JP2023137526A - Identification device, identification information registration device, identification system and identification method - Google Patents

Abstract

To provide an identification device for identifying identity between objects with high accuracy.SOLUTION: An identification device includes a storage device for storing first internal structure information obtained by measuring an internal structure of a reference object, and a processor. The processor acquires second internal structure information by measuring an internal structure of an object by a measurement device from the measurement device, and identifies whether to be the same object between the reference object and the object on the basis of the first internal structure information and the second internal structure information.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to an identification device, an identification information registration device, an identification system, and an identification method.

In order to identify the origin of objects such as manufactured products and parts, and to manage their distribution, it is necessary to identify the identity of items in the upstream and downstream areas of distribution. From this point of view, for example, Patent Document 1 compares the image features of an image of a satin pattern with the image features stored in an image feature storage means, and identifies parts, products, or products having parts as constituent elements. Disclose identification technology. The conventional technology disclosed in Patent Document 1 includes an information display body represented by at least one of characters and figures, which displays information regarding a part, a product, or a product having the component as a component; Information regarding the part or product is acquired based on a photographed image that includes at least the formed satin pattern.

Patent No. 6455679

However, there is a risk that information such as the information display body, satin pattern, etc. may be damaged, tampered with, etc. after the information is attached, for example, during the distribution process. If this information is changed, identity cannot be correctly identified, such as determining that objects that are not the same are the same.

The present disclosure aims to provide an identification device, an identification information registration device, an identification system, and an identification method that accurately identify the identity of an object.

One aspect of the present disclosure is
comprising a storage device that stores first internal structure information obtained by measuring the internal structure of a reference object; and a processor;
The processor includes:
acquiring second internal structure information obtained by the measuring device measuring the internal structure of the object from the measuring device;
identifying whether the reference object and the target object are the same object based on the first internal structure information and the second internal structure information;
Provide an identification device.

One aspect of the present disclosure is
comprising a processor that acquires the first internal structure information from a measuring device that measures the internal structure of the reference object and generates the first internal structure information;
The processor includes:
obtaining a first identifier for identifying the reference object, measurement condition information indicating conditions for measurement by the measurement device, and the first internal structure information;
registering the first identifier, the measurement condition information, and the first internal structure information in an internal or external storage device;
An identification information registration device is provided.

One aspect of the present disclosure is
An identification system comprising an identification information registration device and an identification device,
The identification information registration device includes:
comprising a first processor that acquires the first internal structure information from a first measuring device that measures the internal structure of a reference object and generates first internal structure information;
The first processor is
obtaining a first identifier for identifying the reference object, measurement condition information indicating conditions for measurement by the first measuring device, and first internal structure information;
registering the first identifier, the measurement condition information, and the first internal structure information in an internal or external storage device;
The identification device includes:
comprising a second processor that acquires the second internal structure information from a second measuring device that measures the internal structure of the object and generates second internal structure information;
The second processor is
acquiring the linked first identifier, the measurement condition information, and the first internal structure information from the storage device;
obtaining a second identifier attached to the object;
If the second identifier matches the first identifier, the second measuring device measures the internal structure of the object according to the measurement conditions indicated by the measurement condition information linked to the first identifier. control to measure, and obtain the second internal structure information, which is the measurement result, from the second measuring device;
identifying whether the reference object and the target object are the same object based on the first internal structure information and the second internal structure information;
Provide an identification system.

One aspect of the present disclosure is
a step in which the processor acquires, from a measurement device that measures the internal structure of the object, second internal structure information obtained by the measurement device measuring the internal structure of the object;
A processor determines that the reference object and the target object are the same object based on the first internal structure information obtained by measuring the internal structure of the reference object and the second internal structure information. a step of identifying whether there is a
Provide an identification method, including:

According to the identification device, identification information registration device, identification system, and identification method according to the present disclosure, the identity of an object can be identified with high accuracy.

A block diagram showing a configuration example of an identification system according to a first embodiment of the present disclosure A block diagram showing a configuration example of a reference data registration device according to the first embodiment A block diagram showing a configuration example of an identification device according to the first embodiment Flowchart illustrating the procedure of reference data registration processing according to the first embodiment Table showing an example of reference data of the first embodiment Flowchart illustrating the procedure of temperature image data analysis process S13 in FIG. 4 Phase and amplitude images of welded parts of objects Flowchart illustrating the procedure of identification processing according to the first embodiment A block diagram showing a configuration example of a reference data registration device according to a second embodiment A block diagram showing a configuration example of an identification device according to a second embodiment Flowchart illustrating the procedure of reference data registration processing according to the second embodiment Table showing an example of reference data of the second embodiment Flowchart illustrating the procedure of identification processing according to the second embodiment Table showing an example of reference data in the first modified example of the embodiment of the present disclosure

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings as appropriate. However, more detailed explanation than necessary may be omitted. For example, detailed explanations of well-known matters or redundant explanations of substantially the same configurations may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art. The applicant provides the accompanying drawings and the following description to enable those skilled in the art to fully understand the present disclosure, and they are not intended to limit the subject matter recited in the claims. do not have.

(First embodiment)
[1. composition]
[1-1. Overview of identification system configuration]
FIG. 1 is a block diagram showing a configuration example of an identification system 1 according to a first embodiment of the present disclosure. The identification system 1 includes a reference data registration device 10 and an identification device 20. The reference data registration device 10 is an example of the “identification information registration device” of the present disclosure.

The reference data registration device 10 generates reference data 19 including internal structure information of a reference object 91 such as a product or a product immediately after manufacturing. The internal structure of the reference object 91 is obtained by irradiating the reference object 91 with excitation energy from the excitation source 18 and capturing temperature image data of the reference object 91 with the infrared camera 17.

The reference data 19 includes information on a unique identifier (ID) attached to the reference object 91, and internal structure information, imaging conditions for temperature image data, etc. are linked to the corresponding ID. For example, when there are multiple reference objects 91, the ID is a serial number unique to each reference object 91. The ID is written on a sticker in the form of, for example, text, barcode, two-dimensional code, etc., and this sticker is pasted on the reference object 91. Alternatively, the ID may be written or stamped directly on the reference object 91.

The identification device 20 identifies whether the target object 92 is the same object as the reference object 91 or not. Specifically, for example, the identification device 20 acquires the ID by reading the ID given to the object 92. Alternatively, the ID assigned to the object 92 may be input by the user into the identification device 20 via an input device such as a keyboard. The identification device 20 uses the excitation source 28 and the infrared camera 27 to image the temperature image data of the object 92 under the same conditions as the imaging conditions of the temperature image data corresponding to the acquired ID, and captures the temperature image data of the object 92. Verification target data 26 including internal structure information is generated. The identification device 20 identifies whether the target object 92 is the same object as the reference object 91 by comparing the reference data 19 and the matching target data 26 .

Object fingerprint authentication technology is known that uses external appearance features such as irregularities on the surface exposed to the outside of an object such as a product or product as an object fingerprint. For example, during the distribution process, there is a risk of changes due to damage, tampering, etc. In the conventional technology, if appearance feature information is changed, there is a risk that objects that are not the same may be judged to be the same, and identity may not be correctly identified.

On the other hand, according to the identification system 1 according to the present embodiment, the identity of the target object 92 and the reference object 91 is determined based on the internal structure information such as internal features and defects of the reference object 91 and the target object 92. Can be identified. Internal structure information, unlike external features, is less likely to be easily damaged or changed.

Further, since the internal structure information includes internal features, defects, etc. that do not contribute to fatigue damage of the object 92, the identification system 1 can distinguish between the object 92 and the reference object even if the object 92 is damaged due to fatigue. 91 can be identified.

Furthermore, unlike external appearance features, internal structure information is impossible or difficult to visually recognize, so the identification system 1 can reduce the possibility that internal structure information will be artificially tampered with.

[1-2. Configuration of reference data registration device 10]
FIG. 2 is a block diagram showing a configuration example of the reference data registration device 10 according to the present embodiment. The reference data registration device 10 includes a CPU 11 , a storage device 12 , an input interface (I/F) 13 , and an output interface (I/F) 14 .

The CPU 11 implements the functions of the reference data registration device 10 by performing information processing. Such information processing is realized, for example, by the CPU 11 operating according to instructions from the program 15 stored in the storage device 12. The CPU 11 is an example of a processor according to the present disclosure. The processor may include an arithmetic circuit that performs arithmetic operations for information processing, and is not limited to a CPU. For example, the processor may be configured with a circuit such as an MPU or FPGA.

The storage device 12 is a recording medium that records various information including data and programs 15 necessary for realizing the functions of the reference data registration device 10. The storage device 12 is realized, for example, by a flash memory, a semiconductor storage device such as a solid state drive (SSD), a magnetic storage device such as a hard disk drive (HDD), or other recording medium alone or in combination. Storage device 12 may include volatile memory such as SRAM and DRAM.

The input interface 13 is an interface circuit that connects the reference data registration device 10 and an external device such as the infrared camera 17 in order to input information such as temperature image data from the infrared camera 17 into the reference data registration device 10. The input interface 13 may be a communication circuit that performs data communication according to existing wired communication standards or wireless communication standards.

The output interface 14 is an interface circuit that connects the reference data registration device 10 and an external output device in order to output information from the reference data registration device 10. Such output devices are, for example, the excitation source 18 and other information processing terminals such as server devices. The output interface 14 may be a communication circuit that performs data communication according to existing wired communication standards or wireless communication standards. Input interface 13 and output interface 14 may be realized by similar hardware.

The infrared camera 17 includes, for example, an infrared sensor that detects infrared rays having a wavelength of 3 μm to 15 μm. The excitation source 18 is, for example, a xenon lamp, a laser light source, a vibrator that generates ultrasonic waves, or a coil that generates electromagnetic induction, but is not limited to these, and may be any source that emits energy. For example, when the excitation source 18 is a xenon lamp or a laser light source, the excitation source 18 may pulse-heat the reference object 91 by emitting flash light. The wavelength of the light emitted by the excitation source 18 may be different from the wavelength of the infrared light detected by the infrared camera 17.

[1-3. Configuration of identification device 20]
FIG. 3 is a block diagram showing a configuration example of the identification device 20 according to this embodiment. The identification device 20 includes a CPU 21, a storage device 22, an input interface (I/F) 23, and an output interface (I/F) 24.

The CPU 21 implements the functions of the identification device 20 by performing information processing. Such information processing is realized, for example, by the CPU 21 operating in accordance with instructions from the program 25 stored in the storage device 22. The CPU 21 is an example of a processor according to the present disclosure.

The storage device 22 is a recording medium that records various information including data and programs 25 necessary to realize the functions of the identification device 20. The storage device 22 may have a similar configuration to the storage device 12.

The input interface 23 is an interface circuit that connects the identification device 20 and an external device such as the infrared camera 27 in order to input information such as temperature image data and reference data 19 from the infrared camera 27 to the identification device 20. The input interface 23 may be a communication circuit that performs data communication according to existing wired communication standards or wireless communication standards.

The output interface 24 is an interface circuit that connects the identification device 20 and an external output device in order to output information from the identification device 20. Such output devices are, for example, the excitation source 28, the notification device 29, and other information processing terminals such as a server device. The output interface 24 may be a communication circuit that performs data communication according to existing wired communication standards or wireless communication standards. Input interface 23 and output interface 24 may be realized by similar hardware.

Infrared camera 27 and excitation source 28 have similar configurations to infrared camera 17 and excitation source 18, respectively.

[2. motion]
[2-1. Reference data registration process]
FIG. 4 is a flowchart illustrating the procedure of reference data registration processing according to this embodiment. The reference data registration process in FIG. 4 is executed by the CPU 11 of the reference data registration device 10.

First, the CPU 11 sets generation conditions (measurement conditions) for temperature image data (S11). In this embodiment, the temperature image data is image data generated by active thermography. Therefore, the generation conditions for the temperature image data set in step S11 include, for example, the thermography photographing conditions such as the frame rate of the temperature image data, the photographing time, and the integration time, the excitation method of the excitation source 18, the power, the irradiation time, etc. and excitation conditions such as irradiation frequency.

Next, the CPU 11 generates temperature image data based on the generation conditions set in step S11 (S12). For example, the CPU 11 operates the excitation source 18 in accordance with the excitation conditions set in step S11, photographs the reference object 91 in accordance with the photographing conditions set in step S11, and generates temperature image data. The temperature image data generated in step S12 may be subsequently processed in the next step S13, or may be stored in the storage device 12 or an external server device, storage device, or the like.

In active thermography, the infrared camera 27 captures temperature images in time series while applying excitation energy to the reference object 91 by the excitation source 18 . According to active thermography, the internal structure of the reference object 91 can be observed based on the temperature change of the reference object 91 caused by the excitation energy given by the excitation source 18.

Next, the CPU 11 analyzes the temperature image data generated in step S12 (S13). Through the temperature image data analysis process S13, internal features, defects, and other internal structures of the reference object 91 can be specified. Details of the temperature image data analysis process S13 will be described later.

The CPU 11 links the temperature image data generation conditions set in step S11 and the analysis result of the temperature image data analysis process S13 to the ID of the reference object 91 to generate reference data 19 (S14). The generated reference data 19 is outputted via the output interface 14, for example, and registered in an external storage device such as a server device. Alternatively, reference data 19 may be stored in storage device 12.

FIG. 5 is a table showing an example of the reference data 19. The reference data 19 includes the ID of the reference object 91, the model number of the reference object 91 linked to each ID, temperature image data, generation conditions of the temperature image data, analysis conditions of the temperature image data analysis process S13, analysis results, and feature data are stored. The reference data 19 is used by the identification device 20 to match the reference object 91 and the target object 92 .

[2-2. Temperature image data analysis processing S13]
FIG. 6 is a flowchart illustrating the procedure of the temperature image data analysis process S13 in FIG. 4. In the temperature image data analysis process S13, the CPU 11 first obtains the temperature image data generated in step S12 of FIG. 4 (S131).

Next, the CPU 11 sets analysis conditions indicating conditions for analysis to be performed on the temperature image data (S132). The analysis conditions include, for example, the frame range of the temperature image to be analyzed, the sampling period when acquiring the temperature images in time series, the frequency range of the filter to be used, the analysis frequency in Fourier transform, and the like. The analysis conditions may be determined in advance.

Next, the CPU 11 performs Fourier transformation on the temperature image data acquired in step S131 according to the analysis conditions set in step S132 (S133). Fourier transform is an example of the "orthogonal transform" of this disclosure. For example, the CPU 11 analyzes the temperature image data by performing Fourier transform in the time direction on temperature changes in each pixel of the temperature image.

When analyzing time-series data of temperature images, the CPU 11 can acquire a phase image and an amplitude image in which depth information of the internal structure is reflected according to the frequency band of the applied filter. Here, the "depth information" of objects such as the reference object 91 and the target object 92 is, for example, information regarding the depth from the surface of the object. The surface of the object is, for example, the outer surface of the object that is exposed to an infrared camera and/or an excitation source. By acquiring a phase image and an amplitude image in which depth information is reflected, it is possible to understand internal structure information of an object in a more three-dimensional manner. A phase image and an amplitude image in which such depth information of the internal structure is reflected will be explained using FIG. 7.

FIG. 7 shows phase and amplitude images of a welded portion of an object. If a filter containing A [Hz] in the frequency band is provided, a phase image and an amplitude image of the superficial layer can be obtained, and if a filter containing B [Hz] in the frequency band is provided, it is possible to obtain a middle layer deep than the superficial layer. A phase image and an amplitude image can be obtained. Furthermore, by providing a filter whose band frequency includes C [Hz], it is possible to obtain a phase image and an amplitude image of the deep layer, which is deeper than the middle layer. Here, A>B>C.

Since the shape of the internal structure changes depending on the depth, in both the phase image and the amplitude image in FIG. 7, when the frequency band of the applied filter changes, the images also change. This change allows us to understand the difference in internal structure depending on the depth from the object's surface, making it possible to understand the internal structure information of the object in a more three-dimensional manner. The amplitude image reflects the effects of both the surface state and internal structure of the object. In a phase image, the influence of the state of the object's surface is reduced, and the influence of the internal structure is more strongly reflected.

Note that not only the temperature image data of the welded part but also the temperature image data of the welded part or the bonded part can be analyzed to obtain a phase image and an amplitude image that reflect the depth information of the internal structure.

The CPU 11 may perform filter processing on the Fourier-transformed temperature image data using an image processing filter such as a high-pass filter that can emphasize the edges of the temperature image or a Gaussian filter that smooths the temperature image ( S134).

The CPU 11 may execute a process of extracting the feature amount of the Fourier-transformed temperature image data after step S133 or after step S134. The extracted feature amount is stored in the reference data 19 as feature data.

In addition, in the temperature image data analysis process S13, in order to absorb operational errors of the infrared camera 17 and/or the CPU 11, errors caused by the external environment, etc., the CPU 11 performs normalization processing and/or binary value processing on the temperature image data. A chemical treatment may be applied.

The normalization process is executed by the CPU 11 using, for example, the amount of phase change or the amount of amplitude change of a specific region or the entire temperature image data as target data. For example, in the normalization process, the CPU 11 normalizes the target data so that the minimum value of the normalized data is 0 and the maximum value is 1. Alternatively, the CPU 11 normalizes the target data so that the average of the normalized data is 0 and the variance is 1.

The CPU 11 executes binarization processing using, for example, a brightness value histogram of the temperature image data. At this time, the CPU 11 sets pixels of the temperature image data whose pixel values are greater than or equal to a predetermined threshold value to white, and sets pixels whose pixel values are less than the predetermined threshold value to black. For example, known methods such as the P-tile method, mode method, discriminant analysis method, dynamic threshold determination method, level slice method, Laplacian histogram method, differential histogram method, etc. may be used for the binarization process.

The processing by the image processing filter, normalization processing, and binarization processing as described above may be performed on one or more temperature images captured by the infrared camera 17, and the obtained amplitude image, It may also be performed on phase images and the like.

[2-2. Identification processing]
FIG. 8 is a flowchart illustrating the procedure of the identification process according to this embodiment. The identification process in FIG. 8 is executed by the CPU 21 of the identification device 20.

First, the CPU 21 acquires the ID of the target object 92 (S21). For example, a sticker is pasted on the front, side, back, etc. of the object 92, and the ID is written on the sticker in the form of text, barcode, two-dimensional code, or the like. Alternatively, the ID may be written or stamped directly on the object 92.

Next, the CPU 21 obtains the reference data 19 corresponding to the ID obtained in step S21 from the storage device in which the reference data 19 is stored (S22).

The CPU 21 acquires the generation conditions for the temperature image data linked to the ID acquired in step S21 from the reference data 19 acquired in step S22, and sets the generation conditions for the infrared camera 27 and the excitation source 28 ( S23).

Next, the CPU 21 generates temperature image data based on the generation conditions set in step S23 (S24). The temperature image data generation process S24 is similar to the temperature image data generation process S12 in FIG. 4.

The CPU 21 analyzes the temperature image data generated in step S24 (S25). The temperature image data analysis process S25 is the same process as the temperature image data analysis process S13 in FIG. The CPU 21 may store the result of the temperature image data analysis process S25 in the storage device 22 as the verification target data 26.

Next, the CPU 21 compares the result of the temperature image data analysis process S25 with the analysis result in the reference data 19 (S26). The matching process includes identifying the identity of the target object 92 and the reference object 91. In step S26, for example, the CPU 21 calculates the degree of coincidence, which is an index indicating the degree of coincidence between the result of the temperature image data analysis process S25 and the analysis result in the reference data 19, and if the degree of coincidence is equal to or higher than a predetermined threshold, If so, it is determined that the target object 92 is the same object as the reference object 91 .

The objects to be compared in step S26 may be the temperature images of the target object 92 and the reference object 91 themselves, or may be Fourier-transformed temperature image data. When the temperature image data is subjected to filter processing, the object of comparison in step S26 may be the temperature image data of the target object 92 and the reference object 91 after the filter processing. When the feature amount of the temperature image data is extracted, the object of verification in step S26 may be the feature amount of the target object 92 and the reference object 91.

The CPU 21 outputs the result of the verification process in step S26 to, for example, the storage device 22, the notification device 29, or an external storage device such as a server device (S27). For example, when the CPU 21 identifies that the target object 92 is not the same object as the reference object 91 as a result of the matching process in step S26, the notification device 29 notifies the user of information indicating the identification result.

[3. Effects, etc.]
As described above, the identification device 20 includes the infrared camera 27 (measuring device) that measures the internal structure of the target object 92 and the reference data 19 (first internal data) obtained by measuring the internal structure of the reference object 91. The CPU 21 includes a storage device 22 that stores structure information) and a CPU 21. The CPU 21 acquires the verification target data 26 (second internal structure information) obtained by the infrared camera 27 measuring the internal structure of the object 92 from the infrared camera 27, and compares the reference data 19 and the verification target data 26. Based on this, it is determined whether the reference object 91 and the target object 92 are the same object.

According to this configuration, the identification device 20 can accurately identify the identity of an object. For example, the identification device 20 can identify the identity of the target object 92 and the reference object 91 based on internal structural information such as internal features and defects of the reference object 91 and the target object 92 . Internal structure information, unlike external features, is less likely to be easily damaged or changed. Since the internal structure information includes internal features, defects, etc. that do not contribute to fatigue damage of the object 92, the identification device 20 can distinguish between the object 92 and the reference object 91 even if the object 92 is damaged due to fatigue. can identify the identity of Unlike external appearance features, internal structure information is impossible or difficult to visually recognize, so the identification device 20 can reduce the possibility that internal structure information will be artificially tampered with.

The reference data 19 may be information obtained by measuring the internal structure of the reference object 91 according to predetermined measurement conditions. The storage device 22 may store the first ID for identifying the reference object 91 in association with measurement condition information indicating predetermined measurement conditions. The CPU 21 acquires the second ID associated with the object 92, and when the second ID matches the first ID, the infrared camera 27 performs a predetermined measurement associated with the first ID. The internal structure of the object 92 may be controlled to be measured according to the conditions, and the measurement results as the verification target data 26 may be obtained from the infrared camera 27.

According to this configuration, in addition to the above-mentioned effects, by linking the first ID, product, and measurement conditions, unified management can be performed, and inspection falsification such as internal structure information being artificially tampered can be prevented. can.

The infrared camera 27 may be a thermographic device utilized with an excitation source 28 that emits excitation energy to the object 92. The reference data 19 may be information obtained by the same or other thermography apparatus as the thermography apparatus. The CPU 21 controls the excitation source 28 to apply excitation energy to the object 92 by the excitation source 28, and acquires the captured temperature image from the infrared camera 27, thereby acquiring the verification target data 26. good.

By obtaining an infrared thermography image using the excitation source 28, the internal structure of the object can be grasped with higher accuracy, and the identity of the object can be identified with higher accuracy.

The temperature image may be a plurality of temperature images captured in time series.

According to this configuration, by using time-series data, the influence of differences in the external environment and the emissivity of the object surface can be reduced in the identification process, and the identity of the object can be identified with higher accuracy.

The reference data 19 may be information based on temperature changes of the reference object 91. The verification target data 26 may be information based on the temperature change of the object 92 caused by the excitation energy given by the excitation source 28.

With this configuration as well, it is possible to more accurately grasp the internal structure of an object, and to identify the identity of the object more accurately.

The reference data 19 may include depth information of the reference object 91 , and the verification target data 26 may include depth information of the target object 92 .

Differences in the internal structure of an object depending on the depth information can be seen, allowing a more three-dimensional understanding of the internal structure information of the object.

The reference data 19 may be information based on the phase of temperature change of the reference object 91 , and the verification target data 26 may be information based on the phase of temperature change of the target object 92 .

According to this configuration, by using information based on the phase, it is possible to reduce the influence of the shapes of the surfaces of the reference object 91 and the target object 92, the emissivity of the materials of the surfaces, and the like.

The CPU 21 orthogonally transforms the temperature image data shown by the temperature images showing the temperature of the object 92 captured in time series by the infrared camera 27, thereby determining the phase of temperature change in a part of the object 92 and the temperature change of a portion of the object 92. The phase of temperature change in other parts of the area may also be calculated.

According to this configuration, by using information based on the phase, it is possible to reduce the influence of the shapes of the surfaces of the reference object 91 and the target object 92, the emissivity of the materials of the surfaces, and the like.

The reference data 19 and the matching target data 26 may be normalized and/or binarized information.

According to this configuration, operational errors of the infrared cameras 17, 27 and/or CPUs 11, 21, errors due to the external environment, etc. can be absorbed, and the identity of objects can be identified with higher accuracy.

The identification device 20 may further include a notification device 29 that notifies the user of information. The CPU 21 may notify the user of information indicating the identification result using the notification device 29.

According to this configuration, the user can know the identity identification result. In particular, the identification device 20 identifies an abnormal situation in which the reference object 91 and the target object 92 are not the same object, even though the same ID is attached to the reference object 91 and the target object 92. The user can be notified immediately.

(Second embodiment)
An identification system according to a second embodiment of the present disclosure will be described using FIGS. 9 to 13. Compared to the first embodiment, in the second embodiment, the identification system uses not only the internal structure information obtained by the infrared camera but also the external appearance information obtained by the visible light camera to identify the object 92 and the reference. Identity with object 91 is identified.

FIG. 9 is a block diagram showing a configuration example of the reference data registration device 210 according to this embodiment. Compared to the reference data registration device 10 according to the first embodiment shown in FIG. This differs from the reference data registration device 10 in that it is acquired.

The visible light camera 217 is an example of the "imaging device" of the present disclosure, and generates a captured image using a solid-state imaging device such as a CMOS (Complementary MOS) or a CCD (Charge Coupled Device).

FIG. 10 is a block diagram showing a configuration example of the identification device 220 according to this embodiment. Compared to the identification device 20 according to the first embodiment shown in FIG. , is different from the identification device 20. The visible light camera 227 has the same configuration as the visible light camera 217.

FIG. 11 is a flowchart illustrating the procedure of reference data registration processing according to this embodiment. Steps S11 to S13 in FIG. 11 are similar to steps S11 to S13 in the first embodiment shown in FIG.

In this embodiment, the CPU 11 sets visible image data generation conditions (S15). The visible image data generation conditions include, for example, the frame rate of the visible image data, the shooting time, the distance between the reference object 91 and the visible light camera 227, lens information, and the like.

Next, the CPU 11 acquires visible image data captured by the visible light camera 217 based on the visible image data generation conditions set in step S15 (S16).

At this time, the CPU 11 may acquire visible image data including the measurement location of the temperature image data, such as the welded portion of the reference object 91, and may record it in the storage device 12 or an external storage device such as a server device. By recording the measurement points of the reference object 91 in advance in this way, it is possible to refer to the measurement points recorded when comparing the target object 92. As a result, instead of processing the temperature image data for all parts of the target object 92 during verification, it is only necessary to process the temperature image data near the part corresponding to the recorded measurement point of the reference object 91. The data processing amount and processing load of the CPU 11 can be reduced.

Next, the CPU 11 analyzes the visible image data acquired in step S16 (S17). Through the visible image data analysis process S17, the CPU 11 can obtain appearance information such as the appearance, dimensions, presence or absence of scratches, and shape of the reference object 91. The CPU 11 may perform filter processing on visible image data, processing for extracting feature amounts of visible image data, and the like.

Next, the CPU 11 uses the temperature image data generation conditions set in step S11, the analysis results of the temperature image data analysis process S13, the visible image data generation conditions set in step S15, and the visible image data analysis process. The analysis result of S17 is linked to the ID of the reference object 91 to generate reference data 219 (S14). FIG. 12 is a table showing an example of the reference data 219. The generated reference data 219 is outputted via the output interface 14, for example, and registered in an external storage device such as a server device.

FIG. 13 is a flowchart illustrating the procedure of the identification process according to this embodiment. Steps S21 to S25 and S27 in FIG. 13 are similar to steps S21 to S25 and S27 in the first embodiment shown in FIG. 8, respectively.

In the present embodiment, the CPU 21 acquires the generation conditions for visible image data linked to the ID acquired in step S21 from the reference data 19 acquired in step S22, and sets the generation conditions in the visible light camera 227. (S221).

Next, the CPU 21 acquires visible image data captured by the visible light camera 217 based on the generation conditions set in step S221 (S222), and analyzes the acquired visible image data (S223). The visible image data analysis process S223 is the same process as the visible image data analysis process S17 in FIG.

Next, the CPU 21 collates the results of the temperature image data analysis process S25 and/or the results of the visible image data analysis process S223 with the analysis results in the reference data 219 (S224), and transfers the collation results to the storage device 22, the notification device 29 or to an external storage device such as a server device (S27).

In step S26 of the first embodiment, the CPU 21 determines that if the degree of coincidence between the temperature image data analysis process S25 and the analysis result in the reference data 19 is greater than or equal to a predetermined threshold Th1, It is determined that the object is the same as the object. The degree of matching is, for example, a normalized index that can take a value between 0 and 1.

On the other hand, in step S224 of the present embodiment, the CPU 21 determines that the target object 92 is the same object as the reference object 91, for example, when at least one of the following conditions is satisfied.
(i) The degree of coincidence between the result of the temperature image data analysis process S25 and the temperature image data analysis result in the reference data 219 is greater than or equal to the predetermined threshold Th1.
(ii) The degree of coincidence between the result of the visible image data analysis process S223 and the visible image data analysis result in the reference data 219 is greater than or equal to the predetermined threshold Th2.
(iii) The degree of coincidence between the result of the temperature image data analysis process S25 and the temperature image data analysis result in the reference data 219 is equal to or higher than a predetermined threshold Th3, and the result of the visible image data analysis process S223 and the reference data The degree of coincidence with the visible image data analysis result in 219 is greater than or equal to a predetermined threshold Th4.
Here, Th3<Th1 and Th4≦Th2.

Even if the target object 92 is actually the same as the reference object 91, if only the degree of coincidence regarding temperature image data is used without using a visible image, if the degree of coincidence is lower than Th1, the object 92 will be the same as the reference object 91. There is a possibility that it cannot be determined that the object is the same as object 91. On the other hand, according to condition (iii) of the present embodiment, even if the degree of coincidence regarding temperature image data is lower than the threshold Th1 determined in the first embodiment that does not use a visible image, as long as it is equal to or higher than the threshold Th3, It may be possible to determine that the target object 92 is the same object as the reference object 91. In this way, by considering not only the degree of correspondence regarding temperature image data but also the degree of correspondence regarding visible image data, it is possible to reduce the possibility of misidentification.

Note that in condition (iii) of the present embodiment, an example has been described in which the results of the temperature image data analysis process and the results of the visible image data analysis process are considered together in calculating the degree of coincidence. The plurality of data used for matching the object 91 is not limited to this. For example, an amplitude image and a phase image may be used together.

(Other embodiments)
As mentioned above, the above embodiment has been described as an example of the technology disclosed in this application. However, the technology in the present disclosure is not limited to this, and can also be applied to embodiments in which changes, replacements, additions, omissions, etc. are made as appropriate. Therefore, a modified example as another embodiment will be shown below.

(First modification)
In the above embodiment, an ID, which is a serial number, is used as an example of an identifier. However, the identifier of the present disclosure is not limited to this, and may be any identifier that can uniquely refer to conditions such as generation conditions and analysis conditions of temperature image data. For example, the identifier may be a model number of an object such as a product.

FIG. 14 is a table showing an example of reference data 319 when a model number is used as an identifier. Unlike an ID, which is a serial number, a model number usually corresponds to a plurality of products. Further, in this case, the generation conditions and analysis conditions of the temperature image data in the reference data 319 are generally the same if the model numbers are the same. Therefore, by using the model number as an identifier, conditions such as generation conditions and analysis conditions of temperature image data can be uniquely referenced. Further, in the reference data 319, manufacturing information such as manufacturing location and manufacturing time is linked to the model number.

As a result, if a defect is found in the target object 92 and the identity of the target object 92 and the reference object 91 can be identified, the reference data 319 can be referred to to identify products that may have the same defect. It is possible to specify the manufacturing location and manufacturing time, such as the factory where the product was manufactured. In this way, according to this modification, the identification system 1 can be used to investigate the factory, product lot, manufacturing date, etc. that caused the product defect.

Note that although the generation conditions and analysis conditions for temperature image data are usually different for different model numbers, they are not necessarily different for different model numbers. For example, the generation conditions and analysis conditions of temperature image data for products with model number B1 and model number B2 are different, but the generation conditions and analysis conditions of temperature image data for products with model number B1 and model number B3 may be the same.

(Second modification)
In the above embodiment, an example has been described in which temperature image data analysis processes S13 and S25 are executed, as shown in FIGS. 4 and 7, for example. However, the identification system according to the present disclosure is not limited to the above example as long as it can match the temperature image of the reference object 91 and the temperature image of the target object 92. For example, the temperature image data analysis processes S13 and S25 may not be executed, and in step S26 of FIG. 8, the temperature images of the reference object 91 and the target object 92 may be compared with each other.

(Third modification)
In the embodiment described above, Step S133 is illustrated in which Fourier transform is performed on temperature image data as an example of orthogonal transform. However, the orthogonal transformation is not limited to this, and may be, for example, a discrete Fourier transform (DFT).

(Fourth modification)
In the embodiment described above, an example has been described in which the temperature image is obtained by active thermography, but the temperature image may also be obtained by passive thermography.

(Fifth modification)
In the above embodiment, an example has been described in which the internal structures of the target object 92 and the reference object 91 are measured by infrared thermography, but the measurement method is not limited to infrared thermography. For example, the identification system 1 measures the internal structure of the target object 92 and the reference object 91 using a non-destructive inspection method such as radiography such as X-rays, ultrasonic flaw detection, or eddy current flaw detection instead of infrared thermography. It's okay.

The present disclosure is applicable to identification systems that identify the identity of objects.

1 Identification system 10, 210 Reference data registration device 12 Storage device 13 Input interface 14 Output interface 15 Program 17 Infrared camera 18 Excitation source 19, 219, 319 Reference data 20, 220 Identification device 22 Storage device 23 Input interface 24 Output interface 25 Program 26 Verification target data 27 Infrared camera 28 Excitation source 29 Notification device 91 Reference object 92 Target object 217, 227 Visible light camera

Claims (18)

comprising a storage device that stores first internal structure information obtained by measuring the internal structure of a reference object; and a processor;
The processor includes:
acquiring second internal structure information obtained by the measuring device measuring the internal structure of the object from the measuring device;
identifying whether the reference object and the target object are the same object based on the first internal structure information and the second internal structure information;
Identification device. The first internal structure information is information obtained by measuring the internal structure of the reference object according to predetermined measurement conditions,
The storage device stores a first identifier for identifying the reference object in association with measurement condition information indicating the predetermined measurement condition,
The processor includes:
obtaining a second identifier associated with the object;
If the second identifier matches the first identifier, the measuring device is controlled to measure the internal structure of the object according to the predetermined measurement condition linked to the first identifier. , acquiring a measurement result as the second internal structure information from the measurement device;
The identification device according to claim 1. The identification device according to claim 2, wherein the first identifier is a serial number unique to the reference object. The identification device according to claim 2, wherein the first identifier includes information regarding at least one of a manufacturing location, manufacturing time, or model number of the reference object. The measuring device is a thermography device including an excitation source that emits excitation energy to the object, and an infrared camera that uses infrared rays to capture a temperature image indicating the temperature of the object,
The first internal structure information is information obtained by the same or different thermography device as the thermography device,
The processor controls the excitation source to apply excitation energy to the object by the excitation source, and obtains the second internal structure information by acquiring the captured temperature image from the infrared camera. obtain,
An identification device according to any one of claims 1 to 4. The identification device according to claim 5, wherein the temperature image is a plurality of temperature images taken in time series. The first internal structure information is information based on a temperature change of the reference object,
The second internal structure information is information based on a temperature change of the object caused by excitation energy given by the excitation source.
The identification device according to claim 5 or 6. The first internal structure information includes depth information of the reference object,
the second internal structure information includes depth information of the object;
An identification device according to any one of claims 1 to 7.
The first internal structure information is information based on the phase of temperature change of the reference object,
The second internal structure information is information based on a phase of temperature change of the object,
The identification device according to claim 8. The processor performs orthogonal transformation on temperature image data shown by temperature images showing the temperature of the object captured in time series by an infrared camera, thereby determining the phase of temperature change in a portion of the object and the object. The identification device according to claim 9, which calculates a phase of a temperature change in another part of the inside. The identification device according to claim 1, wherein the first internal structure information and the second internal structure information are normalized and/or binarized information. Further comprising a notification device for notifying the user of information,
The processor notifies the user of information indicating the identification result using the notification device.
An identification device according to any one of claims 1 to 11. The identification device according to any one of claims 1 to 12, wherein the storage device further records information regarding a measurement location of the reference object measured when acquiring the first internal structure information. further comprising an imaging device for imaging the appearance of the object,
The storage device further stores first appearance information obtained by imaging the appearance of the reference object,
The processor includes:
obtaining second appearance information obtained by imaging the appearance of the object from the imaging device;
Based on a comparison between the first internal structure information and the second internal structure information and a comparison between the first appearance information and the second appearance information, the reference object and the target object are determined. identify whether they are the same object or not,
An identification device according to any one of claims 1 to 13. comprising a processor that acquires the first internal structure information from a measuring device that measures the internal structure of the reference object and generates the first internal structure information;
The processor includes:
obtaining a first identifier for identifying the reference object, measurement condition information indicating conditions for measurement by the measurement device, and the first internal structure information;
registering the first identifier, the measurement condition information, and the first internal structure information in an internal or external storage device;
Identification information registration device. The measuring device is a thermography device including an excitation source that emits excitation energy to the reference object, and an infrared camera that uses infrared rays to capture a temperature image indicating the temperature of the reference object,
The processor controls the excitation source to apply excitation energy to the reference object by the excitation source, and obtains the first internal structure information by acquiring the captured temperature image from the infrared camera. obtain,
The identification information registration device according to claim 15. An identification system comprising an identification information registration device and an identification device,
The identification information registration device includes:
comprising a first processor that acquires the first internal structure information from a first measuring device that measures the internal structure of a reference object and generates first internal structure information;
The first processor is
obtaining a first identifier for identifying the reference object, measurement condition information indicating conditions for measurement by the first measuring device, and first internal structure information;
registering the first identifier, the measurement condition information, and the first internal structure information in an internal or external storage device;
The identification device includes:
comprising a second processor that acquires the second internal structure information from a second measuring device that measures the internal structure of the object and generates second internal structure information;
The second processor is
acquiring the linked first identifier, the measurement condition information, and the first internal structure information from the storage device;
obtaining a second identifier attached to the object;
If the second identifier matches the first identifier, the second measuring device measures the internal structure of the object according to the measurement conditions indicated by the measurement condition information linked to the first identifier. control to measure, and obtain the second internal structure information, which is the measurement result, from the second measuring device;
identifying whether the reference object and the target object are the same object based on the first internal structure information and the second internal structure information;
identification system. a step in which the processor acquires, from a measurement device that measures the internal structure of the object, second internal structure information obtained by the measurement device measuring the internal structure of the object;
A processor determines that the reference object and the target object are the same object based on the first internal structure information obtained by measuring the internal structure of the reference object and the second internal structure information. a step of identifying whether there is a
methods of identification, including:

Images