JP2006074166A - Image processing apparatus and method thereof - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide embedding and extraction of watermark information which is capable of suppressing deterioration in a character while embedding information of more watermark information for one character than in conventional technique. <P>SOLUTION: An image input unit 101 inputs a document image, a document analyzing unit 102 extracts the feature point of the character of the document image inputted by the unit 102, and an embedding unit 106 embeds an electronic watermark into the feature point. Meanwhile, the feature point is any one of at least a cross point, a T point, a corner or an end point of the above character. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a technique for embedding information in a document image and extracting the embedded information.

  In recent years, digital image forming apparatuses such as printers and copiers have been remarkably improved in image quality, and it has become possible to easily obtain high-quality printed materials. That is, anyone can obtain the required printed matter by image processing using a high-performance scanner, printer, copier, and computer. For this reason, problems such as unauthorized copying and falsification of documents have occurred, and in recent years, there has been an active movement to embed access control information as watermark information in the printed matter itself in order to prevent or prevent them.

  As such a function, there is an invisible type digital watermark which embeds access control information in a printed matter invisible. As a general realization method, a type of embedding information by controlling the amount of space in an English character string (for example, Patent Document 1, Patent Document 2), a type of rotating a character (for example, Non-Patent Document 1), a character There are proposed a type for enlarging and reducing the size, a type for embedding information by deforming characters, and the like.

  FIG. 19 shows a type of printed matter that controls the amount of space in the English character string. Here, s and p are called spaces. If the watermark information bit to be embedded is 0, this space is set to p1 ← (1 + q) (p + s) / 2, s1 ← (1-q) (p + s) / 2, and if the watermark information bit is 1, p1 ← (1-q) (p + s) / 2 and s1 ← (1 + q) (p + s) / 2. The range of q is 0 <q <1.

  FIG. 20 is a diagram for explaining a character when watermark information is embedded by digital watermark by enlarging or reducing the size of the character. For example, “1” is embedded (A in FIG. 20) when the character size is larger than the original character, and “0” is embedded (B in FIG. 20) when the character size is reduced. . The character to be embedded may be a continuous character, an interval of several characters, or a character at a predetermined position. In FIG. 20, since the character “image” is enlarged and the character “re” is reduced, watermark information “10” is embedded.

FIG. 21 is a diagram for explaining a character when watermark information is embedded by digital watermarking by rotating the character and changing the inclination. For example, “1” is embedded when rotated clockwise (C in FIG. 21), and “0” is embedded when rotated counterclockwise (D in FIG. 21). The character to be embedded may be a continuous character, an interval of several characters, or a character at a predetermined position. In FIG. 21, since the character “image” is rotated clockwise and the character “structure” is rotated counterclockwise, information “10” is embedded.
“Digital Watermarking with Sealed Images on Japanese Documents” (Yasuhiro Nakamura, Kokoo Matsui), Transactions of Information Processing Society of Japan, Vol. 38 No. 11 Nov. 1997. US Pat. No. 6,086,706 JP-A-9-186603

  However, if the watermark information is embedded in the document image by the above method, in any case, only a maximum of 1-bit information can be embedded in one character, so that the amount of information that can be embedded is small.

  The present invention has been made paying attention to the above points, and provides an image processing apparatus and method capable of suppressing deterioration of characters while embedding more watermark information than before in one character. The purpose is to do.

  In order to solve the above problems, an image processing apparatus according to the present invention includes an input unit that inputs the image, an extraction unit that extracts a feature point of the input image, and a digital watermark embedding unit that embeds a digital watermark in the feature point The feature point is at least one of an intersection, a T-point, a corner, and an end point of the character.

  In order to solve the above problems, an image processing apparatus according to the present invention includes an input unit that inputs a document image in which watermark information is embedded, and a feature point extraction unit that extracts character feature points of the input document image. And watermark information extracting means for extracting watermark information from the feature point, wherein the feature point is at least one of an intersection, a T-shaped point, a corner, and an end point of the character.

  According to the present invention, a lot of watermark information can be embedded in one character, and deterioration of the character can be suppressed.

  Hereinafter, a watermark information embedding apparatus according to an embodiment of the present invention will be described with reference to the drawings.

(Embodiment 1)
FIG. 1 is a configuration diagram of a digital watermark embedding apparatus according to the present invention. As shown in FIG. 1, first, a document image 100 to be embedded with watermark information is input to an image input unit 101. Next, the document analysis unit 102 analyzes the positional relationship of characters in the document image 100. The embedding determination unit 103 determines whether or not a digital watermark can be embedded in the document image 100, and the embedding unit 106 embeds the digital watermark in the document image 100 using the watermark information 104 input from the watermark information input unit 105. I do. Then, the watermark embedding image 108 is output by the image output unit 107.

  FIG. 2 is a diagram for explaining the electrical configuration of the digital watermark embedding device and the extraction device according to the present invention. Note that it is not essential to use all the functions shown in FIG. 2 in realizing the digital watermark embedding device and the extraction device.

  In FIG. 2, a computer 201 is a general-purpose information processing device such as a personal computer that is widely used, and can input an image read from an image input device 217 such as a scanner for editing and storage. is there. Further, the image obtained by the image input device 217 can be printed from the printer 216. Various instructions and the like from the user are performed by input operations from the mouse (registered trademark) 213 and the keyboard 214. Inside the computer 201, blocks which will be described later are connected by a bus 207, and various data can be transferred.

  In FIG. 2, the CPU 202 can control the operation of each block inside the computer 201 or can execute a program stored therein. A main storage device (configured by RAM) 203 is a device that temporarily stores a program and image data to be processed for processing performed by the CPU 202. A hard disk (HDD) 204 is a device that can store programs and image data to be transferred to the main storage device 203 or the like in advance, and can store processed image data.

  A scanner interface (I / F) 215 is an I / F that is connected to a scanner 217 that reads an original, a film, and the like and generates image data, and can input image data obtained by the scanner 217. The printer interface 208 is connected to a printer 216 that prints image data, and is an I / F that can transmit image data to be printed to the printer 1216.

  The CD drive 209 is a device that can read or write data stored in a CD (CD-R / CD-RW) that is one of external storage media. Similar to the CD drive 209, the FDD drive 211 is a device that can read from and write to the FDD. Similar to the FDD drive 211, the DVD drive 210 is a device that can read from and write to a DVD. If an image editing program or printer driver is stored on a CD, FDD, DVD, etc., these programs are installed on the HDD 204 and transferred to the main storage device 203 as necessary. It has become.

  An interface (I / F) 212 is an I / F connected to these in order to accept input instructions from the mouse 213 and the keyboard 214. The monitor 206 is a display device that can display a watermark information extraction processing result and a processing process. Further, the video controller 205 is a device for transmitting display data to the monitor 206.

  Even if the present invention is applied to a system composed of a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), a device composed of a single device (for example, a copier, a fuck simulator) You may apply to.

  In the above configuration, by executing a program loaded in the main storage device 203 in response to an input instruction from the mouse 213 or the keyboard 214 using the CPU 202 or the like, it functions as a digital watermark embedding device or an extraction device. Become. At this time, it is also possible to monitor the execution status and the result by the monitor 206.

  Hereinafter, a specific implementation method of the digital watermark embedding method and extraction method will be described.

  FIG. 3 is a flowchart for explaining the operation procedure of the digital watermark embedding apparatus according to this embodiment.

  First, in step S301, a document image 100 to be embedded with watermark information is input to the document analysis unit 102 via the image input unit 101 represented by the scanner 217 in FIG. The document image 101 may be a printed material input from the scanner 217 or the like and converted into a bitmap, or may be electronic data created using a document editing application program. Alternatively, various electronic data such as a format unique to an application program and text format stored in each storage medium connected to the hard disk 204, CD drive 209, DVD drive 210, FDD drive 211, etc., image processing software, etc. It may be converted into a bit map.

  In step S302, the document analysis unit 102 extracts a circumscribed rectangle (character region) from the input document image.

  The circumscribing rectangle of a character is a rectangle circumscribing the character and is originally information indicating an area where character recognition is performed. In the digital watermark technique, it indicates a character area to be embedded. Each pixel value of the document image is projected onto the vertical coordinate axis, and a blank portion (a portion having no black character) is searched to determine a row, and line division is performed. Thereafter, the document image is projected on the horizontal coordinate axis line by line, and a blank portion is searched and divided into characters. As a result, each character can be cut out by a circumscribed rectangle.

  When the circumscribed rectangle is extracted in this way, the watermark information 104 to be embedded is input from the watermark information input unit 105 represented by the keyboard 214 in step S303 in FIG. The watermark information may be selected from those stored in advance in the storage device.

  Next, in step S304, one character to be used for embedding in the document image is input. In step S305, whether or not the character can be embedded in the circumscribed rectangle area before embedding the digital watermark is determined. A determination is made at 103. In the procedure of step S305, only characters larger than a certain area determined so that the watermark information is maintained even after scanning are selected, and characters and codes that are too small are excluded from the characters to be embedded.

  If it is determined in step S305 that the character can be embedded (Yes), the watermark information embedding unit 106 performs digital watermark embedding in step S306. If it is not determined in step S305 that the character can be embedded (No), the process returns to step S304, and the next character is input.

  In this embodiment, a method of changing the density of character feature points, which is one of digital watermark embedding methods in the watermark information embedding unit 106, will be described.

  Here, the feature point of the character in this embodiment is demonstrated.

  FIG. 4 is an example of character feature points, which are the points 401 and 402 in FIG. That is, the character feature points are character intersections, T-shaped points, corners, and the like, which are points detected using an operator formula as shown in FIG. 5 (FIG. 5 will be described later).

  FIG. 6 is an explanatory diagram of intersections before and after embedding a digital watermark in this embodiment.

  701 in FIG. 6 is a character before embedding watermark information “eye”. In the present embodiment, it is assumed that the density level of the character is expressed by 255 bits, black is the density level 0, and white is the density level 255.

  702 in FIG. 6 is a character obtained by thinning the character “eye” in order to search for a feature point of the character. A place where a circle is added to 702 represents the position of the feature point obtained by thinning the character.

  Reference numeral 703 in FIG. 6 represents a case where watermark information is embedded at the position of the feature point searched in 702. The point shade level is increased for the feature point in which “0” is embedded, and the point shade level is decreased for the feature point in which “1” is embedded. The order in which the watermark information is embedded in the feature points is determined in advance (for example, from top to bottom, from left to right, or in the order of randomly generated numbers). The watermark information embedded in 703 in FIG. 6 is 10100011, which shows an example in which the watermark information is embedded from top to bottom and from left to right.

  The digital watermark is embedded using the density level of the character feature points. For example, when embedding “0”, the tone level of the feature point is greater than the tone level of the surrounding points, and when embedding “1”, the tone level of the feature point is less than the tone level of the surrounding points. Change the shade level of feature points.

  FIG. 7 is a flowchart for explaining an example of a digital watermark embedding method according to this embodiment. This corresponds to the detailed view of S306 in FIG.

  First, in step 306a, feature points are extracted from the characters in which the watermark information is embedded. Step 306a will be described in more detail with reference to FIG.

  FIG. 8 is a flowchart for extracting character feature points.

  First, in step S306a1, it is determined whether or not the input character image is a binary image.

  If it is not the character image binary image input in step S306a1 (No), the process proceeds to step S306a2, and the character image is binarized. The binarization process is a process in which, when the input image is a multi-valued image, pixels smaller than a certain gray value are set to black and larger pixels are set to white. This binarization process is a pre-process in the character thinning process.

  On the other hand, if the input character image is a binary image (Yes) in step S306a1, the process proceeds to step S306a3.

  In step S306a3, the binarized character image is thinned. Thinning is an operation of extracting a center line having a line width of 1 from a binary image. Here, thinning is performed using the thinning method of Hilth, which is one of the basic methods of thinning, but is not limited to this. See, for example, “Introduction to Image Processing in C Language; Shogodo; ISBN: 4785631244; (2000/11)” for the thinning method of Hildith. 6 is obtained by thinning the character “eye” in 701 of FIG. 6 by the thinning method of Hilthith, a character as shown by 702 in FIG. 6 is obtained (the circle in 702 is for explanation) Is).

  Feature points are extracted from the thinned character image (step S306a4). In the extraction, eight pixels around the attention point of the character image are examined, and if the operator formula is the same as that in FIG.

  This is because it is determined whether or not the image is a binary image in step S306a1, and the binarization process in step S306a2 is a method in which the thinning method of Hilth in step S306a3 thins the binarized image. That is, if the thinning method in S306a3 is not a binarized image but can be thinned, naturally, steps S306a1 and S306a2 may be omitted.

  Then, in step S306b of FIG. 7, the number of feature points in the character image is given to the variable i. For example, when the character is <eyes>, the number of feature points is 8, i = 8.

  If there are many feature points in one character, the order of embedding watermark information is determined (step S306c). The order is determined by the position information of the feature points, and the order is from top to bottom and left to right. 703 in FIG. 6 is an example in which watermark information (101000001) is embedded in the above order.

  Note that a random number may be generated using the key information K, and the order in which the watermark information is embedded may be determined using the random number. The key information K is generated from random numbers having a certain length. The generated key information k is necessary for watermark extraction and may be stored in a storage device or may be stored secretly by the user.

  Next, in step S306d, it is determined whether or not the variable i is greater than zero. Note that i is given in step S306b.

  If i is larger than 0 in step S306d (Yes), the watermark information is embedded in the given feature point (step S306e). Step S306e will be described in more detail with reference to FIG.

  FIG. 9 is a flowchart for explaining an example of a method of embedding watermark information in feature points.

  First, in step S306e1, the data to be referred to the gray level conversion is extracted from the 8 bits around the given feature point. In this embodiment, it is assumed that p is data that refers to the lowest gray level in the surrounding 8 bits.

  Next, in step S306e2, the first character in which the watermark information 104 is embedded is selected. For example, when information “101001...” Is input as watermark information, the first character is “1”.

  If it is determined in step S306e3 that the corresponding bit is “1” (Yes), the process proceeds to step S306e4, and the feature point shading level −x is set so that the feature point shading level <p. Note that x is determined in advance by the user, and 0 <x <255 and the gray level of feature points−p <x. p is obtained in step S306e1.

  If it is determined in step S306e3 that the corresponding bit is “0” (Yes), the process proceeds to step S306e5, and the feature point density level + x is set so that the feature point density level> p.

  Then, in step S306f in FIG. 7, i = i-1 processing is performed, and the process returns to step S306d.

  If i is 0 in step S306d (Yes), the watermark information embedding of the input character is terminated.

  Then, in step S307 of FIG. 3, it is determined whether or not it is the last character in the document image. As a result, if it is the last character (Yes), in step S308, the watermark information bit embedding process ends, and the image embedded with the digital watermark is embedded in the embedding unit 106 based on the position information of the character feature points. The generated image (step S308) with the embedded watermark information is output from the image output unit 107 (step S309). The output may be printed or stored as image data in a storage device or the like, or may be transmitted from a network or the like to another terminal or the like.

  On the other hand, if it is not yet the last character in step S307 (No), the process returns to step S304 to input the next one character.

  FIG. 10 is a block diagram of the digital watermark extraction apparatus in the present invention. As shown in FIG. 10, a document image 200 from which embedded watermark information is to be extracted is input to an image input unit 901 typified by a scanner 217 in FIG. Then, the document analysis unit 902 analyzes the positional relationship of characters. Then, the embedding determination unit 903 determines the possibility of embedding. The watermark information extraction unit 904 extracts a digital watermark and outputs watermark information 905.

  FIG. 11 is a flowchart for explaining the operation procedure of the digital watermark extracting apparatus according to this embodiment.

  First, in step S1001, an image in which watermark information is embedded is input.

  In step S1002, circumscribed rectangles (characters) are extracted from the image. In the document analysis unit 902, the document image 200 that is an extraction target of the input document is input to the document analysis unit 902 via the image input unit 901 represented by the scanner 217 in FIG. 2. The document image may be a printed image input from a scanner 217 or the like and converted into a bitmap, or electronic data created using a document editing application program, or the hard disk 204, CD drive 209, or DVD drive 210. , Various electronic data stored in each storage medium connected to the FDD drive 211 or the like, such as a format unique to an application program, a text format, and the like may be converted by an image processing software and converted into a bitmap.

  Next, in step S1003, one character is input, and in step S1004, the embedding determination unit 903 determines whether the area of the circumscribed rectangle of the input character is the area of the character in which the digital watermark is embedded. I do. The embedding determination unit 903 is the same as the embedding determination unit 103 in FIG. 1, and can accurately determine a character in which a watermark is embedded with the same operation implementation.

  In step S1005, when it is determined in step S1004 that the digital watermark is embedded (Yes), the watermark information extraction unit 904 performs digital watermark extraction. If it is determined that the digital watermark is not embedded (No), the process returns to step S1003 to input the next character.

  Step S1005 will be described with reference to the flowchart of FIG. The watermark information extraction step S1005 has many processes similar to the watermark information embedding process in step S306 of FIG. The difference is that step S306e embeds watermark information, whereas step S1005a extracts watermark information. FIG. 13 is a flowchart for explaining the watermark information extraction method according to the first embodiment.

  First, the lowest shading level p is obtained for the eight pixels around the feature point (step S1005a1). Next, the density level h of the feature point is obtained (step S1005a2). Then, it is determined whether or not the obtained h is smaller (step S1005a3).

  As a result, when h is smaller than p (Yes), “1” is extracted as watermark information (step S1005a4). On the other hand, if h is greater than or equal to p (No), watermark information “0” is extracted (step S1005a5).

  In step S1006, it is determined whether the character input in step S1003 is the last character. If the determination is Yes, the watermark information is output (step S1006), and the process ends. If the determination is No, the process returns to step S1003 and continues. In the present embodiment, 8-bit watermark information can be embedded in the character “eye” having eight feature points. Further, since watermark information is embedded only in the character feature points, the deformation area is small, and deterioration of the characters can be suppressed.

(Embodiment 2)
In the first embodiment, the watermark information is embedded by changing the density level of the character feature points. In the present embodiment, a method of embedding the watermark information by changing the color of the character feature points will be described. Further, the feature points of the present embodiment are different from those of the first embodiment.

  Here, the feature point of the character in this embodiment is demonstrated.

  FIG. 14 is an example of the character feature points, and is a point having the circles 1401 and 1402 in FIG. That is, the character feature points are the end points of the characters and are points detected using an operator formula as shown in FIG. 15 (FIG. 15 will be described later).

  The configuration and processing procedures necessary for the operation of the second embodiment are the same as those of the first embodiment except for step S306a4, step S306e, and step S1005a of the first embodiment. Step S306a4 is different in that the operator formula shown in FIG. 15 is used.

  FIG. 16 is an explanatory diagram of feature points before and after embedding a digital watermark in the second embodiment. Reference numeral 1201 in FIG. 16 denotes a character before embedding watermark information “10”. The character image that can be used in the present embodiment may be anything from a binary image to a color image. Here, a description is given using a grayscale character image.

  Reference numeral 1202 in FIG. 16 represents a case where the character “ten” is thinned in order to search for a feature point of the character. 1202 indicates the position of the feature point obtained by thinning the character.

  Reference numeral 1203 in FIG. 16 represents a case where watermark information is embedded in the position of the feature point searched in 1202. As for the color of the watermark information and feature points, “00” corresponds to “red”, “01” corresponds to “blue”, “10” corresponds to “green”, and “11” corresponds to “black”. The watermark information embedded in 1203 in FIG. 12 is 10110001, and an example in which the watermark information is embedded in order from left to right and from top to bottom based on the position information of feature points is shown.

  The digital watermark is embedded using color information of character feature points. For example, when embedding “00”, the color of the feature point is changed to red. When embedding “01”, “blue”, “10” is changed to “green”, and “11” is changed to “black”.

  When embedding or extracting watermark information, the procedure for extracting the positions of character feature points is the same as that in step S306a of the first embodiment. However, since the position of the feature point to be searched for is different between the first embodiment and the present embodiment, the operator formula used in step S306a4 is different. In this embodiment, the extraction is performed by examining eight pixels around the attention point of the character image, and if it is the same as the operator formula in FIG. 15, the attention point is determined as the feature point.

  FIG. 17 is a flowchart of step S306e in the second embodiment when embedding watermark information. First, in step S306e21, 2 bits are selected from the first character as watermark information. For example, when information “10110001...” Is input as watermark information, the first 2-bit character is “10”. Here, the first input bit (eg, “1” in “10”) is called the first bit, and the next input bit (eg, “0” in “10”) is called the next bit.

  In step S306e22, it is determined whether or not the first bit of the watermark information to be embedded is “0”.

  If the first bit is “0” in step S306e22 (Yes), the process proceeds to step S306e23. In step S306e23, it is determined whether or not the next bit is “0”. When the next bit is “0” in step S306e23 (Yes), the process proceeds to step S306e25, and the color of the feature point is changed to red. When the next bit is “1” in step S306e23 (No), the process proceeds to step S306e26, and the color of the feature point is changed to blue.

  If it is determined in step S306e22 that the first bit is “1” (No), the process proceeds to step S306e24. In step S306e24, it is determined whether or not the next bit information is “0”. When the next bit is “0” in step S306e24 (Yes), the process proceeds to step S306e27, and the color of the feature point is changed to green. When the next bit is “1” in step S306e24 (No), the process proceeds to step S306e28, and the color of the feature point is changed to black.

  FIG. 18 is a flowchart of step S1005a of Embodiment 2 when extracting watermark information.

  First, the color of the feature point is obtained (step S1005a21). Then, it is determined whether or not the obtained color is red (S1005a22).

  As a result, if the color of the feature point is red (Yes), “00” is extracted as the watermark information (step S1005a23).

  On the other hand, if the color of the feature point is not red (No), the process proceeds to step S1005a24 to determine whether the color of the feature point is blue. In step S1005a24, when the color of the feature point is blue (Yes), “01” is extracted as watermark information (step S1005a25). If it is determined in step S1005a24 that the feature point color is not blue (No), the process advances to step S1005a26 to determine whether the feature point color is green.

  If the color of the feature point is green in step S1005a26 (Yes), “10” is extracted as watermark information (step S1005a27). If the color of the feature point is not green in step S1005a26 (No), “11” is extracted as watermark information (step S1005a28).

  In this embodiment, 2-bit watermark information is embedded in one feature point by changing to four different colors. If eight different colors are embedded, 3-bit watermark information can be embedded in one feature point. Similarly, the more colors used for embedding, the more information can be embedded in one feature point.

  In this embodiment, black, red, green, and blue colors are used, but it is needless to say that the present invention is not limited to these colors. It goes without saying that colors that are not noticeable can be selected depending on the application.

  In the present embodiment, 8-bit watermark information can be embedded in the character “ten” having four feature points. Further, since watermark information is embedded only in the character feature points, the deformation area is small, and deterioration of the characters can be suppressed.

<Other embodiments>
An object of the present invention is to supply a recording medium (or storage medium) that records software program codes for realizing the functions of the above-described embodiments to a system or apparatus, and the computer of the system or apparatus (or CPU or MPU). Needless to say, this can also be achieved by reading and executing the program code stored in the recording medium. In this case, the program code itself read from the recording medium realizes the functions of the above-described embodiment, and the recording medium on which the program code is recorded constitutes the present invention.

  Further, 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. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.

  Furthermore, after the program code read from the recording medium is written into a memory provided in a function expansion card inserted into the computer or a function expansion unit connected to the computer, the function is based on the instruction of the program code. It goes without saying that the CPU or the like provided in the expansion card or the function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

  When the present invention is applied to the recording medium, program code corresponding to the flowchart described above is stored in the recording medium.

  In the above embodiment, the watermark information is inserted into only one dot of the feature point. However, in order to increase the embedding strength, the same watermark information may be embedded into the dots around the feature point. At this time, it is desirable that the dots around the feature points are not dots that are not character portions but dots that are character portions without changing the deformation area of the characters. Further, the number of peripheral dots in which the watermark information should be embedded may be determined according to the embedding strength.

  In the first embodiment, watermark information is embedded by changing the shading level of character feature points (intersections, T-shaped points, corners), and in the second embodiment, watermark information is changed by changing the color of character feature points (end points). Although embedded, it is not limited to this embodiment. For example, the color of character feature points (intersections, T-shaped points, corners) may be changed to embed watermark information, or the lightness level of character feature points (end points) may be changed. Furthermore, a combination thereof may be used, and watermark information may be embedded at intersections, T-shaped points, corners, and end points.

  Although the case of a binary image has been described in the above embodiment, it is needless to say that a color image may be used. Moreover, although the case where it embedded in a Chinese character was demonstrated, it cannot be overemphasized that it may embed in characters, such as a hiragana, a katakana, and an alphabet.

  In the above embodiment, the watermark information is embedded in all the extracted feature points in one character. However, the present invention is not limited to this, and it goes without saying that it may be embedded in a predetermined feature point (for example, only an intersection). .

  In the above embodiment, one watermark information is embedded in one feature point. However, the present invention is not limited to this. For example, one watermark information may be embedded using a difference or sum of pixel values of two feature points. Good.

It is a block diagram of the digital watermark embedding apparatus in this invention. It is a figure for demonstrating the electrical structure of the electronic watermark embedding apparatus in this invention, and an extraction apparatus. 6 is a flowchart for explaining an operation procedure of the digital watermark embedding apparatus according to the first embodiment. 3 is an example of feature points in the first embodiment. 3 is an operator formula for extracting feature points in the first embodiment. 6 is an explanatory diagram of characters before and after embedding a digital watermark in Embodiment 1. FIG. 3 is a detailed flowchart of step S306 in the first embodiment. 5 is a flowchart for explaining a method of extracting feature points in the first embodiment. 5 is a flowchart for explaining a digital watermark embedding method according to the first embodiment. It is a block diagram of the digital watermark extraction apparatus in this invention. It is a flowchart for demonstrating the operation | movement procedure of the digital watermark extraction in this embodiment. It is a detailed flowchart of step S1005 in this embodiment. 5 is a flowchart for explaining a digital watermark extraction method according to the first embodiment. It is an example of the feature point of the character in Embodiment 2. It is an operator type | formula for extracting the feature point in Embodiment 2. FIG. FIG. 10 is an explanatory diagram of characters before and after embedding a digital watermark in Embodiment 2. 10 is a flowchart for explaining a digital watermark embedding method according to the second embodiment. 10 is a flowchart for explaining a digital watermark extraction method according to the second embodiment. It is a figure which shows the example of the original image in the case of performing digital watermark embedding using the space | interval of a character. It is a figure which shows the image after performing digital watermark embedding using the space | interval of a character. It is a schematic diagram for demonstrating the electronic watermark embedding method using the inclination of a character.

Claims (11)

An input means for inputting a document image;
Feature point extracting means for extracting feature points of characters of the input document image;
A digital watermark embedding means for embedding a digital watermark in the feature point;
The image processing apparatus according to claim 1, wherein the feature point is at least one of an intersection, a T-shaped point, a corner, and an end point of the character. An input means for inputting a document image in which watermark information is embedded;
Feature point extracting means for extracting feature points of characters of the input document image;
Watermark information extracting means for extracting watermark information from the feature points;
The image processing apparatus according to claim 1, wherein the feature point is at least one of an intersection, a T-shaped point, a corner, and an end point of the character.   The feature point extracting means includes thinning means for thinning the input document image, and extracting means for extracting feature points by a predetermined process based on the thinning result. 2. The image processing apparatus according to 2.   The image processing apparatus according to claim 3, wherein the predetermined process extracts a feature point from a pixel of interest and eight surrounding pixels from a thinned image.   The image processing apparatus according to claim 1, wherein the digital watermark embedding unit embeds the digital watermark by making a gray level of the feature point larger or smaller than a gray level of surrounding pixels.   The image processing apparatus according to claim 1, wherein the digital watermark embedding unit embeds a digital watermark by changing a color of the feature point.   When embedding a digital watermark in the feature point of the character, the order of embedding the digital watermark in a plurality of feature points is determined by position information of the feature points or by using random numbers generated by key information The image processing apparatus according to claim 1. An image input step of inputting the image;
An extraction process for extracting feature points of the input image;
A digital watermark embedding step of embedding a digital watermark in the feature point;
The image processing method, wherein the feature point is at least one of an intersection, a T-shaped point, a corner, and an end point of the character. An image input process for inputting an image in which watermark information is embedded;
An extraction step of extracting feature points of the input image;
An image processing method comprising an extraction step of extracting watermark information from the feature point, wherein the feature point is at least one of an intersection, a T-shaped point, a corner, and an end point of the character.   The program for making a computer perform the function of the image processing apparatus of any one of Claims 1-7. A computer-readable storage medium storing the program according to claim 10 and readable by a computer.

Images