Data protection method

Abstract

A data protection method is provided. The data protection method includes obtaining a first image; identifying at least one first object image in the first image; analyzing the at least one first object image to obtain a plurality of first feature values of a plurality of first feature points of the at least one first object image; and generating an encryption key according to the plurality of first feature values.

Description

TECHNICAL FIELD

[0001] The present application relates to a method, and particularly to a data protection method. BACKGROUND

[0002] The existing data protection technology is to protect confidential files by requiring a specific unlocking method. For this, the current unlocking method is, for example, by fingerprint unlocking, face unlocking, pattern unlocking, voice unlocking or password unlocking, etc. However, these unlocking methods have been cracked, so that the current security protection of the sensitive file cannot completely eliminate the possibility of being cracked. In other words, the current data protection method has the risk of sensitive file leakage, and cannot provide efficient data protection effect. SUMMARY

[0003] Therefore, the present application provides a data protection method that can generate an encryption key for encrypting a file.

[0004] The data protection method of the present application comprises: obtaining a first image; identifying at least one first object image in the first image; analyzing the at least one first object image to obtain a plurality of first feature values of a plurality of first feature points of the at least one first object image; and generating an encryption key according to the plurality of first feature values.

[0005] Based on the above, the data protection method of the present application can generate a corresponding encryption key according to the image taken by the user to achieve a high protection data protection effect.

[0006] In order to make the above features and advantages of the present application more obvious and easy to understand, the following embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0007] Figure 1 is a schematic diagram of an electronic device of an embodiment of the present application.

[0008] Figure 2 is a flowchart of a data protection method of an embodiment of the present application.

[0009] Figure 3 is a schematic diagram of a first image of an embodiment of the present application.

[0010] Figures 4A to 4E is a schematic diagram of a plurality of object images of an embodiment of the present application.

[0011] Figure 5 is a schematic diagram of a scanned object image of an embodiment of the present application.

[0012] Figure 6 is a flowchart of generating a decryption key of an embodiment of the present application.

[0013] Figure 7 is a flowchart of decrypting an encrypted file according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order that the present application can be more readily understood, the following specific embodiments are given as examples in which the present application can be implemented. In addition, wherever possible, the same reference numerals are used in the drawings and the embodiments to represent the same or similar components / elements / steps.

[0015] Figure 1 is a schematic diagram of an electronic device according to an embodiment of the present application. Referring to Figure 1 , the electronic device 100 comprises a processing device 110, an image acquisition device 120 and a storage device 130. The processing device 110 is coupled to the image acquisition device 120 and the storage device 130. In this embodiment, the electronic device 100 can be, for example, a portable electronic device such as a mobile phone or a tablet, but the present application is not limited thereto. In this embodiment, during the encryption of file data, a user can operate the electronic device 100 to acquire one or more real-time images via the image acquisition device 120, and the processing device 110 can perform image recognition and image analysis on the one or more real-time images to obtain a plurality of feature values. In this embodiment, the processing device 110 can generate an encryption key in accordance with the plurality of feature values, and perform symmetric key encryption on an original file in accordance with the encryption key to generate an encrypted file.

[0016] Correspondingly, during the decryption of data, the user can also operate the electronic device 100 to acquire another one or more real-time images via the image acquisition device 120, and the processing device 110 can perform image recognition and image analysis on the another one or more real-time images to obtain another plurality of feature values. The processing device 110 can generate a decryption key in accordance with the another plurality of feature values, and decrypt the encrypted file in accordance with the decryption key to obtain the original file. In other words, the electronic device 100 of the present application can dynamically generate an encryption key in accordance with the plurality of feature values of the one or more real-time images, and use the encryption key to encrypt a sensitive file to generate an encrypted file with high protection. Moreover, since the encryption key dynamically generated by the electronic device 100 of the present application has difficulty in being copied and reproduced, and only the file encryptor can generate a valid decryption key by acquiring the correct real-time image (only the file encryptor knows the correct image content), the electronic device 100 of the present application can have a highly protective data protection effect.

[0017] In this embodiment, the processing device 110 may, for example, comprise a Central Processing Unit (CPU), or other programmable general purpose or special purpose microprocessors (Microprocessor), Digital Signal Processors (Digital Signal Processor, DSP), programmable controllers, Application Specific Integrated Circuits (Application Specific Integrated Circuits, ASIC), Programmable Logic Devices (Programmable Logic Device, PLD), other similar processing devices or combinations of these devices.

[0018] In this embodiment, the image acquisition device 120 may, for example, comprise a Charge Coupled Device (Charge Coupled Device, CCD) or a Complementary Metal-Oxide Semiconductor (Complementary Metal-Oxide Semiconductor, CMOS). The image acquisition device 120 can be used to take one or more real-time images, and provide to the processing device 110 for image processing and image analysis, wherein each real-time image can comprise one or more continuous images.

[0019] In this embodiment, the storage device 130 may, for example, comprise a Dynamic Random Access Memory (Dynamic Random Access Memory, DRAM), a Flash memory or a Non-Volatile Random Access Memory (Non-Volatile Random Access Memory, NVRAM) and the like. The storage device 130 can be used to store the relevant image processing modules, image analysis modules, key generation modules, encryption modules, decryption modules, encrypted password data, decrypted password data, file data, relevant images and images and the like described in the embodiments of the present application, and the software and data for the processing device 110 to access and execute, so as to realize the data protection method of the present application.

[0020] Figure 2 is a flowchart of the data protection method of the embodiments of the present application. Referring to Figure 1 and Figure 2, the electronic device 100 can perform the following steps S210-S250 to realize the functions of the generation of the encryption key and the data protection. In step S210, the electronic device 100 can acquire a first image through the image acquisition device 120. In step S220, the processing device 110 of the electronic device 100 can identify at least one first object image in the first image. In step S230, the processing device 110 of the electronic device 100 can analyze the at least one first object image to acquire a plurality of first feature values of a plurality of first feature points of the at least one first object image. In step S240, the processing device 110 of the electronic device 100 can generate an encryption key according to the plurality of first feature values. In step S250, the processing device 110 of the electronic device 100 can perform symmetric key encryption on a source file according to the encryption key to generate an encrypted file.

[0021] For example, in combination with reference Figure 3 , Figure 3 is a schematic diagram of a first image according to an embodiment of the present application. In step S210 described above, when a user wants to encrypt an important file, the user can first capture a first image 300 having a plurality of specific objects 310-350 through the image acquisition device 120. Alternatively, in an embodiment, the user can capture a plurality of first images 300 (for example, 3 first images) and acquire the plurality of specific objects 310-350 from the plurality of first images. The specific objects 310-350 can be, for example, a telephone, a pen, a mobile phone, a mouse, and a calculator in sequence. However, the specific objects in the first image according to the present application are not limited to Figure 3 The number and types of objects in the first image according to the present application can be selected by the user.

[0022] In the embodiment, before the processing device 110 performs object detection and identification in the first image 300, the processing device 110 can first perform uniform image format adjustment on the image provided by the image acquisition device 120, for example, conversion to a default image format and image size of a bitmap of 608*608 pixels. Then, the processing device 110 can perform grayscale conversion on the adjusted image to generate the first image 300. Finally, the processing device 110 can use the first image 300 after grayscale conversion to perform the following object detection and identification. In addition, the first image 300 according to the embodiment can include, for example, one image or a plurality of continuous images.

[0023] For example, in combination with reference Figures 4A to 4E , Figures 4A to 4EFig. 4 is a schematic diagram of a plurality of object images of an embodiment of the present application. In step S220, the processing device 110 can identify a plurality of first object images 410-450 in the first image 300. In this embodiment, the processing device 110 can perform a convolutional neural network (CNN) operation on the first image 300. The processing device 110 can perform object detection and recognition in the image by, for example, using a YOLO (You Only Look Once) module. It is noted that the YOLO module can determine the object class and location in the image by performing only one convolutional neural network operation on the image. In addition, the processing device 110 can perform a test training on the YOLO module in advance to improve the recognition rate of small objects in the YOLO module. In addition, in an embodiment, the first object images can be determined by manually selecting the object images in the first image 300 by operating the electronic device 100 by a user.

[0024] In step S230, the processing device 110 can analyze the first object images 410-450 respectively to obtain a plurality of first feature values of a plurality of first feature points respectively corresponding to each of the first object images 410-450, wherein the plurality of first feature values can be grayscale values. In this embodiment, the processing device 110 can obtain the feature values of the first object images 410-450 respectively by using, for example, a SURF (Speed Up Robust Features) algorithm.

[0025] In an embodiment, the processing device 110 can perform a statistical optimization selection in the feature value acquisition process. In detail, the first image 300 can comprise a plurality of continuous images, for example, and the processing device 110 can determine a plurality of valid feature points (valid image features) of each of the first object images 410-450 in the plurality of continuous images, wherein the plurality of valid feature points have the same feature point coordinates and the same feature values in positions of the plurality of continuous images respectively corresponding to the first object images 410-450. The processing device 110 can take the plurality of valid feature points as the plurality of first feature points. In other words, if the processing device 110 determines that a certain feature point does not appear in the same position in the plurality of continuous images, it means that the certain feature point is not a valid feature point. In another embodiment, the processing device 110 can also make hierarchical settings for the flash settings, brightness, focal length, or aperture of the image acquisition device 120 corresponding to the plurality of continuous images, so as to reduce the influence of poor environmental light, hand tremor, or failure on the imaging quality of the images. Thus, the processing device 110 can effectively avoid recording feature points that are not obvious or are misjudged and acquired due to unclear images. In yet another embodiment, the processing device 110 can also automatically filter out images with poor image quality, so as to effectively identify feature points in images by identifying and analyzing images with good image quality, facilitating the generation of the key.

[0026] In step S240, the processing device 110 can determine the encoding range of the numeral system as shown in Table 1 below according to the total number of feature points of the plurality of first feature points of all the object images 410-450, wherein the numeral system can be binary.

[0027]

[0028] Table 1

[0029] Next, the processing device 110 can calculate the average of the feature values of the plurality of first feature points of all the object images as shown in Table 2 below. The processing device 110 can determine the difference ratio of each of the plurality of first feature values of the plurality of first feature points from the average of the feature values, and the processing device 110 can determine a plurality of first numerical values following the numeral system according to the plurality of difference ratios of the plurality of first feature values respectively corresponding to the plurality of first feature points.

[0030]

[0031]

[0032] Taking a total number of feature points between 86 and 128 as an example, as shown in Table 3 below, assuming the total number of feature points of the plurality of first feature points is between 86 and 128, and the feature values ​​of the four feature points of the plurality of first feature points are "90", "130", "170", and "200" respectively. Therefore, as shown in Table 3 below, the first values ​​corresponding to the four feature points are "11", "10", "01", and "00" respectively.

[0033]

[0034] Finally, the processing device 110 can sequentially arrange the plurality of first values ​​obtained through the above embodiments to form an encryption key. For this purpose, the processing device 110 can scan according to the default image scanning order. Figures 4A to 4E Individual whole pixels (or at least pixels of a partial image) of each first object image 410-450 are used to obtain the plurality of first feature points. (See also: [reference]) Figure 5 , Figure 5 This is a schematic diagram of the scanned object image according to an embodiment of the present invention. Taking the first object image 540 as an example (i.e.) Figure 4D The processing device 110 can scan each pixel of the object image 540 (from outside to inside) according to the default image scanning order 500. When the processing device 110 scans a pixel that is identified as a feature point, the processing device 110 reads the corresponding first value of this feature point, such as "11". Then, if the processing device 110 reads the corresponding first values ​​of the second and third feature points, such as "10" and "00", the processing device 110 can sequentially arrange their values ​​into a code "111000". In this way, the processing device 110 can scan... Figures 4A to 4E Each of the first object images 410–450 is encoded to generate a sequence as an encryption key.

[0035] In this embodiment, the encryption key can be 256 bits of password data. In this embodiment, the processing device 110 can determine whether the plurality of first values ​​are sufficient to form 256 bits of password data, and decide whether to sequentially supplement the arrangement of the plurality of first values ​​with a plurality of preset values ​​to form 256 bits of password data. In other words, if the plurality of first values ​​are insufficient to form 256 bits, the processing device 110 can sequentially add preset values ​​such as "11", "01", "10", and "00" after the arrangement of the plurality of first values, but the present invention is not limited thereto.

[0036] In addition, in the embodiment, the processing device 110 can also determine the value arrangement order of the first values corresponding to the first feature points of the first object images 410-450 in the encryption key according to the pixel size order of the first object images 410-450. In other words, the processing device 110 can determine the value arrangement order of the first values corresponding to the first object images 410 (phone), 450 (calculator), 430 (mobile phone), 440 (mouse), and 420 (pen) in the encryption key according to the order of the first object images.

[0037] For example, the first object image 410 (phone) can be used to generate the code "1100" of the first values. The first object image 450 (calculator) can be used to generate the code "1010" of the first values. The first object image 430 (mobile phone) can be used to generate the code "1111" of the first values. The first object image 440 (mouse) can be used to generate the code "0000" of the first values. The first object image 420 (pen) can be used to generate the code "1000" of the first values. The processing device 110 can combine the first values corresponding to the first object images to generate the code "11001010111100001000" of the encryption key.

[0038] It is worth noting that in the implementation scenario of generating the decryption key, since the encryption key and the decryption key required during file encryption and file decryption must be exactly the same, if the image data has influences such as light and shadow, shaking, or light, the encryption key and the decryption key generated based on the image will have a large difference, and the data contents after encryption and decryption will be different. Therefore, the processing device 110 of the embodiment can also generate a fault-tolerant correction code according to the encryption key, wherein the fault-tolerant correction code can be Reed-Solomon Codes (RS codes) (RS(n, k, t)), but the present application is not limited thereto. For this, the fault-tolerant correction code can represent encoding a sequence of information symbol elements with a length of k into a sequence of codeword symbol elements with a length of n, correcting a maximum of t error symbols, and satisfying the condition of n-k=2t. In other words, if the encryption key is 256 bits, the format of the fault-tolerant correction code can be represented as RS(308, 256, 26), wherein the fault-tolerant correction code allows a correction of an error rate of 10%. That is, when the difference between the encryption key and the decryption key is less than 10%, the processing device 110 can consider the decryption key as the same key as the encryption key for file decryption, otherwise as a different key and cannot perform file decryption.

[0039] In step S250, the processing device 110 can encrypt the source file using the encryption key, for example, according to the Advanced Encryption Standard (AES) to generate an encrypted file, but the present application is not limited thereto. In an embodiment, the processing device 110 can also encrypt the source file using other symmetric key encryption methods.

[0040] Figure 6 is a flowchart of generating a decryption key according to an embodiment of the present application. Referring to Figure 1 and Figure 6 In an embodiment where the decryption key must be generated additionally, when a user wants to decrypt the encrypted file according to the above embodiment, the electronic device 100 can generate the decryption key by performing steps S610-S640. In step S610, the electronic device 100 can acquire a second image through the image acquisition device 120. In step S620, the processing device 110 of the electronic device 100 can identify at least one second object image in the second image. In step S630, the processing device 110 of the electronic device 100 can analyze the at least one second object image to acquire a plurality of second feature values of a plurality of second feature points of the at least one second object image. In step S640, the processing device 110 of the electronic device 100 can generate a decryption key according to the plurality of second feature values. In this embodiment, when a user wants to decrypt the encrypted file, the user can use a second image having the same or similar plurality of object images as the first image (for example, the first image 300 of Figure 3 ) used to generate the encryption key to generate the decryption key.

[0041] However, the encryption key and the decryption key are generated in the same way in this embodiment. The second image, the at least one second object image, the plurality of second feature points, the plurality of second feature values, and the decryption key according to this embodiment can be implemented and performed in the same way as the first image, the first object image, the first feature point, the first feature value, and the encryption key according to the above embodiments, and thus a detailed description thereof is omitted here. Figures 2 to 5 Figure 3 In this embodiment, if the user acquires the second image by capturing the same objects 310-350 in the first image according to the image acquisition device 120, the feature points of the image can be the same or highly similar, and thus the processing device 110 can generate the decryption key having the same or highly similar password data as the encryption key according to the second image. In other words, the processing device 110 can directly decrypt the encrypted file using the decryption key to effectively acquire the source file.

[0042] Figure 7 ​is a flowchart of decrypting an encrypted file according to an embodiment of the present application. However, if the user takes the second image by using the image acquisition device 120 to capture a plurality of same type of objects similar to the objects 310-350 in Figure 3 , the password data of the decryption key generated by the processing device 110 can have errors with the encryption key. In this regard, referring to Figure 7 , the electronic device 100 can perform the following steps S710-S740. In step S710, the processing device 110 can perform a consistency comparison between the encryption key and the decryption key to determine whether the difference percentage between the encryption key and the decryption key is greater than a preset percentage. The preset difference percentage is, for example, ten percent (10%), which corresponds to the correction of the allowed error rate of 10% set for the error-tolerant correction code generated in the above embodiment. If yes, the processing device 110 performs step S720 to determine that the decryption key generation fails and requires the user to retake the image. If no, the processing device 110 performs step S730 to correct the decryption key using the error-tolerant correction code as described in the above embodiment. Then, in step S740, the processing device 110 can decrypt the encrypted file using the corrected decryption key to effectively obtain the source file. Therefore, when the user takes the second image by using the image acquisition device 120 to capture a plurality of same type of objects similar to the objects 310-350 in Figure 3 , to generate the decryption key, Figure 6 and Figure 7 the flow of the above embodiment can enable the electronic device 100 to generate an effective decryption key to decrypt the encrypted file.

[0043] It is noted that in the above step S710, the consistency comparison can be, for example, that the processing device 110 can sequentially compare each bit value of the encryption key and the decryption key (e.g., 0-255 bit sequential comparison). If the processing device 110 determines that the comparison of a certain bit value (0 or 1) is not the same, the processing device 110 records the number of errors as 1, and accumulates the total number of errors. Therefore, the processing device 110 can calculate the difference percentage equal to the total number of errors divided by 256, and multiplied by 100 (difference percentage = (error number / 256)*100).

[0044] In summary, the data protection method of the present application can generate an encryption key that is very difficult to crack by using a user to obtain a first image having one or more specific object images in real time, to effectively encrypt a source file to generate a corresponding encrypted file. Moreover, the data protection method of the present application requires the user to take one or more specific objects having the same or similar to the one or more specific objects in the first image to obtain a second image having the same or highly similar to the first image to generate a decryption key similar to the encryption key in the process of decrypting the encrypted file, so as to successfully unlock the encrypted file. Therefore, the data protection method of the present application can provide a file data protection effect with high protection.

[0045] Although the present application has been disclosed with examples as above, it is not intended to limit the present application, and anyone having ordinary knowledge in the art can make some changes and modifications without departing from the spirit and scope of the present application, and the protection scope of the present application shall be defined by the appended patent claims.

[0046]

Symbol Description

[0047] 100: electronic device

[0048] 110: processing device

[0049] 120: image acquisition device

[0050] 130: storage device

[0051] 300: first image

[0052] 310, 320, 330, 340, 350: object

[0053] 410, 420, 430, 440, 450, 540: object image

[0054] 500: image scanning order

[0055] S210, S220, S230, S240, S250, S610, S620, S630, S640, S710, S720, S730, S740: step

Claims

1. A method for data protection, comprising: obtaining a first image; identifying at least one first object image in the first image; analyzing the at least one first object image to obtain a plurality of first feature values of a plurality of first feature points of the at least one first object image; generating an encryption key according to the plurality of first feature values; and determining a value arrangement order in the encryption key according to a pixel size order of the at least one first object image. 2.The method of claim 1, wherein the first image comprises a plurality of continuous images, and the step of obtaining the plurality of first feature values of the plurality of first feature points of the at least one first object image comprises: judging a plurality of valid feature points of the at least one first object image in the plurality of continuous images, wherein the plurality of valid feature points have the same feature point coordinates and the same feature values in positions of the plurality of continuous images corresponding to the at least one first object image respectively; and taking the plurality of valid feature points as the plurality of first feature points of the at least one first object image. 3.The method of claim 1, wherein the step of obtaining the plurality of first feature values of the plurality of first feature points of the at least one first object image comprises: judging the plurality of first feature points in the at least one first object image; and for each first object image, scanning the whole pixels of the each first object image according to a default image scanning order to obtain the plurality of first feature points. 4.The method of claim 1, wherein before the step of identifying the at least one first object image in the first image, the encryption method comprises: converting the first image into a default image size; and performing a gray scale conversion on the adjusted first image to identify the at least one first object image using the first image after the gray scale conversion. 5.The method of claim 4, wherein the step of converting the first image into the default image size comprises: converting the first image into a bitmap image. 6.The method of claim 4, wherein the plurality of first feature values are a plurality of gray scale values. 7.The method of claim 4, wherein the step of analyzing the at least one first object image comprises: analyzing the at least one first object image according to a speeded up robust features (SURF) algorithm to obtain the plurality of first feature values of the plurality of first feature points of the at least one first object image. 8.The method of claim 1, wherein the step of identifying the at least one first object image in the first image comprises: performing a convolutional neural network (CNN) operation on the first image to identify the at least one first object image. 9.The method of claim 1, wherein the step of generating the encryption key according to the plurality of first feature values comprises: determining a coding range of a numeral system according to a total number of the plurality of first feature points of all object images; calculating a feature value average of the plurality of first feature points of all object images; and determining the encryption key according to the coding range and the feature value average. ​ ​ ​ determining a difference ratio of the first feature values of the first feature points to the average of the first feature values; determining first numbers following the base system according to the difference ratio of the first feature values of the first feature points; and sequentially arranging the first numbers to form the encryption key.

10. The data protection method of claim 9, wherein the encryption key is a 256-bit cipher data.

11. The data protection method of claim 10, wherein the step of generating the encryption key according to the first feature values of the first feature points further comprises: determining whether the first numbers are sufficient to form the 256-bit cipher data to determine whether to sequentially supplement the arrangement of the first numbers with preset numbers to form the 256-bit cipher data.

12. The data protection method of claim 9, wherein the base system is a binary system.

13. The data protection method of claim 1, further comprising: generating a forward error correction code according to the encryption key.

14. The data protection method of claim 13, wherein the forward error correction code is a Reed-Solomon code.

15. The data protection method of claim 1, further comprising: performing symmetric key encryption on a source file according to the encryption key to generate an encrypted file.

16. The data protection method of claim 15, comprising: obtaining a second image; identifying at least one second object image in the second image; performing analysis on the at least one second object image to obtain second feature points of the at least one second object image; and generating a decryption key for decrypting the encrypted file according to second feature values of the second feature points.

17. The data protection method of claim 16, further comprising: performing consistency comparison between the encryption key and the decryption key; determining that the decryption key fails to be generated when a difference percentage between the encryption key and the decryption key is greater than a preset percentage; and determining that the decryption key succeeds to be generated when the difference percentage between the encryption key and the decryption key is less than or equal to the preset percentage.

18. The data protection method of claim 17, wherein the difference percentage is ten percent.

19. The data protection method of claim 17, wherein when it is determined that the decryption key succeeds to be generated, the data protection method further comprises: correcting the decryption key by using a forward error correction code; and decrypting the encrypted file by using the corrected decryption key. ​ ​ ​

Images