JP3666979B2 - Image processing method and apparatus, and method of creating reference image data used in the method or apparatus - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image processing method and apparatus, and a method for generating reference image data used in the method or apparatus, and more particularly to an image processing method and apparatus and method for recognizing a specific image from an input digital image. Alternatively, the present invention relates to a method for creating reference image data used in the apparatus.
[0002]
[Prior art]
With the spread of color copiers and color printers in recent years, it has been impossible to create images by using a high-performance color scanner and computer, unless it is a specialized printer. High-quality full-color prints are easily available. While these devices have become widespread, techniques for preventing counterfeiting of banknotes and securities using color copiers and color printers have become necessary. This anti-counterfeiting technology is an image that should not be faithfully reproduced from digital image information to be printed because it is prohibited to be copied by law such as banknotes or securities (hereinafter referred to as “specific image”). ) Is applied.
[0003]
When such anti-counterfeiting technology is applied to a color printer, if it does not have an image memory for storing all the image data for one screen to be printed, a host computer (hereinafter referred to as a host) Judgment whether an image to be printed includes a specific image such as a predetermined banknote or securities using image data stored in an image memory such as a line memory with a small capacity for storing serially transmitted image data It is required to do.
[0004]
[Problems to be solved by the invention]
For this reason, the method of performing pattern matching with the reference image by extracting the contour of the image, which has been used in the anti-counterfeiting technology such as a color copying machine, is difficult to apply because it is necessary to develop all image data in the frame memory.
Furthermore, in a printer having only a small capacity memory such as a line memory, pay attention only to the features (characteristic patterns, numbers, etc.) of banknotes and securities, and whether these features are included in the input image. In order to determine whether or not the feature portion of the input image is present at a certain reference direction (for example, in the case of a laser beam printer, the scanning direction of the light beam or the image forming direction). In this pattern matching, regardless of the angle of the feature that may be included in the input image, this feature is detected and recognized as a specific image. It is required to do. That is, an analysis in consideration of the arrangement of the characteristic portions is required.
[0005]
In consideration of such an arrangement, reference image data (reference data) values created in advance based on image information of a characteristic portion of a specific image such as a predetermined banknote or securities are included in the input image data. If the tolerance of the pattern matching results that can occur due to the arrangement of the features that may be included is slightly different from that of the features of the specific image, the tolerance is large. In this case, there is a problem that a specific image cannot be correctly identified (misrecognition) increases. For this reason, there is a problem in that only reference data compromised at an appropriate recognition rate can be provided in consideration of the arrangement of the characteristic portions and the tradeoff of the degree of occurrence of erroneous recognition.
[0006]
Therefore, for example, even when image data representing an image having a feature portion very similar to the specific image is input at a position slightly deviated from the normal position of the feature portion of the specific image, this can be recognized as the specific image. As a result, there has been a problem that counterfeiting cannot be prevented.
The present invention has been made in view of the above conventional example. For example, even if a feature portion slightly different from the arrangement of the feature portion of the specific image exists in the input image data, the recognition is high in consideration of the arrangement variation. It is an object of the present invention to provide an image processing method and apparatus capable of recognizing a specific image at a rate, and a method of creating reference image data used in the method or apparatus.
[0007]
[Means for Solving the Problems]
In order to achieve the above object, an image processing apparatus of the present invention has the following configuration. That is, an input means for inputting image data, and a plurality of reference images in which different offset values are added in consideration of changes in the arrangement of the feature portions to the image data representing the feature portions of the specific image, and given predetermined values are given. A storage unit for storing data, each of the plurality of reference image data stored in the storage unit, and the image data input by the input unit, and the input image data is permitted by the reference image data. An image processing apparatus comprising: a comparison determination unit that determines whether or not a value is within a range of values; and a control unit that controls image formation of the image data according to a determination result by the comparison determination unit. Prepare.
[0008]
According to another aspect of the present invention, a plurality of reference images that are given predetermined tolerance values by adding different offset values taking into account the change in the arrangement of the feature portions based on image data representing the feature portions of the specific image. A step of creating and storing data in a storage medium, an input step of inputting image data, each of a plurality of reference image data stored in the storage medium, and the input image data are compared, and the input A discriminating step for discriminating whether or not the image data is within an allowable value range of the reference image data; and a control step for controlling image formation of the image data in accordance with a discrimination result in the discriminating step. A characteristic image processing method is provided.
[0009]
According to still another invention, there is provided a method for creating reference image data used in the image processing apparatus or the image processing method having the above-described configuration, wherein the image data representing the feature portion of the specific image is divided into a plurality of blocks. A step of generating a representative value representative of each of the plurality of blocks based on a value of a pixel included in each of the plurality of blocks, and a first reference image having the plurality of representative values as one unit A first data configuration step for configuring data, and a second data configuration for configuring second reference image data in which a predetermined offset value in consideration of a change in the arrangement of the characteristic portion is added to the plurality of representative values And a method for creating reference image data.
[0010]
[Action]
With the configuration described above, the present invention stores a plurality of reference image data in which different offset values are added in consideration of changes in the arrangement of the feature portions to the image data expressing the feature portions of the specific image, and given predetermined values are stored. The input image data is compared with each of the plurality of reference image data stored in the storage means to determine whether the input image data is within the allowable range of the reference image data; In accordance with the determination result, the image forming operation based on the input image data is controlled.
[0011]
Here, the storage means is a non-volatile memory, and an electrophotographic system can be used for image formation. Then, the storage means stores reference image data relating to the characteristic portion of each of the plurality of specific images.
Further, the image data is color image density data, and the data is sequentially input for each page of the recording medium and for each color component. This image data is temporarily held in the line memory.
[0012]
The specific image includes features such as banknotes and securities.
The offset value is determined based on the density variation of the feature portion of the specific image or the spatial frequency variation of the pixel value of the feature portion.
Each of the plurality of reference image data is obtained by adding one of different offset values to the average density value obtained by averaging the densities represented by the pixel pixels of the characteristic portion of the specific image over a predetermined area size. Yes, it is determined whether there is an average density value obtained by averaging the density value of each pixel of the input image data over the same area size as the predetermined area within a predetermined allowable value from this value. In this case, the predetermined allowable value is determined to have a smaller value than the allowable value considered when comparing the input image data using the reference image data generated without adding the offset value.
[0013]
According to another invention, the image data representing the characteristic part of the specific image is divided into a plurality of blocks, and the representative value representing each of the plurality of blocks based on the values of the pixels included in each of the plurality of blocks. And a first reference image data having a plurality of representative values as one unit, and a second reference image obtained by adding a predetermined offset value in consideration of a change in the arrangement of the feature portion to the plurality of representative values By configuring the data, reference image data used by the image processing apparatus configured as described above is created.
[0014]
DETAILED DESCRIPTION OF THE INVENTION
Preferred embodiments of the present invention will be described below in detail with reference to the accompanying drawings.
FIG. 1 shows a typical embodiment of the present invention, which has a resolution of 600 dots / inch (dpi), and forms an image according to an electrophotographic method based on multi-value data in which each pixel of each color component is expressed by 8 bits. 2 is a side sectional view showing the structure of a color laser beam printer (hereinafter referred to as CLBP or printer) 1 that performs the recording. FIG.
[0015]
In the apparatus shown in FIG. 1, the sheet 102 fed from the sheet feeding unit 101 is held at the outer periphery of the transfer drum 103 with its leading end held between grippers 103 f. At this time, the detector 8 detects the leading edge of the paper 102, and a vertical synchronization signal (described later) is generated based on the detection signal. A latent image formed in each color by an optical unit 107 on an image carrier (hereinafter referred to as a photosensitive drum) 100 is developed by each color developing device Dy, Dc, Db, Dn, and rotated a plurality of times on a sheet around the transfer drum. The other color image is formed by copying. Thereafter, the paper 102 is separated from the transfer drum 103 and fixed by the fixing unit 104, and is discharged from the paper discharge unit 105 to the paper discharge tray unit 106.
[0016]
Here, the developing devices Dy, Dc, Db, and Dn of the respective colors have rotation support shafts at both ends thereof, and each is held by the developing device selection mechanism unit 108 so as to be rotatable around the shaft. As a result, as shown in FIG. 1, the developing devices Dy, Dc, Db, and Dn maintain their postures even when the developing device selection mechanism 108 rotates about the rotation shaft 110 for selecting the developing device. Can be kept constant. After the selected developing device is moved to the developing position, the developing device selection mechanism unit 108 is integrated with the developing device and the selection mechanism holding frame 109 is pulled toward the photosensitive drum 100 by the solenoid 109a around the fulcrum 109b. Move in 100 directions.
[0017]
Next, the color image forming operation of the color laser beam printer configured as described above will be specifically described.
First, the photosensitive drum 1 is uniformly charged to a predetermined polarity by the charger 111, and, for example, an M (magenta) latent image is developed on the photosensitive drum 100 by exposure with the laser beam L to an M (magenta) color. Development is performed by the device Dm, and an M (magenta) color first toner image is formed on the photosensitive drum 100. On the other hand, the transfer paper P is fed at a predetermined timing, and a transfer bias voltage (+1.8 kV) having a polarity opposite to that of the toner (for example, plus polarity) is applied to the transfer drum 103, so that the first toner image on the photosensitive drum 100 is obtained. Is transferred to the transfer paper P, and the transfer paper P is electrostatically attracted to the surface of the transfer drum 103. Thereafter, the remaining M (magenta) toner is removed from the photosensitive drum 100 by a cleaner 112 to prepare for a latent image formation and development process for the next color.
[0018]
Next, a second latent image of C (cyan) color is formed on the photosensitive drum 100 by the laser beam L, and then the second latent image on the photosensitive drum 1 is developed by the C (cyan) color developer Dc. The image is developed to form a C (cyan) second toner image. Then, the second toner image of C (cyan) color is transferred to the transfer paper P in accordance with the position of the first toner image of M (magenta) color transferred to the transfer paper P previously. In transferring the second color toner image, a +2.1 kV bias voltage is applied to the transfer drum 103 immediately before the transfer paper P reaches the transfer portion.
[0019]
Similarly, third and fourth latent images of Y (yellow) color and Bk (black) color are sequentially formed on the photosensitive drum 100 and are sequentially developed by the developing devices Dy and Db, respectively. The third and fourth toner images of Y (yellow) color and Bk (black) color are sequentially transferred in alignment with the previously transferred toner image. In this manner, four color toner images are formed on the transfer paper P in an overlapping state. In transferring the toner images of the third color and the fourth color, bias voltages of +2.5 kV and +3.0 kV are applied to the transfer drum 103 immediately before the transfer paper reaches the transfer portion, respectively.
[0020]
The reason why the transfer bias voltage is increased every time the toner image of each color is transferred is to prevent a decrease in transfer efficiency. The main cause of this decrease in transfer efficiency is that when the transfer paper is separated from the photosensitive drum 100 after transfer, the surface of the transfer paper is charged to a polarity opposite to the transfer bias voltage due to air discharge (the transfer paper carrying the transfer paper). The drum surface is also slightly charged.) When this charged charge is accumulated at every transfer and the transfer bias voltage is constant, the transfer electric field is lowered at every transfer.
[0021]
During the transfer of the fourth color, when the leading edge of the transfer paper reaches the transfer start position (including immediately before and after), an effective AC voltage of 5.5 kV (frequency is 500 Hz) is applied when the fourth toner image is transferred. A DC bias voltage +3.0 kV having the same polarity and the same potential as the transferred transfer bias is superimposed and applied to the charger 111. Thus, when transferring the fourth color, the charger 111 is operated when the leading edge of the transfer paper reaches the transfer start position in order to prevent uneven transfer. In particular, in the transfer of a full color image, even if slight transfer unevenness occurs, it is easy to notice a difference in color. Therefore, as described above, it is necessary to apply a required bias voltage to the charger 111 to perform a discharge operation. .
[0022]
Thereafter, when the leading edge of the transfer paper P onto which the four color toner images are superimposed and transferred approaches the separation position, the separation claw 113 approaches and the leading edge contacts the surface of the transfer drum 103 to transfer the transfer paper P. Separate from the drum 103. The tip of the separation claw 113 maintains a contact state with the surface of the transfer drum, and then moves away from the transfer drum 103 and returns to the original position. The charger 111 operates until the trailing edge of the transfer paper leaves the transfer drum 111 from when the leading edge of the transfer paper reaches the transfer start position of the final color (fourth color) as described above. The opposite polarity of the toner) is removed, the separation paper is easily separated by the separation claw 113, and the air discharge during separation is reduced. The transfer bias voltage applied to the transfer drum 103 is turned off (ground potential) when the trailing edge of the transfer paper reaches the transfer end position (exit of the nip formed by the photosensitive drum 100 and the transfer drum 103). To do. At the same time, the bias voltage applied to the charger 111 is turned off. Next, the separated transfer paper P is conveyed to the fixing device 104 where the toner image on the transfer paper is fixed and discharged onto the paper discharge tray 106.
[0023]
Next, an image forming operation by laser beam scanning will be described.
In FIG. 1, reference numeral 107 denotes an optical unit, which includes a detector 9, a semiconductor laser 120, a polygon mirror 121, a scanner motor 122, a lens 123, and a mirror 125. When the recording paper P is fed and its leading edge is conveyed to the transfer drum, the image signal VDO for one page is output to the semiconductor laser 120 in synchronization with the recording paper P, and the light beam L modulated by the image signal VDO is generated. The light beam L is emitted toward the polygon mirror 121 rotated by the scanner motor 122, and the emitted light beam L is guided to the photosensitive drum 100 by the lens 123 and the mirror 125. When the light beam L is emitted, the light beam L is detected by the detector 9 disposed on the main scanning axis, and a BD (beam detection) signal serving as a horizontal synchronizing signal is output. As a result, the photosensitive drum 100 is scanned and exposed in synchronization with the BD signal by the light beam L, and an electrostatic latent image is formed.
[0024]
The color laser beam printer of the present embodiment outputs an image with a resolution of 600 dots / inch (dpi) through the image forming process as described above.
As input data of this apparatus, color image data (for example, density image data expressed by Y, M, C, and Bk components) generated by a host computer (hereinafter referred to as a host) can be considered. For this reason, as shown in FIG. 1, this apparatus receives a printer controller 2 that receives image information and a command (1005) for image formation from a host and generates image data, and a signal for processing the image data. A processing unit 4 is provided.
[0025]
In the embodiment described here, color image data sent from a host is considered as input data.
FIG. 2 is a block diagram showing a functional configuration of the printer 1 according to the present embodiment. In FIG. 2, a printer 1 receives image information sent as density image data for each color component or PDL command data from a host computer 1000 (hereinafter referred to as a host) 1000. The printer controller 2 and the printer engine 3 output as a YMCBk image signal 6 composed of bits (D0 to D7). Therefore, the value of each pixel of each color component takes a value from 0 to 255.
[0026]
Various signals other than the image signal 6 are exchanged between the printer controller 2 and the printer engine 3 in the form of serial communication. These signals include a page (sub-scanning direction) synchronization signal (PSYNC), a main scanning direction synchronization signal (LSYNC), and a data transfer clock (VCLK) sent from the printer engine 3 to the printer controller 2. The printer controller 2 outputs an 8-bit signal of each color component of the image signal 6 in synchronization with the data transfer clock (VCLK).
[0027]
FIG. 3 is a block diagram showing a functional configuration of the printer engine 3 according to this embodiment. In FIG. 3, the reference clock from the reference oscillator 10 included in the optical unit 107 is divided by the frequency divider 11 so that the phase difference between the divided clock and the feedback signal from the scanner motor 122 is a predetermined phase difference. The scanner motor 122 is rotated at a constant speed by a motor control circuit 12 (which incorporates a known phase control circuit (not shown)). Then, the rotation of the scanner motor 122 is transmitted to the polygon mirror 121 to rotate the polygon mirror 121 at a constant speed.
[0028]
On the other hand, the transfer drum 103 is rotated at a constant speed by a drive motor (not shown), the leading edge of the recording paper P on the transfer drum 103 is detected by the detector 8, and a vertical synchronization signal (VSYNC) is output to the signal processing unit 4. The The leading edge of each color image is defined by the vertical synchronization signal (VSYNC). After the vertical synchronization signal (VSYNC) is output, the BD signal generated by the detector 9 is used as the horizontal synchronization signal (HSYNC), and the image signal (VDO) is sequentially transmitted to the semiconductor laser 120 in synchronization with the BD signal. Is done.
[0029]
The CPU 14 built in the signal processing unit 4 performs serial communication with the printer controller 2 to exchange control signals and synchronize the operations of the printer controller 2 and the printer engine 3.
The timings of the image signal (VDO) of the vertical synchronizing signal (VSYNC), horizontal synchronizing signal (BD), and four density color components (YMCBk) described above in the image forming process are as shown in FIG.
[0030]
FIG. 5 is a block diagram showing the configuration of the signal processing unit 4. The signal processing unit 4 is roughly divided into a line memory 20, a pattern recognition unit 21, and a halftone processing unit using PWM.
The line memory 20 stores the multi-value image data (D0 to D7) sent from the printer controller 2 with the data transfer clock (VCLK), and then reads it with the image clock (PCLK) of the printer engine 3.
[0031]
The halftone processing unit using PWM is composed of a γ correction unit 22, a D / A conversion unit 23, a comparator 24, and a triangular wave generation unit 25. The multi-value image data from the line memory 20 is γ corrected by the γ correction unit 22, converted into an analog signal by the D / A conversion unit 23, and then input to the positive input terminal (+) of the comparator 24. Is done. On the other hand, the output signal of the triangular wave generator 25 that generates a triangular wave signal based on the clock of the image clock (PCLK) is input to the negative input terminal (−) of the comparator 23.
[0032]
The comparator 23 compares these two signals and generates a signal having a pulse width corresponding to the multi-value image signal. From the comparator 23, a PWM signal for forming an image having a resolution of 600 dpi is sent to the semiconductor laser 121 as an image signal (VDO).
The pattern recognition unit 21 reads reference data stored in a nonvolatile memory 26 such as an EEPROM via a signal line 28 based on a control signal 27 from the CPU 14, and this data and input multi-value image data Are compared to determine whether the input multi-valued image contains a specific image.
[0033]
FIG. 6 is a block diagram showing the configuration of the pattern recognition unit 21. As shown in FIG. 6, the pattern recognition unit 21 includes a blocking unit 21 a that blocks input multi-valued image data as described below, and a comparison unit 21 b that compares the blocked image data with reference data. It is configured. In this embodiment, the density data of the four color components Y (yellow), M (magenta), C (cyan), and Bk (black) that are sequentially sent from the printer controller 2 for each page of recording paper. Only the density data of one color component, for example, the M (magenta) component having the highest luminance, is compared with the reference data. As a result, the recognition determination process for the specific image is performed at a higher speed. Accordingly, the memory 26 stores reference data for one color component. However, it goes without saying that the density data of which component of the four color components is compared with the reference data may be other than the M (magenta) component described here.
[0034]
First, the blocking unit 21 a inputs multi-value image data from the line memory 20. This input is performed sequentially (surface-sequentially) for each color component of density data for one page of recording paper. Therefore, in the comparison between the input image data and the reference data, the order of the input color components is Y → M → C → Bk, and if the comparison is performed for the M component, the second input color component is compared. Only done for data.
[0035]
Next, the blocking unit 21a converts the input image data into data quantized with an average density for each block of a predetermined size (here, a square having 256 pixels (pixels) on one side), and the quantized data. Is output to the comparison unit 21b. Since the number of pixels corresponding to the size of one page of recording paper is determined from the recording resolution and paper size, which part of the image data is included in each block in this block formation is the input image data. It can be understood by counting the number of pixels.
[0036]
The comparison unit 21b compares the reference data read from the memory 26 with the input quantized data, and outputs a determination result as to whether or not the input image data includes a specific image pattern registered in the memory 26.
Next, the blocking of input image data will be described in detail.
FIG. 7 is a diagram showing an outline of block processing executed in the blocking unit 21a in FIG. As shown in FIG. 7, based on the image data input from the line memory 20, an average value of the density of the pixels in each block is obtained for each square block of 256 pixels (pixels), and this is obtained as 1 of the block image. The block value.
[0037]
Next, reference data registered in the memory 26 will be described in detail.
Reference data is obtained as follows. That is, a characteristic part (characteristic part) is extracted from one original image (for example, banknotes, securities, etc.), and image data representing the characteristic part is displayed in the same manner as performed by the blocking unit 21a. The density value of each color component of each pixel is divided into blocks, the average density value is obtained for each block, and the average density value for 5 × 5 blocks is used as reference data. Furthermore, by providing a tolerance value (for example, ± 20) in the density value of each block, it is easy to recognize the specific image from the input image data.
[0038]
Now, in such a method of comparing the average density in units of blocks, the comparison result reacts extremely sensitively to fluctuations in density offset. For example, if the image represented by the input image data and the feature portion of the specific image are aligned in the horizontal direction, the variation in density offset becomes significant, and the comparison result may be reversed. In other words, if there is a variation in density offset, it cannot be said that the specific image can be accurately determined. In order to cope with such a variation in density offset, it is conceivable to increase the allowable range. Conversely, if the allowable range is increased, the specific image may not be accurately determined. That is, misrecognition increases.
[0039]
Based on this, in this embodiment, the allowable range is increased (for example, ± 20), but the average density comparison range is not expanded, but the allowable range is decreased (for example, ± 10) 1. While the range that can be recognized by one reference data is narrowed, by preparing a plurality of reference data, it is possible to cope with variations in density offset as a whole.
[0040]
FIG. 8 is a diagram showing a plurality of reference data corresponding to one banknote used in this embodiment based on the above. Here, after the image data obtained from the image of the characteristic part of one banknote is made into a block and the average density value of each block is obtained, density offsets of “−10”, “0”, and “+10” are set for each block. In addition to the above, three reference data are created by giving "± 10" tolerance values to each. FIG. 8A shows reference data with a density offset of “0”, FIG. 8B shows reference data with a density offset of “+10”, and FIG. It is a figure which shows the reference data of -10 ".
[0041]
Note that the allowable value of the reference data in FIG. 8 is determined based on the result of a subjective evaluation experiment by visual observation of the print sample.
FIG. 9 is a diagram illustrating a state in which the reference data having the density offsets “−10”, “0”, and “+10” are stored in the reference data portion of the memory 26 for each of the plurality of banknotes A, B, and C. is there. Here, the reference data of three banknotes shows how data having three density offset values is stored, but the number of different density offset values, the offset values, and the number and type of banknotes are other. It goes without saying that the value of
[0042]
Considering the above, in the pattern recognition in the comparison unit 21b, when the block data of the input image data is within the allowable value range of the block of the reference data, the block is regarded as matching, and 5 × 5 When there is a matching portion in all the blocks in the input image, the input image is regarded as including a specific image pattern represented by the reference data. This result is output to the D / A converter 23 as a discrimination result signal (DSR). In this embodiment, a discrimination result signal (DSR) is output for density image data of one color component (for example, M (magenta) component) for each page of the recording paper, and if DSR = “1”, the specified If DSR = "0" indicating that an image has been detected, this indicates that no specific image has been detected.
[0043]
With respect to the DSR, if DSR = “1”, the CPU 14 controls the output of the D / A converter 23 so as to form an image of the entire page with the maximum density in the image formation of the color component. Then, even if image data is sent from the host, the subsequent image formation of the color components is stopped regardless of the data reception.
Note that the image formation control when DSR = “1” is not limited to the above-described control. For example, when DSR = “1” is output, the subsequent image formation is stopped and the image formation control is performed. The output may be controlled not to be output, the black image density may be set to the maximum density, and black toner may be output over the entire page, or a specific image pattern may be specified. A color may be added to the image.
[0044]
Therefore, according to the embodiment described above, a plurality of reference data having various density offset values is provided as reference data obtained from the characteristic portion of one specific image (for example, banknote), and these reference data Since the comparison with the input image is performed using the reference image, it is possible to discriminate the specific image with high accuracy in consideration of the density offset fluctuation of the image while keeping the allowable value of the reference data small (for example, ± 10). .
[0045]
In the example described above, the reference data is created by preparing a plurality of offset values for the average density of the blocked pixels. However, the present invention is not limited to this. For example, when pattern matching is performed with the input image and reference data focused on the spatial frequency of each other's image, a plurality of reference data is prepared in consideration of the position offset of the feature portion of the specific image. The specific image can also be recognized using.
[0046]
Further, in the above example, the density offset value for each banknote is given as the same value up and down from the value without offset, but the present invention is not limited to this, and according to the image characteristics of the feature portion of the specific image Other values can also be used, and the intervals between density offsets can be non-uniform.
Furthermore, the comparison between the input image data and the reference data in the above embodiment is performed for only one color component of the input image data, but the present invention is not limited thereto. For example, reference data for all four density color components may be provided in the memory, and this comparison may be performed for all four density color components. When it is determined that a specific image has been detected for all four color components, it may be determined that the specific image is included in the input image data, or any one of the four color components is selected. When it is determined that a specific image has been detected for one color component, it may be determined that the specific image is included in the input image data. Further, among the four color components, a predetermined number of color components may be determined. When it is determined that a specific image is detected, it may be determined that the specific image is included in the input image data.
[0047]
Furthermore, in the above embodiment, density image data is assumed as input image data from the host, but the present invention is not limited to this. For example, it may be configured to include a color conversion circuit that receives luminance (RGB image data) from the host and performs luminance → density conversion in the printer controller or printer engine. In this case, the comparison between the input image data and the reference data may be performed by paying attention to the G (green) component, which is the component with the highest luminance, for example, and as described above, all the color components are related. Needless to say, a comparison may be made.
[0048]
Furthermore, the printer used in the above embodiments has a line memory, but the present invention is not limited to this. For example, the printer has a frame memory that can store image data for one page of recording paper. The present invention can also be applied to a printer having the above configuration.
Furthermore, the printer used in the above embodiment is configured to perform image formation and recording according to the electrophotographic method, but the present invention is not limited thereto, and for example, performs image formation and recording according to the inkjet method. The present invention can be applied to a printer having a configuration.
[0049]
The present invention may be applied to a system composed of a plurality of devices such as “host computer, interface and printer” or to an apparatus composed of one device “such as a copying machine”. Needless to say, the present invention can also be applied to a case where the present invention is achieved by supplying a program to a system or apparatus. In this case, the system or apparatus receives the effects of the present invention by reading the program from the storage medium storing the program represented by the software for achieving the present invention into the system or apparatus. It becomes possible.
[0050]
【The invention's effect】
As described above, according to the present invention, for example, even when image data including an image having a slightly different arrangement from the feature portion of the specific image is input, the specific image is obtained from the input image data with a high recognition rate. There is an effect that it can be recognized.
[0051]
According to still another invention, image data representing a characteristic portion of a specific image is divided into a plurality of blocks, and representative values representing each of the plurality of blocks are obtained based on pixel values included in each of the plurality of blocks. Second reference image data generated and configured as first reference image data having a plurality of representative values as one unit, and a predetermined offset value in consideration of a change in the arrangement of the feature portion is added to the plurality of representative values. Therefore, there is an effect that reference image data in which a change in the arrangement of the characteristic portions is taken into consideration can be obtained.
[Brief description of the drawings]
FIG. 1 is a side sectional view showing a configuration of a color laser beam printer as a typical embodiment of the present invention.
FIG. 2 is a block diagram illustrating a functional configuration of the printer.
FIG. 3 is a block diagram illustrating a functional configuration of a printer engine.
FIG. 4 is a diagram illustrating timings of a vertical synchronization signal (VSYNC), a horizontal synchronization signal (BD), and an image signal (VDO) in an image forming process.
FIG. 5 is a block diagram showing an internal configuration of a signal processing unit 4;
6 is a block diagram showing a configuration of a pattern recognition unit 21. FIG.
FIG. 7 is a diagram showing an outline of block processing executed in the blocking unit 21a in FIG.
FIG. 8 is a diagram illustrating an example of reference data having different offset values.
9 is a diagram showing a state in which reference data with density offsets of “−10”, “0”, and “+10” are stored in the reference data portion of the memory 26 for banknotes A, B, and C, respectively.
[Explanation of symbols]
20 line memory 21 pattern recognition unit 21a blocking unit 22b comparison unit 26 memory

Claims (15)

Input means for inputting image data;
Storage means for storing a plurality of reference image data to which predetermined offset values are given by adding different offset values in consideration of a change in the arrangement of the feature portions to image data representing the feature portions of the specific image;
Each of the plurality of reference image data stored in the storage means is compared with the image data input by the input means, and whether or not the input image data falls within the allowable value range of the reference image data a comparison discriminating means for discriminating,
An image processing apparatus comprising: a control unit that controls image formation of the image data according to a determination result by the comparison determination unit .   The image processing apparatus according to claim 1, wherein the offset value is determined based on a density variation of a characteristic portion of the specific image.   The image processing apparatus according to claim 1, wherein the offset value is determined based on a variation in a spatial frequency of a value of a pixel of a feature portion of the specific image. The image data is color image density data,
The image processing apparatus according to claim 1, wherein the input unit sequentially inputs density data for one page of the recording medium for each color component.   The image processing apparatus according to claim 1, wherein the input unit includes a line memory that temporarily holds the image data.   The image processing apparatus according to claim 1, wherein the specific image includes a characteristic portion such as a banknote or a securities.   The image processing apparatus according to claim 1, wherein the storage unit stores reference image data relating to a characteristic portion of each of a plurality of specific images.   Each of the plurality of reference image data is obtained by adding one of the different offset values to an average density value obtained by averaging the densities represented by the pixel pixels of the characteristic portion of the specific image over a predetermined area size. The image processing apparatus according to claim 1. The comparison determination means includes
Blocking means for averaging the density value of each pixel of the input image data over the same area size as the predetermined area,
9. The image processing apparatus according to claim 8, further comprising: a determination unit that determines whether an average density value obtained by the blocking unit is within an allowable value of the value of the reference image data. The predetermined allowable value, claims, characterized in that with a smaller value than when considering tolerance when comparing the input image data using the reference image data generated without adding the offset value the image processing apparatus according to 1.   The image processing apparatus according to claim 1, wherein the storage unit is a nonvolatile memory. A plurality of reference image data to which a predetermined allowable value is given by adding different offset values in consideration of a change in the arrangement of the feature portion based on the image data representing the feature portion of the specific image, and a storage medium Storing process to store in,
An input process for inputting image data;
A determination step of comparing each of the plurality of reference image data stored in the storage medium with the input image data and determining whether the input image data is within a range of allowable values of the reference image data ;
An image processing method comprising: a control step of controlling image formation of the image data in accordance with a determination result in the determination step . A method of creating reference image data used in the image processing apparatus according to claim 1 or the image processing method according to claim 12 ,
A dividing step of dividing the image data representing the characteristic portion of the specific image into a plurality of blocks;
A generating step of generating a representative value representing each of the plurality of blocks based on a value of a pixel included in each of the plurality of blocks;
A first data composing step of constructing first reference image data having the plurality of representative values as one unit;
Reference image data comprising: a second data configuration step of configuring second reference image data obtained by adding a predetermined offset value in consideration of a change in the arrangement of the feature portions to the plurality of representative values. How to create The reference image according to claim 13 , further comprising a setting step of setting an allowable value of the similarity in each of the first and second reference image data in order to determine a similarity with the specific image. How to create data. The allowable value is set in the first reference image data when the second reference image data is not created and only the first reference image data is used for similarity determination with the specific image. 15. The method of creating reference image data according to claim 14 , wherein the reference image data is smaller than an allowable value.

Images