Fraud confirmation device, system, and fraud confirmation method

Abstract

To highly accurately confirm fraudulence to a general-purpose and inexpensive object with a more inexpensive configuration.SOLUTION: An image reading unit configured to read reflected light of one type of wavelength band from a subject, the reflected light being a part of invisible light, and acquire an invisible light image; An image characteristic detection unit configured to detect the same or different image characteristics; and a state determination unit configured to determine that the subject is in the first state based on a plurality of detected image characteristics, the image characteristic detection unit detects an image characteristic of a first image region included in the plurality of image regions with respect to a region of an image formed by a material that absorbs at least invisible light, and detects an image characteristic of a second image region included in the plurality of image regions with respect to a region of an image formed by a material that does not absorb at least invisible light, and the state determination unit determines that the subject is in the first state based on a first image characteristic of the first image region and a second image characteristic of the second image region.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a fraud verification device, a system, and a fraud verification method. [Background technology]

[0002] 2. Description of the Related Art Conventionally, fraud checking devices have been devised that can detect fraud such as forgery or tampering in various documents by determining the authenticity of various documents read by a reading device.

[0003] Patent Document 1 discloses a technology for determining the authenticity of banknotes, passports, etc., using infrared light in at least two wavelength bands. Summary of the Invention [Problem to be solved by the invention]

[0004] However, according to the conventional technology, it is necessary to spectrally irradiate the irradiated light containing wavelengths from visible light to around 3000 nm using at least two infrared bandpass filters, or to irradiate the light using infrared LEDs with at least two different emission wavelengths or infrared lasers with at least two different oscillation wavelengths, which has resulted in a problem of high costs.

[0005] Such high-cost fraud verification devices are difficult to apply to determining the authenticity of general-purpose, inexpensive objects such as tickets and coupons, mainly due to cost-effectiveness considerations, and there is a risk that they may overlook fraud such as counterfeiting of these general-purpose, inexpensive objects.

[0006] The present invention has been made in view of the above, and has an object to enable highly accurate tamper detection for general-purpose and inexpensive objects with a cheaper configuration. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the present invention provides a light source that irradiates a subject with invisible light; an image reading unit that reads reflected light of one wavelength band from the subject, which is part of the invisible light, and acquires an invisible light image from the reflected light; an image characteristic detection unit that detects the same or different image characteristics for multiple image regions in the invisible light image; and a state determination unit that determines that the subject is in a first state based on the multiple image characteristics detected by the image characteristic detection unit, wherein the image characteristic detection unit detects image characteristics for a first image region included in the multiple image regions, the region being formed from at least a material that absorbs invisible light, and detects image characteristics for a second image region included in the multiple image regions, the region being formed from at least a material that does not absorb invisible light, and the state determination unit determines that the subject is in the first state based on the first image characteristic of the first image region and the second image characteristic of the second image region. [Effects of the Invention]

[0008] The present invention has the effect of enabling highly accurate authenticity determination of a general-purpose, inexpensive object with a less expensive configuration. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 illustrates an example of a configuration of an image reading apparatus according to the first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a control block of the image reading device. [Figure 3] FIG. 3 is a diagram showing an example of the spectral sensitivity characteristics of an image sensor. [Figure 4] FIG. 4 is a diagram showing an example of the reflection spectral characteristics when toners of different colors are applied to the surface of white paper. [Figure 5] FIG. 5 is a diagram illustrating an example of the configuration of a device that performs fraud confirmation. [Figure 6] FIG. 6 is a flowchart showing an example of the state determination of a subject in the state determination unit. [Figure 7] FIG. 7 is a flowchart showing another example of the state determination of the subject in the state determination section. [Figure 8] FIG. 8 is a flowchart showing yet another example of the state determination of the subject in the state determination section. [Figure 9] FIG. 9 is a diagram showing an example of an original ticket. [Figure 10] FIG. 10 is a diagram showing an example of an invisible light image obtained by reading the original ticket shown in FIG. 9 with near-infrared light. [Figure 11] FIG. 11 is a diagram showing an example of an invisible light image obtained by scanning, with near-infrared light, a copy of the original ticket shown in FIG. 9, which has been copied with black (K) toner. [Figure 12] FIG. 12 is a diagram showing an example of an invisible light image obtained by scanning, with near-infrared light, a copy of the original ticket shown in FIG. 9, which has been copied with dye paint toner. [Figure 13] FIG. 13 is a diagram showing an example of an image region. [Figure 14] FIG. 14 is a diagram showing an example of data of average values ​​of image characteristics of invisible light images. [Figure 15] FIG. 15 is a flowchart showing an example of subject state determination based on threshold determination in the state determination section. [Figure 16] FIG. 16 is a flowchart showing another example of the state determination of the subject based on threshold determination in the state determination section. [Figure 17] FIG. 17 is a flowchart showing yet another example of the state determination of the subject based on threshold determination in the state determination section. [Figure 18] FIG. 18 shows a modified example of the original ticket. [Figure 19] FIG. 19 is a diagram showing an example of an invisible light image obtained by reading the original ticket shown in FIG. 18 with near-infrared light. [Figure 20] FIG. 20 is a diagram showing an example of an invisible light image obtained by scanning, with near-infrared light, a copy of the original ticket shown in FIG. 18, which has been copied with black (K) toner. [Figure 21]FIG. 21 is a diagram showing an example of an invisible light image obtained by scanning, with near-infrared light, a copy of the original ticket shown in FIG. 18, which has been copied with dye paint toner. [Figure 22] FIG. 22 is a diagram showing the configuration of a fraud checking system. [Figure 23] FIG. 23 is a diagram illustrating an example of image characteristic detection in the image characteristic detection unit according to the second embodiment. [Figure 24] FIG. 24 is a diagram illustrating an example of the configuration of the fraud checking device according to the third embodiment. [Figure 25] FIG. 25 is a diagram illustrating an example of an admission pass according to the fourth embodiment. [Figure 26] FIG. 26 is a diagram showing an example of an invisible light image obtained by reading the admission pass shown in FIG. 25 with near-infrared light. [Figure 27] FIG. 27 is a diagram showing an example of an invisible light image obtained by reading, with near-infrared light, a copy of the admission pass shown in FIG. 25 made with black (K) toner. [Figure 28] FIG. 28 is a diagram showing an example of an invisible light image obtained by reading, with near-infrared light, a copy of the admission pass shown in FIG. 25 made with dye paint toner. DETAILED DESCRIPTION OF THE INVENTION

[0010] Embodiments of a fraud confirmation device, system, and fraud confirmation method will be described in detail below with reference to the accompanying drawings. Below, examples of a fraud confirmation device will be shown in which the fraud confirmation device is an image reading device and an image forming device. Note that, while an example in which an image sensor is used as the image reading unit will be shown below, the image reading unit is not limited to an image sensor as long as it is configured to convert light into an electrical signal. The image (also called a read image) and image information output by the image sensor are examples of "information (or read information)" output by the image reading unit. Furthermore, the fraud confirmation device is not limited to an image reading device or an image forming device, but may be a dedicated device with a function for fraud confirmation. Furthermore, the fraud confirmation device may be implemented in a device with other functions as long as the function for fraud confirmation is applicable.

[0011] (First embodiment) Fig. 1 is a diagram showing an example of the configuration of an image reading device 1 according to the first embodiment. Fig. 1 shows the image reading device 1, which is an example of a fraud checking device.

[0012] The image reading device 1 irradiates light from a light source onto an object to be read, such as various certificates or documents, and receives the light reflected from the object with an image sensor to read the image.

[0013] 1, image reading device main body 10 has contact glass 11 on its top surface and has reading means (first reading means) inside image reading device main body 10. Inside image reading device main body 10, as the first reading means, there are provided light source 13, first carriage 14, second carriage 15, lens unit 16, sensor board 17, etc. First carriage 14 has light source 13 and reflecting mirror 14-1, and second carriage 15 has reflecting mirrors 15-1 and 15-2. In addition, image reading device main body 10 has a control board (corresponding to control unit 300 shown in FIG. 2) that controls the entire device.

[0014] The control board moves the first carriage 14 and the second carriage 15, irradiates them with light from the light source 13, and sequentially reads the light reflected from the object to be read placed on the contact glass 11 using the image sensor 402 (see FIGS. 2, 5, etc.). The light reflected from the object to be read by the light from the light source 13 is reflected by the mirror 14-1 of the first carriage 14 and the mirrors 15-1 and 15-2 of the second carriage 15 and enters the lens unit 16. The light emitted from the lens unit 16 forms an image on the image sensor 402 (first reading unit) provided on the sensor board 17. The image sensor 402 is an image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary MOS), and converts the light reflected from the object to an electrical signal to output image information. The light source 13 is not limited to a single light source, and multiple light sources may be provided. The image sensor 402 is not limited to a single image sensor, and multiple image sensors may be provided. The device settings for these combinations of numbers will be explained later as necessary. The reference white plate 12 is a member that is read in advance to perform white correction on the read image.

[0015] 1 is further equipped with an ADF (Automatic Document Feeder) 20, which can also read the target document using a sheet-through method. In the ADF 20, a pickup roller 22 separates a stack of target documents from a tray 21 of the ADF 20 one by one, and by controlling various conveyance rollers 24, etc., one or both sides of the target document conveyed along a conveyance path 23 are read and the document is discharged to a discharge tray 25.

[0016] The object to be read is read through the reading window 19. In this example, the first carriage 14 and the second carriage 15 are moved to and fixed at a predetermined home position, and when the object to be read passes between the reading window 19 and the background portion 26, the image is read by irradiating the first surface (front surface) of the object to be read, which faces the reading window 19, with light from the light source 13. The reading window 19 is a slit-shaped reading window provided in a part of the contact glass 11. The background portion 26 is a background member.

[0017] When double-sided reading of the object to be read is performed, after the object passes through the reading window 19, the second side is read by the reading module 27 of the second reading means provided on the second side (back side). The reading module 27 has an irradiation unit including a light source and a contact-type image sensor 402 (see Figures 2, 5, etc.) which is the second reading unit, and the reflected light of the light irradiated onto the second side is read by the contact-type image sensor 402. Note that this light source is not limited to one light source, and multiple light sources may be provided. Furthermore, the image sensor 402 is not limited to one image sensor, and multiple image sensors may be provided. The background member 28 is made up of a density reference member.

[0018] When reading an object, the first and second reading means perform shading correction using shading data generated based on the density reference member, respectively. The shading correction corrects for variations in accuracy for each pixel of each reading unit.

[0019] Next, the configuration of the control block of the image reading device 1 will be described.

[0020] FIG. 2 is a diagram showing an example of the configuration of the control block of the image reading device 1. As shown in FIG. 2, the image reading device 1 has a control unit 300, an operation panel 301, various sensors 302, a scanner motor 303, various motors 304, an image output unit 305, and a reading unit 400. In addition, various control objects are connected. The various sensors 302 are sensors that detect the reading object. The scanner motor 303 is a motor that drives the first carriage 14 and the second carriage 15 of the image reading device main body 10. The various motors 304 are various motors provided in the ADF 20.

[0021] The operation panel 301 is, for example, a touch panel type liquid crystal display device. The operation panel 301 accepts input operations such as various settings and reading execution (scan execution) from the user via operation buttons, touch input, etc., and transmits corresponding operation signals to the control unit 300.

[0022] Furthermore, operation panel 301 displays various display information from control unit 300 on the display screen. For example, operation panel 301 includes an execute button that allows the user to check whether various certificates, documents, etc. have been fraudulently forged or tampered with. When the execute button is pressed, operation panel 301 instructs control unit 300 to execute fraud check processing.

[0023] The selection of whether or not to perform fraud check may be made on a setting screen on the display screen of the operation panel 301. Also, the setting may be such that fraud check processing is always executed when the scan execution button is operated.

[0024] The control unit 300 outputs the execution results of the fraud confirmation process in a visualized manner. For example, the control unit 300 displays an execution screen (confirmation screen) of the fraud confirmation process on the display screen of the operation panel 301. The control unit 300 may also store the data of the confirmation screen in an external memory or output it to an external printer and print it out.

[0025] 2 shows an example of functional blocks of a reading unit 400 that reads an image. Note that the first reading unit and the second reading unit are not limited to this. The reading unit 400 has a light source 401, a sensor chip 402a, an amplifier 403, an A / D 404, an image processing unit 405, a frame memory 406, an output control circuit 407, and an I / F circuit 408.

[0026] Image data (read image) is output from the output control circuit 407 to the control unit 300 via the I / F circuit 408 for each frame.

[0027] Here, the sensor chip 402a, amplifier 403, A / D 404, image processing unit 405, frame memory 406, output control circuit 407, and I / F circuit 408 are provided on the sensor board 17 (see FIG. 1). Each sensor chip 402a is a pixel sensor provided in the image sensor 402, which is an image reading unit.

[0028] The reading means 400 is driven by the controller 307 based on a reading control signal (such as a timing signal) output from the control unit 300. For example, the reading means 400 irradiates the object to be read with light by turning on the light source 401 based on a lighting signal from the controller 307. The reading means 400 also converts the light from the object to be read, which is imaged on the sensor surface of the image sensor 402, into an electric signal by each sensor chip 402a and outputs the electric signal.

[0029] The reading means 400 amplifies the electrical signals (pixel signals) output from each sensor chip 402a using an amplifier 403, converts the analog signals to digital signals using an A / D 404, and outputs pixel level signals. The image processing unit 405 performs image processing on the output signals from each pixel. For example, the image processing unit 405 performs shading correction on the output signals from each pixel.

[0030] After image processing, each data is stored in a frame memory 406 , and the read image is transferred to the control unit 300 via an output control circuit 407 and an I / F circuit 408 .

[0031] The control unit 300 includes a CPU (Central Processing Unit), memory, etc., and controls the entire device to perform operations such as reading the read target and processing for checking for fraud. The processing unit for checking for fraud may be implemented by a functional unit that is realized by the CPU executing a predetermined program, or may be implemented by hardware such as an ASIC (Application Specific Integrated Circuit), or may be implemented by dividing the functions between them.

[0032] The program executed by the image reading device 1 of this embodiment may be configured to be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, or a DVD (Digital Versatile Disc).

[0033] Furthermore, the program executed by the image reading device 1 of the present embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Also, the program executed by the image reading device 1 of the present embodiment may be provided or distributed via a network such as the Internet.

[0034] When the control unit 300 receives a scan execution operation to which fraud confirmation is applied, it executes a fraud confirmation process when executing the scan, for example, by causing the reading means 400 to perform a reading operation on the object to be read using a combination of a predetermined light source and a predetermined image sensor 402.

[0035] Furthermore, the control unit 300 executes one or more fraud confirmation processes on the read image transferred from the reading means 400, and visualizes and outputs the results. For example, the control unit 300 displays an execution screen (confirmation screen) for the fraud confirmation process on the display screen of the operation panel 301. The control unit 300 may also store the data of the confirmation screen in an external memory or output it to an external printer and print it out.

[0036] The image output unit 305 receives from the control unit 300 the read image (for example, a visible light image of a subject, which will be described later) transferred from the reading means 400, and outputs it to the outside.

[0037] Next, fraud confirmation will be described in detail.

[0038] Hereinafter, the term "visible light image" refers to information that can be seen by the human eye under natural light, or an image that can be seen by a sensing device such as image sensor 402 that is sensitive to visible light (light in the visible wavelength range). Furthermore, the term "invisible light image" refers to an image that cannot be seen by the human eye under natural light, or an image that cannot be seen by a visible light sensing device, such as an image sensor 402 that is sensitive to light in the invisible wavelength range, such as infrared (including near-infrared) or ultraviolet light. Furthermore, among the device configurations described below, information for fraud detection that is pre-applied to the printed surface, and settings such as the number and wavelength range of light sources and image sensors 402 used in the reading means, are broadly considered to be included in the configuration of a "fraud detection device."

[0039] Fig. 3 is a diagram showing an example of the spectral sensitivity characteristics of the image sensor 402. Fig. 4 is a diagram showing an example of the reflection spectral characteristics when each color toner (cyan (C) toner, magenta (M) toner, yellow (Y) toner, black (K) toner) and black (C toner + M toner + Y toner) are applied to the surface of white paper.

[0040] 3, silicon constituting the pixels of a general image sensor 402 is sensitive to the near-infrared wavelength range (invisible range, wavelengths of approximately 780 nm or more) in addition to the visible wavelength range (approximately wavelengths of 380 nm to 780 nm). In other words, although the near-infrared wavelength range cannot be recognized by the human eye, an image sensor 402 that is also sensitive to the near-infrared wavelength range can read near-infrared light and can create an image even when irradiated with near-infrared light.

[0041] As shown in Figure 4, each color toner (C toner, M toner, Y toner, black (K) toner) exhibits different characteristics in the visible wavelength range (wavelengths around 400 to 750 nm), which are visually recognized as different colors. Also, as shown in Figure 4, black (C+M+Y) created by combining C toner, M toner, and Y toner exhibits black with low reflectance in the visible wavelength range and white with high reflectance in the near-infrared light range (wavelengths of 750 nm and beyond). On the other hand, black (K) toner exhibits black with low reflectance across the entire wavelength range.

[0042] In other words, even if two colors are perceived as the same "black" to the naked eye, in the near-infrared wavelength range black (K) is read as black text or images, while black (C+M+Y) is read as white, which shows that near-infrared light can distinguish between black (C+M+Y) and black (K). Utilizing this, it is possible to distinguish between black (C+M+Y) and black (K) even if they appear to be the same black to the naked eye, by using near-infrared light.

[0043] As described above, by using near-infrared light as invisible image reading light, it is possible to use a general-purpose image sensor 402 to check documents such as tickets created with general-purpose toner.

[0044] Carbon is a material that has reflectance characteristics similar to those of black (K) in Figure 4 and is used in toner and ink. It is also effective to use the area containing / not containing carbon as the target area for characteristic extraction.

[0045] In this embodiment, an example will be described in which a color that is visually recognized as black can be distinguished using near-infrared light, but colors that can be distinguished using near-infrared light are not limited to black. For example, colors that include black (K), such as gray, which is an intermediate color, and red, green, and blue that have a certain degree of density (blackness), can also be distinguished using near-infrared light.

[0046] FIG. 5 is a diagram illustrating an example of the configuration of a device that performs fraud confirmation.

[0047] The reading means 400 in Fig. 5 includes a light source 401 and an image sensor 402, but also includes other components such as those shown in the reading means 400 in Fig. 2. A light source including at least an invisible wavelength component is used as the light source 401 shown in Fig. 5, and an image sensor having sensitivity even in the invisible wavelength range of the light source 401 is used as the image sensor 402. For example, a light source 401 of light including a near-infrared wavelength range component and a visible wavelength range component is used, and an image sensor 402 having sensitivity to wavelength ranges including these components is used.

[0048] As shown in the example of this embodiment, it is possible to distinguish between an image that includes black (K) and an image that does not include black (K) using an invisible light image acquired using invisible light of one wavelength band, and there is no need to receive at least multiple types of reflected light. In other words, the reading means 400 does not need to switch between multiple types of invisible light sources on the light-emitting side or multiple types of spectral filters or light-receivers on the light-receiving side, making it possible to perform highly accurate authenticity determination with a cheaper configuration.

[0049] As shown in FIG. 5, the fraud confirmation device includes an image characteristic detection unit 500, a state determination unit 600, and a state determination information notification unit 700 which is a notification unit.

[0050] The image characteristic detection unit 500 includes a plurality of characteristic detection units 501 (501a, 501b), and detects the same or different image characteristics for a plurality of image regions in an invisible light image.

[0051] The state determination unit 600 includes a plurality of threshold determination units 601 and determines the state of the subject based on a plurality of image characteristics detected by the characteristic detection unit 501 .

[0052] For example, the state determination unit 600 determines the state of the subject, such as whether the subject is in an authentic state (first state) without any fraud such as forgery or tampering, an fraudulent state (second state) where the subject has been forged or tampered with, or a state (third state) where it cannot be determined whether the subject is in an authentic state (first state) or a fraudulent state (second state) due to the influence of dirt, scratches, etc.

[0053] Furthermore, the state determination unit 600 determines the state of the subject, such as a state where it is difficult to distinguish between the possibility of tampering and the effects of dirt or scratches, etc., and therefore it is at least impossible to say for sure that the subject is not genuine (a state other than the first state), or a state where it is difficult to distinguish between the possibility of tampering and the effects of dirt or scratches, etc., and therefore it is at least impossible to say for sure that the subject has been tampered with based on the detection results, such as a state where the conditions for being genuine are met but there are severe scratches or dirt, making it difficult to distinguish between them (a state other than the second state).

[0054] FIG. 6 is a flowchart showing an example of the state determination of the subject in the state determination unit 600. In FIG.

[0055] 6, the state determination unit 600 first determines whether the subject is genuine (step S1) based on the determination result by the threshold determination unit 601 which is based on a plurality of image characteristics detected by the characteristic detection unit 501. If the determination result by the threshold determination unit 601 matches the condition of being genuine (Yes in step S1), the state determination unit 600 determines that the subject is genuine (first state) (step S2).

[0056] On the other hand, if the determination result by threshold determination unit 601 does not match the condition that the product is genuine (No in step S1), status determination unit 600 determines whether the product is counterfeit (step S3). If the determination result by threshold determination unit 601 matches the condition that the product is counterfeit (Yes in step S3), status determination unit 600 determines that the product is counterfeit (second state) (step S4). On the other hand, if the determination result by threshold determination unit 601 does not match the condition that the product is counterfeit (No in step S3), status determination unit 600 determines that the product is in an indeterminable state (third state) (step S5).

[0057] FIG. 7 is a flowchart showing another example of the state determination of the subject in the state determination section 600. In FIG.

[0058] As an example, the state determination unit 600 first determines whether the subject is authentic based on the determination result of the threshold determination unit 601 which is based on multiple image characteristics detected by the characteristic detection unit 501, as shown in FIG. 7 (step S11).

[0059] If the result of the determination by the threshold determination unit 601 matches the condition that the product is genuine (Yes in step S11), the state determination unit 600 determines that the product is genuine (first state) (step S12).

[0060] On the other hand, if the judgment result of the threshold judgment unit 601 does not match the condition of authenticity (No in step S11), the state judgment unit 600 judges that the state is other than the authentic state (first state) (step S13).

[0061] For tickets that are in general circulation, there are countless methods and types of fraud, and likewise countless patterns and types of scratches and stains, so it is difficult to grasp and accurately distinguish all of these characteristics. Therefore, by not separating these, it is also effective to reduce the risk of mistakenly reporting the second and third states.

[0062] FIG. 8 is a flowchart showing yet another example of the state determination of the subject in the state determination section 600. In FIG.

[0063] As an example, the status determination unit 600 first determines whether the subject is a counterfeit product based on the determination result of the threshold determination unit 601, which is based on multiple image characteristics detected by the characteristic detection unit 501, as shown in Figure 8 (step S21).

[0064] If the result of the determination by the threshold determination unit 601 matches the condition that the product is a counterfeit product (Yes in step S21), the state determination unit 600 determines that the product is a counterfeit product (second state) (step S22).

[0065] On the other hand, if the judgment result of the threshold judgment unit 601 does not match the condition of a counterfeit product (No in step S21), the state judgment unit 600 judges that the product is in a state other than a counterfeit product (second state) (step S23).

[0066] For example, in the case of entrance passes that are issued and managed only within a specific range, the means of fraud, such as additions or alterations, are limited. Therefore, it is possible to detect fraud, and it may be judged that it is sufficient if it is not detected. This is effective in environments such as certain factories where there is a concern that entrance passes are easily soiled or scratched.

[0067] 5, the status determination information notification unit 700 visualizes the status determined by the status determination unit 600 and outputs it to the display screen of the operation panel 301. Alternatively, the status determination information notification unit 700 visualizes and outputs the processing results as print information so that they can be printed on an external printer.

[0068] That is, the state determination information notification unit 700 notifies the outside or the user of information that the state determination unit 600 has determined to be one of the states (first state, second state, third state, state other than the first state, state other than the second state). The state determination information notification unit 700 may notify, for example, using the operation panel 301, a display device such as a display, a paper printout, a change in color or brightness of an indicator lamp, a sound notification such as a warning sound, etc. Each of these makes it possible to present the authenticity determination information to the user's visual and auditory senses, further improving convenience.

[0069] Next, an example of application of the present invention to authenticity determination using differences in image characteristics will be described using an original ticket and its copy, which are general-purpose and inexpensive objects.

[0070] Here, Fig. 9 is a diagram showing an example of the original ticket T1. The example shown in Fig. 9 is an example of a ticket with a picture mark.

[0071] As shown in Figure 9, the text information on the original ticket T1 is intended to display and confirm detailed information such as the product and expiration date. Therefore, it is desirable for this text information to be clearly visible to the naked eye and have excellent abrasion and heat resistance, so it is primarily composed of carbon (pigment). Carbon is a common and widely used black ink or toner, and does not require dedicated or special systems for printing general tickets. It also has the ability to absorb light in a wide range of wavelengths, including visible light, ultraviolet light, and infrared light, so it is read as "black" by reading devices that operate in all wavelength bands.

[0072] That is, in the master ticket T1 of this embodiment shown in FIG. 9, the characters are image-formed with black (K) toner containing carbon.

[0073] On the other hand, as shown in Figure 9, the coffee cup mark (design) on the original ticket T1 is formed with finer, more vivid dye paints, as its purpose is to supplement the written information, such as the ticket's effectiveness and validity, and to encourage users to use it. Examples of dye paints include inks and toners in cyan, magenta, yellow, red, green, blue, and carbon-free black. These dye paints are also widely used. The security level can be further increased by incorporating a dark color close to black into the coffee cup mark (design). For example, a color scheme with dark colors, as shown in Figure 9, and shadows are natural and effective.

[0074] That is, in the master ticket T1 shown in FIG. 9 of this embodiment, the image is formed in the picture area using carbon-free dye toners (C toner, M toner, Y toner).

[0075] The fraud checking device of this embodiment uses, for example, near-infrared light as invisible light to read an object such as an original ticket T1 shown in FIG.

[0076] FIG. 10 is a diagram showing an example of an invisible light image obtained by reading the original ticket T1 shown in FIG. 9 with near-infrared light.

[0077] As described above, in the master ticket T1 shown in Figure 9, the character area (first image area) is formed with black toner, a material that contains at least carbon, and the picture area (second image area) is formed with carbon-free dye toner, a material that does not contain at least carbon. Black toner, a material that contains carbon, is a material that absorbs at least invisible light. Carbon-free dye toner, a material that does not contain carbon, is a material that does not absorb at least invisible light. Therefore, in the invisible light image obtained by scanning the master ticket T1 with near-infrared light, all the characters are scanned as black, and the picture area is scanned as white, which is approximately the same color as the background.

[0078] Next, the reading of a ticket copy made by copying the original ticket T1 shown in FIG. 9 using near-infrared light will be described.

[0079] Here, Fig. 11 is a diagram showing an example of an invisible light image obtained by scanning, with near-infrared light, a copy of the ticket master T1 shown in Fig. 9, which has been copied with black (K) toner. As described above, black (K) toner is a toner containing carbon.

[0080] In the invisible light image of the ticket counterfeit shown in Fig. 11 read with near-infrared light, all black parts are formed with black having the spectral characteristics of black (K) in Fig. 4, and therefore an image also appears in the image area, unlike the example of the invisible light image of the ticket original T1 read with near-infrared light shown in Fig. 9. In other words, this shows that if it can be detected whether the image level of the image area is white or not, it can be determined whether the ticket that is the subject is an original or a counterfeit.

[0081] On the other hand, Fig. 12 is a diagram showing an example of an invisible light image obtained by scanning, with near-infrared light, a copy of the original ticket T1 shown in Fig. 9, which has been copied with dye-based toner. The dye-based toner is, for example, cyan, magenta, yellow, or carbon-free black toner.

[0082] In the invisible light image of the ticket counterfeit shown in Fig. 12 read with near-infrared light, all black is formed with black having the spectral characteristics of black (C+M+Y) in Fig. 4, and therefore the text area and image of the original ticket T1 have disappeared, unlike the example of the invisible light image of the ticket counterfeit T1 read with near-infrared light shown in Fig. 10. In other words, this shows that if it is possible to detect whether black is included in the image level of the text area, it is possible to determine whether the ticket that is the subject is an original or a copy.

[0083] Here, the threshold value determining unit 601 of the state determining unit 600 will be described in detail.

[0084] As mentioned above, when the original ticket T1 (genuine) is scanned, an invisible light image like the one shown in Figure 10 is obtained. Because the characters are formed with black (K) toner containing carbon and the image area is formed with dye toner that does not contain carbon, the characters are scanned as black and the image area is scanned as white, which is almost the same color as the background.

[0085] 13 is a diagram showing an example of an image area. Therefore, for example, as shown in FIG. 13, image characteristic detection unit 500 preliminarily designates an area in which text is written in the first image area targeted by characteristic detection unit 501a, and an area in which a picture is written in the second image area targeted by characteristic detection unit 501b.

[0086] That is, the image characteristic detection unit 500 detects the first image area to be an image area in which text information is written, and detects the second image area to be an image area other than an image in which text information is written (for example, a picture area).

[0087] In other words, the image characteristic detection unit 500 detects the first image area to be an area containing an image formed from a material that contains at least carbon, and detects the second image area to be an area containing an image formed from a material that does not contain at least carbon.

[0088] Since it is sufficient to detect the characteristics of the invisible light images of both the first image region and the second image region, the image characteristic detection unit 500 may detect the background and skin regions as well, as shown in Fig. 13. Of course, the image characteristic detection unit 500 may also specify and detect only the region containing text or the region containing a picture.

[0089] The image characteristic detection unit 500 detects image characteristic 1 in characteristic detection unit 501a and image characteristic 2 in characteristic detection unit 501b for these image regions, and transmits the detected image characteristics 1 and 2 to the state determination unit 600 at the subsequent stage.

[0090] As described above, the image characteristic detection unit 500 detects a plurality of image regions from which characteristics are to be extracted so that at least one region includes a region in which information visible under a visible light environment is clearly displayed.

[0091] Generally, in the case of tickets, etc., the areas of letters and pictures differ depending on the type of ticket. In other words, it is possible to visually identify areas that contain black (carbon) that absorbs invisible light and areas that do not contain black (carbon) that do not absorb invisible light.

[0092] As shown in Figure 13, by allowing the user to visually check multiple image regions from which image characteristics are extracted and specify the confirmation region, it is possible to further improve convenience, versatility, and accuracy.

[0093] The threshold determination unit 601 determines whether the image characteristic detected by the characteristic detection unit 501 is above or below a threshold. More specifically, the threshold determination unit 601 determines whether image characteristic 1, which is a first image characteristic, is below a first threshold, and whether image characteristic 2, which is a second image characteristic, is above a second threshold. The state determination unit 600 determines, for example, whether black text is present for image characteristic 1, and whether the image has disappeared for image characteristic 2, and if the result is true, the ticket is determined to be genuine (first state), and if the result is false, the ticket is determined to be something other than genuine (first state) (forgery, copy, etc.).

[0094] That is, the status determination unit 600 determines that the subject is a genuine product (first state) from the image of FIG. 10, or performs a status determination that will contribute to the user of the fraud confirmation device of this embodiment determining that the subject is a genuine product (first state).

[0095] 11, characteristic detection unit 501a detects image characteristic 1 in the character area of ​​the ticket, and characteristic detection unit 501b detects image characteristic 2 in the picture area of ​​the ticket. Since a black picture is present in image characteristic 2, state determination unit 600 determines that the subject is in a state other than a counterfeit product (second state) or a genuine product (first state).

[0096] 12, characteristic detection unit 501a detects image characteristic 1 of the character area of ​​the ticket, and characteristic detection unit 501b detects image characteristic 2 of the picture area of ​​the ticket, and they are sent to status determination unit 600. Since there are no black characters in image characteristic 1, status determination unit 600 determines that the subject is in a state other than that of a counterfeit product (second state) or a genuine product (first state).

[0097] That is, the fraud confirmation device of this embodiment determines from the images of Figures 11 and 12 that the subject is a fraudulent product (second state) or a state other than genuine product (first state), or performs a state determination to enable the user of the fraud confirmation device of this embodiment to determine that the subject is a fraudulent product (second state) or a state other than genuine product (first state).

[0098] In the following, an example is shown in which the image characteristic detection unit 500 calculates the average value of the image characteristics of the invisible light image, and the threshold determination unit 601 sets a threshold for that average value. Note that the target image is an 8-bit image with 0 digit (black) to 255 digit (white).

[0099] Fig. 14 is a diagram showing an example of data on average values ​​of image characteristics of invisible light images. The "black text" shown in Fig. 14 represents the word "COFFEE" in Fig. 9, and the "pattern" shown in Fig. 14 represents the image average values ​​at the same positions on the invisible light image (Figs. 10 to 12) at the center of the coffee cup in Fig. 9.

[0100] In the invisible light image of the genuine product (FIG. 10), the text remains in black and the pattern has disappeared. Therefore, the characteristic detection unit 501 calculates the average values ​​(image characteristics) of the image data as 10 digits and 200 digits, respectively.

[0101] On the other hand, in the copy (FIG. 11), both the text and the image remain in black, so the characteristic detection unit 501 calculates the average values ​​of the image data (image characteristics) to be low. Also, in the copy (FIG. 12), both have been lost, so the characteristic detection unit 501 calculates the average values ​​of the image data (image characteristics) to be high.

[0102] 15 is a flowchart showing an example of subject state determination based on threshold determination in state determination unit 600. For example, as shown in FIG. 15, threshold determination unit 601 first sets the threshold for black text areas to 20 digits, and the threshold for picture areas to 100 digits.

[0103] As shown in FIG. 15, the state determination unit 600 determines in the threshold determination unit 601 whether the black character portion is lower than the threshold value (20 digits) and the picture area is higher than the threshold value (100 digits) based on the multiple image characteristics detected by the characteristic detection unit 501 (step S31).

[0104] If the threshold determination unit 601 determines that the black text portion is lower than the threshold (20 digits) and the picture area is higher than the threshold (100 digits) (Yes in step S31), it determines that the subject is genuine (first state) (step S32).

[0105] On the other hand, if the threshold determination unit 601 does not determine that the black character portion is lower than the threshold (20 digits) and the picture region is higher than the threshold (100 digits) (No in step S31), it compares the data with another threshold, a 15-digit threshold for the black character portion and a 150-digit threshold for the picture region, and if the data satisfies either one, it determines that the subject is a counterfeit product. That is, based on the multiple image characteristics detected by the characteristic detection unit 501, the threshold determination unit 601 determines whether the black character portion is lower than the threshold (15 digits) or the picture region is higher than the threshold (150 digits) (step S33).

[0106] If the threshold determination unit 601 determines that the black text portion is lower than the threshold (15 digits) or the picture area is higher than the threshold (150 digits) (Yes in step S33), it determines that the subject is a counterfeit product (second state) (step S34).

[0107] Furthermore, if the threshold determination unit 601 does not determine that the black text portion is lower than the threshold (15 digits) or that the picture area is higher than the threshold (150 digits) (No in step S33), that is, if the data does not satisfy either, it determines that the subject is in an indistinguishable state (third state) (step S35).

[0108] When data deviations occur due to factors such as dirt, the data may take intermediate values ​​rather than extreme values ​​such as black or white. One example of a mechanism for detecting this is to determine that such unintended factors have occurred when the data is slightly below or above a threshold.

[0109] FIG. 16 is a flowchart showing another example of the state determination of the subject based on threshold determination in the state determination section 600. In FIG.

[0110] As shown in FIG. 16, the state determination unit 600 determines in the threshold determination unit 601 whether the black character portion is lower than the threshold value (20 digits) and the picture area is higher than the threshold value (100 digits) based on the multiple image characteristics detected by the characteristic detection unit 501 (step S41).

[0111] If the threshold determination unit 601 determines that the black text portion is lower than the threshold (20 digits) and the picture area is higher than the threshold (100 digits) (Yes in step S41), it determines that the subject is an authentic product (first state) (step S42).

[0112] On the other hand, if the threshold determination unit 601 determines that the black text portion is lower than the threshold (20 digits) and the picture area is not higher than the threshold (100 digits) (No in step S41), it determines that the product is in a state other than genuine (first state) (step S43).

[0113] FIG. 17 is a flowchart showing yet another example of the state determination of the subject based on threshold determination in the state determination section 600. In FIG.

[0114] As shown in FIG. 17, the state determination unit 600 determines in the threshold determination unit 601 whether the black character portion is higher than the threshold value (20 digits) and the picture area is lower than the threshold value (100 digits) based on the multiple image characteristics detected by the characteristic detection unit 501 (step S51).

[0115] If the threshold determination unit 601 determines that the black text portion is higher than the threshold (20 digits) and the picture area is lower than the threshold (100 digits) (Yes in step S51), it determines that the subject is a counterfeit product (second state) (step S52).

[0116] On the other hand, if the threshold determination unit 601 does not determine that the black text portion is higher than the threshold (20 digits) and the picture area is lower than the threshold (100 digits) (No in step S51), it determines that the product is in a state other than counterfeit (second state) (step S53).

[0117] As described above, by using the fraud confirmation device of this embodiment to detect both whether the image level of the picture area is white and whether the image level of the text area contains black, it is possible to determine with high accuracy whether the ticket in question is genuine, fraudulent, or in an undeterminable state. Furthermore, no special ink or toner is required for the ticket, and there is no need to extract dedicated / special embedded information such as encryption information, making it possible to determine authenticity with an inexpensive configuration on both the ticket issuing (printing) side and the receiving (reading) side.

[0118] In this embodiment, it is necessary to specify the positions on the image that need to be checked, such as the text area or the picture area, but the means for specifying these positions is not limited as long as they are determined before the fraud confirmation device makes a judgment, such as specifying a fixed position in advance, automatically determining / judging from the scanned image, preparing several variations and allowing the user to select, or having the user specify (prompt) the position.

[0119] As described above, according to this embodiment, by detecting image characteristics in multiple image regions within an invisible light image and determining the state using the information on those characteristics, it is possible to determine the authenticity of a generic and inexpensive object with a low-cost configuration and with high accuracy. Therefore, it is possible to configure a fraud verification device that can detect all variations other than "genuine products." It is possible to determine authenticity from at least one image obtained by at least one subject reading control.

[0120] 5, the light source 401 and the image sensor 402 may each be configured with one, or may be configured with multiple types. Also, while an example of a configuration with N characteristic detection units 501 has been shown, the present invention is not limited to this, and may be configured with one block that detects image characteristics by dividing or switching between multiple image regions. Furthermore, the image characteristics 1,...N may have the same or different characteristic values ​​or data detection methods.

[0121] [Variations] Here, a modified version of the original ticket will be described.

[0122] Fig. 18 is a diagram showing a modified example of a master ticket T2. The master ticket T2 shown in Fig. 18 is a ticket without a picture but with a colored background pattern or design. In the master ticket T2 shown in Fig. 18, the characters are formed with black toner containing carbon, and the picture area is formed with dye toner that does not contain carbon. In the master ticket T2 shown in Fig. 18, the image characteristic detection unit 500 defines the first image area as the area where characters are written, and the second image area as the background area without characters (the area with a colored background pattern or design).

[0123] Fig. 19 is a diagram showing an example of an invisible light image obtained by reading the master ticket T2 shown in Fig. 18 with near-infrared light. In the master ticket T2 shown in Fig. 18, the characters are formed with black toner containing carbon, and the picture area is formed with dye toner not containing carbon. Therefore, in the invisible light image obtained by reading the master ticket T2 with near-infrared light, all the characters are read as black, and the background area is read as white, which is approximately the same color as the skin.

[0124] Fig. 20 is a diagram showing an example of an invisible light image obtained by scanning, with near-infrared light, a copy of the ticket T2 shown in Fig. 18, which has been copied with black (K) toner. As described above, black (K) toner contains carbon.

[0125] In the invisible light image of the ticket counterfeit shown in Fig. 20 read with near-infrared light, all black parts are formed with black having the spectral characteristics of black (K) in Fig. 4, and therefore, unlike the example of the invisible light image of the ticket original T2 read with near-infrared light shown in Fig. 18, an image also appears in the background region. In other words, if it can be detected whether the image level of the background region other than the characters is white, it is possible to determine whether the subject ticket is an original or a counterfeit.

[0126] On the other hand, FIG. 21 is a diagram showing an example of an invisible light image obtained by reading, with near-infrared light, a copy of the original ticket T2 shown in FIG. 18, which has been copied with dye paint toner.

[0127] In the invisible light image of the ticket counterfeit shown in Fig. 21 read with near-infrared light, all black is formed with black having the spectral characteristics of black (C+M+Y) in Fig. 4, and therefore, unlike the example of the invisible light image of the ticket counterfeit T2 read with near-infrared light shown in Fig. 18, both the character area and the image of the ticket counterfeit T2 have disappeared. In other words, this shows that if it is possible to detect whether black is included at the image level of the character area and the other background area, it is possible to determine whether the ticket that is the subject is an original or a counterfeit.

[0128] In this embodiment, the state determination unit 600 is provided in the fraud confirmation device, but this is not limited to this. In a fraud confirmation system that includes a fraud confirmation device and a server, the state determination unit 600 may be provided on the server side.

[0129] Here, Fig. 22 is a diagram showing the configuration of a fraud confirmation system. As shown in Fig. 22, the fraud confirmation system is a system in which an image reading device 1, which is an example of a fraud confirmation device, and a server S are connected via a network N. The network N is the Internet, a LAN (Local Area Network), or the like.

[0130] Server S is equipped with a control device such as a CPU (Central Processing Unit), storage devices such as ROM (Read Only Memory) and RAM (Random Access Memory), external storage devices such as HDD (Hard Disk Drive) and DVD (Digital Versatile Disc) drive devices, display devices such as a display device, and input devices such as a keyboard and a mouse, and has a hardware configuration that utilizes a normal computer.

[0131] 22, an image reading device 1, which is an example of a fraud confirmation device, includes an image characteristic detection unit 500 and a status determination information notification unit 700. On the other hand, a server S includes a status determination unit 600. In the server S, the CPU reads and executes a program from the ROM or HDD, whereby the status determination unit 600 is loaded onto the RAM, and the status determination unit 600 is generated on the RAM.

[0132] The status determination unit 600 of the server S includes a plurality of threshold determination units 601, and receives a plurality of image characteristics detected by the characteristic detection unit 501 of the image reading device 1 via the network N. The status determination unit 600 of the server S determines the status of the subject based on the plurality of image characteristics detected by the characteristic detection unit 501 of the image reading device 1.

[0133] The status determination information notification unit 700 of the image reading device 1 receives the status determined by the status determination unit 600 of the server S via the network N. The status determination information notification unit 700 of the image reading device 1 visualizes the status determined by the status determination unit 600 of the server S and outputs it to the display screen of the operation panel 301. Alternatively, the status determination information notification unit 700 of the image reading device 1 visualizes and outputs the processing result as print information so that it can be printed by an external printer.

[0134] (Second embodiment) Next, a second embodiment will be described.

[0135] The second embodiment differs from the first embodiment, which uses an average value that is easy to calculate, in that the calculation method for calculating image characteristics in characteristic detection unit 501 is any one of the average value of image characteristics of invisible light images, the standard deviation value of image characteristics of invisible light images, the median value of image characteristics of invisible light images, and the mode value of image characteristics of invisible light images. In the following description of the second embodiment, descriptions of the same parts as in the first embodiment will be omitted, and only differences from the first embodiment will be described.

[0136] Here, Fig. 23 is a diagram showing an example of image characteristic detection in the characteristic detection unit 501 according to the second embodiment. Fig. 23 shows a histogram on an invisible light image when an original ticket (genuine) is read. The horizontal axis of the histogram represents the image data level (digits), and the vertical axis of the histogram represents the number of occurrences (times).

[0137] In the first embodiment, an example was shown in which threshold determination was performed using the average value of the image characteristics of the invisible light image, which is easier to calculate in the image characteristic detection by the characteristic detection unit 501. However, this is not limited to this. For example, in the image characteristic detection by the characteristic detection unit 501, if the median of each character or pattern is used, it is possible to efficiently remove the influence of outliers such as stains that are singular points. Alternatively, if the standard deviation is used, it is possible to perform a highly accurate determination that also takes into account the size of the data, as shown in FIG. 23. Furthermore, in the image characteristic detection by the characteristic detection unit 501, if the mode is used, it is possible to simplify area designation and perform calculations that are robust against image misalignment. Furthermore, in the image characteristic detection by the characteristic detection unit 501, any of the average value of the image characteristics of the invisible light image, the standard deviation value of the image characteristics of the invisible light image, the median value of the image characteristics of the invisible light image, and the mode value of the image characteristics of the invisible light image may be combined.

[0138] (Third embodiment) Fig. 24 is a diagram showing an example of the configuration of a fraud confirmation device according to the third embodiment. Fig. 24 shows an image forming device 2, which is generally called a multifunction peripheral (MFP), as an example of a fraud confirmation device. A multifunction peripheral (MFP) has at least two of the following functions: copy function, printer function, scanner function, and facsimile function.

[0139] 24 includes an image reading device 1 (image reading device main body 10 and ADF 20) which is an unauthorized verification device on the top. The configuration of the image reading device 1 is a repetition of the description of the first embodiment, so the description of the configuration of the image reading device 1 will be omitted here.

[0140] 24 has an image forming unit 80 and a paper feeding unit 90 below an image reading device main body 10. The image forming device 2 prints an output image based on a read image read by the image reading device main body 10 onto recording paper (an example of a "recording medium") using the image forming unit 80. The output image is a visible image or an invisible image.

[0141] The image forming section 80 includes an optical writing device 81, tandem imaging units (Y, M, C, K) 82, an intermediate transfer belt 83, and a secondary transfer belt 84. In the image forming section 80, the optical writing device 81 writes an image to be printed onto the photosensitive drum 820 of the imaging unit 82, and the toner image of each plate is transferred from each photosensitive drum 820 onto the intermediate transfer belt 83. The K plate is formed with K toner containing carbon black.

[0142] 24, the imaging unit (Y, M, C, K) 82 has four rotatable photosensitive drums (Y, M, C, K) 820, and is provided with imaging elements including a charging roller, a developing unit, a primary transfer roller, a cleaner unit, and a static eliminator around each photosensitive drum 820. The imaging elements operate around each photosensitive drum 820 in a predetermined image creation process to form an image on each photosensitive drum 820, and the image formed on each photosensitive drum 820 is transferred as a toner image onto the intermediate transfer belt 83 by a primary transfer roller.

[0143] Intermediate transfer belt 83 is stretched across a drive roller and a driven roller in the nip between each photosensitive drum 820 and each primary transfer roller. The toner image that has been primarily transferred onto intermediate transfer belt 83 is secondarily transferred onto recording paper on secondary transfer belt 84 by a secondary transfer device as intermediate transfer belt 83 travels. The recording paper is then transported to fixing device 85 as secondary transfer belt 84 travels, where the toner image is fixed onto the recording paper as a color image. The recording paper is then ejected to a paper ejection tray outside the machine.

[0144] For example, a paper feed unit 90 feeds out a desired recording paper from paper feed cassettes 91 and 92 that store recording paper of different sizes, and transports it by a transport means 93 consisting of various rollers to supply it to the secondary transfer belt 84.

[0145] The image forming section 80 is not limited to one that forms images by the electrophotographic method as described above, but may also be one that forms images by an inkjet method.

[0146] The image reading device (image reading device main body 10 and ADF 20) 1 may be provided with a light source that emits light including visible wavelength components in addition to the light source 401 that emits light including at least invisible wavelength components (near-infrared wavelength components). This makes it possible to determine the authenticity of electronic image data simultaneously when copying or scanning the subject, further improving convenience.

[0147] In the above embodiment, an example was given in which the fraud confirmation device of the present invention is applied to a multifunction device having at least two of the functions of a copy function, a printer function, a scanner function, and a facsimile function, but the device can be applied to any image forming device such as a copier, printer, scanner device, or facsimile device.

[0148] (Fourth embodiment) Next, a fourth embodiment will be described.

[0149] The fourth embodiment differs from the first embodiment in that it is applied to a security check mechanism. In the following explanation of the fourth embodiment, explanations of the same parts as in the first embodiment will be omitted, and only differences from the first embodiment will be explained.

[0150] In this embodiment, an example using an entrance pass will be described as an application example to a security check mechanism. For example, when access to an area where only authorized personnel are allowed to enter is controlled by a gate pass (entrance pass), security can be improved by identifying copies.

[0151] Here, Fig. 25 is a diagram showing an example of admission pass T3 according to the fourth embodiment. The example shown in Fig. 25 is an example of admission pass T3 with a picture mark.

[0152] In the admission permit T3 shown in Fig. 25, the character area (first image area) is imaged with black (K) toner containing carbon, while the picture area (second image area) in the admission permit T3 shown in Fig. 25 is imaged with dye toners (C toner, M toner, Y toner) that do not contain carbon.

[0153] FIG. 26 is a diagram showing an example of an invisible light image obtained by reading the admission pass T3 shown in FIG. 25 with near-infrared light.

[0154] 25, the character area (first image area) is formed with black toner containing carbon, and the picture area (second image area) is formed with dye toner not containing carbon. Therefore, in the invisible light image obtained by scanning the admission pass T3 with near-infrared light, all the characters are scanned as black, and the picture area is scanned as white, which is almost the same color as the background.

[0155] Next, the reading of a copy of the admission pass, which is a copy of the admission pass T3 shown in FIG. 25, using near-infrared light will be described.

[0156] Here, Fig. 27 is a diagram showing an example of an invisible light image obtained by reading, with near-infrared light, a copy of the admission pass T3 shown in Fig. 25 made with black (K) toner. As described above, black (K) toner is a toner containing carbon.

[0157] In the invisible light image of the copy of the admission pass shown in Fig. 27 read with near-infrared light, all of the black parts are formed with black having the spectral characteristics of black (K) in Fig. 4, and therefore an image also appears in the picture area, unlike the example of the invisible light image of admission pass T3 read with near-infrared light shown in Fig. 25. In other words, if it can be detected whether the image level in the picture area is white or not, it is possible to determine whether the admission pass that is the subject is an original or a copy.

[0158] On the other hand, Fig. 28 is a diagram showing an example of an invisible light image obtained by reading, with near-infrared light, a copy of the admission pass T3 shown in Fig. 25 made with dye paint toner. The dye paint is, for example, cyan, magenta, yellow, or carbon-free black toner.

[0159] In the invisible light image of the ticket counterfeit shown in Fig. 28 read with near-infrared light, all black is formed with black having the spectral characteristics of black (C+M+Y) in Fig. 4, and therefore, unlike the example of the invisible light image of admission pass T3 read with near-infrared light shown in Fig. 25, both the text area and the image of admission pass T3 have disappeared. In other words, this shows that if it is possible to detect whether or not black is included at the image level of the text area, it is possible to determine whether the admission pass that is the subject is an original or a copy.

[0160] As described above, according to this embodiment, by detecting both whether the image level of the picture area is white or not and whether the image level of the text area contains black or not, it is possible to determine with high accuracy whether the admission pass in question is genuine or a copy (counterfeit).

[0161] Furthermore, the admission pass does not require special ink or toner, and there is no need to extract dedicated / special embedded information such as encryption information, which provides the following advantages:

[0162] First, it is possible to prevent a decrease in security effectiveness caused by "imparting security effects." Currently, there are many ways to impart security effects, such as by adding a QR code (registered trademark), but this can limit or lead to inference of key security points on a document, which can result in a decrease in security accuracy. In this embodiment, the information on the face of the card is composed only of natural images and text information, so the security points are not narrowed down, and there is an effect of preventing a decrease in effectiveness.

[0163] Secondly, it is possible to obtain the effect of issuing an inexpensive document. In this embodiment, cost-effective configurations such as creating and embedding a special QR code or incorporating an IC chip are not required.

[0164] Although the embodiments and modifications of the present invention have been described above, these embodiments and modifications are presented as examples and are not intended to limit the scope of the invention. These novel embodiments and modifications can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are included within the scope and spirit of the invention, and are also included in the inventions and their equivalents as set forth in the claims.

[0165] For example, aspects of the present invention are as follows. <1> a light source that irradiates an object with invisible light; an image reader that reads reflected light of one wavelength band from the subject, which is a portion of the invisible light, and acquires an invisible light image from the reflected light; an image characteristic detection unit that detects the same or different image characteristics for a plurality of image regions in the invisible light image; a state determination unit that determines that the subject is in a first state based on the plurality of image characteristics detected by the image characteristic detection unit; Equipped with The image characteristic detection unit detecting image characteristics of a first image area included in the plurality of image areas, with respect to an area of ​​the image formed by a material that absorbs at least invisible light; detecting image characteristics of a second image area included in the plurality of image areas, the second image area being formed of a material that does not absorb at least invisible light; the state determination unit determines that the subject is in a first state based on a first image characteristic of the first image area and a second image characteristic of the second image area; A fraud confirmation device characterized by: <2> the state determination unit includes a threshold determination unit that determines whether the first image characteristic is equal to or less than a first threshold and whether the second image characteristic is equal to or greater than a second threshold; Characterized by <1> The fraud confirmation device described in <3> The image characteristic detection unit detecting the first image area as an image area containing text information; detecting the second image area to be an image area other than the image in which the character information is written; Characterized by <1> or <2> The fraud confirmation device described in <4> The image characteristic detection unit Detecting the second image region as a picture region; Characterized by <3> The fraud confirmation device described in <5> the invisible light contained in the light source is infrared light, the image reading unit reads reflected light in at least an infrared wavelength band; Characterized by <1> Or <4> 10. The fraud confirmation device according to claim 9, wherein <6> The image characteristic detection unit detecting the first image area as an area including an image formed of a material containing at least carbon; detecting the second image area to be an area of ​​an image formed of a material that does not contain at least carbon; Characterized by <1> Or <5> 10. The fraud confirmation device according to claim 9, wherein <7> The image characteristic detection unit The plurality of image regions are detected so as to include at least one region in which information visible under a visible light environment is clearly displayed. Characterized by <1> Or <6> 10. The fraud confirmation device according to claim 9, wherein <8> the image characteristic detection unit detects the image characteristics using any one of an average value of the image characteristics of the invisible light image, a standard deviation value of the image characteristics of the invisible light image, a median value of the image characteristics of the invisible light image, and a mode value of the image characteristics of the invisible light image. Characterized by <1> Or <7> 10. The fraud confirmation device according to claim 9, wherein <9> a notification unit that notifies an external device or a user of information that the state determination unit has determined that the subject is in the first state; Characterized by <1> Or <8> 10. The fraud confirmation device according to claim 9, wherein <10> a visible light source including light in at least the visible light wavelength range; a second image reader that can read at least a portion of the visible light reflected from the subject and acquire a visible light image from the reflected visible light; Equipped with Characterized by <1> Or <9> 10. The fraud confirmation device according to claim 9, wherein <11> an image forming unit that forms the visible light image of the subject on a recording medium; Characterized by <10> The fraud confirmation device described in <12> an image output unit that outputs the visible light image of the subject to an external device; Characterized by <10> The fraud confirmation device described in <13> In a system including a fraud confirmation device and a server, The fraud confirmation device a light source that irradiates an object with invisible light; an image reader that reads reflected light of one wavelength band from the subject, which is a portion of the invisible light, and acquires an invisible light image from the reflected light; an image characteristic detection unit that detects the same or different image characteristics for a plurality of image regions in the invisible light image; Equipped with The server a state determination unit that determines that the subject is in a first state based on the plurality of image characteristics detected by the image characteristic detection unit, The image characteristic detection unit detecting image characteristics of a first image area included in the plurality of image areas, with respect to an area of ​​the image formed by a material that absorbs at least invisible light; detecting image characteristics of a second image area included in the plurality of image areas, the second image area being formed of a material that does not absorb at least invisible light; the state determination unit determines that the subject is in a first state based on a first image characteristic of the first image area and a second image characteristic of the second image area; A system characterized by: <14> a light source that irradiates an object with invisible light; an image reader that reads reflected light of one wavelength band from the subject, which is part of the invisible light, and acquires an invisible light image from the reflected light; A fraud confirmation method in a fraud confirmation device comprising: an image characteristic detection step of detecting the same or different image characteristics for a plurality of image regions in the invisible light image; a state determination step of determining that the subject is in a first state based on the plurality of image characteristics detected in the image characteristic detection step; Including, The image characteristic detection step includes: detecting image characteristics of a first image area included in the plurality of image areas, with respect to an area of ​​the image formed by a material that absorbs at least invisible light; detecting image characteristics of a second image area included in the plurality of image areas, the second image area being formed of a material that does not absorb at least invisible light; the state determination step determines that the subject is in a first state based on a first image characteristic of the first image area and a second image characteristic of the second image area; A fraud confirmation method characterized by: [Explanation of symbols]

[0166] 1, 2 Fraud confirmation device 13, 401 light source 80 Image forming unit 305 Image output unit 402 Image reading unit 500 Image characteristic detection unit 600 Status determination unit 700 Notification Department [Prior art documents] [Patent documents]

[0167] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-246821

Claims

1. a light source that irradiates an object with invisible light; an image reader that reads reflected light of one wavelength band from the subject, which is a portion of the invisible light, and acquires an invisible light image from the reflected light; an image characteristic detection unit that detects the same or different image characteristics for a plurality of image regions in the invisible light image; a state determination unit that determines that the subject is in a first state based on the plurality of image characteristics detected by the image characteristic detection unit; Equipped with The image characteristic detection unit detecting image characteristics of a first image area included in the plurality of image areas, with respect to an area of ​​the image formed by a material that absorbs at least invisible light; detecting image characteristics of a second image area included in the plurality of image areas, the second image area being formed of a material that does not absorb at least invisible light; the state determination unit determines that the subject is in a first state based on a first image characteristic of the first image area and a second image characteristic of the second image area; A fraud confirmation device characterized by:

2. the state determination unit includes a threshold determination unit that determines whether the first image characteristic is equal to or less than a first threshold and whether the second image characteristic is equal to or greater than a second threshold; 2. The fraud confirmation device according to claim 1.

3. The image characteristic detection unit detecting the first image area as an image area containing text information; detecting the second image area to be an image area other than the image in which the character information is written; 2. The fraud confirmation device according to claim 1.

4. The image characteristic detection unit Detecting the second image region as a picture region; 4. The fraud confirmation device according to claim 3.

5. the invisible light contained in the light source is infrared light, the image reading unit reads reflected light in at least an infrared wavelength band; 2. The fraud confirmation device according to claim 1.

6. The image characteristic detection unit detecting the first image area as an area including an image formed of a material containing at least carbon; detecting the second image area to be an area of ​​an image formed of a material that does not contain at least carbon; 2. The fraud confirmation device according to claim 1.

7. The image characteristic detection unit The plurality of image regions are detected so as to include at least one region in which information visible under a visible light environment is clearly displayed.

2. The fraud confirmation device according to claim 1.

8. the image characteristic detection unit detects the image characteristics using any one of an average value of the image characteristics of the invisible light image, a standard deviation value of the image characteristics of the invisible light image, a median value of the image characteristics of the invisible light image, and a mode value of the image characteristics of the invisible light image.

2. The fraud confirmation device according to claim 1.

9. a notification unit that notifies an external device or a user of information that the state determination unit has determined that the subject is in the first state; 2. The fraud confirmation device according to claim 1.

10. a visible light source including light in at least the visible light wavelength range; a second image reader that can read at least a portion of the visible light reflected from the subject and acquire a visible light image from the reflected visible light; Equipped with 10. The fraud confirmation device according to claim 1.

11. an image forming unit that forms the visible light image of the subject on a recording medium; 11. The fraud confirmation device according to claim 10.

12. an image output unit that outputs the visible light image of the subject to an external device; 11. The fraud confirmation device according to claim 10.

13. In a system including a fraud confirmation device and a server, The fraud confirmation device a light source that irradiates an object with invisible light; an image reader that reads reflected light of one wavelength band from the subject, which is a portion of the invisible light, and acquires an invisible light image from the reflected light; an image characteristic detection unit that detects the same or different image characteristics for a plurality of image regions in the invisible light image; Equipped with The server a state determination unit that determines that the subject is in a first state based on the plurality of image characteristics detected by the image characteristic detection unit, The image characteristic detection unit detecting image characteristics of a first image area included in the plurality of image areas, with respect to an area of ​​the image formed by a material that absorbs at least invisible light; detecting image characteristics of a second image area included in the plurality of image areas, the second image area being formed of a material that does not absorb at least invisible light; the state determination unit determines that the subject is in a first state based on a first image characteristic of the first image area and a second image characteristic of the second image area; A system characterized by:

14. a light source that irradiates an object with invisible light; an image reader that reads reflected light of one wavelength band from the subject, which is part of the invisible light, and acquires an invisible light image from the reflected light; A fraud confirmation method in a fraud confirmation device comprising: an image characteristic detection step of detecting the same or different image characteristics for a plurality of image regions in the invisible light image; a state determination step of determining that the subject is in a first state based on the plurality of image characteristics detected in the image characteristic detection step; Including, The image characteristic detection step includes: detecting image characteristics of a first image area included in the plurality of image areas, with respect to an area of ​​the image formed by a material that absorbs at least invisible light; detecting image characteristics of a second image area included in the plurality of image areas, the second image area being formed of a material that does not absorb at least invisible light; the state determination step determines that the subject is in a first state based on a first image characteristic of the first image area and a second image characteristic of the second image area; A fraud confirmation method characterized by:

Images