JP3728209B2 - Image processing method and apparatus, computer program, and storage medium - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image processing apparatus and method for embedding digital watermark information in digital data of a document image, or extracting digital watermark information therefrom, and a storage medium storing the method.
[0002]
[Prior art]
In recent years, digital watermark technology has attracted attention as a copyright protection means for digital data such as images and sounds on the Internet. The digital watermark technique is a technique for embedding digital watermark information by manipulating digital data such as images and sounds to the extent that humans cannot perceive.
[0003]
As a digital watermark technique for a multi-valued image, various methods using the redundancy of pixel density are generally known. As a digital watermark technique for a document image that is a binary image, for example, Japanese Patent Laid-Open No. 9-186603 (US Pat. No. 5,861,619) is known in which digital watermark information is embedded by changing the blank length between English (European) words. Yes.
[0004]
[Problems to be solved by the invention]
However, it is difficult to obtain a natural output result with the simple technique of adjusting a distance between words using a plurality of characters as a processing unit in the prior art.
[0005]
Therefore, the present invention makes it possible to embed information by using the distance of the blank portion between characters to obtain a natural output, and to embed more information than that between words It is an object of the present invention to provide an image processing apparatus and method, a program, and a storage medium.
[0006]
Another object of the present invention is to provide an image processing apparatus and method, a program, and a storage medium that provide a more natural output result even if a space between words is used.
[0007]
[Means for Solving the Problems]
In order to solve this problem, for example, an image processing apparatus of the present invention comprises the following arrangement. That is ,
An image processing apparatus for embedding digital watermark information in a document image,
Extraction means for extracting a rectangle circumscribing a character image in the document image or an element image which is an element constituting the character;
A shift amount calculating means for determining a shift amount for shifting the position of the target rectangle to any of the other adjacent rectangles based on the logical value of the bit of the information to be embedded;
Shift means for shifting the character image or element image of the target rectangle based on the shift amount calculated by the shift amount calculation means;
The shift amount calculation means is a digital watermark based on the ratio of PS and P + S, where P is the distance from another rectangle located in front of the rectangle of interest and S is the distance from the rectangle located behind. The shift amount of the position of the target rectangle is calculated so as to be represented by the information.
[0008]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings.
[0009]
<First Embodiment>
In this embodiment, using document image analysis technology consisting of region segmentation and character element circumscribed rectangle extraction for Japanese document data (document data using kanji), using the space length between character element circumscribed rectangles, A digital watermark for embedding information will be described. More specifically, for example, when the technique applied between words in Japanese Patent Laid-Open No. 9-186603 (US Pat. No. 5,816,619) is adopted as it is, the kanji characters “hen” and “making” are separated. In view of the problem of creating an unnatural document image, in the present embodiment, a space length between characters or elements constituting the character (hen, structure, etc.) is used instead of between words, and as unnatural as possible. We propose an embedding method that can extract watermark information reliably on digital.
[0010]
This embodiment can be broadly divided into a digital watermark embedding method and a digital watermark extraction method. FIG. 1 shows an outline of the digital watermark embedding method, and FIG. 2 shows an outline of the digital watermark extraction method. In the following, description will be given in order.
[0011]
<Embedding method>
First, the digital watermark embedding method will be described. In FIG. 1, an input document image 101 (for example, read by an image scanner) is first divided into graphic areas such as a text area and a graph by a document image analysis unit 102 described later. A circumscribed rectangle is extracted for each element. The result is the reference numeral 104 shown in the figure. Here, the character element is a rectangular area extracted using a projection technique known in the character recognition technique (a technique for creating a histogram of dots in the horizontal and vertical directions to determine line spacing and character elements). A rectangle that circumscribes the spread of successive significant dots) and may be a single character or a component of a character (hen, structure, etc.). A known technique is used for dividing (separating) a text area (character string area) and a non-text area in a document image. In addition, the reference numeral 104 shown in the figure is easy to understand. Actually, for example, the upper left corner of the document image is set as the origin, and the coordinates of the upper left corner and the lower right corner of each rectangle from the position, or the coordinates of the upper left corner of the rectangle. And data such as the height and width of the rectangle are extracted and stored in the memory in the order in which the characters are arranged, and the rectangle is not drawn as shown.
[0012]
Further, the blank length between the circumscribed rectangles is calculated from the circumscribed rectangle information (coordinate data) of each character (or character element) in the extracted text area.
[0013]
Although details will be described later, when there are 30 rectangles in a certain line (the number of characters is not necessarily 30), the rectangles at both ends are excluded, the second rectangle, the fourth rectangle, and so on. Focus on the even-numbered rectangle. Now, a blank length P between a certain target rectangle and a rectangle positioned in front of it (hereinafter referred to as the previous rectangle) and a blank length S between the target rectangle and the subsequent rectangle (rear rectangle) are calculated. One bit (0 or 1) of information is embedded in the target rectangle by controlling the relationship between P and S by shifting the rectangle from side to side by a minute distance. When one line is 30 rectangles, 30 / 2-1 = 14 bits are embedded. Although an example of embedding information for even-numbered rectangles is shown here, it is only necessary to embed information in a rectangle where there are preceding and following rectangles, so as long as this condition is satisfied, information is embedded in odd-numbered rectangles. You can embed it. In addition, every other rectangle to be embedded (one non-embedded rectangle is provided between them) is a state in which information is embedded in successive rectangles in order to share a rectangle with one blank distance. This is because the distance from the rear rectangle can always be controlled, errors are gradually accumulated, and the layout changes greatly.
[0014]
As described above, the document image 105 in which the digital watermark information 106 is embedded is generated by the watermark embedding process (103) by shifting the area in a circumscribed rectangle to the left and right.
[0015]
<Document image analysis technology>
Document image analysis technology is essentially one of the elemental technologies of character recognition technology. The input document image is divided into text regions and graphic regions such as graphs, and for text regions, Cut out in character units using projection. As an example, JP-A-6-68301 can be mentioned.
[0016]
<Extraction method>
Next, a digital watermark extraction method will be described. In the digital watermark extraction method, as in the digital watermark embedding method, first, the document image analysis unit 202 used in the character recognition technology performs segmentation and projection from the watermark embedded image 201 (read by an image scanner or the like) for each character. The circumscribed rectangle 203 is extracted. Next, using the extracted circumscribed rectangle group information, the blank length between adjacent circumscribed rectangles is calculated.
[0017]
Focusing on the even-numbered rectangles, 1 bit of information embedded in the target rectangle is extracted from the relationship between the distance P between the front rectangles and the distance S between the rear rectangles. This is similarly performed for other rectangles in the row (even-numbered rectangles), and the embedded information is extracted.
[0018]
<Embedding rules>
Next, embedding rules will be described. First, the blank lengths before and after a rectangle in which 1-bit information is embedded are determined as P and S as described above (see FIG. 3). This rectangle for embedding one bit is determined every other line except for the rectangles at both ends in one row as described above. Next, (PS) / (P + S) is calculated for the blank lengths P and S determined here (however, since this value is 0 or a small value, the denominator is multiplied by a small value or the numerator Quantize with an appropriate quantization step. The quantization representative value is assigned with 0 or 1 alternately.
[0019]
When extracting watermark information, for example, the embedded value is extracted by Equation 1 in FIG. 4 (“mod” is a function that returns the remainder when divided by 2 and means binarization. Can be). Here, α indicates a quantization step.
[0020]
When embedding watermark information, Equation 1 in FIG. 4 is calculated while shifting the region in the rectangle (character or character component) circumscribing rectangle for embedding 1 bit to the left and right one pixel at a time. The direction of translation (left or right) and the width (number of pixels) are searched until the value to be embedded (0 or 1) is reached.
[0021]
Flow charts for this search are shown in FIG. 5 and FIG. Details thereof will be described below. In order to simplify the description, an example in which the document image is horizontally written will be described.
[0022]
First of all, the meaning of variables is as follows.
[0023]
The variable i indicates a translation width candidate. The variable Flag1 indicates whether or not the rectangle that is moved to embed information is in contact with the right rectangle when it is moved to the right by the distance i. The variable Flag2 indicates whether or not to touch when moving the rectangle to the left by the distance i. Like Flag1, take 1 when touching.
[0024]
Next, each process of this flowchart is demonstrated along the flow of a process. This flow starts from step S501.
[0025]
When this process is started, first, in step S502, initial values of variable groups are set. That is, i = flag1 = flag2 = 0.
[0026]
Next, in step S503, when a target rectangle to be moved for embedding (a focused image or a partial image of a character element, hereinafter abbreviated) is translated to the right by a distance i, a rectangle that is a character or character element adjacent to the right. It is determined whether or not (front rectangle) is touched. In the case of contact, the process proceeds to step S504, and the variable flag1 is set to “1”.
[0027]
In step S505, it is determined whether or not the rectangle of interest touches the rectangle on the left when the rectangle of interest is translated left by the distance i. If contact is made, flag2 is set to “1” in step S506.
[0028]
In step S507, it is determined whether or not both the left and right sides are touched when the value indicated by the parallel movement distance i is reached. If both the left and right sides are touched, the translation width is set to 0 in step S508, the calculation of the translation width is terminated, and in this case, embedding is impossible.
[0029]
If it is determined that the left and right are not touched, the process proceeds to step S601 in FIG. In this step S601, it is determined whether or not the bit to be embedded can be obtained by Equation 1 in FIG. 4 when the target rectangle is translated to the right by the distance i. If it is obtained, in step S602, the parallel movement width is set to i and the calculation of the parallel movement width is terminated. Here, the translation width is determined to mean translation to the right when the value is positive, and to translate to the left when the value is negative.
[0030]
In step S603, it is determined whether or not the bit to be embedded can be obtained by Equation 1 in FIG. 4 when the target rectangle is translated to the left by the distance i. If it is obtained, the parallel movement width is set to -i in step S604, and the calculation of the parallel movement width is ended.
[0031]
In step S605, the value of i is incremented, and the process returns to step S503.
[0032]
The search result is determined as the direction and distance of translation, and the region in the circumscribed rectangle of the character for actually embedding one bit is translated. By performing the above processing on the entire document image, the digital watermark information can be embedded in the document image.
[0033]
Since the shift amount for all characters or all character elements to be embedded is determined (the determined shift amount of each rectangle is temporarily stored in the memory in association with the information for specifying the rectangle). The image in the corresponding rectangle is shifted according to the determined shift amount, and a document image after embedding is generated.
[0034]
The embedding method and extraction method described above can be realized using the signal processing apparatus shown in FIG.
[0035]
In the figure, the host computer 701 can be realized by, for example, a widely used personal computer. A scanner 714 reads an original of a document to be embedded with watermark information. The computer 701 can edit and store the read image. Further, the image obtained here can be printed from the printer 715. In addition, various manual instructions from the user are performed by input from the mouse 712 and the keyboard 713.
[0036]
Inside the host computer 701, blocks described later are connected by a bus 716, and various data can be transferred.
[0037]
In the figure, reference numeral 703 denotes a CPU capable of controlling the operation of each internal block or executing a program stored therein. A ROM 704 stores a specific image that is not permitted to be printed, or stores a necessary image processing program or the like in advance. Reference numeral 705 denotes a RAM that temporarily stores a program and image data to be processed for processing by the CPU. Reference numeral 706 denotes a hard disk (HD) capable of storing in advance programs and image data to be transferred to a RAM or the like such as an OS or application, and storing processed image data. A scanner interface (I / F) 707 is connected to a scanner that reads an original or film with a CCD and generates image data, and can input image data obtained by the scanner. Reference numeral 708 denotes a CD drive capable of reading or writing data stored in a CD (CD-R) which is one of external storage media. Reference numeral 709 denotes an FD drive capable of reading from the FD and writing to the FD as in the case of 708. Similarly to 708, reference numeral 710 denotes a DVD drive that can read from and write to DVD. If an image editing program or a printer driver is stored on a CD, FD, DVD, etc., these programs are installed on the HD 706 and transferred to the RAM 705 as necessary. . Reference numeral 711 denotes an interface (I / F) connected to the mouse 712 or the keyboard 713 to accept input instructions.
[0038]
In such a configuration, a document to be embedded with watermark information is read by the scanner 714 using an application (in some cases, a document image stored in the HD 706 or a removable storage medium may be used). Next, watermark information (for example, information such as the author's name) is input from the keyboard 713 or the like, the information is converted into a bit string, a program for executing the processing described above is executed, and information is embedded. The embedded and generated document image may be stored on a network so that it can be viewed by a third party, or may be printed by the printer 715.
[0039]
Further, in the above embodiment, the equation of FIG. 4 is used as the information of the bit to be embedded. One bit of “0” and “1” may be embedded depending on whether the value obtained by simply subtracting S from P is 0 or less, but in this case, the character size of the document image is not considered at all. That is, it cannot adaptively deal with documents with small characters or documents with large characters. In this respect, the configuration shown in FIG. 4 can be applied to a relatively large distance between characters (rectangles) when the character size is large, and a more natural output result can be obtained. Further, α to be multiplied by the denominator in FIG. 4 takes a small value, but this value may also be adaptively changed (for example, it changes according to the average distance between rectangles).
[0040]
In the above-described embodiment, the variable i indicating the shift amount is “1”, that is, an example of shifting in units of one pixel in the read image has been described. One pixel in this case depends on the reading resolution of the image scanner, but a third party does not always read at the same resolution. Therefore, the minimum unit for shifting may be determined depending on the reading resolution of the document. The simplest method is based on the size of one pixel when reading at 200 dpi because most existing image scanners will have a resolution of 200 dpi at a minimum. Accordingly, when reading is performed by a scanner having a resolution of 600 dpi, the variable i is increased to “3” units.
[0041]
Further, in the above embodiment, the processing is performed by paying attention to the characters or the elements constituting the characters, but the formula of FIG. 4 may be applied to a blank portion between words in a sentence in a language such as English. Generally speaking, English words are composed of several characters, so the number of blank spaces between words in a line is less than that of Kanji characters such as Japanese, and the amount of information to be embedded is small, but there are blank spaces between words. It is possible to maintain a natural state. A distinction between a space between words and a space between characters may be performed by, for example, recognizing that a predetermined distance or more is between words. Of course, shifting will shift the entire word. The reason for extracting the embedded information is that the object in the first embodiment is changed from a character to a word, and the description thereof is omitted.
[0042]
<Second Embodiment>
The first embodiment has been described using an existing document image as an example, but the present invention is not limited to this. For example, when the OS running on the personal computer is Windows of Microsoft Corporation in the United States, the above function may be installed in the printer driver installed therein.
[0043]
Hereinafter, an operation process when the printer driver is implemented will be described with reference to the flowchart of FIG.
[0044]
When a print instruction is received from an application such as a word processor, the printer driver is activated.
[0045]
First, in step S81, a message for inquiring whether to embed a document to be printed is displayed, and the operator is made to select it. Note that this selection may be displayed when an option is selected using a dialog box displayed during the printing process.
[0046]
In any case, in step S82, it is determined whether or not embedding has been instructed. If not, the process proceeds to step S83 to perform the same operation as that of a normal printer driver (for example, converted into a PDL description language and output). Process).
[0047]
If it is determined in step S82 that the embedding is instructed, the process proceeds to step S84, and the operator inputs information to be embedded. The timing for inputting the embedding information does not have to be this timing. For example, the embedding information may be input at the timing of embedding in step S81, or may be registered in the registry as a file in which copyright information is described in advance. You may make it utilize the contents beforehand.
[0048]
In step S85, data to be printed received from the application via the OS is analyzed. If the data to be printed is related to a character, a character pattern for printing is generated and the circumscribed rectangle (for one character) is generated. Information may be embedded in the target rectangle based on the calculation of two possible occurrences and the distance from the preceding and following rectangles. Since the rectangle to be embedded needs to have a subsequent rectangle, it is actually performed every time three rectangles are generated. In any case, if the data passed from the application is analyzed, it is possible to reliably determine whether it is related to characters or non-character information such as images and figures, so image area separation is simple. It becomes possible.
[0049]
In this way, when an embedded image (for example, an image for one page) of the minimum unit sufficient for printing is generated, it is output to the OS in step S86, and the OS performs processing for outputting the data to the printer. It will be.
[0050]
As described above, in the case of the second embodiment, when embedding watermark information, document data including characters must be output to a printer in the form of image data. It is possible to embed as part of the work in the application. That is, it can be realized without special knowledge about embedding.
[0051]
<Other embodiments>
As described above, the present invention can be realized by a computer (CPU or MPU) of a general-purpose information processing apparatus (personal computer or the like). Accordingly, there may be a case in which the above embodiment is realized by supplying a software program code for realizing the above embodiment to a computer and causing the computer of the above system or apparatus to operate the above various devices according to this program code. It is included in the category of the present invention.
In this case, the program code of the software itself realizes the functions of the above embodiments, and the program code itself and a storage medium for supplying the program code to the computer, specifically, the program A magnetic disk (floppy disk or hard disk) storing a code, an optical disk (CDROM, CD-R, etc.), a memory card, a tape (paper tape, magnetic tape, etc.), a ROM element, etc. can be used.
In addition, the computer controls various devices according to only the supplied program code, so that the functions of the above-described embodiments are realized, and the OS (operating system) on which the program code is running on the computer. Such program code is also included in the scope of the present invention when the above embodiment is realized in cooperation with a system) or other application software.
[0052]
Further, after the supplied program code is stored in the memory of the function expansion board of the computer or the function expansion unit connected to the computer, the program code is stored in the function expansion board or function storage unit based on the instruction of the program code. A case in which the CPU or the like provided performs part or all of the actual processing and the above embodiment is realized by the processing is also included in the scope of the present invention.
[0053]
As described above, according to the present embodiment, it is suitable for a document image in which a blank length exists for each character or for each partial structure such as “hen” or “make” that constitutes the character. It is possible to embed digital watermark information. Also, whatever the blank length of each adjacent word, character, partial structure, etc., the amount of variation in this blank length for embedding digital watermark information is minimized to suppress visual image quality degradation. Can do.
[0054]
Also, whatever the blank length of each adjacent word, character, partial structure, etc., the amount of variation of this blank length for embedding digital watermark information can be minimized to suppress visual image quality degradation. It becomes possible.
[0055]
【The invention's effect】
As described above, according to the present invention, it is possible to embed information by using the distance of the blank portion between characters to obtain a natural output, and more information than that between words. Can be embedded.
[0056]
Further, according to another invention, even if a space between words is used, a more natural output result can be obtained.
[Brief description of the drawings]
FIG. 1 is a functional block diagram for embedding a digital watermark in an embodiment.
FIG. 2 is a functional block diagram for extracting a digital watermark in the embodiment.
FIG. 3 is a diagram for explaining an embedding process in the embodiment.
FIG. 4 is a diagram illustrating an arithmetic expression for quantization in embedding / extraction processing in the embodiment.
FIG. 5 is a flowchart of an embedding process in the embodiment.
FIG. 6 is a flowchart of an embedding process in the embodiment.
FIG. 7 is a block configuration diagram when applied to the information processing apparatus in the embodiment.
FIG. 8 is a flowchart illustrating an operation processing procedure of a printer driver according to a second embodiment.

Claims (15)

An image processing apparatus for embedding digital watermark information in a document image,
Extraction means for extracting a rectangle circumscribing a character image in the document image or an element image which is an element constituting the character;
A shift amount calculating means for determining a shift amount for shifting the position of the target rectangle to any of the other adjacent rectangles based on the logical value of the bit of the information to be embedded;
Shift means for shifting the character image or element image of the target rectangle based on the shift amount calculated by the shift amount calculation means ;
The shift amount calculation means is a digital watermark based on the ratio of PS and P + S, where P is the distance from another rectangle located in front of the rectangle of interest and S is the distance from the rectangle located behind. An image processing apparatus that calculates a shift amount of a position of a target rectangle so as to be represented by information .   The image processing apparatus according to claim 1, wherein the document image is input from an image scanner. The image processing apparatus according to claim 1 or 2 , wherein the rectangle to be embedded with information is every other rectangle in the group of rectangles in one row. An image processing method for embedding digital watermark information in a document image,
An extraction step of extracting a rectangle circumscribing a character image in the document image or an element image that is an element constituting the character;
Based on the logical value of the bit of information to be embedded, a shift amount calculating step for determining a shift amount to shift the position of the target rectangle to any of the other adjacent rectangles;
Based on the shift amount calculated in the shift amount calculation step, a shift step of shifting the character image or element image of the target rectangle ,
The shift amount calculating step is based on the ratio between PS and P + S, where P is the distance from another rectangle located in front of the rectangle of interest and S is the distance from the rectangle located later. An image processing method characterized by calculating a shift amount of a position of a target rectangle so that information can be expressed. A computer program for embedding digital watermark information in a document image,
A program code of an extraction process for extracting a rectangle circumscribing a character image in the document image or an element image that is an element constituting the character;
Based on the logical value of the bit of information to be embedded, the program code of the shift amount calculation step for determining the shift amount to shift the position of the target rectangle to any of the other adjacent rectangles;
Based on the shift amount calculated in the shift amount calculation step, have a program code shift step of shifting a character image or element image of the target rectangle,
The program code of the shift amount calculation step is based on the ratio of P−S and P + S, where P is the distance from another rectangle located in front of the rectangle of interest and S is the distance from the rectangle located behind. A computer program for calculating a shift amount of a position of a target rectangle so that digital watermark information can be expressed . The computer program according to claim 5 is a printer driver program,
A program code for displaying a selection user interface for selecting whether or not to embed digital watermark information when a print instruction is given;
A program for the step of generating a character pattern from information on characters in the data passed from the host process and passing the generated character pattern or an element image pattern constituting the character pattern to the extraction step when there is an instruction to embed A computer program comprising a code. Storage medium storing a computer program according to paragraph 5 or paragraph 6 claims. An image processing apparatus for inputting a document image and extracting watermark information embedded in the document image,
Circumscribing rectangle discrimination means for discriminating a rectangle circumscribing a character image in the document image or an element image which is an element constituting the character;
A calculation means for calculating a distance from another rectangle adjacent to the target rectangle;
Information embedded in the target rectangle based on the distance calculated by the calculation means, and embedded information extraction means ,
The embedding information extracting means is configured such that P−S and P + S, where P is the distance between the target rectangle and the rectangle positioned in front of the target rectangle, and S is the distance between the target rectangle and the rectangle positioned after the target rectangle. An image processing apparatus , wherein bits of embedded information are extracted based on the ratio . An image processing method for inputting a document image and extracting watermark information embedded in the document image,
A circumscribed rectangle determining step for extracting a rectangle circumscribing a character image in the document image or an element image that is an element constituting the character;
A calculation step of calculating a distance from another rectangle adjacent to the target rectangle;
The calculated on the basis of the output distance calculated in step, and an embedded information extraction step information embedded against target rectangle,
In the embedding information extraction step, P−S and P + S, where P is the distance between the target rectangle and the rectangle positioned in front of the target rectangle, and S is the distance between the target rectangle and the rectangle positioned after the target rectangle. An image processing method characterized in that bits of embedded information are extracted based on the ratio . An image processing apparatus for embedding digital watermark information in a document image consisting of a plurality of words,
A digital watermark embedding unit that embeds digital watermark information in the document image by changing a distance between words adjacent to each word in the document image;
The digital watermark embedding means may represent digital watermark information based on a quantized value of a ratio of PS and P + S, where P and S are distances between a predetermined word and adjacent words before and after the predetermined word. An image processing apparatus characterized by that. An image processing method for embedding digital watermark information in a document image consisting of a plurality of words,
A digital watermark embedding step of embedding digital watermark information in the document image by changing a distance between words adjacent to each word in the document image,
In the digital watermark embedding step, when each distance between a predetermined word and adjacent words before and after it is P and S, the digital watermark information is expressed based on the quantized value of the ratio of PS and P + S. An image processing method characterized by that. A storage medium storing an image processing program for embedding digital watermark information in a document image composed of a plurality of words in a state readable by a computer,
A digital watermark embedding step of embedding digital watermark information in the document image by changing a distance between words adjacent to each word in the document image,
In the digital watermark embedding step, when each distance between a predetermined word and adjacent words before and after it is P and S, the digital watermark information is expressed based on the quantized value of the ratio of PS and P + S. A storage medium characterized by that. An image processing apparatus for extracting digital watermark information from a document image composed of a plurality of words,
In the document image, comprising a digital watermark detection means for detecting digital watermark information in the document image based on a distance between words adjacent to each word,
The digital watermark information detected by the digital watermark detection means is a quantized value of a ratio of PS and P + S, where P and S are distances between a predetermined word and adjacent words before and after the predetermined word. An image processing apparatus characterized by being represented on the basis of the above. An image processing method for extracting digital watermark information from a document image consisting of a plurality of words,
In the document image, comprising a digital watermark detection step of detecting digital watermark information in the document image based on a distance between words adjacent to each word,
The digital watermark information detected in the digital watermark detection step is a quantized value of a ratio of PS and P + S, where P and S are distances between a predetermined word and adjacent words before and after the predetermined word. An image processing method characterized by being expressed based on the above. A storage medium storing an image processing program for extracting digital watermark information from a document image composed of a plurality of words in a state readable by a computer,
In the document image, comprising a digital watermark detection step of detecting digital watermark information in the document image based on a distance between words adjacent to each word,
The digital watermark information detected in the digital watermark detection step is a quantized value of a ratio of PS and P + S, where P and S are distances between a predetermined word and adjacent words before and after the predetermined word. A storage medium characterized by being expressed based on the above.

Images