Electronic device for inserting and extracting watermark, and control method therefor

Abstract

This electronic device comprises: at least one processor including a processing circuit; and a memory for storing instructions, wherein, when the instructions are individually or collectively executed by the at least one processor, the electronic device acquires information about the magnitude of a frequency component for a plurality of color channels forming an image, identifies a color channel having the highest magnitude ratio of a high frequency component from among the plurality of color channels, identifies the insertion strength of a watermark for each of a plurality of regions on the basis of the magnitude of the high frequency component of the identified color channel for each of the plurality of regions forming the image, embeds, into the watermark, information corresponding to the insertion strength for each of the plurality of regions and the position for each of the plurality of regions, and inserts, into the image, the watermark embedded with the information corresponding to the insertion strength for each of the plurality of regions and the position for each of the plurality of regions.

Description

Electronic device for inserting and extracting watermarks and method for controlling the same

[0001] The present disclosure relates to an electronic device and a method for controlling the same, and more specifically, to an electronic device and a method for controlling the same for inserting a watermark into an image or extracting an inserted watermark from an image in which a watermark has been inserted.

[0002] Various technologies are being used to protect image copyrights in the digital environment. Among them, deep learning-based watermarking technology is being used to maintain image integrity and prevent illegal copying.

[0003] Deep learning-based watermarking technology uses trained AI models to insert and extract watermarks into images, preventing unauthorized use of the images through this process. Notably, this technology demonstrates robustness against various forms of image modification, such as image compression and conversion, allowing the presence of a watermark to be detected while preserving the original image state.

[0004] However, deep learning-based watermarking technology shows excellent performance for images similar to those used when training the AI ​​model, but has a problem where performance decreases in terms of robustness and image quality degradation for images that are not similar.

[0005] An electronic device according to the present disclosure comprises at least one processor including a processing circuit and a memory for storing instructions. When the instructions are executed individually or collectively by the at least one processor, the electronic device may acquire information regarding the magnitude of frequency components for a plurality of color channels constituting an image, identify the color channel with the highest ratio of the magnitude of the high-frequency component among the plurality of color channels, identify the embedding strength of a watermark for each of the plurality of regions based on the magnitude of the high-frequency component of the identified color channel for each of the plurality of regions constituting the image, embed information corresponding to the embedding strength of the plurality of regions and the position of the plurality of regions into the watermark, and embed the watermark with the embedded information corresponding to the embedding strength of the plurality of regions and the position of the plurality of regions into the image.

[0006] In this case, when the above instructions are executed individually or collectively by the at least one processor, the electronic device generates quantized Discrete Cosine Transform (DCT) coefficients from a plurality of sub-regions constituting each of the plurality of regions, wherein the quantized DCT coefficients include at least one AC coefficient, and for each of the plurality of sub-regions, determines the ratio of the sum of at least one AC coefficient excluding the AC coefficient of the intermediate frequency region relative to the DC coefficient among the quantized DCT coefficients, wherein the AC coefficient of the intermediate frequency region is located between the DC coefficient and the at least one AC coefficient, and among the plurality of color channels, the color channel having the highest average of the ratios determined from each of the plurality of sub-regions can be identified as the color channel with the highest complexity.

[0007] Meanwhile, when the above commands are individually or collectively executed by the at least one processor, the electronic device can increase the embedding strength of the watermark in an area having the highest size ratio of the high-frequency component among the plurality of areas.

[0008] Meanwhile, when the commands are individually or collectively executed by the at least one processor, the electronic device can generate a pattern corresponding to a position of each of the plurality of regions in each of the plurality of regions, and combine the bit values ​​constituting the watermark with the generated pattern.

[0009] In this case, when the above instructions are executed individually or collectively by the at least one processor, the electronic device may arrange random numbers in a pattern corresponding to the location of each of the plurality of regions and embed the arranged random numbers in a watermark in which information corresponding to the insertion strength for each of the plurality of regions and the location of each of the plurality of regions is embedded.

[0010] In this case, when the above instructions are executed individually or collectively by the at least one processor, the electronic device can acquire an image with the watermark inserted by inputting a watermark, in which information corresponding to the identified color channel, the insertion intensity for each of the plurality of regions, and the position for each of the plurality of regions is embedded, into an artificial intelligence model corresponding to the identified color channel among a plurality of first artificial intelligence models.

[0011] Meanwhile, when the commands are individually or collectively executed by the at least one processor, the electronic device, when the image into which the watermark is inserted is acquired, determines the size ratio of the high-frequency components of each of the plurality of color channels constituting the acquired image to identify a color channel into which the watermark is inserted among the plurality of color channels constituting the projected image, identifies at least one of the information on the plurality of areas from the color channel into which the watermark is inserted, identifies the location of the plurality of areas into which the watermark is inserted from at least one of the information on the plurality of areas, and identifies a bit value constituting the watermark inserted in each of the plurality of areas based on the location of the plurality of areas into which the watermark is inserted, thereby extracting the inserted watermark.

[0012] In this case, when the commands are individually or collectively executed by the at least one processor, the electronic device can identify an embedding intensity embedded in the watermark for each of a plurality of regions constituting the color channel into which the watermark is embedded based on a size ratio of high frequency components for each of a plurality of regions constituting the color channel into which the watermark is embedded, and extract the watermark from the color channel into which the watermark is embedded using the embedding intensity embedded in the watermark.

[0013] Meanwhile, when the above commands are individually or collectively executed by the at least one processor, the electronic device can input the color channel into which the watermark is inserted and the embedding strength embedded in the watermark into an artificial intelligence model corresponding to the color channel into which the identified watermark is inserted among a plurality of second artificial intelligence models, thereby extracting the watermark from the color channel into which the watermark is inserted.

[0014] A control method for an electronic device according to the present disclosure may include: acquiring information regarding the magnitude of frequency components for a plurality of color channels constituting an image; identifying the color channel among the plurality of color channels that has the highest ratio of the magnitude of the high-frequency component; identifying the embedding strength of a watermark for each of the plurality of regions based on the magnitude of the high-frequency component of the identified color channel for each of the plurality of regions constituting the image; embedding information corresponding to the embedding strength of the plurality of regions and the position of the plurality of regions into the watermark; and inserting the watermark with the embedded information corresponding to the embedding strength of the plurality of regions and the position of the plurality of regions into the image.

[0015] In this case, the control method may further include the steps of: generating quantized Discrete Cosine Transform (DCT) coefficients from a plurality of sub-regions constituting each of the plurality of regions; determining the ratio of the sum of at least one AC coefficient, excluding the AC coefficient of the intermediate frequency region for the DC coefficient among the quantized DCT coefficients, for each of the plurality of sub-regions; and identifying the color channel with the highest average of the ratios determined from each of the plurality of sub-regions among the plurality of color channels as the channel with the highest complexity.

[0016] Meanwhile, the above control method may further include a step of increasing the insertion intensity of the watermark in the region with the highest ratio of the magnitude of the high-frequency component among the plurality of regions.

[0017] Meanwhile, the control method may further include the steps of generating a pattern corresponding to the position of each of the plurality of regions in each of the plurality of regions and combining a bit value constituting the watermark with the generated pattern.

[0018] In this case, the control method may further include the steps of arranging random numbers in a pattern corresponding to the position of each of the plurality of regions and embedding the arranged random numbers into a watermark in which information corresponding to the insertion strength for each of the plurality of regions and the position of each of the plurality of regions is embedded.

[0019] In this case, the control method may further include the step of acquiring an image with the watermark inserted by inputting a watermark, in which information corresponding to the identified color channel, the insertion intensity for each of the plurality of regions, and the position for each of the plurality of regions is embedded, into an artificial intelligence model corresponding to the identified color channel among a plurality of first artificial intelligence models.

[0020] The above and other aspects, features and advantages of the present invention will become more apparent by describing embodiments of the present invention below with reference to the attached drawings.

[0021] FIG. 1 is a diagram illustrating the operation of an electronic device according to one or more embodiments of the present disclosure.

[0022] FIG. 2 is a block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure.

[0023] FIG. 3 is a flowchart illustrating a method for an electronic device according to one embodiment of the present disclosure to identify a color channel for inserting a watermark among a plurality of color channels constituting an image.

[0024] FIG. 4 is a flowchart illustrating a specific method for an electronic device according to one embodiment of the present disclosure to identify the complexity of color channels constituting an image.

[0025] FIGS. 5 and 6 are diagrams illustrating a method for an electronic device according to an embodiment of the present disclosure to identify the complexity of a color channel.

[0026] FIG. 7 is a flowchart illustrating a method for an electronic device according to an embodiment of the present disclosure to insert a watermark into a color channel having the highest complexity among a plurality of color channels constituting an image.

[0027] FIGS. 8 to 13 are diagrams for explaining a method for an electronic device according to an embodiment of the present disclosure to insert a watermark into a color channel having the highest complexity among a plurality of color channels constituting an image.

[0028] FIG. 14 is a flowchart illustrating a method for an electronic device according to an embodiment of the present disclosure to extract a watermark from an image with an embedded watermark.

[0029] FIG. 15 is a diagram illustrating a method for an electronic device according to an embodiment of the present disclosure to extract a watermark from an image with an embedded watermark.

[0030] FIG. 16 is a flowchart for explaining a control method of an electronic device according to one embodiment of the present disclosure.

[0031] The embodiments described herein are subject to various modifications and may have various forms; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope of specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the present disclosure. In relation to the description of the drawings, similar reference numerals may be used for similar components.

[0032] In describing the present disclosure, if it is determined that a specific description of a related known function or configuration may unnecessarily obscure the gist of the present disclosure, a detailed description thereof will be omitted.

[0033] Additionally, the following embodiments may be modified in various other forms, and the scope of the technical concepts of the present disclosure is not limited to the following embodiments. Rather, these embodiments are provided to further faithfully and completely convey the technical concepts of the present disclosure to those skilled in the art.

[0034] The terminology used in this disclosure is for the purpose of describing specific embodiments only and is not intended to limit the scope of the rights. Singular expressions include plural expressions unless the context clearly dictates otherwise.

[0035] In this disclosure, expressions such as “has,” “can have,” “includes,” or “may include” indicate the presence of a corresponding feature (e.g., a component such as a number, function, operation, or part), and do not exclude the presence of additional features.

[0036] In this disclosure, expressions such as “A or B,” “at least one of A or B,” “at least one of A and B,” or “one or more of A and / or B” can include all possible combinations of the listed items. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” can all refer to cases where (1) A is included, (2) B is included, or (3) both A and B are included.

[0037] The expressions “first,” “second,” “first,” or “second,” etc., used in this disclosure can describe various components, regardless of order and / or importance, and are only used to distinguish one component from another, but do not limit the components.

[0038] When it is said that a component (e.g., a first component) is “(operatively or communicatively) coupled with / to” or “connected to” another component (e.g., a second component), it should be understood that said component may be directly coupled to said other component, or may be coupled via another component (e.g., a third component).

[0039] On the other hand, when it is said that a component (e.g., a first component) is "directly connected" or "directly connected" to another component (e.g., a second component), it can be understood that no other component (e.g., a third component) exists between said component and said other component.

[0040] As used in this disclosure, the expression “configured to” may be replaced, depending on the context, with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of.” The term “configured to” may not necessarily mean only “specifically designed to” in hardware.

[0041] Instead, in some contexts, the phrase "a device configured to" may mean that the device, in conjunction with other devices or components, is "capable of" performing A, B, and C. For example, the phrase "a processor configured (or set) to perform A, B, and C" may refer to a dedicated processor (e.g., an embedded processor) for performing those operations, or a general-purpose processor (e.g., a CPU or application processor) that can perform those operations by executing one or more software programs stored in a memory device.

[0042] In the embodiments, a 'module' or 'part' performs at least one function or operation, and may be implemented as hardware or software, or as a combination of hardware and software. Furthermore, a plurality of 'modules' or 'parts' may be integrated into at least one module and implemented as at least one processor, except for a 'module' or 'part' that needs to be implemented as a specific hardware.

[0043] Meanwhile, the various elements and areas in the drawings are schematically drawn. Therefore, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.

[0044] Hereinafter, with reference to the attached drawings, embodiments according to the present disclosure will be described in detail so that a person having ordinary knowledge in the technical field to which the present disclosure pertains can easily implement the present disclosure.

[0045] FIG. 1 is a drawing for explaining the operation of an electronic device according to one embodiment of the present disclosure.

[0046] Referring to FIG. 1, an electronic device (100) can obtain an image (10). The image (10) may be an image to be subject to watermark insertion.

[0047] An image (10) may include multiple color channels. An electronic device (100) may insert a watermark (20) into one color channel (11) of the multiple color channels constituting the image (10).

[0048] A watermark (20) may refer to information for preventing illegal copying of an image or information for indicating metadata of an image.

[0049] Accordingly, the electronic device (100) can obtain an image (30) in which a watermark (20) is inserted into the first color channel (11).

[0050] A specific method for inserting a watermark into an image by an electronic device (100) will be described with reference to the drawings below.

[0051] FIG. 2 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present disclosure.

[0052] The electronic device (100) may include a memory (110) and a processor (120). The electronic device (100) may further include other components in addition to the above components.

[0053] The electronic device (100) may be implemented as a server, but this is only one or more embodiments, and the electronic device (100) may be implemented in various forms, such as a smartphone, a TV, a smart TV, a set-top box, a mobile phone, a PDA (personal digital assistant), a laptop, a media player, an e-book reader, a digital broadcasting terminal, a navigation device, a kiosk, an MP3 player, a wearable device, a home appliance, and other mobile or non-mobile computing devices.

[0054] The memory (110) can store at least one instruction regarding the electronic device (100). The memory (110) can store an operating system (O / S) for driving the electronic device (100). In addition, the memory (110) can store various software programs or applications for operating the electronic device (100) according to various embodiments of the present disclosure. In addition, the memory (110) can include a semiconductor memory such as a flash memory or a magnetic storage medium such as a hard disk.

[0055] In particular, the memory (110) can store information about an image for inserting a watermark. In addition, the memory (110) can store information about a watermark for inserting into an image.

[0056] The processor (120) can control the overall operation and function of the electronic device (100). Specifically, the processor (120) is connected to the configuration of the electronic device (100) including the memory (110), and can control the overall operation of the electronic device (100) by executing the commands stored in the memory (110) as described above. Although FIG. 2 illustrates an example of the electronic device (100), embodiments of the present invention are not limited thereto. For example, embodiments of the present disclosure can also be implemented in a distributed system in which one or more tasks are distributed and performed between the electronic device and one or more servers.

[0057] FIG. 3 is a flowchart illustrating a method for an electronic device according to an embodiment of the present disclosure to identify a color channel for inserting a watermark among a plurality of color channels constituting an image.

[0058] Referring to FIG. 3, the electronic device (100) can acquire an image (S310).

[0059] The image may be an image to be watermarked. In one or more embodiments, the image may be an image pre-stored in the memory (110) or an image received by the electronic device (100) from an external device.

[0060] An image may be composed of multiple color channels. For example, an image may be composed of R, G, and B channels. In one or more embodiments, an image may be composed of Y, Cb, and Cr channels.

[0061] In the present disclosure, “color channel” may be replaced with terms of the same or similar concept, such as “channel,” “component,” “component,” or “layer.”

[0062] A watermark embedded in an image can consist of multiple bits. For example, a watermark can be expressed as a sequence of bits, each representing a value of 0 or 1. For example, a watermark can be expressed as "1101100101..."

[0063] In the present disclosure, “watermark” may be replaced with terms of the same or similar concept, such as “message,” “image,” “text,” “digital watermark,” “digital signature,” “logo,” “mark,” “hidden tag,” “invisible watermark,” or “hidden watermark.” In one or more examples, a watermark embedded in an image may be visible. In one or more embodiments, a watermark embedded in an image may not be visible. In one or more examples, an image may include two or more watermarks. For example, the image may include a visible first watermark and an invisible second watermark. In one or more examples, each watermark included in an image may or may not be visible.

[0064] The electronic device (100) can divide an image into multiple regions. In addition, the electronic device (100) can divide each of the multiple regions into multiple sub-regions.

[0065] The electronic device (100) can divide an image into a plurality of regions each including a first number of pixels. Then, the electronic device (100) can divide each of the plurality of regions into a plurality of sub-regions each including a second number of pixels. For example, each region can include N pixels, and each sub-region can include M pixels, where N is greater than M (N > M). For example, one region can include 100 pixels, and the region can be divided into four sub-regions each including 25 pixels.

[0066] Additionally, the electronic device (100) may divide each of the plurality of color channels constituting an image into a plurality of regions including a first number of pixels. Furthermore, the electronic device (100) may divide each of the plurality of regions constituting the color channels into a plurality of sub-regions including a second number of pixels.

[0067] For example, the electronic device (100) can divide an image or color channel into a plurality of regions (e.g., a first region, a second region, …, an n-th region) each consisting of 16x16 pixels. In addition, the electronic device (100) can divide each of the plurality of regions into a plurality of sub-regions (e.g., a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region) each containing 8x8 pixels.

[0068] In the present disclosure, “region” may be replaced with terms of the same or similar concept, such as “block” or “image block.” For example, “multiple regions” constituting an image may be replaced with “multiple image blocks,” and “multiple sub-regions” may be replaced with “multiple sub-image blocks.”

[0069] The electronic device (100) can identify a channel for inserting a watermark among a plurality of color channels that constitute an image (S320).

[0070] For example, if the image consists of R, G, and B channels, the electronic device (100) can identify one of the R, G, and B channels as a color channel for inserting a watermark.

[0071] The electronic device (100) can identify the color channel with the highest complexity among the plurality of color channels constituting an image. The electronic device (100) can identify the color channel with the highest complexity among the plurality of color channels as the channel for inserting a watermark. Here, the channel for inserting a watermark may be referred to as an “embedding channel.”

[0072] The “complexity” of a color channel can refer to the degree to which visual elements within the channel are diverse, detailed, and interact. The higher the complexity of a color channel, the more robustly a watermark can be embedded. In other words, the higher the complexity of the color channel, the higher the insertion intensity with which the watermark can be embedded. In this case, the watermark may be embedded with an intensity that is difficult to detect with the naked eye.

[0073] In the present disclosure, “complexity” may be replaced with terms of the same or similar concept, such as “precision,” “amount of change,” “rate of change,” etc.

[0074] When the color channel complexity is high, a single pixel in the color channel may differ significantly from its neighboring pixels. A pixel with a large difference from its neighboring pixels may have high spatial frequency (high frequency) components.

[0075] When the color channel complexity is low, a single pixel that constitutes a color channel may differ little from its neighboring pixels. A pixel with a small difference from its neighboring pixels may have low spatial frequency (low frequency) components.

[0076] The "complexity" of a color channel can be determined by the high-frequency components among the frequency components that make up the color channel. The frequency of a color channel can be a measure of how much spatial variation occurs in the color channel.

[0077] Accordingly, the electronic device (100) can identify the complexity of a color channel based on the size of a high-frequency component among the frequency components constituting the color channel. This will be described with reference to FIG. 4.

[0078] FIG. 4 is a flowchart illustrating a specific method for an electronic device according to one embodiment of the present disclosure to identify the complexity of color channels constituting an image.

[0079] Referring to FIG. 4, the electronic device (100) can obtain information about the magnitude of frequency components for a plurality of color channels that constitute an image (S410).

[0080] For example, if an image is composed of R, G, and B channels, the electronic device (100) can identify the magnitude of the frequency component for the R channel, the magnitude of the frequency component for the G channel, and the magnitude of the frequency component for the B channel.

[0081] The electronic device (100) can convert pixel values ​​in the spatial domain into components in the frequency domain by performing a Discrete Cosine Transform (DCT) on each of a plurality of sub-regions constituting a color channel. At this time, the frequency components in the plurality of sub-regions can be expressed as DCT coefficients. That is, the electronic device (100) can generate a plurality of DCT coefficients by performing a Discrete Cosine Transform on each of the plurality of sub-regions. Here, the plurality of DCT coefficients may be referred to as “DCT blocks.”

[0082] And, the electronic device (100) can obtain a plurality of quantized DCT coefficients by performing quantization on a plurality of acquired DCT coefficients.

[0083] That is, for each of the plurality of color channels, the electronic device (100) can obtain a plurality of quantized Discrete Cosine Transform (DCT) coefficients from a plurality of sub-regions constituting each of the plurality of regions.

[0084] For example, referring to FIG. 5, the electronic device (100) can extract a pixel value (520) of one area (511) among a plurality of areas constituting one color channel (510) among a plurality of color channels. At this time, one area (511) among the plurality of areas may be composed of 8x8 pixels. Then, the electronic device (100) can perform a DCT transform on the pixel value (520) of one area (511) to generate a plurality of DCT coefficients (530) for one area (511). At this time, among the plurality of DCT coefficients (530), a low-frequency component may be arranged at the upper left and a high-frequency component may be arranged at the lower right.

[0085] The electronic device (100) can identify the color channel with the highest ratio of the magnitude of the high-frequency component to the low-frequency component among the plurality of color channels (S420). The electronic device (100) can identify the color channel with the highest ratio of the magnitude of the high-frequency component among the plurality of color channels as the channel to insert the watermark.

[0086] Specifically, the electronic device (100) can calculate the sum value of at least one AC coefficient for the DC coefficient among the quantized DCT coefficients for each of the plurality of sub-regions. As will be understood by those skilled in the art, the DCT coefficients can be divided into AC coefficients and DC coefficients, the DC coefficients being DCT coefficients having a frequency of 0 in both directions, and the AC coefficients being the remaining DCT coefficients having a frequency other than 0.

[0087] For example, referring to FIG. 6, a plurality of DCT coefficients (530) obtained from the first region (511) may include a DC coefficient (610) and a plurality of AC coefficients (620, 630).

[0088] Here, the DC coefficient (610) may be a coefficient corresponding to a low-frequency component, and a plurality of AC coefficients (620, 630) may be coefficients corresponding to high-frequency components.

[0089] At this time, the electronic device (100) can calculate the sum of at least one AC coefficient (630) for the DC coefficient (610). At this time, the at least one AC coefficient (630) may be a coefficient excluding an AC coefficient (620) close to a low-frequency component among a plurality of AC coefficients (620, 630). In one or more embodiments, the AC coefficient (620) close to a low-frequency component may mean an AC coefficient (620) arranged in an area adjacent to the DC coefficient (610).

[0090] In one or more embodiments, the electronic device (100) may calculate a sum ratio of at least one AC coefficient excluding an intermediate frequency region for the DC coefficient among the quantized DCT coefficients for each of the plurality of sub-regions. For example, the AC coefficient (620) may correspond to an intermediate frequency region for the DC coefficient, and the electronic device (100) may calculate a sum ratio of at least one AC coefficient excluding the AC coefficient (620).

[0091] The electronic device (100) can calculate the size ratio of high-frequency components to low-frequency components from the acquired DCT coefficients.

[0092] The ratio of the size of the high frequency component to the low frequency component can be defined as in mathematical equation 1 below.

[0093] Mathematical formula 1

[0094] The ratio of the magnitude of the high frequency components =

[0095] Here, DC can mean the value of the DC coefficient. ak can mean the AC coefficient of order k.

[0096] That is, the electronic device (100) may exclude AC coefficients of order 1, 2, and 4 among a plurality of AC coefficients. At this time, AC coefficients of order 1, 2, and 4 may refer to AC coefficients arranged in an area adjacent to a DC coefficient among a plurality of AC coefficients.

[0097] That is, the electronic device (100) can calculate the size ratio of at least one AC coefficient (630) to a DC coefficient (610) among a plurality of DCT coefficients (530).

[0098] The electronic device (100) can calculate the size ratio of high-frequency components to low-frequency components for each of the plurality of sub-regions according to the method described above. In addition, the electronic device (100) can identify the color channel with the highest average value of the size ratio of high-frequency components to low-frequency components calculated from each of the plurality of sub-regions as the channel with the highest complexity.

[0099] Accordingly, the electronic device (100) can identify the color channel most suitable for inserting a watermark. The color channel most suitable for inserting a watermark may mean a color channel that is so complex that it is difficult to detect with the naked eye even when the watermark is inserted with high insertion intensity.

[0100] When the color channel with the highest complexity among the multiple color channels constituting an image is identified according to the method described above, the electronic device (100) can insert a watermark into the identified color channel. This will be explained with reference to FIG. 7.

[0101] FIG. 7 is a flowchart illustrating a method for an electronic device according to one embodiment of the present disclosure to insert a watermark into the color channel with the highest complexity among a plurality of color channels constituting an image.

[0102] Referring to FIG. 7, the electronic device (100) can map a plurality of bits constituting a watermark to a plurality of regions constituting an image (S710).

[0103] Specifically, the electronic device (100) can acquire a plurality of bits constituting a watermark. The watermark may be implemented in the form of an image, text, or audio signal, and the electronic device (100) can convert the watermark into a plurality of bit sequences. For example, the electronic device (100) can convert the watermark into a plurality of bit sequences, such as “1101100101…”. Here, the acquired plurality of bit sequences may be referred to as a plurality of bits constituting the watermark.

[0104] Alternatively, a plurality of bits constituting the watermark may be pre-stored in the memory (110). The electronic device (100) may load the plurality of bits pre-stored in the memory (110).

[0105] When multiple bits constituting a watermark are acquired, the electronic device (100) can map each of the multiple bits to multiple regions constituting an image.

[0106] For example, referring to FIG. 8, the electronic device (100) can divide the first color channel (810) into multiple regions. At this time, the first color channel (810) may be a color channel with the highest complexity among the multiple color channels constituting the image.

[0107] The electronic device (100) can obtain a plurality of bits (820) mapped to each of a plurality of areas. The electronic device (100) can map a first bit (821) among the plurality of bits (820) to a first area (811) among the plurality of areas. In addition, the electronic device (100) can map a second bit (822) among the plurality of bits (820) to a second area (812) among the plurality of areas. Based on the mapped information, the electronic device (100) can insert information about the first bit (821) into the first area (811) and insert information about the second bit (822) into the second area (821).

[0108] That is, the electronic device (100) can generate a matrix containing information about a plurality of bits (820). Here, the matrix generated by the electronic device (100) may be referred to as a “watermark matrix,” “watermark bit matrix,” “bit matrix,” or “message matrix,” etc.

[0109] At this time, each element included in the generated matrix may correspond to one bit among the plurality of bits. The number of elements included in the matrix may correspond to the number of the plurality of regions. In addition, the position of each element included in the matrix may correspond to the position of each of the plurality of regions. For example, if the plurality of regions are 5x5, the number of elements of the matrix may be 5x5. In addition, information about the first bit (821) located in the first row and the first column of the generated matrix may be inserted into the first region (811) of the color channel. In addition, information about the second bit (822) located in the fourth row and the first column may be inserted into the second region (812) of the color channel.

[0110] In one or more examples, the number of bits constituting the watermark may be smaller than the number of regions constituting the image. In this case, the electronic device (100) may repeatedly insert bits constituting the watermark.

[0111] For example, if the number of multiple regions constituting the image is 8,040 and the number of multiple bits constituting the watermark is 804, the electronic device (100) can insert each bit constituting the watermark 10 times. That is, the electronic device (100) can insert the bits constituting the watermark once from the 1st region to the 804th region. And, the electronic device (100) can insert the bits constituting the watermark once from the 805th region to the 1608th region. That is, the electronic device (100) can insert information about the first bit among the multiple bits into the 1st region, the 805th region, the 1609th region, etc.

[0112] The electronic device (100) can insert one of the bits constituting the watermark into each of the multiple regions constituting the image with a different insertion strength. That is, the electronic device (100) can identify the insertion strength of the watermark for each of the multiple regions constituting the image (S720).

[0113] The "embedding strength" of a watermark can refer to a value indicating the size or intensity of the watermark signal. A higher embedding strength makes it easier to extract the watermark, but may degrade the quality of the original data. In one or more examples, a lower embedding strength may maintain the quality of the original data, but may make watermark extraction more difficult.

[0114] In the present disclosure, “insertion strength” may be replaced with terms of the same or similar concept, such as “weight,” “insertion weight,” “insertion degree,” “insertion level,” “embedding weight,” “embedding degree,” “embedding strength,” or “embedding level.”

[0115] Specifically, the electronic device (100) can insert a first bit according to a first insertion strength in a first area among a plurality of areas constituting an image, insert a second bit according to a second insertion strength in a second area, and insert a third bit according to a third insertion strength in a third area.

[0116] Specifically, the electronic device (100) can identify insertion intensity for each of the multiple regions constituting the color channel based on the complexity of each of the multiple regions constituting the color channel.

[0117] The electronic device (100) can identify the watermark embedding strength for each of the plurality of regions constituting the image based on the complexity of the identified color channels for each of the plurality of regions constituting the image. The electronic device (100) can increase the watermark embedding strength in a region with a higher complexity among the plurality of regions constituting the image. Accordingly, a first region with a higher complexity than a second region can have a higher embedding strength than the second region.

[0118] At this time, at least part of the method by which the electronic device (100) identifies the complexity of the color channels identified by the plurality of areas may be the same as the method described above.

[0119] Specifically, the electronic device (100) can identify multiple sub-regions constituting one region among multiple regions constituting an image. Then, the electronic device (100) can calculate the size ratio of the high-frequency component to the low-frequency component of the color channel of each of the multiple sub-regions. Then, the electronic device (100) can identify the average of the values ​​(or ratios) calculated from each of the multiple sub-regions constituting one region as the complexity of one region. Then, the electronic device (100) can map an insertion intensity corresponding to the complexity of one identified region to the identified region.

[0120] For example, referring to FIG. 9, the electronic device (100) can divide a color channel (910) into multiple regions. At this time, the color channel (910) may be a color channel with the highest complexity among the multiple color channels constituting the image. The electronic device (100) can obtain an insertion intensity (920) mapped to each of the multiple regions.

[0121] Specifically, if the complexity of a first region (911) among the plurality of regions constituting the image falls within a first range, the electronic device (100) can identify the insertion intensity of the first region (911) as an A level (921). In addition, if the complexity of a second region (912) among the plurality of regions falls within a second range that is higher than the first range, the electronic device (100) can identify the insertion intensity of the second region (912) as an F level (922) that is higher than the A level.

[0122] That is, the electronic device (100) can generate a matrix representing insertion strengths for multiple regions.

[0123] The embedding strength of the watermark for each of multiple areas can be expressed as one of multiple discrete levels, such as, but not limited to, Level A, Level B, Level C, Level D, Level E, and Level F. In this case, the embedding strength for each level can be expressed as a discrete integer, fraction, or a combination thereof, such as “1,” “1.5,” “2,” “2.5,” “3,” and “3.5.”

[0124] When multiple region-specific insertion intensities are identified, the electronic device (100) can embed the multiple region-specific insertion intensities into multiple bits constituting the watermark (S730).

[0125] Specifically, the electronic device (100) can reflect the insertion strength in the plurality of bits by multiplying the bits mapped to each of the plurality of areas by the insertion strength corresponding to each of the plurality of areas.

[0126] For example, referring to FIG. 10, a plurality of bits (820) constituting a watermark may be configured as “1101100101…”. At this time, among the plurality of bits (820), a bit mapped to a first area may be 1, a bit mapped to a second area may be 1, and a bit mapped to a third area may be 0. In addition, according to the insertion strengths (920) for each of the plurality of areas, a first insertion strength corresponding to the first area, a second insertion strength corresponding to the second area, and a third insertion strength corresponding to the third area may be level A, level A, and level C, respectively. At this time, the insertion strengths corresponding to level A and level C may be 1 and 2, respectively.

[0127] The electronic device (100) can insert 1, which is the product of 1, the first bit among the bits constituting the watermark, and 1, the first embedding strength, into the first area. The electronic device (100) can insert 1, which is the product of 1, the second bit among the bits constituting the watermark, and 1, the second embedding strength, into the second area. The electronic device (100) can insert information about 0, which is the product of 0, the third bit among the bits constituting the watermark, and 2, the third embedding strength, into the third area. That is, the watermark (1010) with embedded embedding strengths can be “{1}, {1}, {0}, …”

[0128] Accordingly, the electronic device (100) can obtain information about a watermark (1010) embedded with multiple area-specific insertion intensities.

[0129] In one or more embodiments, when inserting bits constituting a watermark into a plurality of areas constituting an image, the electronic device (100) may embed location information corresponding to each of the plurality of areas into the watermark, and insert a watermark with the location information embedded into the plurality of areas.

[0130] For example, the electronic device (100) can embed information about the location of multiple regions in a watermark (710) in which insertion strengths for multiple regions are embedded (S740).

[0131] Specifically, the electronic device (100) can generate patterns corresponding to multiple area-specific locations. At this time, the generated patterns can be expressed as images or matrices.

[0132] For example, as illustrated in FIG. 11, the electronic device (100) can generate a first pattern (1120) corresponding to a first region (1111) among a plurality of regions constituting a first color channel (1110) among a plurality of color channels constituting an image. The first color channel (1110) may be the color channel with the highest complexity among the plurality of color channels constituting an image. The generated first pattern (1120) may mean a pattern in which random numbers are arranged as a pattern corresponding to the first region in a matrix corresponding to the number of pixels included in the first region (1111).

[0133] That is, the electronic device (100) can arrange random numbers corresponding to the number of pixels in each of the plurality of areas. For example, if each of the plurality of areas is composed of 16 x 16 pixels, the electronic device (100) can arrange random numbers in the form of a 16 x 16 matrix.

[0134] The patterns corresponding to each of the multiple regions constituting the image may be different from each other. That is, the pattern corresponding to the first region and the pattern corresponding to the second region among the multiple regions may be different, and thus, each region may be distinguished from each other.

[0135] In addition, the electronic device (100) can embed the generated pattern into a plurality of bits constituting the watermark. Specifically, the electronic device (100) can embed information about the positions of multiple regions into the plurality of bits by multiplying each bit, in which the insertion intensity is reflected, by a matrix representing the positional patterns of multiple regions.

[0136] For example, as illustrated in FIG. 12, the electronic device (100) can obtain information about a watermark (1220) embedded with information about the plurality of region-specific insertion intensities and the plurality of region-specific positions by embedding a pattern (1210) corresponding to the plurality of region-specific positions into a watermark (1010) embedded with a plurality of region-specific insertion intensities.

[0137] Specifically, the electronic device (100) can obtain a first bit in which information about the location of the first region is embedded by multiplying a first bit, which is mapped to the first region and reflects a first insertion strength, by random numbers arranged in a first pattern corresponding to the first region. In the same way, the electronic device (100) can obtain a second bit in which information about the location of the second region is embedded, ..., an nth bit in which information about the location of the nth region is embedded.

[0138] When a watermark is obtained in which information regarding multiple region-specific insertion intensities and multiple region-specific locations is embedded, the electronic device (100) can insert the watermark in which information regarding multiple region-specific insertion intensities and multiple region-specific locations is embedded into an image (S750). At this time, the electronic device (100) can input the watermark in which information regarding multiple region-specific insertion intensities and multiple region-specific locations is embedded and the image into an artificial intelligence model to obtain an image in which the watermark is inserted.

[0139] For example, referring to FIG. 13, an electronic device (100) can obtain a color channel (1330) with a watermark inserted by inputting data of a watermark (1220) with information about multiple region-specific insertion intensities and multiple region-specific locations embedded therein, and a color channel (1310) to which the watermark is to be inserted, into a watermark embedding model (1320). The “watermark embedding model” may be referred to by terms such as “artificial intelligence model” or “neural network.”

[0140] Accordingly, the electronic device (100) can insert a watermark in which information on multiple region-specific insertion intensities and multiple region-specific locations are embedded in one color channel among multiple color channels constituting an image.

[0141] In one or more embodiments, the electronic device (100) of the present disclosure can extract an embedded watermark from an image into which a watermark has been embedded according to the method described above. This will be described with reference to FIG. 14.

[0142] FIG. 14 is a flowchart illustrating a method for an electronic device according to one embodiment of the present disclosure to extract a watermark from an image in which a watermark has been inserted.

[0143] Referring to FIG. 14, the electronic device (100) can acquire an image with an embedded watermark (S1410). At this time, the image may refer to an image with an embedded watermark according to the aforementioned method. At this time, the image may be an image with a portion of the image with an embedded watermark that has been compressed, cropped, or otherwise modified.

[0144] The electronic device (100) can receive an image with an embedded watermark from an external device. Alternatively, when the image with an embedded watermark is projected onto a projection surface, the electronic device (100) can extract the image with the embedded watermark from an image captured on the projection surface onto which the image is projected.

[0145] The electronic device (100) can identify the color channel with the watermark inserted among the plurality of color channels constituting the acquired image (S1420).

[0146] Specifically, the electronic device (100) can identify the color channel with the highest complexity among a plurality of color channels constituting an image with a watermark inserted. At this time, the color channel with the highest complexity may be the channel with the watermark inserted. That is, the electronic device (100) can identify a color channel containing information about the watermark and extract the watermark from the identified color channel.

[0147] At this time, the method by which the electronic device (100) identifies the channel with the highest complexity among the multiple color channels that constitute the image may be the same as the method described with reference to FIGS. 3 and 4.

[0148] When a color channel with a watermark inserted is identified, the electronic device (100) can identify the insertion intensity of the watermark inserted in the identified color channel (S1430).

[0149] At this time, the method for identifying the insertion intensity embedded in the watermark inserted into the identified color channel by the electronic device (100) may be the same as the method described in step S720 of FIG. 7.

[0150] When the color channel into which the watermark is inserted and the insertion strength for each of the multiple regions are identified, the electronic device (100) can extract information about the watermark inserted into the color channel (S1440).

[0151] Specifically, the electronic device (100) can acquire information about a watermark inserted into a color channel by inputting information about a color channel and information about an insertion intensity into an artificial intelligence model. In this case, the artificial intelligence model may be replaced with terms such as "watermark extraction model" or "neural network."

[0152] In this case, the information regarding the acquired watermark may be a watermark in which multiple region-specific insertion intensities and multiple region-specific locations are embedded.

[0153] The electronic device (100) can identify a plurality of bit sequences constituting a watermark from a watermark in which information about a plurality of region-specific insertion strengths and a plurality of region-specific positions is embedded (S1450).

[0154] Specifically, the electronic device (100) can identify the pattern of each region in which at least one of the plurality of bits constituting the watermark is inserted from the information about the acquired watermark.

[0155] Accordingly, the electronic device (100) can identify at least one region containing a pattern corresponding to the region where the nth bit of the watermark is inserted among the plurality of regions constituting the color channel in which the watermark is inserted.

[0156] And, the electronic device (100) can extract a value for at least one bit inserted in at least one identified area. And, the electronic device (100) can obtain a weighted average of the extracted bit values. At this time, the electronic device (100) can calculate the weighted average of the extracted bit values ​​using insertion intensities for multiple areas constituting the color channel in which the watermark is inserted. When calculating the weighted average, the electronic device (100) can assign a high weight to the value extracted from the area with a high insertion intensity.

[0157] If the calculated weighted average is greater than or equal to a predetermined value, the electronic device (100) can identify the value of the nth bit as “1”. If the calculated weighted average is less than a predetermined value, the electronic device (100) can identify the value of the nth bit as “0”.

[0158] For example, referring to FIG. 15, the electronic device (100) can identify a first area (1511), a second area (1512), a third area (1513), and a fourth area (1514) in which the first bit of a plurality of bits constituting the watermark is inserted in a color channel (1510) in which the watermark is inserted.

[0159] At this time, the values ​​for the bits extracted from the first area (1511), the second area (1512), the third area (1513), and the fourth area (1514) may be 1, 0, 1, and 0, respectively.

[0160] And, the insertion strength of each of the first region (1511), the second region (1512), the third region (1513), and the fourth region (1514) may be level A, level B, level C, and level D.

[0161] At this time, the electronic device (100) can obtain an average of the values ​​obtained by multiplying the bit values ​​extracted from each region by the values ​​corresponding to the insertion strengths of each region. The electronic device (100) can obtain “1” by multiplying the value 1 extracted from the first region (1511) by the value 1 corresponding to the insertion strength A level. In addition, the electronic device (100) can obtain “0” by multiplying the value 0 extracted from the second region (1512) by the value 1.5 corresponding to the insertion strength B level. In addition, the electronic device (100) can obtain “2” by multiplying the value 1 extracted from the third region (1513) by the value 2 corresponding to the insertion strength C level. In addition, the electronic device (100) can obtain “0” by multiplying the value 0 extracted from the fourth region (1514) by the value 2 corresponding to the D level. And, the electronic device (100) can calculate 1, which is an average value of the acquired values ​​“1”, “0”, “2”, and “0”. At this time, since the calculated value 1 is greater than or equal to the predetermined value 1, the electronic device (100) can identify the value of the first bit among the plurality of bits constituting the watermark as 1. The electronic device (100) can identify the plurality of bit sequences constituting the watermark by repeatedly performing the above-described operation for each of the plurality of bits constituting the watermark.

[0162] FIG. 16 is a flowchart for explaining a control method of an electronic device according to one embodiment of the present disclosure.

[0163] Referring to FIG. 16, the electronic device (100) can obtain information on the magnitude of frequency components for multiple color channels constituting an image (S1610).

[0164] The electronic device (100) can identify a color channel with the highest ratio of high-frequency components among multiple color channels (S1620).

[0165] According to one embodiment of the present disclosure, the electronic device (100) can generate quantized DCT (Discrete Cosine Transform) coefficients from a plurality of sub-regions constituting each of a plurality of regions. In addition, the electronic device (100) can calculate a ratio of the sum of at least one AC coefficient excluding an intermediate frequency region to a DC coefficient among the quantized DCT coefficients for each of the plurality of sub-regions. The electronic device (100) can identify a channel having the highest average of the ratios calculated from each of the plurality of sub-regions among the plurality of channels as a channel having the highest complexity.

[0166] The electronic device (100) can identify the insertion strength of the watermark for each of the plurality of regions based on the magnitude of the high-frequency component of the identified color channel for each of the plurality of regions constituting the image (S1630).

[0167] According to one embodiment of the present disclosure, the electronic device (100) can increase the insertion strength of a watermark in an area having a high ratio of high frequency components among a plurality of areas.

[0168] The electronic device (100) can embed information about insertion strengths for each of multiple regions and positions for each of multiple regions into a watermark (S1640).

[0169] According to one embodiment of the present disclosure, the electronic device (100) can generate a pattern corresponding to a location of each of the plurality of regions in each of the plurality of regions. The electronic device (100) can combine a bit value constituting a watermark with the generated pattern.

[0170] According to one embodiment of the present disclosure, the electronic device (100) can arrange random numbers in a pattern corresponding to the location of each of a plurality of areas. The electronic device (100) can embed the arranged random numbers in a watermark with an embedded insertion strength.

[0171] The electronic device (100) can insert a watermark embedded with information about insertion strengths for each of multiple regions and positions for each of multiple regions into an image (S1650).

[0172] According to one embodiment of the present disclosure, the electronic device (100) can obtain an image with an embedded watermark by inputting a watermark in which information about a color channel identified among a plurality of first artificial intelligence models and information about insertion intensities for each of a plurality of regions and positions for each of a plurality of regions are embedded into an artificial intelligence model corresponding to an identified channel among a plurality of first artificial intelligence models.

[0173] According to one embodiment of the present disclosure, when an image with an embedded watermark is acquired, the electronic device (100) can calculate the size ratio of high frequency components of each of a plurality of color channels constituting the acquired image to identify a color channel in which a watermark is embedded among a plurality of channels constituting the projected image. The electronic device (100) can identify at least one of information on a plurality of areas from the color channel in which the watermark is embedded. The electronic device (100) can identify the positions of the plurality of areas in which the watermark is embedded from at least one of the information on the plurality of areas. Based on the positions of the plurality of areas in which the watermark is embedded, the electronic device (100) can identify a bit value constituting a watermark embedded in each of the plurality of areas, and extract the embedded watermark.

[0174] According to one embodiment of the present disclosure, the electronic device (100) can identify an embedding intensity embedded in a watermark for each of a plurality of regions constituting a channel into which a watermark is embedded, based on a size ratio of high frequency components for each of a plurality of regions constituting a channel into which a watermark is embedded. The electronic device (100) can extract a watermark from a color channel into which a watermark is embedded using the embedding intensity embedded in the watermark.

[0175] According to one embodiment of the present disclosure, an electronic device (100) can extract a watermark from a channel into which a watermark is inserted by inputting a color channel into which a watermark is inserted and an insertion strength embedded in the watermark to an artificial intelligence model corresponding to a channel into which an identified watermark is inserted among a plurality of second artificial intelligence models.

[0176] Although various embodiments have been described above, each embodiment is not necessarily implemented individually, and may be combined with at least one other embodiment, either wholly or partially, to be implemented together in a single product.

[0177] Meanwhile, the terms "part" or "module" used in the present disclosure include units composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A "part" or "module" may be an integrally composed component, a minimum unit performing one or more functions, or a portion thereof. For example, a module may be composed of an application-specific integrated circuit (ASIC).

[0178] Various embodiments of the present disclosure may be implemented as software comprising instructions stored on machine-readable storage media (e.g., a computer). The machine may include an electronic device (100) according to the disclosed embodiments, which is a device capable of calling instructions stored from the storage media and operating according to the called instructions. When the instructions are executed by a processor, the processor may perform a function corresponding to the instructions directly or using other components under the control of the processor. The instructions may include code generated or executed by a compiler or an interpreter. The machine-readable storage media may be provided in the form of non-transitory storage media. Here, "non-transitory" means only that the storage media does not contain a signal and is tangible, and does not distinguish whether data is stored semi-permanently or temporarily in the storage media.

[0179] According to one or more embodiments, the method according to the various embodiments disclosed herein may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or online through an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a storage medium such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0180] Each component (e.g., a module or a program) according to various embodiments may be composed of one or more entities, and some of the aforementioned sub-components may be omitted, or other sub-components may be further included in various embodiments. Alternatively or additionally, some components (e.g., a module or a program) may be integrated into a single entity, which may perform the same or similar functions as those performed by each of the respective components prior to integration. Operations performed by a module, program, or other component according to various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added.

Claims

1. In electronic devices, At least one processor comprising a processing circuit; and memory for storing commands; When the above instructions are individually or collectively executed by the at least one processor, the electronic device, Obtain information about the magnitude of frequency components for multiple color channels constituting an image, Identifying the color channel having the highest ratio of high frequency components among the above plurality of color channels, Based on the magnitude of the high frequency component of the identified color channel for each of the plurality of regions constituting the image, the embedding strength of the watermark for each of the plurality of regions is identified, Embedding information corresponding to the insertion strength for each of the plurality of regions and the positions for each of the plurality of regions into the watermark, An electronic device that inserts a watermark into the image, wherein information corresponding to the insertion strength for each of the plurality of regions and the positions for each of the plurality of regions is embedded therein.

2. In paragraph 1, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, Generating quantized DCT (Discrete Cosine Transform) coefficients from a plurality of sub-regions constituting each of the plurality of regions, wherein the quantized DCT coefficients include at least one AC coefficient, For each of the plurality of sub-regions, determine the ratio of the sum of at least one AC coefficient excluding the AC coefficient of the intermediate frequency region to the DC coefficient among the quantized DCT coefficients, and the AC coefficient of the intermediate frequency region is located between the DC coefficient and the at least one AC coefficient. An electronic device that identifies a color channel having the highest average of ratios determined from each of the plurality of sub-regions among the plurality of color channels as a color channel having the highest complexity.

3. In paragraph 1, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, An electronic device that increases the insertion strength of the watermark in an area having the highest ratio of the size of the high-frequency component among the above multiple areas.

4. In paragraph 1, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, Generate a pattern corresponding to the location of each of the plurality of regions in each of the plurality of regions, An electronic device that combines the bit values ​​constituting the watermark with the generated pattern.

5. In paragraph 4, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, Arrange random numbers in a pattern corresponding to the location of each of the above multiple areas, An electronic device that embeds the arranged random numbers in a watermark in which information corresponding to the plurality of region-specific insertion intensities and the plurality of region-specific locations is embedded.

6. In paragraph 1, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, An electronic device that inputs a watermark, in which information corresponding to the identified color channel, the insertion intensity for each of the plurality of regions, and the location for each of the plurality of regions are embedded, into an artificial intelligence model corresponding to the identified color channel among a plurality of first artificial intelligence models, thereby obtaining an image in which the watermark is inserted.

7. In paragraph 1, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, When the image with the watermark inserted is acquired, the size ratio of the high frequency components of each of the plurality of color channels constituting the acquired image is determined to identify the color channel with the watermark inserted among the plurality of color channels constituting the projected image, Identifying at least one of the information for the plurality of areas from the color channel into which the watermark is inserted, Identifying the location of the plurality of areas in which the watermark is inserted from at least one of the information about the plurality of areas, An electronic device that extracts the inserted watermark by identifying the bit values ​​constituting the watermark inserted in each of the plurality of regions based on the positions of the plurality of regions in which the watermark is inserted.

8. In paragraph 7, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, Based on the size ratio of high frequency components of each of a plurality of regions constituting the color channel into which the watermark is inserted, the insertion strength embedded in the watermark is identified for each of a plurality of regions constituting the color channel into which the watermark is inserted, An electronic device that extracts a watermark from a color channel into which the watermark is embedded by using an embedding intensity embedded in the watermark.

9. In paragraph 7, When the above instructions are individually or collectively executed by the at least one processor, the electronic device, An electronic device that extracts a watermark from a color channel into which the watermark is inserted by inputting the color channel into which the watermark is inserted and the insertion strength embedded in the watermark into an artificial intelligence model corresponding to the color channel into which the identified watermark is inserted among a plurality of second artificial intelligence models.

10. In a method for controlling an electronic device, A step of obtaining information on the magnitude of frequency components for multiple color channels constituting an image; A step of identifying a color channel having the highest ratio of high frequency components among the plurality of color channels; A step of identifying the embedding strength of a watermark for each of the plurality of regions based on the magnitude of the high frequency component of the identified color channel for each of the plurality of regions constituting the image; A step of embedding information corresponding to the insertion strength for each of the plurality of regions and the positions for each of the plurality of regions into the watermark; and A control method comprising: a step of inserting a watermark into the image, wherein information corresponding to the insertion strength for each of the plurality of regions and the positions for each of the plurality of regions is embedded therein.

11. In paragraph 10, The above control method is, A step of generating quantized DCT (Discrete Cosine Transform) coefficients from a plurality of sub-regions constituting each of the plurality of regions; A step of determining a ratio of the sum of at least one AC coefficient excluding the AC coefficient of the intermediate frequency region to the DC coefficient among the quantized DCT coefficients for each of the plurality of sub-regions; and A control method further comprising: a step of identifying a color channel having the highest average of ratios determined from each of the plurality of sub-regions among the plurality of color channels as a channel having the highest complexity.

12. In paragraph 10, The above control method is, A control method further comprising: a step of increasing the insertion strength of the watermark in an area having the highest size ratio of the high-frequency component among the plurality of areas.

13. In paragraph 10, The above control method is, A step of generating a pattern corresponding to the location of each of the plurality of regions in each of the plurality of regions; and A control method further comprising a step of combining bit values ​​constituting the watermark with the generated pattern.

14. In paragraph 13, The above control method is, A step of arranging random numbers in a pattern corresponding to the location of each of the plurality of areas; and A control method further comprising a step of embedding the arranged random numbers into a watermark in which information corresponding to the plurality of region-specific insertion intensities and the plurality of region-specific locations is embedded.

15. In paragraph 10, The above control method is, A control method further comprising: a step of inputting a watermark, in which information corresponding to the identified color channel and the insertion intensity for each of the plurality of regions and the positions for each of the plurality of regions are embedded, into an artificial intelligence model corresponding to the identified color channel among a plurality of first artificial intelligence models, thereby obtaining an image in which the watermark is inserted.

Images