KR20230006939A - Method and apparatus for discriminating between original image and forgery image based on adding noise - Google Patents

Abstract

The present disclosure relates to a method and apparatus for discriminating between an original image and a forgery image using noise addition. A method for discriminating between an original image and a forgery image according to some embodiments of the present disclosure, performed by a computing device, may include the steps of: detecting an object region included in an input image; applying noise to at least a part of the input image based on the detected object region; and performing out-of-distribution (OOD) detection on the input image to which the noise is applied.

Description

Forgery image determination method and device using noise addition

The present disclosure relates to a method and apparatus for determining a forged image using noise addition. More specifically, based on the object region of the input image, noise is added to at least a part of the input image, and OOD (Out-Of-Distribution) detection is performed on the noise-added input image, thereby determining the performance of forgery image determination. It relates to a method and apparatus capable of improving

Damage caused by forged or altered images, such as deepfake images, is increasing rapidly with the advent of the Internet of Things (IoT) era. The victims range from entertainers to the general public, and forged images are used in various crimes such as digital sex crimes, illegal copying, and copyright infringement. Furthermore, damage caused by forged images (e.g., deepfake images) in which images are forged frame by frame of the video is also increasing with the development of computing devices.

Forged images and forged images produced using advanced artificial intelligence technology have a problem in that it is difficult to determine whether or not they have been forged or altered with the naked eye of a person. In addition, such forgery or falsification technology has a problem in that it is rapidly evolving along with the development of artificial intelligence technology.

Therefore, in order to prevent damage caused by forged images and forged images, a technique for determining forged images and forged images is required.

Korean Patent Publication No. 10-2020-0091799 (published on January 23, 2019)

A technical problem to be solved through some embodiments of the present disclosure is to provide a device for determining a forged image and a method performed by the device.

Another technical problem to be solved through some embodiments of the present disclosure is to provide a device capable of improving the performance of forgery and forgery image determination and a method performed by the device.

Another technical problem to be solved through some embodiments of the present disclosure is to provide an apparatus for determining an application area of noise for improving the performance of forgery and forgery image determination and a method performed by the apparatus.

Another technical problem to be solved through some embodiments of the present disclosure is to provide a device for determining a type of noise for improving the performance of forgery and forgery image determination and a method performed by the device.

The technical problems of the present disclosure are not limited to the above-mentioned technical problems, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

In order to solve the above technical problem, a forgery image determination method according to some embodiments of the present disclosure is a method performed by a computing device, comprising: detecting an object region included in an input image; Based on this, the method may include applying noise to a part of the input image and performing out-of-distribution (OOD) detection on the input image to which the noise is applied.

In some embodiments, the applying of the noise includes applying noise to at least a part of the detected object region, or includes applying noise to an edge of the detected object region, or includes applying noise to an edge of the detected object region. When the input image includes a plurality of object areas including a first object area and a second object area, applying noise to an area where the first object area and the second object area overlap, or the input image Converting to the frequency domain and applying noise to a region of a reference frequency or higher among regions included in the input image converted to the frequency domain, or applying a first noise to a part of the input image and the input image. determining a noise to be applied to a portion of the input image based on a property of the detected object region, and applying a second noise distinct from the first noise to a portion of the image; It may include applying to a part of the input image.

In some embodiments, the performing of the OOD detection may include determining whether a plurality of classes determined based on a plurality of original images and a class having a degree of relevance to the input image equal to or greater than a reference value exist. there is. Here, as a result of determining the degree of relevance, if a class having a degree of relevance with the input image equal to or greater than a reference value exists, the step of determining the input image as an original image is further included, or as a result of determining the degree of relevance, the class with the input image The method may further include determining the input image as a forged image if there is no class in which the degree of relevance of is greater than or equal to a reference value. In addition, the step of determining whether a class having a degree of relevance greater than or equal to a reference value may include calculating a degree of relevance between the input image and each of the plurality of classes, and whether the maximum value of the calculated degree of relevance is equal to or greater than the reference value. It may include a step of determining.

An apparatus for determining a forged or altered image according to some embodiments of the present disclosure includes a processor, a network interface, a memory, and a computer program loaded into the memory and executed by the processor, wherein the computer program includes an input image An instruction for detecting an included object region, an instruction for applying noise to a part of the input image based on the detected object region, and OOD (Out-Of-Distribution) detection for the input image to which the noise is applied It may contain instructions that perform. Here, a camera may be further included.

1 illustrates an exemplary environment to which a forgery image determination device according to some embodiments of the present disclosure may be applied.
2 is an exemplary flowchart illustrating a forgery image determination method according to some embodiments of the present disclosure.
3 and 4 are exemplary flowcharts for explaining in detail the operation of applying noise described with reference to FIG. 2 .
FIG. 5 is an exemplary flowchart for more specifically describing an out-of-distribution (OOD) detection operation described with reference to FIG. 2 .
FIG. 6 is an exemplary flowchart for explaining the relevance determination operation described with reference to FIG. 5 in more detail.
7 to 10 are exemplary diagrams for describing noise application areas that may be referred to in some embodiments of the present disclosure.
11 and 12 are exemplary diagrams for explaining a conversion operation to a frequency domain and an application operation of noise that may be referred to in some embodiments of the present disclosure.
13 is an exemplary diagram for describing an OOD detection operation that may be referred to in some embodiments of the present disclosure in more detail.
FIG. 14 is a diagram for explaining an example in which the OOD detection operation described with reference to FIG. 13 is applied to an image.
15 is an exemplary hardware configuration diagram in which an apparatus according to some embodiments of the present disclosure may be implemented.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Advantages and features of the present disclosure, and methods of achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the technical idea of the present disclosure is not limited to the following embodiments and can be implemented in various different forms, and only the following embodiments complete the technical idea of the present disclosure, and in the technical field to which the present disclosure belongs. It is provided to completely inform those skilled in the art of the scope of the present disclosure, and the technical spirit of the present disclosure is only defined by the scope of the claims.

In adding reference numerals to components of each drawing, it should be noted that the same components have the same numerals as much as possible even if they are displayed on different drawings. In addition, in describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present disclosure, the detailed description will be omitted.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those of ordinary skill in the art to which this disclosure belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined. Terminology used herein is for describing the embodiments and is not intended to limit the present disclosure. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase.

Also, terms such as first, second, A, B, (a), and (b) may be used in describing the components of the present disclosure. These terms are only used to distinguish the component from other components, and the nature, order, or order of the corresponding component is not limited by the term. When an element is described as being “connected,” “coupled to,” or “connected” to another element, that element is or may be directly connected to the other element, but there is another element between the elements. It will be understood that elements may be “connected”, “coupled” or “connected”.

As used herein, "comprises" and/or "comprising" means that a stated component, step, operation, and/or element is the presence of one or more other components, steps, operations, and/or elements. or do not rule out additions.

Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

1 illustrates an exemplary environment to which a forgery image determination device 100 according to some embodiments of the present disclosure may be applied. Although FIG. 1 shows that three user devices 300a, 300b, and 300c are connected to a network, this is only for convenience of understanding, and the number of user devices 300 requesting forgery or falsification of an image. can vary at any time.

Meanwhile, FIG. 1 only illustrates a preferred embodiment for achieving the object of the present disclosure, and some components may be added or deleted as necessary. In addition, it should be noted that components of the exemplary environment shown in FIG. 1 represent functionally differentiated functional elements, and a plurality of components may be implemented in a form integrated with each other in an actual physical environment. For example, the forgery image determination device 100 and the database 200 may be implemented in the form of different logics in the same computing device.

Hereinafter, individual components shown in FIG. 1 will be described in more detail.

The forgery image determination device 100 may receive an original image stored in the database 200 from the database 200 . Here, the original image may mean an original image that is not forged or altered. Here, the forgery image determination device 100 may use a plurality of original images stored in the database 200 as learning data to learn an out-of-distribution (OOD) detection model. Here, a plurality of original images stored in the database 200 can be defined as In-Distribution data and learned, and not only the stored plurality of original images but also cropped images, rotated images, and inverted images of the original images are In-Distribution data. It can be defined as data and learned. A more detailed description related to OOD detection will be embodied later through the description of the specification.

The forgery image determination device 100 may receive an image from the user device 300 . Here, an image photographed through a camera module provided in the user device 300 may be received by the forged image determining device 100, and an image stored in the user device 300 may be received by the forged image determining device 100. may be In this case, the forgery image determination device 100 may determine whether the image received from the user device 300 is forged or altered. In order to prevent redundant descriptions, detailed operations for determining whether an input image is forged or altered by the forgery image determination device 100 will be described later with reference to FIGS. 2 to 12 .

Meanwhile, the forgery image determination device 100 may be implemented with one or more computing devices. For example, all functions of the forgery image determination device 100 may be implemented in a single computing device. As another example, the first function of the forgery image determination device 100 may be implemented in a first computing device, and the second function may be implemented in a second computing device. Here, the computing device may be a notebook, a desktop, or a laptop, but is not limited thereto and may include any type of device equipped with a computing function. However, in an environment in which an artificial neural network for determining a forged image should be implemented in the forged image determination device 100, it may be preferable that the forgery image determination device 100 is implemented as a high-performance server-class computing device. An example of the aforementioned computing device will be described later with reference to FIG. 15 .

Next, the database 200 may store a plurality of original images. In addition, the database 200 may transmit some or all of the plurality of original images to the forged image determination device 100 . Here, the original image may refer to an original image that has not been forged or altered as described above.

Next, the user device 300 may capture an image and transmit it to the forgery image determination device 100 . In addition, the user device 300 may transmit the stored image to the forgery image determination device 100 . However, the present disclosure is not limited to the above-described examples, and the user device 300 transmits content being reproduced through the web to the forged image determining device 100 through various methods such as the forgery image determining device 100 ). Here, the content may include images and videos. For example, the image itself may be transmitted to the forgery image determination device 100, but is not limited thereto, and an image obtained by taking a screenshot according to a standard rule is transmitted to the forgery image determination device 100. may be

The user device 300 may be a laptop, a desktop (Desktop, 300a), a laptop (Laptop), a smart phone (300b), a tablet (Tablet, 300c), etc., but is not limited thereto, and is equipped with a computing function. It may contain a variety of devices.

Meanwhile, each component shown in FIG. 1 may mean software or hardware such as a Field Programmable Gate Array (FPGA) or an Application-Specific Integrated Circuit (ASIC). However, components are not meant to be limited to software or hardware, and may be configured to reside in an addressable storage medium or configured to execute one or more processors. Functions provided in the components may be implemented by more subdivided components, or may be implemented as a single component that performs a specific function by combining a plurality of components.

In some embodiments, the forgery image determination device 100 may communicate with other components through a network. The network may be implemented in all types of wired/wireless networks such as a Local Area Network (LAN), a Wide Area Network (WAN), a mobile radio communication network, and Wibro (Wireless Broadband Internet). there is.

So far, with reference to FIG. 1 , an exemplary environment to which the forgery image determination device 100 according to some embodiments of the present disclosure can be applied has been described. Hereinafter, methods for determining forged or altered images according to various embodiments of the present disclosure will be described with reference to FIGS. 2 to 14 .

Each step of the above methods may be performed by a computing device. In other words, each step of the methods may be implemented as one or more instructions executed by a processor of a computing device. All of the steps involved in the methods could be performed by one physical computing device, but first steps of the methods are performed by a first computing device and second steps of the methods are performed by a second computing device. may be Hereinafter, description will be continued on the assumption that each step of the methods is performed by the forgery/falsified image determination device 100 illustrated in FIG. 1 . However, for convenience of description, the description of the subject of operation of each step included in the methods may be omitted.

2 is an exemplary flowchart illustrating a forgery image determination method according to some embodiments of the present disclosure. However, this is only a preferred embodiment for achieving the object of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.

Referring to FIG. 2 , in step S100 , an object area included in an input image may be detected. Here, the object area may refer to an area where a specific object is located in the input image, and the specific object may include a person or an object.

Various techniques for detecting the object area may be applied in step S100. For example, a machine learning-based object detection model may be used. Here, the machine learning-based object detection model is a model that is learned through a machine learning algorithm and predicts a region where an object is located in an input image using a threshold value. Although an AdaBoost algorithm may be used to implement the above-described object detection model, it should be noted that the types of algorithms that may be used may vary. For reference, the Adaboost algorithm is a machine learning algorithm that learns a plurality of weak classifiers and builds at least one strong classifier. Since the algorithm is already widely known in the art, a detailed description thereof will be omitted. For another example, the object region may be detected by analyzing the histogram of the input image. Back-projection, which analyzes the histogram of the input image and extracts a specific object included in the input image, is a technique that is already widely known in the art, so a detailed description thereof will be omitted.

Next, in step S200, noise may be applied to at least a part of the input image based on the detected object region. For example, as shown in FIG. 7 , noise may be applied to the object region 11 of the input image 10 , but noise may be applied to the entire input image. For another example, noise may be applied to a part of the object area. Here, various types of noise may be used as noise that may be applied to the input image. For example, Gaussian noise, Gaussian blur, Salt and Pepper, etc. may be noises that may be applied to an input image, but the scope of the present disclosure is not limited to these examples, and all known noises may be applied to an input image. there is. According to this embodiment, by applying noise to at least a part of an input image, OOD detection performance, which will be described later, can be improved. Since the forged image statistically has a predetermined outlier in pixel values, the above-mentioned noise is added to the forged image to maximize the outlier, so that the performance of forgery image determination through OOD detection can be improved.

In some embodiments related to step S200, noise may be applied to an edge of the detected object region. According to the present embodiment, since the object area is usually changed in the case of forged images, by adding noise to the edge of the object area, the detection performance of the forged image can be improved and computing resources due to noise addition can be saved. For a more detailed explanation related to this, it will be described with reference to FIG. 9 .

FIG. 9 shows an example in which noise is added to the edge 17 of the object area 11 of the input image 10 . As described above, since the forged image is usually a case where the object area is changed, noise is added to the edge 17 of the object area 11 to improve detection performance of the forged image. Furthermore, computing resources may be saved by adding noise to a portion of the input image 10 .

In some other embodiments related to step S200, if the input image includes a plurality of object areas including the first object area and the second object area, noise is applied to an area where the first object area and the second object area overlap. can According to the present embodiment, in the case of a forged image, since the area where a plurality of object areas overlap is changed, by adding noise to the overlapping area, the detection performance of the forged image is improved and computing resources due to noise addition are improved. You can save. For a more detailed explanation related to this, it will be described with reference to FIG. 8 .

FIG. 10 shows an example in which noise is added to an overlapping area 25 where the first object area 21 and the second object area 23 of the input image 10 overlap. As described above, since the forged image is usually a case where the overlapping area 25 in which the object area overlaps is changed, by adding noise to the overlapping area 25, detection performance of the forged image can be improved. Furthermore, computing resources may be saved by adding noise to a portion of the input image 10 .

In some other embodiments related to step S200, the first noise may be applied to at least a portion of the input image, and the second noise may be applied to at least a portion of the input image. For example, as shown in FIG. 8 , a first noise may be applied to the first area 13 of the object area, and a second noise may be applied to the second area 15 of the object area. That is, different types of noise may be applied to different regions. For another example, an average of the first noise and the second noise may be applied to at least a part of the input image. That is, averages of different types of noise may be overlapped and applied to the same region of the input image. For another example, a weighted sum of the first noise and the second noise may be applied to at least a portion of the input image. That is, the highest sum of the first noise and the second noise may be overlapped and applied to the same region of the input image. Here, the first noise may be Gaussian noise and the second noise may be Salt and Pepper, but the type of noise is not limited to the above example, and the first noise and the second noise are different types of noise as long as they are different. It should be noted that may vary. According to this embodiment, a method of adding various noises to an input image may be provided. In addition, it can be understood that by using various combinations of noise, optimal noise for determining a forged image can be determined.

For a more detailed explanation related to step S200, it will be described with reference to FIGS. 3 and 4 below.

Referring to FIG. 3 , an input image may be converted to a frequency domain (S210), and noise may be applied to a region of a reference frequency or higher among regions included in the input image converted to the frequency domain (S220). Here, various known techniques for converting an input image into a frequency domain may be applied. For example, an input image may be changed from a time domain to a frequency domain based on a Fast Fourier Transform (FFT) algorithm. For a more detailed explanation related to this, it will be described with reference to FIGS. 11 and 12 .

As a result of applying the FFT algorithm to the input image 30 shown in FIG. 11, FIG. 12 shows an example of conversion to the frequency domain. The converted image 31 shown in FIG. 12 is an image converted to represent the real part of the frequency domain, that is, the magnitude of the frequency. Here, an area outside the figure 33 representing the reference frequency is an area equal to or greater than the reference frequency. Therefore, by adding noise to an area outside the figure 33 representing the reference frequency, the noise may be applied to an area equal to or higher than the reference frequency. According to the embodiment described with reference to FIG. 3 and related exemplary drawings, noise is added to a high-frequency region that may represent an edge of an object region, thereby improving detection performance of forged and forged images.

Referring to FIG. 4 , noise to be applied to at least a portion of the input image may be determined (S230) based on the attribute of the detected object region, and the determined noise may be applied to at least a portion of the input image (S240). Here, the attribute of the object region may include the image histogram, but is not limited thereto, and may include everything related to the attribute of the object region. In this case, the noise that may be determined based on the property of the object may include Gaussian noise, Gaussian blur, salt and pepper, motion blur, brightness jitter, contrast jitter, saturation jitter, ISO noise, and the like. According to the present embodiment, noise corresponding to the attribute of the object region is determined according to a predetermined rule, so that noise corresponding to the input image may be added to the input image, and thus OOD detection performance may be further improved.

It will be described with reference to FIG. 2 again.

Referring to FIG. 2 , in step S300 , out-of-distribution (OOD) detection may be performed on an input image to which noise is applied. Here, the OOD detection may mean a detection operation in which, when the distribution of the original image is defined as in-distribution data, the distribution of other images is determined as out-of-distribution data. That is, the OOD detection operation is a detection operation using a multi-class classification model that trains a multi-class classification model using an original image and detects an image other than the original image as a forged image (i.e. Out-Of-Distribution). According to this embodiment, it is possible to more accurately determine a forged image through OOD detection. For a more detailed description, it will be described with reference to FIGS. 13 and 14 .

FIG. 13 is an exemplary diagram for more specifically describing an OOD detection operation that may be referred to in some embodiments of the present disclosure, and FIG. 14 illustrates an example in which the OOD detection operation described with reference to FIG. 13 is applied to an image. It is a drawing for

For example, assuming that there is a model that predicts which number among 0 to 9 is an image drawn by a user with a mouse, FIG. 13 shows an example of an input image 40 to be input to the above-described model. Since the input image 40 is a picture unrelated to the numbers 0 to 9, it is reasonable to classify it as “Unknown” when inputting it to the ideal model 43. However, in the case of the exemplary CNN model 41, the input image 40 was classified into the class “3” with a very high probability, and in the case of the exemplary MLP model 42, the input image 40 was classified with a high probability. Classified as "0".

As in the above example, if the input image does not belong to a specific class, there may be a method of classifying it by adding a new class called "Unknown", but this method is a problem in that the trained artificial neural network must be retrained by adding a class. There is, and there is also a problem of acquiring various learning data to be included in the "Unknown" class. Therefore, OOD detection can be utilized as a technique capable of determining cases that do not belong to a specific class without classification into a new class.

Classes can be classified with high reliability by using a kind of multi-class classification operation, for example, the Softmax algorithm, for OOD detection. More specifically, the Softmax algorithm outputs the probability that an input image belongs to each of a plurality of classes, and compares the maximum probability (Maximum Softmax Probability) among the probabilities of belonging to each of a plurality of classes with a predetermined reference value to determine a plurality of predetermined It is possible to determine a case that does not belong to any one of the classes of . The reason for this determination is that the maximum probability when the input data is out-of-distribution data tends to be smaller than the maximum probability when the input data is in-distribution data. For example, when the maximum probability is smaller than the reference value, the input data may be determined as out-of-distribution data (i.e. forged or altered image). For another example, if the maximum probability is greater than the reference value, the input data may be determined as In-Distribution data (i.e. original image).

14 shows an original image 50 and other images 51 . At this time, by learning a multi-class classification model using the original image 50 and classifying the image 51 other than the original image into a forged image class, which is a new class not included in the multi-class, the image 51 other than the original image It can be classified as forged images. It should be noted that the present disclosure is not limited to the specific examples described in FIGS. 13 and 14 so far, and all known techniques can be applied to multi-class classification operations that can be applied in some embodiments of the present disclosure. For a more detailed description related to step S300, it will be described with reference to FIGS. 5 and 6.

In step S310 of FIG. 5 , it may be determined whether a plurality of classes determined based on the original image and a class having a degree of relevance to the input image of a reference value or more exist, and if a class having a degree of relevance of a reference value or more exists (S320 ), the input image may be determined as the original image in step S330. In addition, if there is no class having a degree of relevance greater than or equal to the reference value (S330), the input image may be determined as a forged image. Referring to step S310 in more detail with reference to FIG. 6 , the degree of relevance between the input image and each of the plurality of classes may be calculated in step S311, and the degree of relevance of the class having the maximum degree of relevance calculated in step S312 is a reference value. abnormality can be determined.

In some embodiments related to step S311, the degree of relevance may mean a probability that the input image belongs to each of a plurality of classes using a Softmax algorithm, and the degree of relevance of the class having the maximum degree of relevance is such that the calculated probability is the maximum. may mean the probability of a class of

So far, with reference to FIGS. 2 to 14 , various methods according to some embodiments of the present disclosure have been described in detail. According to the described embodiments, by adding noise to at least a part of an input image, performance of OOD detection for determining whether an input image is forged or altered can be improved. That is, when the input image is a forged image, since the pixel values of the input image have predetermined outliers, noise is added to the input image to maximize the outliers, thereby improving OOD detection performance. In addition, computing resources may be saved by adding noise only to a specific region rather than the entire region of the input image. In addition, the performance of OOD detection may be further improved by determining noise corresponding to the attribute of the input image.

Hereinafter, with reference to FIG. 15 , an exemplary computing device 1500 capable of implementing an apparatus for determining a forged or altered image according to some embodiments of the present disclosure will be described in more detail.

The computing device 1500 includes one or more processors 1510, a bus 1550, a communication interface 1570, a memory 1530 for loading a computer program 1591 executed by the processor 1510, and a computer A storage 1590 for storing the program 1591 may be included. However, only components related to the embodiment of the present disclosure are shown in FIG. 15 . Accordingly, those skilled in the art to which the present disclosure belongs may know that other general-purpose components may be further included in addition to the components shown in FIG. 15 .

The processor 1510 controls the overall operation of each component of the computing device 1500 . The processor 1510 includes a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphics processing unit (GPU), or any type of processor well known in the art of the present disclosure. It can be. Also, the processor 1510 may perform an operation for at least one application or program for executing a method according to embodiments of the present disclosure. Computing device 1500 may include one or more processors.

Memory 1530 stores various data, commands and/or information. Memory 1530 may load one or more programs 1591 from storage 1590 to execute a method according to embodiments of the present disclosure. The memory 1530 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

The bus 1550 provides a communication function between components of the computing device 1500 . The bus 1550 may be implemented as various types of buses such as an address bus, a data bus, and a control bus.

The communication interface 1570 supports wired and wireless Internet communication of the computing device 1500 . Also, the communication interface 1570 may support various communication methods other than Internet communication. To this end, the communication interface 1570 may include a communication module well known in the art of the present disclosure.

According to some embodiments, communication interface 1570 may be omitted.

The storage 1590 may non-temporarily store the one or more programs 1591 and various data.

The storage 1590 may be non-volatile memory, such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc., a hard disk, a removable disk, or as is well known in the art. It may be configured to include any known type of computer-readable recording medium.

Computer program 1591 may include one or more instructions that when loaded into memory 1530 cause processor 1510 to perform methods/operations in accordance with various embodiments of the present disclosure. That is, the processor 1510 may perform methods/operations according to various embodiments of the present disclosure by executing the one or more instructions.

In the above case, the forgery image determination device according to some embodiments of the present disclosure may be implemented through the computing device 1500 .

So far, various embodiments of the present disclosure and effects according to the embodiments have been described with reference to FIGS. 1 to 15 . Effects according to the technical idea of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the specification.

The technical idea of the present disclosure described with reference to FIGS. 1 to 15 so far may be implemented as computer readable code on a computer readable medium. The computer-readable recording medium may be, for example, a removable recording medium (CD, DVD, Blu-ray disc, USB storage device, removable hard disk) or a fixed recording medium (ROM, RAM, computer-equipped hard disk). can The computer program recorded on the computer-readable recording medium may be transmitted to another computing device through a network such as the Internet, installed in the other computing device, and thus used in the other computing device.

In the above, even though all the components constituting the embodiments of the present disclosure have been described as being combined or operated as one, the technical idea of the present disclosure is not necessarily limited to these embodiments. That is, within the scope of the purpose of the present disclosure, all of the components may be selectively combined with one or more to operate.

Although actions are shown in a specific order in the drawings, it should not be understood that the actions must be performed in the specific order shown or in a sequential order, or that all depicted actions must be performed to obtain a desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of the various components in the embodiments described above should not be understood as requiring such separation, and the described program components and systems may generally be integrated together into a single software product or packaged into multiple software products. It should be understood that there is

Although the embodiments of the present disclosure have been described with reference to the accompanying drawings, those skilled in the art may implement the present disclosure in other specific forms without changing the technical spirit or essential features. can understand that there is Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. The protection scope of the present disclosure should be construed by the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of rights of the technical ideas defined by the present disclosure.

Claims (13)

In a method performed by a computing device,
detecting an object region included in an input image;
applying noise to a portion of the input image based on the detected object region; and
Including the step of performing OOD (Out-Of-Distribution) detection on the input image to which the noise is applied,
A method for determining forged images using noise addition. According to claim 1,
The step of applying the noise,
Including applying noise to at least a part of the detected object area,
A method for determining forged images using noise addition. According to claim 1,
The step of applying the noise,
Including applying noise to an edge of the detected object area,
A method for determining forged images using noise addition. According to claim 1,
The step of applying the noise,
If the input image includes a plurality of object areas including a first object area and a second object area, applying noise to an area where the first object area and the second object area overlap,
A method for determining forged images using noise addition. According to claim 1,
The step of applying the noise,
transforming the input image into a frequency domain; and
Applying noise to a region of a reference frequency or higher among regions included in the input image converted to the frequency domain,
A method for determining forged images using noise addition. According to claim 1,
The step of applying the noise,
applying a first noise to a portion of the input image; and
Applying a second noise distinct from the first noise to a portion of the input image,
A method for determining forged images using noise addition. According to claim 1,
The step of applying the noise,
determining noise to be applied to a portion of the input image based on the detected attribute of the object region; and
Applying the determined noise to a portion of the input image,
A method for determining forged images using noise addition. According to claim 1,
The step of performing the OOD detection,
Determining whether a plurality of classes determined based on a plurality of original images and a class having a degree of relevance to the input image greater than or equal to a reference value exist,
A method for determining forged images using noise addition. According to claim 8,
As a result of determining the degree of relevance, if a class having a degree of relevance to the input image that is equal to or greater than a reference value exists, determining the input image as an original image.
A method for determining forged images using noise addition. According to claim 8,
As a result of the determination of the degree of relevance, if there is no class having a degree of relevance with the input image equal to or greater than a reference value, determining the input image as a forged image.
A method for determining forged images using noise addition. According to claim 8,
In the step of determining whether a class having a degree of relevance equal to or greater than a reference value exists,
calculating a degree of relevance between the input image and each of the plurality of classes; and
Including the step of determining whether the calculated maximum value of the degree of relevance is greater than or equal to a reference value,
A method for determining forged images using noise addition. processor;
network interface;
Memory; and
A computer program loaded into the memory and executed by the processor,
The computer program,
an instruction for detecting an object region included in an input image;
an instruction for applying noise to a portion of the input image based on the detected object region; and
Including an instruction for performing OOD (Out-Of-Distribution) detection on the input image to which the noise is applied.
Forgery and falsification image determination device using noise addition. According to claim 12,
further comprising a camera,
Forgery and falsification image determination device using noise addition.

Images