JP2004287923A - Image processing decision device, image processing decision method and image processing decision program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide electronic watermark technology fit for on-demand printing, using contents on a network to obtain printed matter such as a book. <P>SOLUTION: When deciding whether a decision target image is an image obtained by processing an original image or not, decision target image data including element drawing data for drawing each element constituting the decision target image are acquired, a similarity decision amount is calculated about the element constituting the image shown by the decision target image data acquired by referring to similarity decision amount calculation data showing a calculation technique for the similarity decision amount predetermined about the element constituting the image by the calculation technique shown by the similarity decision amount calculation data, and a similarity degree between the decision target image and the original image is decided by a similarity degree between the calculated similarity decision amount and the similarity decision amount about the corresponding element inside the original image. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an image processing determination device, an image processing determination method, and an image processing determination program.
[0002]
[Prior art]
Recent development of networks has made it possible to easily acquire digital data including images. However, since the contents of digital data can be easily changed, it is desired that the presence or absence of tampering can be easily determined for the purpose of copyright protection or the like. As a technique for determining the presence or absence of tampering, a so-called digital watermark is known, and a digital watermark technique for vector data is also known (for example, see Patent Document 1).
[0003]
[Patent Document 1]
JP-A-2002-24844
[0004]
[Problems to be solved by the invention]
The conventional digital watermarking technique is not suitable for on-demand printing for obtaining a printed matter such as a book using contents on a network. In other words, in the future, it is assumed that on-demand printing service will be provided by describing the content based on XML (extensible Markup Language), and the similarity of the image described in the XML can be effectively and easily determined. There has been a demand for a technique for judging the presence or absence of tampering.
The present invention has been made in view of the above problems, and has an image processing determination apparatus capable of effectively and easily determining the similarity of an image and determining the presence or absence of falsification of an image described in XML. It is an object to provide a processing determination method and an image processing determination program.
[0005]
Means for Solving the Problems and Effects of the Invention
In order to achieve the above object, in the present invention, in a configuration in which an image is formed from image data having element drawing data for drawing an element constituting an image, a calculation method of a similarity determination amount is determined in advance for this element and converted into data. From this data, the similarity determination amount of a certain element in the determination target image is calculated. Then, the similarity between the two images is determined from the similarity between the similarity determination amount and the similarity determination amount of the corresponding element in the original image. If the degree of similarity can be determined, it can be determined that the determination target image has been processed with respect to the original image by determining that the image is similar but not the same as the original image. Note that the degree of similarity can be defined by a predetermined threshold value for the similarity determination amount. Further, the processing refers to making a correction such as a change in the position of an element constituting the image, and refers to all the correction processes other than the change in the relative size and the rotation of the entire image.
[0006]
The image only needs to be formed by combining the above-described elements, and all elements obtained by decomposing the image can be subjected to similarity determination. The elements include, for example, figures such as rectangles, circles, lines, and polygons, colors, patterns, characters, and the like, and all elements constituting an image are elements. The image data in the present invention has element drawing data for drawing these elements, and one element is formed by forming the elements according to the element drawing data.
[0007]
A more specific example is SVG (Scalable Vector Graphics) used when describing an image in XML. That is, in SVG, elements such as rectangles and circles are indicated by tags, and each element can be drawn by defining its shape by its coordinates and size. Image data in SVG format is suitable for the present invention. Applicable.
[0008]
In the present invention, the degree of similarity is determined from the similarity determination amount between the determination target image and the original image. The degree of similarity is determined for a common element in both images. That is, since the elements constituting the image are various and the element drawing data is different for each element, the comparison is performed for the common elements. In order to extract a common element, the element drawing data may be referred to. For example, in the SVG, a common element can be extracted by referring to a tag. Of course, various configurations can be adopted as a configuration for extracting an element to be compared, and a UI that allows a user to specify a part of an image may be applied, and the element may be extracted from the input content of the UI.
[0009]
Since the shape in the image differs depending on each element, the present invention employs a method of calculating a similarity determination amount that differs depending on the element, and determines a calculation method in advance and stores similarity determination amount calculation data indicating the calculation method in a predetermined storage. Store it on the medium. Therefore, by referring to the similarity determination amount calculation data, it is possible to calculate a similarity determination amount that differs depending on the element. The similarity determination amount only needs to be able to provide an index for determining the degree of similarity between a certain element in the original image and an element in the determination target image, and various configurations can be adopted.
[0010]
For example, if the similarity determination amount is calculated for each element, the similarity can be determined for each element constituting the image. Therefore, the degree of similarity is determined for a plurality of elements in the image. If all of these elements are similar, it can be said that the original image and the determination target image are similar, and the plurality of similarity determination amounts are Various processing determinations can be performed, such as determining that a part of an image has been processed when the same plurality of other similarity determination amounts indicate similarity of elements.
[0011]
Note that it is not essential that the similarity determination amount be calculated for each element. That is, the similarity determination amount may be calculated collectively for a plurality of elements. For example, a distance between a plurality of elements, a distance between parts of each element, an angle at which a straight line connecting the center points intersects, or the like can be used as the similarity determination amount. Of course, a plurality of similarity determination amounts may be calculated for one element. Further, a similarity determination amount calculated for each element and a similarity determination amount calculated collectively for a plurality of elements may be used together.
[0012]
In addition, the method of designating an element in XML is highly arbitrary, and the creator of the original image can independently define the rule of the tag. This allows the author to define the element drawing method independently. Even in this case, in the present invention, similarity determination amount calculation data corresponding to this drawing method is defined in advance and stored in a predetermined storage medium. Therefore, it is possible to easily determine the presence or absence of processing even for an image described in XML having such high arbitraryness.
[0013]
In the present invention, it suffices if it is possible to determine whether or not the processing has been performed by determining the degree of similarity, and calculate the similarity determination amount for a certain element of the determination target image and compare it with the similarity determination amount of the original image. I just want to be able. Accordingly, the original similarity determination amount may be calculated each time the image processing is determined, or may be calculated in advance and stored in a predetermined storage medium, and various configurations can be adopted. With the above configuration, it is possible to judge the processing of the image from the degree of similarity. Therefore, when the original image is published as content that can be viewed on the Internet, if the image data that seems to have been processed is acquired, the image data is described with this image data It can be determined whether or not the processed image is obtained by processing the original.
[0014]
In addition, when determining processing of an image, in addition to determining whether or not the determination target image has been processed by determining the degree of similarity between the determination target image and the original image based on the degree of similarity with the similarity determination amount, Processing of an image can be determined by various configurations. As an example of the configuration, a predetermined watermark constant is added in advance to the similarity determination amount of the original image to determine the processing presence / absence determination amount, and the difference between the similarity determination amount of the determination target image and the processing determination is determined. May be.
[0015]
That is, when the original image is made public and it is determined whether or not processing has been performed on the disclosed image, it is determined whether or not the difference between the processing presence determination amount and the similarity determination amount of the determination target image is different from the watermark constant. If the difference is different from the watermark constant, the image to be determined is different from the original image, so it can be estimated that the image has been processed. Of course, even when the image to be determined is an image completely different from the original image, the difference is different from the watermark constant, so that the processing is performed when the difference is within a range defined by a predetermined threshold and different from the watermark constant. Various configurations, such as determining that the operation has been performed, can be adopted.
[0016]
In addition, if image data having element drawing data that gives a similarity determination amount after adding the watermark constant is made public and this image data is set as an original image, it is determined whether the difference is “0”. The presence or absence of processing can be determined. That is, if the image data after the watermark is embedded is processed, the similarity determination amount calculated for the determination target image and the above-mentioned processing presence / absence determination amount are the same when the image data is unprocessed, so that the difference is “0”. It is possible to determine the presence or absence of processing based on whether or not processing is performed.
[0017]
Various values can be adopted as specific values of the similarity determination amount. However, as a suitable configuration when image data having element drawing data that gives a similarity determination amount after adding a watermark constant is disclosed. Alternatively, it is possible to adopt a configuration in which the calculation method of the similarity determination amount is determined so that the variation between the images formed by the element drawing data giving the similarity determination amount before and after the addition of the watermark constant is reduced. That is, since the element drawing data that gives the similarity determination amount after adding the watermark constant is made public, the image formed by the element drawing data and the image formed by the element drawing data before adding the watermark constant are compared. Is different, the contents of the original image to be disclosed greatly fluctuates due to the addition of the watermark constant. This makes it easier for a third party to recognize the presence of the watermark.
[0018]
Therefore, if the similarity determination amount is determined so that the variation between the images formed by the element drawing data before and after the addition of the watermark constant is reduced, the similarity determination amount after adding the watermark constant is obtained. When an image formed by drawing data is made public, the image to be made public and the original image to be made public can be recognized as almost the same. Further, it is possible to prevent a third party from recognizing that the watermark is embedded. Note that the watermark embedding target may be a parameter of element drawing data in addition to the similarity determination amount.
[0019]
The similarity determination amount is preferably set to a value that does not change even when the size is changed and the element is rotated. With such a configuration, it can be considered that the image is the same as the original image only by relatively changing the size or rotating the image. As a more specific example of such a similarity determination amount, there is a configuration in which a value indicating a relative relationship between elements is calculated from element drawing data. That is, the relative distance between the vertices constituting the element, the ratio of the relative distance, the angle of the line connecting the vertices, and the like do not change only by relatively changing the size of the image or rotating the image. Such a value may be used as the similarity determination amount.
[0020]
Various examples can be adopted as a method of calculating the similarity determination amount. As an application example of element drawing data including vector graphic data specifying the shape of each element, a plurality of parameters constituting the vector graphic data are used. It is possible to adopt a configuration example in which parameters used for calculating the similarity determination amount are extracted and the similarity determination amount is calculated from these parameters. The extraction rule for this parameter is set as similarity determination amount calculation data.
[0021]
That is, the vector graphic data includes various parameters such as data indicating the coordinates of the vertices constituting the element and the tangential direction of the outer periphery of the figure, and the similarity determination amount is calculated using any of these parameters. At this time, the rule for extracting the parameter is not known to the third party, so that the third party cannot erase the trace of the processing. That is, the similarity determination amount is calculated from any of the parameters of the vector graphic data, but the similarity determination amount is not changed unless a third party knows from which parameter the similarity determination amount is calculated. Processing of the image becomes impossible, and processing can be determined based on the similarity determination amount.
[0022]
Note that a configuration using a password may be employed as a preferred configuration example that ensures that the extracted parameters are not known to a third party. That is, a data string is generated by a one-way function from an arbitrary password specified by a person who manages the original image, such as the owner of the original image, and the parameters to be extracted are determined from the data string. More specifically, for example, in the bit string obtained by the one-way function, “1” is used for calculating the similarity determination amount, “0” is not used, and the bit string is sequentially used as a parameter of the vector graphic data. It is also possible to adopt a configuration such as one corresponding to the above.
[0023]
The password assigned to the one-way function can adopt various configurations, and may be a character or a number. When the password is a character, a specific numerical value may be applied to the character and substituted into the function. Various functions such as RSA and MD5 can be adopted as the one-way function.
[0024]
The similarity determination means only needs to be able to determine the similarity between the determination target image and the original image based on the similarity, and various configurations can be adopted. For example, a configuration using a frequency distribution of a plurality of similarity determination amounts can be adopted. That is, a plurality of similarity determination amounts are calculated for a certain element, and a frequency distribution of the similarity determination amounts is calculated. Since the similarity determination amount serving as a sample value when calculating the frequency distribution is a specific value for a certain element or a certain image, the frequency distribution is also unambiguous. The distribution index indicating the spread of the frequency distribution, for example, a standard deviation or a variance, is a value uniquely determined by the frequency distribution, and the distribution index is a close value between those having a close frequency distribution.
[0025]
Thus, the degree of similarity of the images can be determined by comparing the distribution indices. Therefore, when the distribution indices match, the images are not processed, and when they do not match and the difference between the distribution indices of the images is equal to or less than a certain threshold, both images can be regarded as similar. . According to the distribution index, it is possible to statistically determine whether or not the similarity determination amounts of the elements forming the image are similar. It can be determined whether or not processing has been performed by determining whether or not processing has been performed.
[0026]
Meanwhile, the above-described image processing determination device also functions as a method of performing a predetermined process in a time series for calculating a similarity determination amount and determining a similarity degree and the presence or absence of processing. Therefore, it is also possible to adopt a configuration corresponding to claims 2 to 7, which constitutes the invention as an image processing determination method as in the inventions described in claims 8 and 9. In addition, such an image processing determination device may exist alone, or may be used in a state of being incorporated in a certain device. The idea of the invention is not limited to this, but includes various aspects. It is a thing. Therefore, it can be changed as appropriate, such as software or hardware. When the control software of the image processing determination device is used as an example of realizing the idea of the present invention, a program for realizing such a function naturally exists. The invention according to claims 10 and 11 is an image processing determination program that realizes the above-described functions. Needless to say, a configuration corresponding to claims 2 to 7 can be adopted here.
[0027]
BEST MODE FOR CARRYING OUT THE INVENTION
Here, embodiments of the present invention will be described in the following order.
(1) Outline of image processing determination:
(2) Calculation of data required for processing:
(3) Configuration and processing of the image processing determination device:
(4) Other embodiments:
[0028]
(1) Outline of image processing determination:
FIG. 1 is an explanatory diagram for explaining an outline of image processing determination according to the present invention, and FIG. 2 is a diagram showing an example of image data to be determined. The image data in FIG. 2 is described in an XML file, and the contents of the elements constituting the image are specified by SVG format text. That is, in the SVG image data of FIG. 2, parameters of the rectangular element are described in the <rect> tag, and the position, size, presence or absence or color of the rectangle, and the color and width of the line are defined by the parameter. I have. Also, parameters of the polygon element are described in the <polygon> tag, and this parameter defines the presence or absence or color of the polygon, the color and width of the line, and the coordinates of each vertex.
[0029]
Therefore, one image can be formed by sequentially drawing the elements with reference to the parameters described in each tag. In the image data shown in FIG. 2, two polygonal elements are defined, and form a star and a hexagon, respectively. Elements described in the SVG image data are not limited to rectangles and polygons, and images can be formed using tags indicating circles, ellipses, straight lines, polygonal lines, and text. Further, any other tag is arbitrarily created, data indicating the meaning of the created tag is created, and this data is referred to when the image is drawn by the SVG image data. Can be included within.
[0030]
Needless to say, the SVG image data shown in FIG. 2 is an example, and it is preferable to apply the present invention to an image formed from a larger number of elements. FIG. 1 illustrates the image processing determination of the present invention by taking a hexagon as an example for simplicity. Here, as shown in the upper left of FIG. 1, hexagonal vertices are numbered 1 to 6 and described. The coordinates of each vertex are specified by the coordinate values of the polygon shown in FIG. In the present embodiment, the relative distance between vertices is used as the similarity determination amount. In other words, the distance between the vertices can be calculated based on the coordinates. However, if the distance is an absolute distance, the value fluctuates due to the scaling of the element. The relative value is used as the similarity determination amount.
[0031]
In the present embodiment, the similarity determination amount is calculated for a specific vertex instead of calculating the similarity determination amount for all vertices. The vertex used for calculating the similarity determination amount is uniquely specified by a predetermined password. The password is predetermined by the administrator of the original image, and a data string is generated by substituting a numerical value based on the password into a one-way function, and "1" in the data string means extraction of a parameter. I do.
[0032]
That is, the generated data sequence is sequentially compared with the vertices 1 to 6, and the coordinates of the vertices (vertices 2 and 4 in FIG. 2) corresponding to “1” are set as parameters used for calculating the similarity determination amount. According to this configuration, it is possible to make it difficult for a third party to determine which part of each element is used for calculating the similarity determination amount. As described above, when the parameters used for calculating the similarity determination amount are determined, the distance between the vertex and another vertex is calculated.
[0033]
In the example shown in FIG. 1, the distance from vertex 2 to vertices 1, 5, 6, 4, and 2 and the distance from vertex 4 to vertices 3, 2, 1, 6, and 5 are calculated. In FIG. 1, r _nm Indicates the relative distance between the vertices, n indicates the number of the vertex existing at the start point of the arrow shown in FIG. 1, and m indicates the number of the vertex existing at the end point of the arrow shown in FIG. I have. In the present embodiment, since the relative distance is used, processing such as normalization is performed so that the distance between specific vertices is “1”.
[0034]
After calculating the relative distances, a frequency distribution is obtained for the obtained plurality of relative distances. Then, the standard deviation σ of the frequency distribution is calculated, and the degree of similarity between the original image and the image to be determined is evaluated based on the standard deviation. That is, since the standard deviation is a value reflecting the nature of the frequency distribution, one value can be evaluated at a time for a plurality of relative distances. Therefore, in the present embodiment, the closer the standard deviation calculated for the original image and the standard deviation calculated for the determination target image, the more similar the two images are regarded to be. If the two images are similar but the standard deviations are not the same value, the image to be determined is considered to be the person who processed the original image.
[0035]
(2) Calculation of data required for processing:
In the present embodiment, necessary data is prepared in advance to execute the above-described image processing determination. FIG. 3 is a flowchart showing an operation for creating these data. Since this operation requires a lot of arithmetic processing, it is performed by a computer. Since the created data is used by an image processing determination device described later, it is preferable that the data be generated by the image processing determination device. In step S100, image data indicating an original image (an original image for determining whether or not the image has been processed) is obtained. This image data also includes SVG image data, and each element of the original image is described by the SVG image data.
[0036]
In step S110, an element for which a similarity determination amount is to be calculated is determined from the elements described in the SVG image data. Of course, all of the plurality of elements described in the SVG image data may be targeted, some may be targeted, or a plurality of targets may be determined for each element or a plurality of elements collectively. The similarity determination amount may be calculated for the target. In step S120, a password is determined to extract parameters used for calculating the similarity determination amount. The determined password may be input to the computer using an input device (not shown) such as a keyboard.
[0037]
In step S130, a numerical value corresponding to the input password is substituted into a predetermined one-way function to generate the data string and extract parameters used for calculating the similarity determination amount from the parameters of each element. The one-way function only needs to have such a property that an input value cannot be easily calculated from an output value obtained by substituting an arbitrary input value into the function, and various functions can be adopted.
[0038]
In step S140, a similarity determination formula is determined. Here, the similarity determination formula is a formula for calculating the similarity determination amount. The similarity determination formula does not change even if the image is enlarged / reduced or rotated for the determined element, but the similarity determination value changes due to movement or deformation of the coordinates. The determination amount is determined, and an equation for calculating the similarity determination amount is determined. In the example shown in FIG. 1, an equation for calculating the relative distance is determined. After determining this formula, in step S150, the similarity determination amount calculation data indicating the similarity determination formula is stored in a storage medium (not shown). Note that the similarity determination amount calculation data is determined for each target element. Further, an expression indicating the one-way function used when extracting the parameter is also stored in association with the element.
[0039]
After storing the similarity determination amount calculation data, in step S160, the stored similarity determination amount calculation data is referred to, and the similarity determination amount for the target element in the image data acquired in step S100 is calculated. Then, in step S170, a standard deviation is calculated from the frequency distribution of the similarity determination amount, and σ ₀ The data is stored in the storage medium (not shown) as data. This σ ₀ The data is a standard deviation calculated for the target element of the original image, and is used at the time of subsequent processing determination. This σ ₀ Data is also stored for each target element.
[0040]
(3) Configuration and processing of the image processing determination device:
Next, the configuration and processing of the image processing determination device will be described. FIG. 4 is a block diagram illustrating a configuration of the image processing determination device according to the present embodiment, and FIG. 5 is a processing flow of an image processing determination program. The image processing determination device can be configured by a computer, and in the present embodiment, it is assumed that the image processing determination device is configured by a general-purpose computer. Therefore, the image processing determination device 10 includes, in addition to the hard disk 12, an input device such as a keyboard (not shown) and a program execution environment such as a CPU and a RAM. 20 is configured to be executable.
[0041]
The image processing determination program 20 includes an image data acquisition unit 21, a similarity determination amount calculation unit 22, and a similarity determination unit 23. The similarity determination amount calculation unit 22 includes a data string generation unit 22a and a calculation unit 22b, and the similarity determination unit 23 includes a frequency distribution calculation unit 23a and a determination unit 23b. The similarity determination amount calculation data 12b created by the operation shown in FIG. ₀ Data 12c and password data 12a indicating the password determined in the operation shown in FIG. 3 are stored.
[0042]
The image data acquisition unit 21 acquires an XML file including the SVG image data of the determination target image via an I / F (not shown) in step S200, and passes the SVG image data to the similarity determination amount calculation unit 22. In step S210, the similarity determination amount calculation unit 22 refers to the similarity determination amount calculation data 12a to determine an element to be determined in the SVG image data. In step S220, the data sequence generation unit 22a generates a data sequence for the element to be determined by referring to the password data 12a and the similarity determination amount calculation data 12a, and sets a parameter used for calculating the similarity determination amount of the element. Is extracted.
[0043]
In step S230, the calculation unit 22b extracts the similarity determination formula for the element to be determined with reference to the similarity determination amount calculation data 12a, and calculates the similarity determination amount using the parameters. The obtained similarity determination amount is transferred to the frequency distribution calculation unit 23a of the similarity determination unit 23. In step S240, the frequency distribution calculation unit 23a calculates the frequency distribution of the similarity determination amount and calculates the standard deviation σ of the determination target image. The determination unit 23b stores the σ stored in the hard disk 12 in step S250. ₀ From the data 12c, the σ of the element to be determined ₀ Is obtained, and in step S260, | σ ₀ It is determined whether −σ | is smaller than a predetermined threshold T.
[0044]
The threshold value T is specified in advance, and is a maximum value as long as the images can be regarded as similar even if there is a difference in the standard deviation between the image to be determined and the original image. Therefore, in step S260, | σ ₀ If −σ | is not determined to be smaller than the predetermined threshold T, it is determined in step S275 that both images are dissimilar. In step S260, | σ ₀ When it is determined that −σ | is smaller than the predetermined threshold T, it is determined in step S270 that both images are similar.
[0045]
In the present embodiment, if it is determined in step S270 that the images are similar, then in step S280, the σ ₀ Is determined whether or not σ of the determination target image is equal to or not. If it is determined in step S280 that the two are equal, it is determined in step S290 that the determination target image has not been processed with respect to the original image. If it is not determined in step S280 that the two are equal, it is determined in step S295 that the determination target image has been processed from the original image.
[0046]
As described above, in the present embodiment, a plurality of similarity determination amounts for determining the degree of similarity of elements from the parameters of each element are calculated for the image data in which the elements of the image are described by the vector graphic data. Then, a distribution index indicating the distribution of the similarity determination amount is compared. Therefore, the degree of similarity of the image constituted by each element can be determined, and whether or not the image has been processed can be determined based on the determination of the degree of similarity. Since the SVG image data is image data described in XML, it is possible to easily determine whether or not the image is a processed original image when handling the image in XML. For this reason, it is also possible to determine the presence or absence of image tampering. For example, if an original image is published on the Internet and image data of an image that is considered to have been used by falsifying the original image is obtained, by applying the present invention to the image as a determination target image, The presence or absence can be determined.
[0047]
(4) Other embodiments:
The above embodiment is an example of realizing the image processing determination device, the image processing determination method, and the image processing determination program according to the present invention, and it is needless to say that other configurations can be adopted. For example, a watermark α may be added to the similarity determination amount at the time of similarity determination, and the presence or absence of processing may be determined using the watermark. Further, the image processing determination device according to the present invention can be used in various situations. FIG. 6 shows a configuration example when the image processing apparatus according to the present invention is used for image processing determination during on-demand printing.
[0048]
In the figure, the certificate authority 100, the client 200, the Web servers 300 and 310, and the printer 400 can be connected to the Internet and can perform two-way communication with each other. The certification authority 100 is a computer provided with a processing presence / absence determination unit 110, and the processing presence / absence determination unit 110 causes the certification authority 100 to function as an image processing determination device. The client 200 is a computer used by a user who receives the on-demand printing service, and the user creates the XML file 210 via an input device such as a keyboard (not shown).
[0049]
In the XML file 210, various tags (not shown) and links 210a and 210b indicating SVG image data that can be obtained via the Internet are described. In FIG. 6, SVG image data 1 and 2 at the link destination are stored in Web servers 300 and 310, respectively. When performing on-demand printing, the XML file 210 created by the client 200 is transmitted to the certificate authority 100.
[0050]
In the certification authority 100, the creator of the original image has registered the password and the similarity determination amount calculation data in advance, and σ ₀ Data has been calculated. The processing presence / absence determining unit 100 acquires the XML file 210 transmitted from the client 200, and acquires the SVG image data of the link destination according to the description of the links 210a and 210b. Then, processing determination is performed on these SVG image data using the similarity determination amount calculation data and the like.
[0051]
As a result, when it is determined that the original image has not been processed, the image is rendered based on the SVG image data to generate printable data, and transferred to the printer 400. The printer 400 performs printing based on this data. Accordingly, a user using the client 200 can obtain a printed matter of a document for which a print execution request has been issued by visiting a store or the like (for example, a convenience store) where the printer 400 is installed. If the original image has been processed, the printing is not executed, or the printing is executed but the printing log (information specifying the client 200, the Web server 300, 310, the XML file 210, the execution date and time, etc.) , Various types of information) can contribute to copyright protection.
[0052]
In this configuration, data (password data 12a, similarity determination amount calculation data 12b, σ ₀ If any one or a combination of the data is created by the administrator of the certificate authority 100, it is preferable to store these data in the certificate authority 100. However, the creator of the original image may create these data. In this case, the data can be stored in a web server or the like other than the certificate authority 100, and various configurations can be adopted. .
[Brief description of the drawings]
FIG. 1 is an explanatory diagram illustrating an outline of image processing determination according to the present invention.
FIG. 2 is a diagram illustrating an example of image data to be determined.
FIG. 3 is a flowchart illustrating a data creation operation.
FIG. 4 is a block diagram illustrating a configuration of an image processing determination device.
FIG. 5 is a processing flowchart of an image processing determination program.
FIG. 6 is a block diagram illustrating a configuration example according to another embodiment.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 10 ... Image processing determination apparatus, 20 ... Presenter PC, 21 ... Network I / F, 22 ... Communication control part, 23 ... Transmission control program, 23a ... Distribution availability setting part, 24 ... Hard disk drive, 24a ... Presentation data, 25 ... Presentation program, 26 display unit, 27 input device control unit, 30 projector, 31 network I / F, 32 communication control unit, 33 projector control program, 34 projection control unit, 35 projection unit, 40 ... Client PC, 41 ... Network I / F, 42 ... Communication control unit, 43 ... Reception control program, 44 ... Display control unit, 45 ... Display unit

Claims (11)

An image processing determination device that determines whether the determination target image is obtained by processing the original image,
Determination target image data acquisition means for obtaining determination target image data including element drawing data for drawing each element constituting the determination target image,
A similarity determination amount calculation data storage unit that stores similarity determination amount calculation data indicating a predetermined similarity determination amount calculation method for an element configuring an image;
A similarity determination amount calculation unit that calculates a similarity determination amount by a calculation method indicated by the similarity determination amount calculation data for an element configuring an image indicated by the acquired determination target image data;
A similarity determination unit configured to determine a similarity between the determination target image and the original image based on a similarity between the calculated similarity determination amount and the similarity determination amount for a corresponding element in the original image. Image processing determination device. An image processing determination device that determines whether the determination target image is obtained by processing the original image,
Determination target image data acquisition means for obtaining determination target image data including element drawing data for drawing each element constituting the determination target image,
A similarity determination amount calculation data storage unit that stores similarity determination amount calculation data indicating a predetermined similarity determination amount calculation method for an element configuring an image;
A similarity determination amount calculation unit that calculates a similarity determination amount by a calculation method indicated by the similarity determination amount calculation data for an element configuring an image indicated by the acquired determination target image data;
A processing presence / absence determination amount calculating means for calculating a similarity determination amount for the elements constituting the original image by the calculation method indicated by the similarity determination amount calculation data and adding a predetermined watermark constant to the similarity determination amount to obtain a processing presence / absence determination amount When,
An image processing determination device, comprising: a processing presence / absence determination unit that determines whether or not processing has been performed based on a difference between the similarity determination amount calculated for the determination target image and the processing presence / absence determination amount. 3. The method according to claim 1, wherein the similarity determination amount is a value such that a change between images formed by element drawing data that provides a similarity determination amount before and after the addition of the watermark constant becomes small. 4. The image processing determination device according to any one of the above. The method according to any one of claims 1 to 3, wherein the similarity determination amount is a value that does not change even when the size of the element is changed and the element is rotated. Image processing determination device. The element drawing data includes vector graphic data specifying the shape of each element, and the similarity determination amount calculation data is used to extract a parameter used for calculating a similarity determination amount from a plurality of parameters constituting the vector graphic data. The image processing determination device according to claim 1, further comprising data indicating a rule. 6. The image processing determination apparatus according to claim 5, wherein a parameter used for calculating the similarity determination amount is determined from a value obtained by substituting a predetermined password into a one-way function. The similarity determination means compares the distribution index indicating the spread of the frequency distribution of a plurality of similarity determination amounts calculated for a certain element between the determination target image and the original image to thereby determine the similarity between the similarity determination amounts of the two images. 7. The image processing determination device according to claim 1, wherein An image processing determination method for determining whether the determination target image is obtained by processing the original image,
A determination target image data obtaining step of obtaining determination target image data including element drawing data for drawing each element constituting the determination target image,
Reference is made to similarity determination amount calculation data indicating a predetermined similarity determination amount calculation method for the elements constituting the image, and the similarity determination amount calculation data indicates the elements constituting the image indicated by the acquired determination target image data. A similarity determination amount calculating step of calculating a similarity determination amount by a calculation method,
A similarity determination step of determining the similarity between the determination target image and the original image based on the similarity between the calculated similarity determination amount and the similarity determination amount for the corresponding element in the original image. Image processing determination method to be performed. An image processing determination method for determining whether the determination target image is obtained by processing the original image,
A determination target image data obtaining step of obtaining determination target image data including element drawing data for drawing each element constituting the determination target image,
Referring to similarity determination amount calculation data indicating a predetermined similarity determination amount calculation method for an element configuring an image, the similarity determination amount calculation data is determined for the element configuring the image indicated by the acquired determination target image data. A similarity determination amount calculating step of calculating a similarity determination amount by the calculation method shown,
A processing presence / absence determination amount calculating step of calculating a similarity determination amount for the elements constituting the original image by the calculation method indicated by the similarity determination amount calculation data and adding a predetermined watermark constant to the similarity determination amount to obtain a processing presence / absence determination amount When,
An image processing determination method, comprising: a processing presence / absence determination step of determining the presence / absence of processing based on a difference between the similarity determination amount calculated for the determination target image and the processing presence / absence determination amount. An image processing determination program that determines whether the determination target image is obtained by processing the original image,
A determination target image data obtaining function for obtaining determination target image data including element drawing data for drawing each element constituting the determination target image,
A similarity determination amount calculation data storage function for storing similarity determination amount calculation data indicating a method of calculating a predetermined similarity determination amount for an element constituting an image;
A similarity determination amount calculation function of calculating a similarity determination amount by a calculation method indicated by the similarity determination amount calculation data for an element configuring an image indicated by the acquired determination target image data;
A computer implements a similarity determination function of determining a similarity between a determination target image and an original image based on a similarity between the calculated similarity determination amount and a similarity determination amount of a corresponding element in the original image. An image processing determination program characterized by the following. An image processing determination program that determines whether the determination target image is obtained by processing the original image,
A determination target image data obtaining function for obtaining determination target image data including element drawing data for drawing each element constituting the determination target image,
A similarity determination amount calculation data storage function for storing similarity determination amount calculation data indicating a method of calculating a predetermined similarity determination amount for an element constituting an image;
A similarity determination amount calculation function of calculating a similarity determination amount by a calculation method indicated by the similarity determination amount calculation data for an element configuring an image indicated by the acquired determination target image data;
A processing presence / absence determination amount calculation function that calculates a similarity determination amount for the elements constituting the original image by the calculation method indicated by the similarity determination amount calculation data and adds a predetermined watermark constant to the similarity determination amount to determine a processing presence / absence determination amount. When,
An image processing determination program for causing a computer to realize a processing presence / absence determination function of determining whether or not processing has been performed based on a difference between the similarity determination amount calculated for the determination target image and the processing presence / absence determination amount.

Images