JP4235352B2 - Image discrimination apparatus, copying machine, and image discrimination method - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image discriminating apparatus, a copying machine, and an image discriminating method, for example, an image discriminating apparatus, a copying machine, and an image discriminating method for discriminating a specific image pattern formed on a copy original.
[0002]
[Prior art]
Due to recent technological developments in full-color copiers, it has become possible to make the image quality of copies (copy) not much different from that of manuscripts. Generation copying is being performed in which the output is a manuscript and the copying is repeated.
[0003]
However, the image quality of the generation copy is usually less than the copy image quality of the original document. In recent years, the color copy machine has a mode for performing predetermined image processing for generation copy, and the image quality of the generation copy is To prevent deterioration.
[0004]
In addition, with the improvement of the image quality of color copiers, there is a concern about forgery of manuscripts that are legally prohibited from copying, such as banknotes and securities, and to prevent forgery of such manuscripts, A technique is known in which an image pattern unique to a machine is printed on a printed material during a copying operation so that it can be specified which machine the illegally copied material was copied.
[0005]
[Problems to be solved by the invention]
However, in the conventional technique described above, when performing image processing during generation copying, it is necessary to manually switch to the generation copy mode, which is troublesome for the operator.
[0006]
In addition, the specific image pattern added to the original image at the time of copying strongly depends on the scanning direction in the printing unit of the color copying machine. For this reason, it is difficult to automatically perform discrimination and code extraction when the document is read in a direction different from the direction assumed when reading the document, and the original document is determined from the image pattern printed on the document. It is not easy to read information such as the machine number of an apparatus (for example, a copier) that printed
[0007]
Accordingly, the present invention provides an image determination apparatus, a copying machine, and an image determination method for accurately determining a document image including a predetermined image pattern regardless of the direction of the document image and performing appropriate processing. With the goal.
[0008]
[Means for Solving the Problems]
In order to achieve the above object, an image discriminating apparatus according to the present invention is characterized by the following configuration.
[0009]
That is, an image discriminating apparatus for discriminating an image pattern composed of a plurality of marks included in a document image, wherein the plurality of marks include a positioning mark and a concentric virtual contour centered on the positioning mark. A plurality of information marks arranged above, and a plurality of feature points respectively corresponding to the plurality of marks are extracted from an input document image; and the plurality of points extracted by the extraction unit It is determined whether or not the number of feature points matches a predetermined number, and when the number of feature points matches the predetermined number, a central feature point corresponding to the positioning mark and the plurality of features It is determined whether or not the sum of the distances to the other feature points of the points is within a predetermined value range, and if the sum of the distances is within the predetermined value range, Calculate the distance between feature points and calculate Based on the distance between the other feature points, and a discrimination means for identifying information which the image pattern is represented, the identification means includes a case where the number of the plurality of feature points does not coincide with the predetermined number, the When the total sum of distances is not within the predetermined value range, it is determined that the document image does not include an image pattern .
[0011]
In order to achieve the above object, a copying machine according to the present invention is characterized by the following configuration.
[0012]
That is, a copying machine for printing a copy of an original based on image information of the original to be copied, an image processing means for performing predetermined image processing on the image information, and an image discrimination device having the above-described configuration The image processing means performs image processing different from the case where the predetermined information is not identified when the identifying means identifies the predetermined information .
[0013]
In the above copying machine, the image processing means may display the identified information when the identifying means identifies predetermined information.
[0016]
In order to achieve the above object, an image discrimination method according to the present invention is characterized by the following configuration.
[0017]
That is, an image discrimination method for discriminating an image pattern composed of a plurality of marks included in a document image, wherein the plurality of marks include a positioning mark and a concentric virtual contour centered on the positioning mark. A plurality of information marks arranged above, and a plurality of feature points respectively corresponding to the plurality of marks are extracted from the input document image, and the extraction step is performed by the extraction step. It is determined whether or not the number of the plurality of feature points matches the predetermined number, and when the number of the plurality of feature points matches the predetermined number, the center feature point corresponding to the positioning mark and the plurality of features It is determined whether or not the sum of the distances to the other feature points of the points is within a predetermined value range, and if the sum of the distances is within the predetermined value range, Calculate the distance between feature points, and calculate the other Based on the distance between feature points, have a, an identification step of identifying the information which the image pattern is represented, in the above identifying step, and if the number of the plurality of feature points does not coincide with the predetermined number, the When the total sum of distances is not within the predetermined value range, it is determined that the document image does not include an image pattern .
[0019]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an image determination apparatus according to the present invention will be described in detail as an embodiment applied to a color copying machine with reference to the drawings.
[0020]
FIG. 1 is a block diagram showing a schematic configuration of a color copying machine according to the present embodiment.
[0021]
In the figure, reference numeral 101 denotes a scanner unit including a document table, which reads an image of a document by a general optical process. An image processing unit 102 performs processing for restoring image deterioration (such as filter processing) and color space conversion suitable for printer output (such as output masking) for an image signal of a document image output from the scanner unit 101. It is. A printer unit 103 records the image signal sent from the image processing unit 102 as an image on a sheet as a recording medium by a general method.
[0022]
In order to add a predetermined image pattern as illustrated in FIG. 2 to a copy output (copy material) output from the printer unit 103 during a copying operation for copying a document image read by the scanner unit 101. The image pattern adding apparatus sets an image signal representing the image pattern in the image processing unit 102. This image pattern represents predetermined information (details will be described later).
[0023]
Reference numeral 104 denotes an image pattern discrimination device that receives an image signal that has been subjected to predetermined image processing such as input masking by the image processing unit 102, and whether or not a document image read by the scanner unit 101 includes a predetermined image pattern. The image processing unit 102 is notified of the determination result and the information represented by the image pattern if the image pattern is included (details will be described later).
[0024]
In the image processing unit 102, when the image pattern determination device 104 determines that the document image includes an image pattern, the document image is copied by a color copying machine having the same function as the color copying machine according to the present embodiment. In order to prevent deterioration of the image quality of a copy image reproduced when printing by the printer unit 103 (in order to improve image quality), the filter coefficient or the output masking coefficient is determined. A coefficient different from that used for a normal document that does not include an image pattern is set, output image processing is performed using the set coefficient, and information represented by the image pattern is displayed on an operation unit (not shown).
[0025]
The operation of each unit described above operates cooperatively under the control of the control unit 106.
[0026]
FIG. 2 is a diagram illustrating an example of an image pattern formed on a copy document during the copying operation of the color copying machine according to the present embodiment.
[0027]
In this embodiment, the image pattern adding apparatus 105, as shown in the figure, is a concentric positioning mark A (201) printed as an image pattern in a predetermined range of color density within an area of 1 inch square. Are arranged in the center of the area, and code information marks B, C, D, and E (202) are arranged on a concentric virtual contour 203 having a predetermined radius centered on the mark A.
[0028]
In this embodiment, B and C are arranged on the inner virtual contour, and D and E are arranged on the outer virtual contour. This arrangement is based on the distance between B and C, and D and E. The coordinate information is calculated by the image pattern adding apparatus 105 based on a predetermined relationship set in advance so that the distance between the images indicates individual information such as the machine number of the copying machine, and the arrangement is made according to the calculation result. It is determined.
[0029]
Further, the image pattern is arranged on the entire copy output so that the areas where the image pattern exists do not overlap.
[0030]
Here, the color density of the positioning mark 201 and the code information mark 202 is printed so as to have a predetermined color density, but a light yellow color that is not noticeable is preferable. Specifically, printing is performed by increasing the density of Yellow among four colors of Y (yellow), M (magenta), C (cyan), and Bk (black) that are generally used during printing, or reading, This can be realized by reducing the luminance of blue in the color space of R (red), G (green), and B (blue) used in the image processing.
[0031]
FIG. 3 is a block diagram showing the internal configuration of the image pattern discriminating apparatus 104. The image pattern discriminating apparatus 104 performs the processing described below for each pixel of the document image.
[0032]
In the figure, an image processing unit 102 inputs an image signal 301 having R, G, and B color components read by a scanner unit 101 to an image pattern discrimination device 104.
[0033]
The image signal 301 input from the image processing unit 102 is first binarized by the binarization block 302, and the resulting binary image is sent to the feature point extraction block 303.
[0034]
In the feature point extraction block 303, the features of the positioning mark 201 and the code information mark 202 are extracted, and feature point position information 304 representing the extracted features is stored in the feature point position buffer 305.
[0035]
Whether the discrimination / code extraction block 306 includes a predetermined image pattern (FIG. 2) in the image signal 301 read by the scanner unit 101 based on the feature point position information stored in the feature point position buffer 305. Is determined. As a result, if it is determined that an image pattern is included, code information represented by the image pattern is extracted, and a determination result signal 307 corresponding to the extracted code information is returned to the image processing unit 102.
[0036]
The image processing unit 102 selects output image processing to be performed on the image signal 301 read by the scanner unit 101 in accordance with the determination result signal 307 acquired from the determination / code extraction block 306, and performs the selected output image processing. Then, the data is output to the printer unit 103.
[0037]
FIG. 4 is a block diagram showing an internal configuration of the binarization block 302.
[0038]
In the present embodiment, the binarization block 302 receives the image signal 301 of each component 8 bits / pixel composed of R, G, and B3 components input from the image processing unit 102, and the threshold value processing unit 401 for each component. A comparison with a predetermined threshold is performed at. Here, as a threshold value processing method in the threshold value processing unit 401, a value 1 is adopted for pixels constituting the image pattern (hereinafter referred to as mark pixels), and a value 0 is adopted for pixels that are not mark pixels. To process.
[0039]
Then, the comparison result in the threshold value processing unit 401 for each color component is synthesized by, for example, taking a logical sum in the synthesis block 402 in the subsequent stage, and as a synthesis result, an image of 1 bit / 1 pixel is added to the feature point extraction block 303. Pass the signal (ie binary image).
[0040]
The feature point extraction block 303 holds the 1-bit image input from the binarization block 302 in the memory by the size of the positioning mark 201, and the input image is a mark pixel that forms an image pattern. Is determined by mask processing described below.
[0041]
FIG. 5 is a diagram illustrating a mask pattern used for mask processing for feature extraction in this embodiment, 510 is a feature extraction mask pattern for positioning marks, and 520 is for code information marks. It is a feature extraction mask pattern.
[0042]
The two types of mask patterns illustrated in FIG. 5 have a size of 15 (dots) × 15 (dots) as an example, 501 is a pixel of value 1 (shown as a black pixel in the figure), and 502 is It consists of pixels with a value of 0 (shown as white pixels in the figure).
[0043]
In the feature point extraction block 303, in order to discriminate between the positioning mark 201 and the code information mark 202 described above, a binary image input from the binarization block 302 is used using the above-described two types of mask patterns. What is necessary is just to perform a product-sum operation and perform threshold processing on the operation result.
[0044]
When the feature point extraction block 303 determines that the pixel is a mark pixel, the center position of the mark pixel is stored in the feature point position buffer 305 as feature point position information 304.
[0045]
FIGS. 6 and 7 are conceptual diagrams showing how the feature point position information 304 is stored in the feature point position buffer 305. FIG. 6 shows the original on the document table of the scanner unit 101. FIG. FIG. 7 shows a case where the original is rotated and placed.
[0046]
The feature point position buffer 305 is composed of a memory having a size that can store the entire area of the image pattern. In this embodiment, the image pattern is 1 inch square, so the size of the feature point position buffer 305 is 1 It must have a memory capacity large enough to cover 414inch x 1.414inch.
[0047]
FIG. 8 is a flowchart showing the procedure of the discrimination process performed by the discrimination / code extraction block 306 in this embodiment. Details of the processing of the discrimination / code extraction block 306 will be described below with reference to FIG.
[0048]
Step S800: When the center position of the feature point position buffer 305 matches the center point of the positioning mark extracted by the feature point extraction block 303, the process proceeds to the following determination process.
[0049]
Step S801, Step S808: The number of feature points stored in the feature point position buffer 305 is counted, and the count value is compared with a predetermined number. In the case of this embodiment, if the set of feature points stored in the buffer has an image pattern as illustrated in FIG. 2, five positioning marks A, code information marks B, C, D, and E are used. There should be feature points. That is, in the present embodiment, the predetermined number is “5”.
[0050]
If the number of feature points is not five as a result of this determination, the value 0 is returned to the image processing unit 102 as a value indicating that the image does not include an image pattern (step S808).
[0051]
Step S802: If the number of feature points matches in step S801, the distance from the center point A to each feature point is obtained. In this case, four distances from the mark A to the marks B, C, D, and E are calculated (in the following description, the distance from the point X to the point Y calculated in this step is expressed as distXY). To do).
[0052]
Here, the distance between the two points in step S802 may be calculated by a general Euclidean distance (√x ² + y ² ) or a square of the Euclidean distance (x ² + y ² ).
[0053]
Step S803: Next, the sum ΣdistAx (x = B, C, D, E) of the distances from the mark A calculated in step S802 to each feature point is obtained and stored as distA.
[0054]
Step S804: It is checked whether or not the sum ΣdistA of the distance from the mark A to each feature point is within a predetermined value range. In the case of the present embodiment, as shown in FIG. 2, since two code information marks 202 are arranged on two concentric circles (virtual contour 203), the sum of the distances is calculated between the inner circle and the outer circle. Add the circle diameter and divide by 2.
[0055]
If the condition in step S804 is not satisfied, the process proceeds to step S808 described above. If the condition is satisfied, the process proceeds to step S805.
[0056]
As a result of the check in step S804 as described above, even if the binarization block 302 or the feature point extraction block 303 has erroneously detected or erroneously extracted, the discrimination / code extraction block 306 has made an error. The risk of making a decision and extracting incorrect information is reduced.
[0057]
Step S805, Step S806: The distance between the feature points B and C on the inner virtual contour is calculated and stored as distBC (Step S805). In Step S806, the feature points D and E on the outer virtual contour are calculated. The distance is calculated and stored as distDE (step S806). In this case, if distBC and distDE are each quantized to about 64 levels, it is possible to embed numerical values of 4096 levels, that is, information, in the image pattern by combining the two distances. Further, if the number of concentric circles is further increased, or the number of code information marks arranged on the concentric circles is increased, a larger number of information can be embedded.
[0058]
Steps S807 and S809: The information extracted in this way is returned to the image processing unit 102 (step S807), and the process is terminated (step S809).
[0059]
Thereafter, the image processing unit 102 holds the value returned from the discrimination / code extraction block 306 for one page of the document, and performs a discrimination / code extraction process during pre-scanning prior to the copying operation. As a result, when an image pattern is detected from the document, the processing is switched so as to perform optimum image processing for the copy output. At the time of copying, by performing discrimination / code extraction processing, information represented by the image pattern (for example, the machine number of the apparatus that printed the original read this time) is displayed on an operation unit (not shown).
[0060]
According to the above-described embodiment, the presence or absence of an image pattern included in a read original can be reliably determined regardless of the orientation of the original image. In this case, it is determined that the original read this time is an already copied original, and it is possible to automatically perform an optimum process for preventing deterioration of image quality during generation copying.
[0061]
In addition, when an image pattern is included in the read original, information represented by the image pattern can be extracted regardless of the orientation of the original image. For example, a color copying machine having any body number for the original (copy original) You can know if it was copied at
[0062]
[Other Embodiments]
Note that the present invention can be applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, and a printer), and a device (for example, a copying machine and a facsimile device) including a single device. You may apply to.
[0063]
Another object of the present invention is to supply a storage medium (or recording medium) in which a program code of software that realizes the functions of the above-described embodiments is recorded to a system or apparatus, and the computer (or CPU or This is also achieved by the MPU) reading and executing the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code 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. A case where part or all of the actual processing is performed and the functions of the above-described embodiments are realized by the processing is also included.
[0064]
Furthermore, after the program code read from the storage 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 determined based on the instruction of the program code. The case where the CPU of 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 is also included.
[0065]
【The invention's effect】
As described above, according to the present invention, an image discriminating apparatus and a copying machine that discriminate a document image including a predetermined image pattern with high accuracy regardless of the direction of the document image and perform appropriate processing. And providing an image discrimination method.
[Brief description of the drawings]
FIG. 1 is a block diagram illustrating a schematic configuration of a color copying machine according to an embodiment.
FIG. 2 is a diagram illustrating an example of an image pattern formed on a copy document during a copying operation of the color copying machine according to the embodiment.
3 is a block diagram showing an internal configuration of an image pattern discrimination device 104. FIG.
4 is a block diagram showing an internal configuration of a binarization block 302. FIG.
FIG. 5 is a diagram illustrating a mask pattern used for mask processing for feature extraction in the present embodiment.
6 is a conceptual diagram showing how feature point position information 304 is stored in a feature point position buffer 305. FIG.
7 is a conceptual diagram showing how feature point position information 304 is stored in a feature point position buffer 305. FIG.
FIG. 8 is a flowchart showing a procedure of discrimination processing performed in a discrimination / code extraction block 306 in the present embodiment.

Claims (4)

An image discriminating apparatus for discriminating an image pattern composed of a plurality of marks included in a document image,
The plurality of marks include a positioning mark and a plurality of information marks arranged on a concentric virtual contour with the positioning mark as a center position,
Extracting means for extracting a plurality of feature points corresponding to the plurality of marks, from the input document image,
It is determined whether or not the number of the plurality of feature points extracted by the extraction unit matches a predetermined number, and when the number of the plurality of feature points matches the predetermined number, it corresponds to the positioning mark It is determined whether or not the sum of the distances between the center feature point and each of the other feature points of the plurality of feature points is within a predetermined value range, and the sum of the distances is within the predetermined value range An identification means for calculating a distance between the other feature points , and identifying information represented by the image pattern based on the calculated distance between the other feature points ;
Equipped with a,
The identification unit determines that the document image does not include an image pattern when the number of the feature points does not match the predetermined number and when the sum of the distances is not within the range of the predetermined value. An image discriminating apparatus characterized by: A copying machine that prints a copy of a document based on image information of the document to be copied,
Image processing means for performing predetermined image processing on the image information;
An image discrimination device according to claim 1,
With
The copying machine according to claim 1, wherein when the identification unit identifies predetermined information, the image processing unit performs image processing different from that performed when the predetermined information is not identified. 3. The copying machine according to claim 2 , wherein the image processing unit displays the identified information when the identifying unit identifies predetermined information. An image discrimination method for discriminating an image pattern composed of a plurality of marks included in a document image,
The plurality of marks include a positioning mark and a plurality of information marks arranged on a concentric virtual contour with the positioning mark as a center position,
An extraction step of extracting a plurality of feature points corresponding to each of the plurality of marks, from the input document image,
It is determined whether or not the number of the plurality of feature points extracted in the extraction step matches a predetermined number, and when the number of the plurality of feature points matches the predetermined number, it corresponds to the positioning mark It is determined whether or not the sum of the distances between the center feature point and each of the other feature points of the plurality of feature points is within a predetermined value range, and the sum of the distances is within the predetermined value range An identification step for calculating the distance between the other feature points , and identifying information represented by the image pattern based on the calculated distance between the other feature points ;
I have a,
In the identification step, the original image does not include an image pattern when the number of the plurality of feature points does not match the predetermined number and when the sum of the distances is not within the predetermined value range. image discrimination wherein the determining <br/>.

Images