Method for generating watermark and electronic device performing the same

Abstract

A method for generating a watermark performed by an electronic device is disclosed. The watermark generation method includes the steps of receiving an input image and information corresponding to the input image; generating watermark data based on the information corresponding to the input image; dividing the input image into a plurality of regions; determining a candidate region among the plurality of regions to insert the watermark data based on the input image and the watermark data; and generating a watermark image by inserting the watermark data into the candidate region.

Description

Technology Field

[0001] The present disclosure relates to a method for generating a watermark, a non-transient computer-readable storage medium, and an electronic device. Background Technology

[0002] Digital watermarking technology is being developed to prevent the illegal copying and forgery of digital content. Digital watermarking involves embedding identification data that is not visible to the naked eye into content such as images, audio, and video, and is used to track the source of the content or protect copyright.

[0003] Generally, watermarks are inserted using pixel modulation in the frequency domain (DCT, DWT, etc.) or spatial domain, and upon restoration, the inserted data is detected to verify authenticity or information stored in the data. However, limitations in conventional digital watermarking technology, such as reduced visual quality and reduced data stability, have been pointed out.

[0004] In particular, conventional digital watermarking technology often involves uniformly inserting watermarks across the entire image area, which has resulted in problems such as distortion or color deformation in visually important areas. This issue causes a quality degradation perceptible to users, and consequently, the insertion of the watermark itself can lower the visual credibility of the content. The problem to be solved

[0005] One embodiment aims to provide a watermark generation method that can invisibly insert watermark data while maintaining the visual quality of an input image.

[0006] One embodiment aims to provide a watermark generation method that determines a watermark insertion location by considering the visual characteristics of each region of an input image and inserts watermark data at the determined location.

[0007] One embodiment aims to provide a watermark generation method that minimizes visual distortion by variably adjusting the watermark insertion intensity based on an interest score for each of a plurality of regions.

[0008] One embodiment aims to provide a watermark generation method that improves data reliability by verifying the quality after inserting watermark data and selecting only watermark images that have successfully been verified as final output targets.

[0009] However, the problems that the present invention aims to solve are not limited to those mentioned above, and may include problems that are not mentioned but can be clearly understood by those skilled in the art from the description below. means of solving the problem

[0010] A watermark generation method performed by an electronic device according to one or more embodiments of the present disclosure, comprising: receiving an input image and information corresponding to the input image; generating watermark data based on the information corresponding to the input image; dividing the input image into a plurality of regions; determining a candidate region among the plurality of regions to insert the watermark data based on the input image and the watermark data; and generating a watermark image by inserting the watermark data into the candidate region.

[0011] A non-transient computer-readable storage medium storing computer instructions that cause the electronic device to perform an operation when executed by a processor of an electronic device according to one or more embodiments of the present disclosure, wherein the operation comprises: receiving an input image and information corresponding to the input image; generating watermark data based on the information corresponding to the input image; dividing the input image into a plurality of regions; determining a candidate region among the plurality of regions to insert the watermark data based on the input image and the watermark data; and generating a watermark image by inserting the watermark data into the candidate region.

[0012] An electronic device according to one or more embodiments of the present disclosure includes a non-transient computer-readable storage medium having a watermark printed on its surface that is generated using the watermark generation method described above, and a processor configured to retrieve and play data stored in the non-transient computer-readable storage medium. Effects of the invention

[0013] One embodiment inserts watermark data in an invisible form while maintaining the visual quality of the input image, so stable watermark processing without visual distortion may be possible.

[0014] In one embodiment, the watermark insertion area and insertion intensity can be variably adjusted based on the interest score for each region of the input image, thereby improving the reliability of watermark detection while preventing quality degradation of visually important parts.

[0015] One embodiment can encrypt various information corresponding to an input image and convert it into watermark data, thereby effectively identifying the source or authenticity of the content.

[0016] One embodiment can precisely adjust the insertion strength by controlling the degree of compression and deformation of the watermark data, thereby enabling the generation of an invisible watermark image without visual distortion. Brief explanation of the drawing

[0017] FIG. 1 is a schematic block diagram of a computing system according to one or more embodiments. FIG. 2 is a flowchart illustrating a method for an electronic device according to one or more embodiments to generate a watermark image. FIG. 3 is a flowchart illustrating a watermark data generation process according to one or more embodiments. FIG. 4 is a diagram illustrating a process for determining feature data according to one or more embodiments. FIG. 5 is a diagram illustrating a candidate region determination process according to one or more embodiments. FIG. 6 is a flowchart for explaining the process of inserting watermark data according to the watermark insertion strength according to one or more embodiments. FIG. 7 is a drawing for explaining the process of generating a watermark image according to one or more embodiments. FIG. 8 is a flowchart illustrating the process of verifying the quality of watermark data according to one or more embodiments. Specific details for implementing the invention

[0018] The various embodiments described in this specification are illustrative for the purpose of clearly explaining the technical concept of this disclosure and are not intended to limit it to specific embodiments. The technical concept of this disclosure includes various modifications, equivalents, alternatives, and embodiments optionally combined from all or part of each embodiment described in this specification. Furthermore, the scope of the technical concept of this disclosure is not limited to the various embodiments presented below or the specific descriptions thereof.

[0019] Terms used in this specification, including technical or scientific terms, may have the meaning generally understood by those skilled in the art to which this disclosure pertains, unless otherwise defined.

[0020] Expressions used herein such as “comprising,” “may compose,” “possessing,” “possessing,” “having,” and “possessing” imply the existence of the subject feature (e.g., function, operation, or component, etc.) and do not exclude the existence of other additional features. That is, such expressions should be understood as open-ended terms implying the possibility of including a second embodiment.

[0021] In this specification, singular expressions include plural expressions unless the context clearly specifies them as singular. Additionally, plural expressions include singular expressions unless the context clearly specifies them as plural. Throughout the specification, when a part is described as including a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0022] Additionally, the terms 'module' or 'part' as used in the specification refer to software or hardware components, and the 'module' or 'part' performs certain roles. However, the meaning of 'module' or 'part' is not limited to software or hardware. The 'module' or 'part' may be configured to reside in an addressable storage medium or configured to run on one or more processors. Thus, as an example, the 'module' or 'part' may include components such as software components, object-oriented software components, class components, and task components, and at least one of processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. The components and the functions provided within the 'module' or 'part' may be combined into a smaller number of components and 'modules' or 'parts', or further separated into additional components and 'modules' or 'parts'.

[0023] According to one embodiment of the present disclosure, a ‘module’ or ‘part’ may be implemented as a processor and memory. The term ‘processor’ should be broadly interpreted to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, the term ‘processor’ may refer to an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. The term ‘processor’ may also refer to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors combined with a DSP core, or any other combination of such configurations. Additionally, the term ‘memory’ should be broadly interpreted to include any electronic component capable of storing electronic information. 'Memory' may refer to various types of processor-readable media, such as Random Access Memory (RAM), Read-Only Memory (ROM), Non-Volatile Random Access Memory (NVRAM), Programmable Read-Only Memory (PROM), Erasable-Programmable Read-Only Memory (EPROM), Electrically Erasable PROM (EEPROM), Flash Memory, Magnetic or Optical Data Storage Devices, Registers, etc. If a processor can read information from memory and / or write information to memory, the memory is said to be in an electronic communication state with the processor. Memory integrated into a processor is in an electronic communication state with the processor.

[0024] Expressions such as "first," "second," or "first," "second" as used in this specification are used to distinguish one object from another when referring to a plurality of objects of the same kind, unless otherwise indicated in the context, and do not limit the order or importance of said objects.

[0025] Expressions used herein such as “A, B, and C,” “A, B, or C,” “A, B, and / or C,” or “at least one of A, B, and C,” “at least one of A, B, or C,” “at least one of A, B, and / or C,” “at least one selected from A, B, and C,” “at least one selected from A, B, or C,” “at least one selected from A, B, and / or C,” etc., may mean each of the listed items or all possible combinations of the listed items. For example, “at least one selected from A and B” may refer to (1) A, (2) at least one of A, (3) B, (4) at least one of B, (5) at least one of A and at least one of B, (6) at least one of A and B, (7) at least one of B and A, and (8) all of A and B.

[0026] As used herein, the expression “based on” is used to describe one or more factors affecting an act or action of a decision or judgment described in the phrase or sentence containing such expression, and such expression does not exclude additional factors affecting said act or action of a decision or judgment.

[0027] As used in this specification, the expression that a certain component (e.g., a first component) is "connected" or "connected" to another component (e.g., a second component) may mean that the said certain component is not only directly connected or connected to the said other component, but is also connected or connected through a new other component (e.g., a third component).

[0028] As used herein, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," or "capable of." Such expression is not limited to the meaning of "specifically designed in hardware," and, for example, a processor configured to perform a specific operation may mean a generic-purpose processor capable of performing that specific operation by executing software.

[0029] Various embodiments of the present disclosure will be described below with reference to the accompanying drawings. In the accompanying drawings and the description thereof, identical or substantially equivalent components may be given the same reference numerals. Furthermore, in the description of the various embodiments below, the description of identical or corresponding components may be omitted, but this does not mean that such components are not included in the embodiments.

[0030] FIG. 1 is a schematic block diagram of a computing system according to one or more embodiments.

[0031] Referring to FIG. 1, a computing system (10) according to one embodiment can obtain playback information of a sound source played in an electronic device (100) and playback information of a sound source played in a playback device (200). The computing system (10) can verify the validity of the playback information obtained from each of the electronic device (100) and the playback device (200), and can identify the number of times a sound source is played from the valid playback information for which verification was successful.

[0032] A computing system (10) according to one embodiment can verify the validity of the playback information of a sound source played in the playback device (200) by determining whether there is a match between the first identification information of the playback device (200) and the second identification information stored in the electronic device (200).

[0033] A computing system (10) according to one embodiment acquires an image (hereinafter referred to as an input image) printed on one surface of a storage device inserted into a playback device (200), and can acquire watermark data from the acquired input image. Here, the watermark data may include data regarding sound source information stored in the storage device and identification information of the storage device. The computing system (10) can verify the validity of the playback information of a sound source played on the playback device (200) based on the watermark data.

[0034] A computing system (10) according to one embodiment can verify the validity of identification information of an electronic device (100) and playback information of a sound source played on an electronic device (100) based on a database stored in a server (300).

[0035] A computing system (10) according to one embodiment can aggregate the number of times a sound source played on a playback device (200) and the number of times a sound source played on an electronic device (100) is played on a server (300), and then transmit the aggregated number of plays to a Digital Service Provider (DSP). The DSP can update playback statistics data by identifying the total number of plays for a specific sound source and the playback contribution per user.

[0036] In this way, the computing system (10) can implement reliable sound source playback data management by verifying the validity of the playback information and transmitting the verified playback information to the DSP.

[0037] A computing system (10) according to one embodiment includes an electronic device (100), a playback device (200), and a server (300). However, it is not limited thereto, and the computing system (10) may be implemented with some components excluded or with additional components included.

[0038] An electronic device (100) according to one embodiment can receive playback information for a sound source played from a playback device (200). The electronic device (100) can verify the validity of the playback information received from the playback device (200) and transmit the playback information for which verification was successful and the playback information for the sound source played from the electronic device (100) to a server (300). Here, the electronic device (100) can be implemented as various types of electronic devices such as a portable communication terminal (mobile phone), a smartphone, a tablet PC, a wearable device, an artificial intelligence (AI) device, etc.

[0039] An electronic device (100) according to one embodiment can generate watermark data and generate a watermark image with the watermark data inserted. The watermark image may be placed on or printed on the outer surface of a storage device. According to an embodiment, the entity generating the watermark image may be a component outside the computing system (10).

[0040] The electronic device (100) can acquire an image of the storage device using a camera. The electronic device (100) can acquire watermark data by reading the image of the storage device. For example, the electronic device (100) can acquire second sound source information stored in the storage device from the watermark image and verify the validity of the playback information for the sound source played in the playback device (200) by comparing it with the first sound source information of the sound source played in the playback device (200).

[0041] A playback device (200) according to one embodiment may be a device for playing a sound source stored in a storage device. Specifically, the playback device (200) may be a device for playing a sound source stored in a storage device inserted into the playback device (200). Here, the playback device (200) may be implemented as various types of electronic devices such as an audio player, a digital media player, a smart speaker, a set-top box, a portable music player, etc. However, the embodiment is not necessarily limited thereto, and the storage device may further store images, videos, etc., and the playback device (200) may provide data to the user by visually outputting it through a display.

[0042] A playback device (200) according to one embodiment may play a sound source stored in a storage device and transmit a first sound source information, a first playback information, and a first identification information of the played sound source to an electronic device (100). A playback device (200) according to one embodiment may play a video stored in a storage device and transmit a second sound source information, a second playback information, and a second identification information of the played video to an electronic device (100). According to an embodiment, if the sound source and the video match, the playback device (200) may sum the playback information and transmit it to the electronic device (100). For example, if the video is a music video corresponding to the sound source, the playback device (200) may sum the first and second playback information.

[0043] A playback device (200) according to one embodiment receives artist information corresponding to user input, receives an alarm time and alarm text for outputting an alarm, and can generate voice data by using an artificial neural network module to convert the alarm text into an artist voice based on the artist information. When the alarm time arrives, the playback device (200) can output an alarm based on the voice data.

[0044] A server (300) according to one embodiment manages sound source information and playback information received from an electronic device (100) and can verify the validity of the received playback information. The server (300) can verify the validity of the playback information by comparing the sound source information received from the electronic device (100) with the sound source information stored in a sound source database. If the server (300) verifies that the playback information is valid, it can store the playback information as a valid playback history and then transmit the sound source information and playback information to a DSP.

[0045] A storage device according to one embodiment may be a storage medium inserted into a playback device (200) to provide sound sources, images, video, voice, etc. Here, the storage device is a non-temporarily computer-readable storage medium and may be implemented in various types such as, for example, an SD card (Secure Digital Card), a microSD card, a CF (Compact Flash) card, a USB memory device, but the embodiment is not necessarily limited thereto.

[0046] A storage device according to one embodiment may include original data of a sound source, identification information of the sound source, voice, image, video of an artist (or each member belonging to the artist), copyright information, manufacturer information, and a watermark image. A playback device (200) may read the data of the storage device and output it audibly or visually. The watermark image may include watermark data as an image printed on one surface of the storage device. The watermark image may be used to verify the validity of the data stored in the storage device. When the storage device is inserted into the playback device (200), the data stored internally may be played by a program stored in the playback device (200).

[0047] Meanwhile, the electronic device (100) may generate a watermark image placed on one surface of a storage device to verify the validity of sound source information and playback information received from the playback device (200). Hereinafter, various embodiments in which the electronic device (100) generates a watermark image will be described in detail with reference to the drawings.

[0048] FIG. 2 is a flowchart illustrating a method for an electronic device according to one or more embodiments to generate a watermark image.

[0049] Referring to FIG. 2, an electronic device according to one embodiment can receive an input image and information corresponding to the input image (S210).

[0050] The input image may be an image comprising at least one of an album main image and a person image printed on one surface of a storage device. The input image may be a digital image captured through a scanning device or a camera. For example, the input image may be a representative image printed on the cover of an album, or a portrait image of an artist or a specific person included in the album.

[0051] Information corresponding to the input image may be information including at least one of manufacturer information, album information, person information, agency information, image capture information, release date information, and track information. For example, information corresponding to the input image may include various information such as the name of the manufacturer that produced the album or playback device, the date of production of the album, the album name, the number of songs included, the artist name, the group name, the track order, and the playback time.

[0052] According to one embodiment, the electronic device can generate watermark data based on information corresponding to an input image (S220).

[0053] Watermark data may be data obtained by encrypting or encoding each piece of information corresponding to the input image. Watermark data may be data obtained by combining information corresponding to the input image and encrypting or encoding it. Watermark data may include a unique identifier corresponding to the input image. For example, watermark data may include data obtained by encrypting or hashing strings corresponding to the manufacturer code, album ID, and release date, respectively. However, watermark data is not limited thereto and may be referred to in various ways, such as authentication data, identification data, or security data; nevertheless, in this disclosure, it will be collectively referred to as watermark data.

[0054] According to one embodiment, an electronic device can generate watermark data using manufacturer information and album information as inputs. The electronic device can obtain a standardized string by performing a standardization process of uppercase conversion, delimiter removal, and limiting the allowed character set on the manufacturer information and album information.

[0055] An electronic device can perform processing to distinguish between manufacturer information and album information. For example, the electronic device can generate a first message and a second message by combining at least one of a domain distinguishing constant and an optional salt with each of the manufacturer information and album information. The domain distinguishing constant may be a fixed string that is combined during hash calculation to distinguish between different types of input data, such as a manufacturer and an album. Even if the manufacturer information and album information happen to be identical, the electronic device can secure independent hash spaces for each type of data through the domain distinguishing constant, thereby preventing hash collisions between different input data.

[0056] An optional salt can be a random number or a private string added to the input data during hash calculation to reduce the predictability of the hash value. Electronic devices can prevent backtracking or forgery from the outside by generating different hash values ​​for the same input data due to different salt values.

[0057] The electronic device can calculate a first hash value and a second hash value for a first message and a second message. The electronic device can obtain a combined hash by performing a bitwise exclusive OR (XOR) operation on the first and second hash values. The electronic device can generate watermark data based on the combined hash. For example, the electronic device can generate watermark data by taking a predetermined leading bit (e.g., 160 bits) of the combined hash.

[0058] According to an embodiment, the electronic device may form a final hash by placing a version field (e.g., 4 bits) and a namespace field (e.g., 4 bits) at the front of the combined hash for watermark format compatibility, and adding an error detection code (e.g., CRC16) for the payload itself at the rear if necessary.

[0059] According to one embodiment, the electronic device can divide the input image into a plurality of regions (S230).

[0060] An electronic device can divide an input image into multiple regions, either evenly or unequally, according to the size, resolution, and visual characteristics of the input image. For example, the electronic device can divide the entire pixel area of ​​the input image into blocks of a certain size evenly. For example, the electronic device can divide the entire pixel area of ​​the input image evenly into 8×8 pixel or 16×16 pixel regions.

[0061] For example, an electronic device can detect a main subject in an input image and determine a background area or a complex textured area excluding the main subject in the input image. The electronic device may also perform uneven segmentation centered on the background area or the complex textured area. For example, the electronic device can identify areas containing a person's face, a logo, or an album title from the input image and unevenly segment the input image centered on the areas excluding the identified areas.

[0062] According to one embodiment, the electronic device can determine a candidate region among a plurality of regions to insert watermark data based on an input image and watermark data (S240).

[0063] The electronic device analyzes the visual features and statistical characteristics of each divided region to determine as candidate regions areas where visual distortion is minimized and detection reliability is high when watermark data is inserted.

[0064] For example, an electronic device acquires interest information including visual attention information, brightness distribution information, color contrast information, and object recognition information for each region, and can determine areas with high contrast or low brightness distribution as candidate regions based on the interest information for each region. In other words, the electronic device can insert watermark data into the determined candidate regions by determining areas that are difficult for humans to perceive due to the presence of minute pixel variations as candidate regions.

[0065] According to one embodiment, the electronic device can generate a watermark image by inserting watermark data into a candidate area (S250).

[0066] A watermark image may be an image in which watermark data is invisibly embedded in the input image. Although the watermark image is visually identical to the original input image, watermark data may be invisibly embedded due to the presence of minute pixel changes or frequency component changes that are imperceptible to the human eye.

[0067] A watermark image may be an image captured by a camera and used to verify a storage device. For example, when a user photographs the surface of a storage device with a camera, the electronic device can extract watermark data from the captured image and verify whether the storage device is genuine, an official release of a specific album, or a counterfeit or duplicate product. The server may store multiple genuine watermark data in storage for authentication purposes. The electronic device can determine the authenticity of the watermark data detected by the server. For example, the electronic device transmits the detected watermark data to the server, and the server determines the authenticity of the received watermark data by comparing it with the storage data and notifies the electronic device.

[0068] FIG. 3 is a flowchart illustrating a watermark data generation process according to one or more embodiments.

[0069] Referring to FIG. 3, an electronic device according to one embodiment can convert information corresponding to an input image into feature data (S310).

[0070] Feature data may be data obtained by converting information corresponding to an input image into a form that can be processed by an electronic device. Feature data may be used as input values ​​for encryption and encoding during the watermark data generation process. Feature data may be data generated by combining or processing parts of data corresponding to manufacturer information, album information, person information, agency information, image capture information, release date information, and track information, respectively.

[0071] According to one embodiment, the electronic device can perform encryption based on feature data and a preset encryption key (S320).

[0072] The pre-configured encryption key may be a manufacturer's proprietary key registered to the electronic device, a server authentication key, or an encryption key stored in a security module within the electronic device. The pre-configured encryption key may be a manufacturer's proprietary key provided through the server.

[0073] According to one example, the electronic device may encrypt feature data using symmetric key encryption (e.g., AES, SEED, ARIA) or asymmetric key encryption (e.g., RSA, ECC) algorithms. When performing encryption, the electronic device may selectively apply a block cipher or a stream cipher method depending on the length and format of the feature data. The electronic device may perform encryption by generating different ciphertexts by combining an Initialization Vector (IV) or a random seed.

[0074] According to one embodiment, the electronic device can generate watermark data by converting the result of performing encryption into bit-unit data (S330).

[0075] According to one example, an electronic device can convert the result of performing encryption into a bitstream form according to a certain rule. For example, if the encrypted result is a ciphertext of length 128 bits or 256 bits, the electronic device can divide the data into 1-bit units and convert it into a continuous bitstream form.

[0076] For example, an electronic device can generate watermark data by adding an Error Correction Code (ECC) or a parity bit to bit-unit data. By adding the ECC and parity bit, the original bit sequence can be accurately restored upon watermark detection, even if some data loss or noise occurs.

[0077] FIG. 4 is a diagram illustrating a process for determining feature data according to one or more embodiments.

[0078] Referring to FIG. 4, according to one embodiment, the electronic device can convert each piece of information corresponding to an input image (410) into candidate feature data (420-1 to 420-3). The candidate feature data may be digital data generated by normalizing or hashing the text, number, or code value of each piece of information.

[0079] For example, among the information corresponding to the input image, the electronic device can convert manufacturer information into first candidate feature data (420-1), release date information into second candidate feature data (420-2), and artist information into third candidate feature data (420-3). However, the embodiment is not necessarily limited thereto, and the electronic device can determine candidate feature data by combining various information corresponding to the input image.

[0080] According to one embodiment, the electronic device can determine the final feature data (440) for generating watermark data based on a pre-set importance list (430) among a plurality of candidate feature data (420-1 to 420-3).

[0081] The pre-set importance list may be a list in which candidate feature data (420-1 to 420-3) are listed according to a pre-set importance priority based on the type of the input image (410). For example, if the input image (410) is a person image, the importance of artist information and agency information may be set relatively high. For example, if the input image (410) is an album cover image, the importance of album information and release date information may be set relatively high. In the embodiments, the importance of manufacturer information may be set highest.

[0082] For example, if the input image (410) is a person image, the priority list can be set in the order of the first candidate feature data (420-1) corresponding to manufacturer information, the third candidate feature data (420-3) corresponding to artist information, and the second candidate feature data (420-2) corresponding to release date information.

[0083] According to one embodiment, the electronic device can determine the final feature data (440) based on a threshold number of candidate feature data that are set to have a higher priority among a preset importance list.

[0084] For example, if the threshold number is set to 2, the electronic device can determine the final feature data (440) based on the first candidate feature data (420-1) and the third candidate feature data (420-3), which are set with higher priority among the pre-set importance lists.

[0085] In other words, the electronic device can prevent unnecessary data duplication during watermark generation and improve the data efficiency, recognition accuracy, and identification reliability of the watermark by reflecting only selected information based on a pre-set importance list in the final feature data, rather than including all information corresponding to the input image.

[0086] FIG. 5 is a diagram illustrating a candidate region determination process according to one or more embodiments.

[0087] Referring to FIG. 5, an electronic device according to one embodiment can divide an input image (510) into a plurality of regions (520-1 to 520-20). For example, the electronic device can divide the input image (510) into 20 equal regions in the shape of 4 x 5.

[0088] According to one embodiment, the electronic device may determine interest information (530) for each of a plurality of regions (520-1 to 520-20). Based on the interest information (530), the electronic device may determine candidate regions (520-1, 520-4, 520-10, 520-17).

[0089] The interest information (530) may be information including visual attention information, brightness distribution information, color contrast information, and object recognition information. The interest information (530) may be information that quantitatively expresses the visual characteristics of each region, serving as an indicator representing the visual, structural, or object recognition characteristics of the input image (510).

[0090] Visual attention information may be information containing attention values ​​for each area by analyzing the area among multiple areas (520-1 to 520-20) where the user's gaze is likely to be focused. Visual attention information may be obtained using an algorithm that analyzes color, brightness, contrast, and texture contrast, or an artificial neural network that is pre-trained based on deep learning and outputs a probability of gaze focus. Brightness distribution information may be information containing values ​​for the average brightness and brightness standard deviation of each area. Color contrast information may be information containing values ​​calculated by analyzing the color difference between adjacent areas for each of the multiple areas (520-1 to 520-20). Object recognition information may be information indicating whether one or more objects included in the input image (510) are recognized and whether the corresponding object is included in each area.

[0091] According to one embodiment, the electronic device can synthesize interest information (530) to calculate an interest score (540) corresponding to each of a plurality of regions (520-1 to 520-20).

[0092] The interest score (540) may be a final score calculated by applying a pre-set weight to each score corresponding to visual attention information, brightness distribution information, color contrast information, and object recognition information. The weight applied to the visual attention information may be greater than the weights applied to the brightness distribution information and color contrast information. For example, if a weight of 0.4 is set for visual attention, 0.2 for brightness distribution, 0.2 for color contrast, and 0.2 for object recognition information, the electronic device may calculate an interest score (540) for the first area (520-1) by summing the visual attention value*0.4, brightness distribution value*0.2, color contrast value*0.2, and object recognition value*0.2.

[0093] By assigning the greatest weight to visual attention information, the electronic device can insert watermark data centered on areas that are not visually perceived, thereby avoiding areas where the human gaze is focused. As a result, visual quality degradation or distortion of the watermarked image is minimized, and an effect can be achieved where it is difficult for users to visually distinguish the difference between the original image and the watermarked image.

[0094] In particular, since visual attention reflects the characteristics of actual human visual perception better than brightness or color contrast, visual consistency within the gaze area of ​​the image can be maintained even after watermark insertion by assigning a high weight to such information. As a result, the watermark insertion method of the present embodiment can simultaneously secure visual naturalness and invisibility without compromising the reliability of watermark detection.

[0095] According to one embodiment, the electronic device may identify a region among a plurality of regions (520-1 to 520-20) in which the interest score (540) is lower than or equal to the first score as a candidate region (520-1, 520-4, 520-10, 520-17). The electronic device may determine that a region with a low interest score, i.e., a region lower than or equal to the first score, is a suitable region for inserting watermark data.

[0096] Areas with low interest scores may be uniform areas with low visual attention, minimal changes in brightness and color, and no recognizable objects. Since areas with low interest scores can minimize image quality degradation or visual distortion when watermark data is inserted, these areas may be determined as candidate areas (520-1, 520-4, 520-10, 520-17). According to an embodiment, the electronic device may select a predetermined number of candidate areas in order of lowest interest scores.

[0097] It goes without saying that the first score can be set differently depending on user settings.

[0098] For example, the electronic device may determine the first area (520-1) and the fourth area (520-4) as candidate areas for inserting watermark data, as the first area (520-1) and the fourth area (520-4) are background areas with low visual prominence and are areas where no object is recognized.

[0099] For example, the electronic device may determine the 10th area (520-10) and the 17th area (520-17) as candidate areas for inserting watermark data, as the 10th area (520-10) and the 17th area (520-17) are areas containing a dark background color, with little change in brightness and color, and are areas where no object is recognized.

[0100] FIG. 6 is a flowchart for explaining the process of inserting watermark data according to the watermark insertion strength according to one or more embodiments.

[0101] Referring to FIG. 6, according to one embodiment, the electronic device can determine the watermark insertion strength based on the interest score of the candidate region (S610).

[0102] The watermark insertion intensity may be data containing information regarding the degree of compression and deformation of the watermark data. The degree of compression is information used to adjust the size or precision of the watermark data according to the characteristics of the insertion target area; in areas where a low insertion intensity is applied, a high compression ratio may be applied to reduce visual deformation. The degree of deformation of the watermark data may be information indicating how much the watermark data affects the pixel values ​​or frequency components of the image during the insertion process.

[0103] Watermark insertion intensity may be a parameter representing the magnitude of the influence that watermark data has on pixel values ​​or pixel value components of an input image when watermark data is inserted into specific candidate regions within the input image. Watermark insertion intensity may be a parameter for controlling the visibility of a watermark inserted into an input image.

[0104] A high watermark insertion strength has the advantage of allowing stable detection even under external deformations such as compression, rotation, and noise, as the watermark data is strongly reflected in the image; however, this increases the likelihood of visual quality degradation or color distortion. Conversely, a low insertion strength results in minimal change in visual quality, keeping the watermark invisible, but this may lower detection reliability. Therefore, the electronic device can dynamically adjust the watermark insertion strength based on an interest score.

[0105] According to one embodiment, if the interest score of the candidate region is greater than or equal to the second score, the electronic device may determine the watermark insertion strength as the first insertion strength (S620). The second subcore may be a score less than the first score.

[0106] The electronic device may determine the watermark insertion intensity for a specific candidate region as a first insertion intensity if that region has relatively high visual importance. The first insertion intensity may be an intensity value that sets the insertion intensity relatively low so that the watermark data is not visually exposed. In other words, by inserting a watermark with a low intensity in regions with high interest scores, degradation of image quality or visual distortion can be prevented.

[0107] According to one embodiment, if the interest score of the candidate region is less than the second score, the electronic device may determine the watermark insertion strength as the second insertion strength (S630).

[0108] In the case of a uniform background area with low visual attention or one that does not contain objects, the electronic device may determine the watermark insertion intensity to be a second insertion intensity higher than the first insertion intensity. This is because in areas with a low interest score, setting the watermark insertion intensity high does not have a significant impact on visual quality.

[0109] According to one embodiment, the electronic device can insert watermark data into a candidate area based on the watermark insertion strength (S640).

[0110] FIG. 7 is a drawing for explaining the process of generating a watermark image according to one or more embodiments.

[0111] According to one embodiment, the electronic device may insert watermark data (730) into an input image (710). The electronic device may generate a watermark image (720) with the watermark data (730) inserted.

[0112] According to one example, the electronic device may print a watermark image (720) on one surface of the storage device (740). For example, the electronic device may print the watermark image (720) on an outer label area or the main body surface of the storage device (740) so that the storage device can be visually identified as a device associated with a specific manufacturer or album.

[0113] FIG. 8 is a flowchart illustrating the process of verifying the quality of watermark data according to one or more embodiments.

[0114] Referring to FIG. 8, an electronic device according to one embodiment can verify the quality of watermark data inserted into a watermark image (S810).

[0115] Quality verification of watermark data may be an operation to evaluate whether watermark data embedded in an input image is maintained without damage and can be reliably restored during decoding of the watermark data.

[0116] According to one embodiment, the electronic device can recover watermark data from a watermark image (S820).

[0117] For example, an electronic device can extract frequency components based on DCT (Discrete Cosine Transform) or DWT (Discrete Wavelet Transform) from a watermark image and decode the inserted bit pattern to restore it to the original watermark data form.

[0118] According to one embodiment, the electronic device can calculate the similarity between the restored watermark data and the generated watermark data (S830).

[0119] Similarity can be an indicator that quantitatively represents the degree of agreement between the restored watermark data and the original watermark data used during generation. Similarity can be used as a criterion to evaluate the extent to which watermark data was preserved during the insertion and restoration process by mathematically calculating the difference or correlation between the two data. For example, electronic devices can calculate similarity based on Hamming distance, correlation coefficient, or mean squared error (MSE).

[0120] According to one embodiment, the electronic device may determine that verification is successful if the similarity is greater than or equal to a preset threshold similarity (S840).

[0121] For example, if the similarity is 0.95 or higher, the electronic device may determine that the watermark data has been reliably inserted and restored. For example, if the similarity is below a preset threshold similarity, the electronic device may re-insert the watermark data or correct the image quality by adjusting the insertion strength, compression ratio, or modulation parameters.

[0122] According to one embodiment, the electronic device can generate a final watermark image based on a verified watermark image (S850).

[0123] The electronic device can identify the verified final watermark image as the final output or print target. The electronic device can transmit the verified final watermark image to a server or a printing device.

[0124] According to one embodiment, the electronic device may include a non-transient computer-readable storage medium on which a generated watermark is printed on the surface and a processor configured to retrieve and play data stored in the non-transient computer-readable storage medium by using a method that generates watermark data, divides an input image into a plurality of regions, determines a candidate region among the plurality of regions to insert the watermark data based on the input image and the watermark data, and generates a watermark image by inserting the watermark data into the candidate region. Here, the electronic device may be the same device as the playback device (200) described above, or it may be another electronic device.

[0125] It is obvious that each step or operation of the method according to the embodiments of the present disclosure may be performed by a computer comprising one or more processors in accordance with the execution of a computer program stored in a computer-readable recording medium.

[0126] The computer-executable instructions stored on the aforementioned recording medium can be implemented through a computer program programmed to perform each corresponding step, and such a computer program can be stored on a computer-readable recording medium and executed by a processor. The computer-readable recording medium may be a non-transitory readable medium. In this case, a non-transitory readable medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short moment, such as a register, cache, or memory. Specifically, programs for performing the various methods described above may be provided by being stored on a non-transitory readable medium, such as semiconductor memory devices including erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks such as internal hard disks and removable disks; optical-magnetic disks; and non-volatile memory including CD-ROMs and DVD-ROMs.

[0127] Methods according to the various examples disclosed in this document may be provided by being included in a computer program 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 on a storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0128] As explained above, a person skilled in the art to which this disclosure pertains will understand that this disclosure may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of this disclosure is defined by the claims set forth below rather than by the detailed description, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts should be interpreted as being included within the scope of this disclosure.

[0129] The features and advantages described herein are not all included, and in particular, many additional features and advantages will become apparent to those skilled in the art by considering the drawings, the specification, and the claims. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and instructional purposes and may not be chosen to describe or limit the subject matter of this disclosure.

[0130] The foregoing description of the embodiments of the present disclosure is provided for illustrative purposes only. It is not intended to limit the present disclosure to the exact form disclosed or to make it incomplete. Those skilled in the art will understand that many modifications and variations are possible in light of the foregoing disclosure.

[0131] Therefore, the scope of the present disclosure is not limited by the detailed description but by any of the claims of the application based thereon. Accordingly, the disclosure of embodiments of the present disclosure is illustrative and does not limit the scope of the present disclosure as set forth in the following claims.

Claims

Claim 1 A watermark generation method performed by an electronic device, comprising: receiving an input image and information corresponding to the input image; generating watermark data based on the information corresponding to the input image; dividing the input image into a plurality of regions; obtaining interest information for each of the plurality of regions; determining a candidate region among the plurality of regions to insert the watermark data based on the interest information; and generating a watermark image by inserting the watermark data into the candidate region; wherein the interest information is information including visual attention information, brightness distribution information, color contrast information, and object recognition information. Claim 2 A watermark generation method according to claim 1, wherein the step of generating the watermark data comprises: a step of converting information corresponding to the input image into feature data; a step of performing encryption based on the feature data and a pre-set encryption key; and a step of generating the watermark data by converting the result of the encryption into bit-unit data. Claim 3 A watermark generation method according to claim 2, wherein the step of converting information corresponding to the input image into feature data comprises: a step of converting each of the information corresponding to the input image into candidate feature data; and a step of determining the feature data to be generated as watermark data based on a pre-set importance list among the candidate feature data, wherein the pre-set importance list is a list in which the candidate feature data are listed according to a pre-set importance priority based on the type of the input image. Claim 4 delete Claim 5 A watermark generation method according to claim 1, wherein the step of determining the candidate region comprises: a step of calculating an interest score for each of the plurality of regions based on the interest information; and a step of identifying a region in which the interest score is less than or equal to a first score as the candidate region; wherein the interest score is a final score obtained by applying a pre-set weight to the score corresponding to each of the visual attention information, the brightness distribution information, the color contrast information, and the object recognition information. Claim 6 A watermark generation method according to claim 5, wherein the step of generating the watermark image comprises: a step of determining a watermark insertion strength based on an interest score of the candidate region; and a step of inserting the watermark data into the candidate region based on the watermark insertion strength, wherein the watermark insertion strength is data including information on the degree of compression and degree of deformation of the watermark data. Claim 7 A watermark generation method according to claim 6, wherein the step of determining the watermark insertion strength comprises: a step of determining the watermark insertion strength as a first insertion strength when the interest score of the candidate region is greater than or equal to a second score; and a step of determining the watermark insertion strength as a second insertion strength when the interest score of the candidate region is less than the second score, wherein the second insertion strength is an insertion strength greater than the first insertion strength, and the second score is a score less than the first score. Claim 8 A watermark generation method according to claim 1, wherein the input image is an image including at least one of an album main image and a person image printed on one surface of a storage device, and the information corresponding to the input image is information including at least one of manufacturer information, album information, person information, agency information, image shooting information, release date information, and track information. Claim 9 A method for generating a watermark according to claim 8, wherein the watermark image is an image in which the watermark data is invisibly inserted into the input image, and is an image captured by a camera and used to verify the storage device. Claim 10 A watermark generation method according to claim 1, further comprising: a step of verifying the quality of watermark data inserted into the watermark image; and a step of generating a final watermark image based on the watermark image for which the verification was successful. Claim 11 A watermark generation method according to claim 10, wherein the step of verifying the quality of the watermark data comprises: a step of restoring the watermark data from the watermark image; a step of calculating the similarity between the restored watermark data and the generated watermark data; and a step of determining that the verification is successful if the similarity is greater than or equal to a preset threshold similarity. Claim 12 A non-transient computer-readable storage medium having a watermark printed on its surface that is generated using the method of any one of paragraphs 1 to 3 and paragraphs 5 to 11. Claim 13 An electronic device comprising: a non-transient computer-readable storage medium having a watermark printed on its surface that is generated using the method of any one of claims 1 to 3 and claims 5 to 11; and a processor configured to retrieve and play data stored in the non-transient computer-readable storage medium.

Images