JP4654898B2 - Image processing apparatus and image processing method - Google Patents

Description

  The present invention relates to an image processing apparatus and the like used for a copying machine, a printer, a facsimile machine, and a multifunction machine of these.

  Analyzing the image data obtained when the document is read by the image scanner and the image data received by the facsimile machine, performing character recognition processing on the area where characters in the image are written, and from the document read as an image Techniques for extracting sentences are known. In this technique, the fact that the read image has no inclination, that is, no skew, is a precondition for accurately extracting the original text. If the read image has skew, the skew is corrected. There is a need. Various techniques have been proposed as techniques for detecting the skew amount to be corrected (see, for example, Patent Document 1).

  In Patent Document 1, when an image of a document is read by receiving reflected light of light emitted toward the document, a document size detection process for detecting the position and width of the document from the output of the CCD is performed by an image processing unit. Based on the detection result, a skew that is the inclination of the original is determined by the CPU, and the inclination of the image data of the original read based on the determined skew is corrected by the image processing unit under the control of the CPU.

JP 2001-358914 A

  However, the technique for detecting the position and width of the document and obtaining the skew disclosed in Patent Document 1 is based on the premise that the document is read without being inclined with respect to the scanner. For this reason, a mechanism that can maintain a state in which the document does not tilt with respect to the scanner is required, and it is difficult to reduce the cost. The technique disclosed in Patent Document 1 is based on the premise that there is no relative inclination between the document itself and the image of the document. For this reason, it is difficult to cope with the case where the image of the document is inclined with respect to the document itself. As described above, when the conventional technique is used, it is difficult to perform image skew correction with high accuracy without much cost.

The present invention has been made to solve the technical problems as described above, and an object of the present invention is to provide an image processing apparatus and the like that can accurately detect an image skew amount. It is in.
Another object is to provide an image processing apparatus and the like that can reduce the cost for image skew correction.

For this purpose, an image processing apparatus to which the present invention is applied includes an image input means for inputting an image to which code information for machine reading formed in a pattern combining oblique lines is added in advance, and an image input means Extraction means for extracting code information from the image input by the above, a plurality of patterns associated with one oblique line and skew angle included in the code information extracted by the extraction means using a pattern matching circuit; pattern matching means for performing matching, the matching result by the pattern matching unit, and the skew angle decision means for determining a skew angle associated with the pattern that is the most frequent pattern among the plurality of patterns, the skew angle decision double Rutotomoni at skew angle decision means using the skew angle determined by means Obtaining a skew correction amount by software configuration using the angle made by one diagonal line and contained in the extracted encoded information by one diagonal line and extracting means included in the pattern that is the most common pattern among the patterns Based on the skew correction amount determination means, the skew correction amount obtained by the skew correction amount determination means, the skew correction means for performing skew correction on the image input by the image input means, and the skew correction means performed the skew correction. And instruction means for transmitting image data to the outside and instructing image output to a sheet.

  The code information added in advance to the image can be characterized in that it is prohibition information indicating copy prohibition.

From another point of view, an image processing apparatus to which the present invention is applied can display an image whose output prohibition has been canceled by inputting a password when the read image includes a prohibition pattern that indicates output prohibition by combining diagonal lines. An image processing apparatus for outputting to an image output apparatus, wherein a pattern matching circuit is used to perform matching between one oblique line of a prohibited pattern included in a read image and a plurality of patterns associated with skew angles and matching means, the matching by the pattern matching unit result is determined by the skew angle decision means for determining a skew angle associated with the pattern that is the most frequent pattern among the plurality of patterns, the skew angle decision means Rutotomoni with skew angles, among a plurality of patterns at a skew angle decision means Skew correction amount determining means for determining a skew correction amount by software configuration using the angle formed between one of the oblique line inhibited pattern included in one diagonal line and the read image is also included in the pattern that is a large pattern And skew correction means for correcting the skew correction amount obtained by the skew correction amount determination means for the read image.

Further, from another viewpoint, the image processing method to which the present invention is applied includes image data that includes code information for machine reading formed by a pattern combining diagonal lines that are not related to skew correction. An acquisition step of acquiring code information, an extraction step of extracting code information from the image acquired by the acquisition step, and one oblique line and a skew angle included in the code information extracted by the extraction step using a pattern matching circuit A pattern matching step for matching with a plurality of patterns associated with the pattern , and a skew angle for determining a skew angle associated with the pattern that is the largest pattern among the plurality of patterns as a result of matching by the pattern matching step determine a constant step, the skew angle decision step With use of the skew angle to be constant, one diagonal line contained in one diagonal line and the extracted code information extracted by the steps included in the pattern that is the most common pattern of the plurality of patterns at a skew angle decision step The skew correction amount determining step for obtaining the skew correction amount by the software configuration using the angle formed by the image, and the image based on the image data acquired by the acquiring step based on the skew correction amount determined by the skew correction amount determining step A skew correction step for performing skew correction, and an instruction step for instructing image output to a sheet by transmitting image data subjected to skew correction in the skew correction step to the outside.

  According to the present invention, it is possible to accurately detect the skew amount of an image.

Embodiments of the present invention will be described below in detail with reference to the accompanying drawings.
FIG. 1 is a block diagram for explaining an image processing apparatus 10 according to the present embodiment.
As shown in FIG. 1, the image processing apparatus 10 is input with an image input unit (image input unit) 20 to which an image of a document is input, and an image processing unit 30 that performs predetermined image processing on the input image. A copy prohibition code detection unit (extracting means, selection unit) 50 for detecting a copy prohibition code from the recorded image, and a skew correction amount determination unit for finally determining a skew correction amount based on the result of the copy prohibition code detection unit 50 (Calculation unit) 60 and an embedded information decoding unit 70 for decoding embedded information used for copying. The image processing unit 30 includes a skew correction unit (correction unit) 40 that performs image skew correction based on the determined skew angle.

  The image processing apparatus 10 configured as described above is connected to a UI 80 having a display device (display screen) for displaying contents to be notified to the user and an input unit for the user to input instruction contents. The image processing apparatus 10 is connected to an image output unit 90 that outputs an image to be copied to a sheet.

  The image input unit 20 optically reads an image of a document and inputs image data obtained thereby. The image input unit 20 can be configured by, for example, a document reading device that reads an image of a document set on a transparent document table. The document reading device receives an optical scanning system including a lamp, a mirror, a carriage, and the like, a lens system that forms an optical image scanned by the optical scanning system, and an optical image formed by the lens system. And a reading sensor such as a CCD for converting into an electrical signal. When the original image is full-color four colors, the image of the original (color original) formed with a color image is read by the reading sensor for each of the primary colors B (blue), G (green), and R (red). read.

  Here, in the original image, specific information is embedded as inconspicuously in the image as pattern information (pattern image). In the present embodiment, as an example of pattern information, an array pattern (hereinafter also referred to as a slash pattern) in which a right-up oblique line “/” and a left-up oblique line “\” are combined is employed. For this reason, in the present embodiment, it is assumed that specific information is preliminarily embedded in an image of a document using this pattern information. Therefore, specific information is added as electronic data to the image data obtained by reading the image of the document with the image input unit 20 in the form of a slash pattern.

  The original image in which the predetermined information is embedded is an image for which copy prohibition is set. Therefore, when the user does not input a predetermined password through the UI 80, the copy-prohibited image data is not output to the image output unit 90.

  Here, the specific information described above is embedded as visible information or invisible information in the image of the document read by the image input unit 20. If the specific information is visible information, it is embedded in the image of the document using a printing material such as ink or toner. At this time, it is preferable to embed the specific information in the image of the original document, for example, in the same manner as a known watermark so that the visible information representing the specific information is not so noticeable on the original document. Specifically, when the original image is a color image, it is desirable to embed specific information using a light-colored printing material such as Y (yellow) that is difficult to see with human eyes.

In addition, when the specific information is invisible information, when embedding this invisible information in the image of the document, the light is remarkably emitted only in the ultraviolet region or infrared region, except for the wavelength region of the visible light region that can be confirmed by human eyes. It is desirable to embed specific information using a printing material that reflects light.
When invisible information (specific information) is embedded using a printing material that significantly reflects light in the ultraviolet region, image input can be performed by using a reading sensor equipped with an optical filter that selectively transmits light in the ultraviolet region. The invisible information can be optically read by the unit 20. In addition, when invisible information (specific information) is embedded using a printing material that significantly reflects light in the infrared region, a reading sensor including an optical filter that selectively transmits light in the infrared region is used. Invisible information can be optically read by the image input unit 20.
Furthermore, in addition to optical reading, if invisible information is embedded in an image of a manuscript using a printing material containing magnetic powder, for example, this invisible information can be read magnetically using a magnetic sensor. It becomes.

  The image processing unit 30 is for performing predetermined image processing on the image data input by the image input unit 20. That is, the image data read by the reading sensor of the image input unit 20 is converted into digital image data by A / D (analog / digital) conversion. Then, after determining a skew angle, which will be described later, the digital image data is subjected to skew correction by the skew correction unit 40 of the image processing unit 30. The skew-corrected image data is decomposed into toner primary colors Y (yellow), C (cyan), M (magenta), and K (black), and further, reproducibility such as color, gradation, and definition. In order to increase the color tone, the color gradation toner signal is converted into an on / off binary signal by performing various image processing. The image data read from the color original in this way is output from the image input unit 20 to the image output unit 90 during the copying operation.

  The image output unit 90 includes a laser scanning unit (laser ROS) (not shown) and a photosensitive drum (not shown). Around the photosensitive drum (not shown), a charger (not shown) for uniformly charging the surface of the photosensitive drum, and an electrostatic latent image written on the surface of the photosensitive drum by the laser scanning unit are used as toner. A developing unit (not shown) for developing the image, a transfer device (not shown) for transferring the toner image to the paper, and a cleaner (not shown) for collecting the residual toner that has not been transferred to the paper are arranged. Yes. Further, the image output unit 90 includes a fixing device (not shown) for fixing the toner image transferred to the paper.

  The copy prohibition code detection unit 50 detects the prohibition code using the image data processed by the image processing unit 30. The copy prohibition code detection unit 50 transmits the detection result of the prohibition code to the image processing unit 30, the skew correction amount determination unit 60, and the embedded information decoding unit 70 when the prohibition code is detected.

  The skew correction amount determination unit 60 determines an actual skew angle using the detection result from the copy prohibition code detection unit 50 and sends the result to the skew correction unit 40 of the image processing unit 30. The skew correction unit 40 performs image skew correction according to the determination result by the skew correction amount determination unit 60.

  The embedded information decoding unit 70 assembles individual information identified by the copy prohibition code detection unit 50 in accordance with a predetermined format, and restores the original additional information embedded by decoding the information. It is.

FIG. 2 is a flowchart showing a processing procedure for determining a skew angle in the image processing apparatus 10 according to the present embodiment.
As shown in FIG. 2, when the user presses the job start button of the UI 80, the instruction is sent as a signal to the image processing unit 30. When receiving the instruction (step 101), the image processing unit 30 instructs the image input unit 20 to read the image. Upon receiving the instruction, the image input unit 20 starts reading an image of the document (step 102). The document image data read by the image input unit 20 is sent to the image processing unit 30. The image processing unit 30 sends the image data to the copy prohibition code detection unit 50 and instructs the start of detection of the copy prohibition code (illegal copy prohibition code). Upon receiving the instruction, the copy prohibition code detection unit 50 starts detecting the copy prohibition code for the image data (step 103).

  The copy prohibition code is detected as follows. First, the image data of each page input from the image input unit 20 is divided into pixel blocks of a predetermined size (for example, 7 pixels × 7 pixels). Then, the copy prohibition code detection unit 50 determines whether or not each divided pixel block includes a pattern image that matches a preset pattern image using a pattern matching circuit (hardware) (not shown). To do.

Here, FIG. 3 is an explanatory diagram for explaining eight types of patterns used to detect the copy prohibition code in the copy prohibition code detection unit 50, and FIG. 4 is an actual object that is the target of the copy prohibition code detection. It is explanatory drawing explaining the image data of.
As shown in FIG. 3, the eight patterns, the direction code is classified into a pattern P ₀ and the pattern P _1, the further each of the patterns P ₀ and the pattern P _1, the four per skew angle It is divided. As the skew angle, four types of “−22.5 degrees”, “0 degrees”, “+22.5 degrees”, and “+45 degrees” are set. Specifically, the pattern P ₀ includes a pattern P _{0-2 of} −22.5 degrees, a pattern P _{0/0 of} 0 degrees, a pattern P _{0 + 2} of +22.5 degrees, and a pattern P _{0+ of} +45 degrees. _Four of 4 are set. The pattern P ₁ includes a pattern P _{1-2 of} −22.5 degrees, a pattern P _{1/0 of} 0 degrees, a pattern P _{1 + 2} of +22.5 degrees, and a pattern P _{1 + 4} of +45 degrees. One is set. In other words, the eight patterns are set to have an interval of 22.5 degrees.

  The copy prohibition code is detected when the copy prohibition code detection unit 50 determines whether the image data shown in FIG. 4 approximates any of the eight types of patterns shown in FIG. That is, a pattern matching circuit (hardware) (not shown) reads a predetermined number of pixels of the document and performs matching with eight types of patterns according to the skew angle, whereby the copy prohibition code detector 50 detects the copy prohibition code. Perform detection.

  Returning to the flowchart of FIG. As a result of matching by the above-described pattern matching circuit (not shown), the copy prohibition code detection unit 50 sets the most angular pattern as the skew angle A (step 104). Thus, the skew angle A or the skew angle range is determined by a pattern matching circuit (not shown).

More specifically, the closest pattern of the eight types of patterns shown in FIG. 3 for detecting the copy prohibition code is the pattern P _1-2 , that is, the code direction is the pattern P ₁ and the skew angle A Is a pattern of -22.5 degrees. In other words, the skew angle range is from −22.5 degrees to 0 degrees.
Here, the pattern P _{a1 of the} image data shown in FIG. 4 does not completely match the pattern P _1-2 . Therefore, if a skew angle smaller than 22.5 degrees is set as the skew correction amount, a more accurate skew correction can be performed.

In order to enable such highly accurate skew correction, step 105 is performed. That is, the skew correction amount determination unit 60 performs pattern matching with software from an angle close to the skew angle A detected in step 104 (step 105), and the skew angle Δ to be used as the skew correction amount (see FIG. 5). Is detected. When the skew correction amount determination unit 60 finishes detecting the skew angle Δ, the skew angle Δ that is the detection result is sent to the skew correction unit 40 of the image processing unit 30.
The skew correction unit 40 performs skew correction based on the skew angle Δ received from the skew correction amount determination unit 60 (step 106), and when the skew correction is completed, a series of processing procedures ends.

Here, the processing procedure in step 105 will be described.
FIG. 5 is an explanatory diagram showing simplified pixel blocks when there is no skew in an image and when there is skew. FIG. 5A shows the case where there is skew in the image, and FIG. 5B shows the case where there is no skew in the image.
As shown in FIG. 5 (a), the pattern P _a1 of the actual image data is located between the pattern P _1/0 and the pattern P _1-2. In other words, it is not sufficient in accuracy to just correct the skew angle at intervals of 22.5 degrees described in step 104. By obtaining a more accurate skew correction amount in step 105 to be described later, a state without skew shown in FIG. 5B can be achieved.

More specifically, the skew correction amount determination unit 60 (see FIG. 1) uses the pattern matching circuit (not shown) of the copy prohibition code detection unit 50 to perform pattern P _1-2 and pattern P _a1 shown in FIG. Is calculated by pattern matching using software. Then, an angle Δ, which is a value obtained by subtracting the intersection angle B from the skew angle A, is calculated. When the skew correction is performed on the actual image data by the angle Δ thus obtained, there is no skew as shown in FIG. Further, as shown in FIG. 5 (a), the pattern P _a1, so positioned between the pattern P _1/0 and the pattern P _1-2, can also be determined the direction of skew correction.

Thus, in step 105, it is to determine the skew correction amount based on the detection pattern P _1-2 of copy inhibition code determined in step 104. A more accurate skew correction amount can be acquired by determining the skew correction amount through a two-step processing procedure.

Next, a processing procedure after the skew correction is performed will be described.
FIG. 6 is a flowchart showing a processing procedure after the skew correction is performed. Note that the flowchart shown in FIG. 6 can be performed together with skew correction.
After the copy prohibition code detection unit 50 detects the copy prohibition code and the skew correction unit 40 performs the skew correction, as shown in FIG. 6, the image processing unit 30 reads the document to be copied via the UI 80. Notifies the user that copying is prohibited and that a password for releasing the copying prohibition is necessary, and displays a password input screen (step 201). When the user inputs a password via the UI 80, the image processing unit 30 accepts the password (step 202).

  The image processing unit 30 determines whether or not the accepted password matches the set password (step 203). As a result of the determination, when it is determined that the passwords match, the image processing unit 30 instructs the image output unit 90 to output an image (step 204), and the image output unit 90 converts the image after skew correction into the embedded information. The information is output on a sheet together with information from the decoding unit 70. When the image processing unit 30 determines that the passwords do not match, the image processing unit 30 ends.

It is a block diagram for demonstrating the image processing apparatus with which this Embodiment is applied. It is a flowchart which shows the process sequence for determining a skew angle in an image processing apparatus. It is explanatory drawing explaining eight types of patterns used in order to detect a copy prohibition code in a copy prohibition code detection part. It is explanatory drawing explaining the actual image data which are the objects of a copy prohibition code detection. It is explanatory drawing which simplifies and shows the pixel block in the case where there is no skew in an image and when there is skew. It is a flowchart which shows the process sequence after skew correction is performed.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Image processing apparatus, 20 ... Image input part, 30 ... Image processing part, 40 ... Skew correction part, 50 ... Copy prohibition code detection part, 60 ... Skew correction amount determination part, 70 ... Embedded information decoding part, 80 ... UI , 90 ... Image output unit

Claims (4)

Image input means for inputting an image to which code information for machine reading formed in a pattern combining oblique lines is added in advance;
Extraction means for extracting code information from the image input by the image input means;
Using a pattern matching circuit, a pattern matching means for matching one oblique line included in the code information extracted by the extraction means and a plurality of patterns associated with the skew angle;
It said pattern matching means according to the matching result, and the skew angle decision means for determining the skew angle associated with the pattern and largest pattern among the plurality of patterns,
Extracted by the skew angle determined Rutotomoni using a skew angle determined by the constant unit, the skew angle determined one diagonal line and the extraction means contained in the pattern that is the most common pattern of the plurality of patterns at a constant means Skew correction amount determining means for obtaining a skew correction amount by a software configuration using an angle formed with one oblique line included in the generated code information ;
Based on the skew correction amount obtained by the skew correction amount determining means, skew correction means for performing skew correction on the image input by the image input means;
An image processing apparatus comprising: instruction means for transmitting image data subjected to skew correction by the skew correction means to the outside and instructing image output to a sheet.   The image processing apparatus according to claim 1, wherein the code information added in advance to the image is prohibition information indicating copy prohibition. An image processing apparatus that outputs an image whose output prohibition is canceled by inputting a password to an image output apparatus when the read image includes a prohibition pattern indicating output prohibition by combining diagonal lines.
Using the pattern matching circuit, a pattern matching means for performing matching between a plurality of patterns associated with one diagonal line and the skew angle of the forbidden pattern included in the read image,
It said pattern matching means according to the matching result, and the skew angle decision means for determining the skew angle associated with the pattern and largest pattern among the plurality of patterns,
The skew angle determined Rutotomoni using a skew angle determined by the constant unit, the skew angle determined one diagonal line and the read image included in the pattern that is the most common pattern of the plurality of patterns at a constant means A skew correction amount determining means for obtaining a skew correction amount by a software configuration using an angle formed with one oblique line of the prohibited pattern included in
Skew correction means for correcting the skew correction amount obtained by the skew correction amount determination means for the read image;
An image processing apparatus. An acquisition step of acquiring image data including code information for machine reading formed by a pattern combining oblique lines irrelevant to skew correction;
An extraction step of extracting code information from the image acquired by the acquisition step;
Using a pattern matching circuit, a pattern matching step for matching one oblique line included in the code information extracted by the extraction step and a plurality of patterns associated with the skew angle;
The pattern matching result of the matching by step, the skew angle decision step of determining the skew angle associated with the pattern that is the most frequent pattern among the plurality of patterns,
With use of the skew angle determined by the skew angle decision step, it is extracted by a single hatched and the extraction step contained in patterns which are the most common pattern of the plurality of patterns at the skew angle decision step A skew correction amount determining step for obtaining a skew correction amount by a software configuration using an angle formed with one oblique line included in the code information ;
Based on the skew correction amount obtained by the skew correction amount determination step, a skew correction step for performing skew correction on the image based on the image data acquired by the acquisition step;
An image processing method comprising: an instruction step of transmitting the image data subjected to the skew correction in the skew correction step to the outside and instructing the image output to the paper.

Images