram illustrating an example of a contour image in which the contour of the reference image in FIG. 10 is thinned to one pixel.

FIG. 12 is a diagram illustrating an example of a bit sequence of access control information.

FIG. 13 illustrates an image processing apparatus according to the present embodiment.
9 is a flowchart illustrating a process of embedding access control information in a document image.

FIG. 14 illustrates an image processing apparatus according to the present embodiment.
9 is a flowchart illustrating a process of embedding access control information in a document image.

FIG. 15 shows an example in which a first principal component vector is obtained from a reference pattern feature vector space, and a feature vector space of a document image (observation pattern) into which watermark information is to be inserted is changed in accordance with the watermark information. It is a conceptual diagram.

FIG. 16 is a diagram illustrating an example in which a document image is divided into blocks.

17 is a diagram illustrating an example in which an access control information bit sequence and a random number sequence are assigned to each block divided in FIG.

FIG. 18 is a block diagram illustrating a hardware configuration of the image processing apparatus according to the present embodiment.

FIG. 19 is a flowchart illustrating a process of extracting, from a printed image, access control information in which the image is embedded.

FIG. 20 is a flowchart illustrating a process of extracting, from a printed image, access control information in which the image is embedded.

FIG. 21 is a diagram illustrating an example of embedding control information by controlling the amount of space between words.

FIG. 22 is a diagram illustrating a state before rotation of a character.

FIG. 23 is a view for explaining processing for embedding control information by rotating characters.

FIG. 24 is a diagram illustrating an example in which control information is embedded by enlarging / reducing characters.

Continued on front page F-term (reference) 2C087 AA13 AC08 BB10 BC05 BD06 CB03 CB06 CB13 DA13 5B021 LG08 LL01 5B057 AA11 BA02 CA02 CA06 CA12 CA17 CB02 CB06 CB12 CB17 CB19 CC03 CE08 CE09 CG07 CH08 DA17 DC02 DC05 DC03 DC02 AA40 BA06 9A001 BB02 BB03 GG01 HH23 HH34 JJ35 KK42 LL03

Claims (18)

[Claims] 1. An image processing apparatus for inputting and processing a binary image, comprising: an arithmetic unit for calculating a pattern score average of the target binary image based on the target binary image and a first principal component value of a reference pattern. Comparing means for comparing a pattern score average of the target binary image with a reference pattern score based on a sum of distances between a first principal component direction of the reference pattern and a reference vector; And the subject 2
Translation means for translating the feature vector space of the target binary image in accordance with the access control information embedded in the value image; and translating the target binary image based on the result of translating the feature vector space. An image processing apparatus, comprising: changing means for changing. 2. The pattern score average of the target binary image is obtained by the following equation: zz1 * = (a11μ1 * + a12μ2 * + a13μ3 * + a14μ4 * +
a15μ5 * + a16μ6 * + a17μ7 * + a18μ8 *) / p where a11,..., a18 are the first principal components of the reference pattern, and μ1 * to
2. The image processing apparatus according to claim 1, wherein μ8 * is each component value of a standardized binary image pattern feature amount space, and p is the number of pixels in the binary image pattern feature amount space. 3. The image processing apparatus according to claim 1, wherein the parallel moving unit moves in a direction in which a value of each element of a feature amount vector of the target binary image increases. 4. The reference pattern score is obtained by the following equation: z1 * = a11x1 * + a12x2 * + a13x3 * + a14x4 * + a15
x5 * + a16x6 * + a17x7 * + a18x8 * where a11,..., a18 are the first principal components of the reference pattern and x1 * to
2. The image processing apparatus according to claim 1, wherein x8 * is each component value of a standardized reference vector. 5. The pattern feature space includes the object 2
2. The image processing apparatus according to claim 1, wherein each of the pixels in the contour image of the value image is a set of vector information indicating whether a peripheral pixel of the pixel exists. 6. The parallel moving means, when the value of the access control information is 0, moves so that a pattern score average of the target binary image is larger by a predetermined amount than the reference pattern score. 2. The method according to claim 1, wherein when the value of the control information is 1, the movement is performed such that the sum of the reference pattern score and the predetermined amount is larger than the average of the pattern scores of the target binary image. Image processing device. 7. The image processing apparatus according to claim 1, further comprising a printing unit that prints based on image data corresponding to the target binary image changed by the changing unit. 8. Reading a document image formed based on the target binary image changed by the changing means,
Extracting means for extracting a contour part of the image; means for calculating a pattern score average of an image corresponding to the contour part; reference based on a sum of distances between a first principal component direction of the reference pattern and a reference vector; Difference calculating means for calculating a difference between the pattern score and the average of the pattern scores, and, according to the difference obtained by the difference calculating means,
2. The image processing apparatus according to claim 1, further comprising: a detection unit configured to detect the access control information embedded in the document image. 9. An extracting means for reading a document image and extracting a contour part of the image, a means for calculating a pattern score average of an image corresponding to the contour part, a first principal component direction of a reference pattern and a reference vector, Difference calculating means for calculating a difference between the reference pattern score and the average of the pattern score based on the sum of distances between, according to the difference obtained by the difference calculating means,
An image processing apparatus comprising: a detection unit configured to detect control information embedded in the document image. 10. An image processing method for inputting and processing a binary image, comprising: a calculating step of calculating a pattern score average of the target binary image based on a first principal component value of the target binary image and a reference pattern. A comparison step of comparing a pattern score average of the target binary image with a reference pattern score based on a sum of distances between a first principal component direction of the reference pattern and a reference vector; A translation step of translating the feature vector space of the target binary image in accordance with the obtained comparison result and access control information embedded in the target binary image; And a changing step of changing the target binary image based on the image processing method. 11. The pattern score average of the target binary image is obtained by the following equation: zz1 * = (a11μ1 * + a12μ2 * + a13μ3 * + a14μ4 * +
a15μ5 * + a16μ6 * + a17μ7 * + a18μ8 *) / p where a11,..., a18 are the first principal component values of the reference pattern, and μ
11. The image according to claim 10, wherein 1 * to .mu.8 * are each component value of the pattern feature amount space of the standardized binary image, and p is the number of pixels in the pattern feature amount space of the binary image. Processing method. 12. The image processing method according to claim 10, wherein in the parallel moving step, the object binary image is moved in a direction in which a value of each element of a feature amount vector increases. 13. The reference pattern score is obtained by the following equation: z1 * = a11x1 * + a12x2 * + a13x3 * + a14x4 * + a15
x5 * + a16x6 * + a17x7 * + a18x8 * where a11,..., a18 are the first principal component values of the reference pattern, and x
11. The image processing method according to claim 10, wherein 1 * to x8 * are each component value of a standardized reference vector. 14. The pattern feature quantity space is a set of vector information indicating whether or not a peripheral pixel of the pixel exists in each pixel in the contour image of the target binary image. The image processing method according to claim 10. 15. In the parallel moving step, when the value of the access control information is 0, the target binary image is moved so that the average of the pattern scores is larger than the reference pattern score by a predetermined amount. 11. The method according to claim 10, wherein when the value of the control information is 1, the movement is performed such that the sum of the reference pattern score and the predetermined amount is larger than the pattern score average of the target binary image. Image processing method. 16. The object 2 changed in the changing step
Reading an original image formed based on the value image and extracting an outline of the image; obtaining an average of pattern scores of an image corresponding to the outline; a first principal component of the reference pattern; A difference calculation step of obtaining a difference between a reference pattern score based on the sum of distances between the direction and the reference vector and the pattern score average, and embedding in the document image according to the difference obtained in the difference calculation step 11. The image processing method according to claim 10, further comprising a detecting step of detecting the access control information that has been set. 17. An extraction step of reading a document image and extracting a contour part of the image; a step of obtaining a pattern score average of an image corresponding to the contour part; a first principal component direction and a reference vector of a reference pattern; A difference calculation step for obtaining a difference between a reference pattern score based on a sum of distances between the reference pattern score and the pattern score average, and control information embedded in the document image according to the difference obtained in the difference calculation step. And a detection step of detecting the image processing. 18. A computer-readable storage medium storing a control program for executing the image processing method according to claim 10. Description: