Method and apparatus for processing image data

Abstract

A method, an apparatus, and a computer readable medium for processing image data are provided. The method comprises the following steps: converting original image data into a visual image; determining a specific area including sensitive information in the visual image; determining specific original image data corresponding to the specific area in the original image data; and performing desensitization processing on the specific original image data in the original image data. Therefore, the data loss is reduced while the processing speed is improved.

Description

Technical Field

[0001] The present invention relates to the field of data security, and in particular to the processing of image data. Background Art

[0002] With the development of big data technology, the integration, transaction and value development of large amounts of data are encouraged, which inevitably leads to people's concern about data security. Among the large amounts of data, there are sensitive data such as user private information. If these sensitive data are stolen, it may bring adverse consequences to users. Data security has become a key factor in the development of the big data industry.

[0003] Currently, data desensitization technology has been used to transform sensitive data in a large amount of data, so as to prevent the data from being stolen and causing adverse consequences. However, as far as image data is concerned, the current desensitization technology still has room for improvement. Summary of the invention

[0004] It is desirable to provide a method and apparatus for processing image data, which can not only improve the processing speed but also reduce the data loss.

[0005] According to one aspect, a method for processing image data is provided, comprising: converting original image data into a visible image; determining a specific area in the visible image that includes sensitive information; determining specific original image data in the original image data corresponding to the specific area; and desensitizing the specific original image data in the original image data.

[0006] According to another aspect, a device for processing image data is provided, including: a conversion unit, which converts original image data into a visible image; a positioning unit, which determines a specific area in the visible image that includes sensitive information; and a processing unit, which determines specific original image data in the original image data corresponding to the specific area and desensitizes the specific original image data in the original image data.

[0007] According to another aspect, an electronic device is provided, comprising: a memory storing at least one computer-executable instruction; and one or more processors executing the at least one computer-executable instruction to: convert original image data into a visible image; determine a specific area in the visible image that includes sensitive information; determine specific original image data in the original image data that corresponds to the specific area; and desensitize the specific original image data in the original image data.

[0008] According to still another aspect, a computer-readable medium is provided, storing a computer program, wherein when the computer program is executed by a computer or a processor, the computer or the processor executes the method according to various embodiments of the present invention.

[0009] According to various embodiments of various aspects of the present invention, desensitization processing is performed directly on the original image data itself instead of the visible image, and the step of converting the desensitized visible image into the original image data is no longer required. This reduces the possibility of data loss, minimizes data loss as much as possible, and improves the speed of the desensitization processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Embodiments are illustrated by way of example only and not by way of limitation in the figures of the accompanying drawings in which like reference numerals refer to similar elements.

[0011] Figure 1 A prior art method for processing image data is shown;

[0012] Figure 2 A flow chart of a method for processing image data according to an embodiment of the present invention is shown;

[0013] Figure 3 A scene of processing original image data using a method for processing image data according to an embodiment of the present invention is shown;

[0014] Figure 4 A block diagram of a device for processing image data according to an embodiment of the present invention is shown;

[0015] Figure 5 A block diagram of an electronic device for executing a method for processing image data according to an embodiment of the present invention is shown.

[0016] Various aspects and features of various embodiments of the present invention are described with reference to the above drawings. The above drawings are only illustrative and not restrictive. In addition, not all parts of the device of the embodiment of the present invention are marked with reference numerals in the above drawings. Only relevant parts are marked in some drawings, which does not limit the parts to those shown in the drawings of the specification. DETAILED DESCRIPTION

[0017] In the field of smart transportation, a large amount of image data needs to be collected. These image data may contain sensitive data such as license plates and user faces. These sensitive data need to be processed to prevent them from being stolen. Although the example of smart transportation is used, this is not restrictive. The desensitization of image data can be widely used in various fields, such as the medical field.

[0018] Figure 1 A flow chart of a method 100 for processing image data in the prior art is shown. According to the method flow, sensitive data in the original image data is desensitized, thereby eliminating the sensitive data in the original image data. Desensitization refers to the deformation of data of certain sensitive information through desensitization rules to achieve reliable protection of sensitive privacy data. In cases involving user security data or some commercial sensitive data, under the condition of not violating system rules, real data needs to be transformed for subsequent use, such as identity card number, mobile phone number, bank card number, customer number, user face, license plate number and other personal information all need to be desensitized. Various data processing means can be used to achieve desensitization, and the means for achieving desensitization are not limited here.

[0019] According to the method 100, at step 110, raw image data is obtained. The raw image data here refers to the raw data obtained from an image acquisition device such as a camera or a scanner and has not been processed to generate a visible image, especially the raw data that has not been processed in any way. Usually, the raw image data is binary data. Taking the raw video image data as an example, its usual data structure includes a file header, camera sensor metadata, image metadata, image thumbnail, frame sequence, sensor image data, and optionally a JPEG (Joint Photographic Experts Group) conversion of the image. After the above raw image data is obtained at an image acquisition device such as a camera, the raw image data can be processed to generate a visible image.

[0020] At step 120, the acquired raw image data is processed to generate a visible image. At step 130, sensitive areas in the visible image are determined, that is, specific areas in the visible image that include sensitive information, such as areas showing license plate numbers, are identified. At step 140, the determined sensitive areas are desensitized in the visible image. At step 150, the desensitized visible image is reconverted into raw image data, that is, the desensitized visible image is reconverted into a binary format like the raw data obtained from the image acquisition device. After step 150, the desensitized raw image data can be obtained at step 160 for transmission and / or storage.

[0021] According to Figure 1The method flow shown performs desensitization processing on the original image data, and it is necessary to first convert the original image data into a visible image, and then identify and process the sensitive area based on the visible image to achieve the purpose of desensitization. After the visible image is desensitized, it is necessary to convert the desensitized visible image into the original image data. Converting the original image data into a visible image, and then converting the desensitized visible image into the format of the original image data, after multiple conversions, will inevitably cause data loss and affect the speed of the desensitization processing.

[0022] According to various embodiments of the present invention, desensitization is performed directly on the original image data itself rather than on the visible image, and there is no need to convert the desensitized visible image into the original image data. This reduces the possibility of data loss, minimizes data loss as much as possible, and improves the speed of the desensitization process.

[0023] Figure 2 FIG. 2 is a flow chart showing a method 200 for processing image data according to an embodiment of the present invention. Figure 2 As shown, according to the method 200, at step 210, the original image data is obtained, which is similar to Figure 1 The step 110 in the method 100 is similar. The acquired original image data includes two-dimensional image data or three-dimensional image data.

[0024] At step 220, the acquired raw image data is processed to generate a visible image. That is, the raw image data is converted into a visible image. Any format of visible image is contemplated. There is no restriction on the type of the generated visible image.

[0025] At step 230, a specific area in the visible image that includes sensitive information is determined. Sensitive information can be any type of information involving personal privacy or commercial sensitivity, such as face, bank card number, ID card number, etc.

[0026] The specific area in the visible image that includes sensitive information can be determined by any means in the prior art. This includes but is not limited to image processing, based on user input, and using machine learning techniques. In one embodiment, the coordinate position of the specific area in the visible image that includes sensitive information is identified and determined in this step, and the coordinate position of the specific area can be represented by various types of coordinates, which are not limited here. In another embodiment, the visible image can be displayed to the user in this step, and then the coordinate position of the specific area in the visible image that includes sensitive information is determined based on user input. Of course, it is desirable to be able to automatically determine the specific area in the visible image that includes sensitive information without manual intervention. For example, based on machine learning technology, the visible image can be input into a trained machine learning model to output the coordinate position of the specific area in the visible image that includes sensitive information.

[0027] After determining the specific area including sensitive information in the visible image, at step 240, the specific original image data in the original image data corresponding to the determined specific area including sensitive information is determined and the specific original image data in the original image data is directly desensitized.

[0028] The specific original image data corresponding to the specific area including sensitive information in the original image data can be determined by mapping the coordinate positions between the visible image and the original image data. Specifically, the coordinate position of the specific area including sensitive information in the visible image can be first obtained in the aforementioned steps, and then the coordinate position of the specific area in the visible image is mapped to the original image data based on the mapping relationship between the coordinate positions of the visible image and the original image data, thereby obtaining the specific original image data corresponding to the specific area including sensitive information. The mapping relationship can be predetermined, and it can vary according to the type of the original image data and / or the type of the image acquisition device that acquires the original image data, etc.

[0029] After determining the specific original image data involving sensitive information, it is only necessary to perform desensitization processing on the specific original image data to avoid leakage of the sensitive information. After the desensitization processing at step 240, at step 250, the desensitized original image data is obtained for storage and / or output.

[0030] Obviously, Figure 1 Unlike the method 100 shown in FIG. 1 , according to the method 200 of this embodiment of the present invention, after determining the specific area in the visible image that includes sensitive information, at step 240, the specific area is mapped back to the original image data to find the corresponding specific original image data, and then the desensitization process is directly performed on the specific original image data instead of the sensitive area in the visible image. This avoids the following problems: Figure 1The steps shown for reconverting the desensitized visible image back to the original image data reduce the possibility of data loss, save processing steps, and thus increase the speed of the desensitization process.

[0031] Figure 3 FIG. 2 shows a scenario in which raw image data is processed using a method 200 for processing image data according to an embodiment of the present invention. Figure 3 As shown, at step 210, original image data a is obtained, at step 220, the original image data a is converted into a visible image b, and at step 230, a specific area containing sensitive information is determined based on the visible image b. Here, sensitive information such as a person's face and a license plate number is illustrated in Figure c. Then, at step 240, the specific area in the visible image is mapped to specific original image data in the original image data, and the specific original image data is desensitized, thereby obtaining the desensitized original image data d at step 250.

[0032] Although the reference Figure 2 and 3 A method according to an embodiment of the present invention is described. It is to be understood that one or more steps thereof may vary according to different scenarios.

[0033] In one embodiment, the original image data includes video image data. In this case, the original video image data can be converted into multiple frames of visible images at step 220. It is desirable to identify in parallel the specific area of ​​each visible image in the multiple frames of visible images that includes sensitive information; and to determine in parallel the specific original image data in the original image data corresponding to the specific area in each visible image frame, and finally desensitize all the specific original image data in the original image data for each visible image in the multiple frames of visible images. Performing the positioning and mapping of sensitive areas in parallel may save processing time and increase processing speed.

[0034] Of course, this does not exclude the serial execution of one or more steps of the method according to various embodiments of the present invention. For example, after the original video image data is converted into multiple frames of visible images at step 220, the operations of steps 230-240 can be sequentially performed on the visible images frame by frame, and finally, after all the specific original image data involving sensitive information corresponding to each part of all frames of visible images are desensitized, the final desensitized original image data is obtained at step 250. In fact, the various steps of the method according to the embodiment of the present invention can be executed serially or in parallel for different types of original image data as needed.

[0035] Although the above describes the processing performed in frames, this is not restrictive, and the original image data can also be arbitrarily divided into different data blocks according to other requirements, and then the method according to the embodiment of the present invention is performed in data blocks.

[0036] In addition, to increase the processing speed, if steps 210-250 are used as a processing chain, multiple such processing chains can be set to process different original image data (or data blocks) respectively. The number of processing chains is set according to the processing capacity of the device.

[0037] In the field of big data, data security has always been an important concern. In one embodiment, considering the security of image data, it is desirable to desensitize the original image data before the image acquisition device acquires the original image data but has not yet stored the original image data. In one case, a component with processing capabilities, such as a graphics processing unit (GPU) or a central processing unit (CPU), can be set locally in the image acquisition device to desensitize the original image data before sending or storing the original image data. In this case, after the original image data is acquired by the image acquisition device, the method according to the present invention is directly executed, that is, converting the original image data into a visible image; determining a specific area including sensitive information in the visible image; determining specific original image data corresponding to the specific area in the original image data; and desensitizing the specific original image data in the original image data. The desensitized original image data finally obtained can be sent and / or stored locally.

[0038] In another case, the image acquisition device may not be locally provided with a component with processing capabilities and a component with the ability to store raw image data. In this case, the raw image data needs to be sent to a remote end for processing and storage. In this case, the raw image data is obtained from the image acquisition device, and then the method according to the present invention is performed, that is, the raw image data is converted into a visible image; a specific area including sensitive information in the visible image is determined; specific raw image data corresponding to the specific area in the raw image data is determined; and the specific raw image data in the raw image data is desensitized. The resulting desensitized raw image data can be sent and / or stored at a remote end.

[0039] Figure 4 FIG. 1 shows a block diagram of a device 10 for processing image data according to an embodiment of the present invention. Figure 4 As shown, the device 10 at least includes a conversion unit 11, a positioning unit 12, and a processing unit 13. It is contemplated that the device 10 may further include an acquisition unit 14, a sending unit 15, and / or a storage unit 16.

[0040] The acquisition unit 14 acquires the original image data. In one embodiment, the original image data is acquired by an image acquisition device, and the acquisition unit 14 may be an interface unit for receiving the original image data from the image acquisition device. In another embodiment, the acquisition unit 14 itself includes the image acquisition device.

[0041] The conversion unit 11 converts the original image data into a visible image; the positioning unit 12 determines a specific area in the visible image that includes sensitive information; the processing unit 13 determines the specific original image data in the original image data corresponding to the specific area and performs a desensitization process on the specific original image data in the original image data. In one embodiment, the processing unit 13 includes a first processing unit 131 and a second processing unit 132. The first processing unit 131 determines the specific original image data in the original image data corresponding to the specific area, which is determined in particular by a mapping relationship between the coordinate position of the visible image and the original image data. The second processing unit 132 performs a desensitization process on the specific original image data in the original image data.

[0042] In the case where the original image data includes video image data, the visible image obtained by the conversion unit 11 may include multiple frames of visible images. It is desirable to process the multiple frames of visible images in parallel. For each frame of the multiple frames of visible images, the positioning unit 12 determines in parallel a specific area of ​​the frame of visible images that includes sensitive information and the first processing unit 131 determines in parallel specific original image data in the original image data that corresponds to the specific area in the frame of visible images. The second processing unit 132 performs desensitization processing on each specific original image data in the original image data for each frame of the multiple frames of visible images.

[0043] The desensitized original image data may be sent via the sending unit 15 and / or stored via the storage unit 16. This may be selected according to actual needs. For example, if the desensitized original image data needs to be sent to a remote storage location for storage, the device according to the present invention includes a sending unit 15, which sends the desensitized original image data; or, if the desensitized original image data needs to be stored only locally, the sending unit 15 may not be included, and the desensitized original image data may be directly stored in the local storage unit 16. It is also contemplated that the device according to the present invention includes both the sending unit 15 and the storage unit 16.

[0044] Although the reference Figure 4A device 10 for processing image data according to the present invention is shown, which is not restrictive, and one or more components thereof can be omitted, merged, split and / or changed, as long as the technical solution under the concept of the present invention can be implemented. For example, the processing unit can be merged with the positioning unit, or the function of the first processing unit in the processing unit can be incorporated into the positioning unit. For another example, when used as an interface unit with an external device, the acquisition unit 14 and the sending unit 15 can be implemented by the same interface unit. Any setting and arrangement of the various unit components that can realize the concept of the present invention should be included in the equivalent scope of the technical solution defined by the claims of the present invention.

[0045] In one embodiment, the device 10 can also include an image acquisition device. Therefore, the so-called device for processing image data should be understood as a device having the ability to process image data, rather than a device only for processing image data.

[0046] In a specific scenario, the device according to the present invention may include a CPU (central processing unit), a GPU (graphics processing unit), a memory, and an image acquisition device such as a camera. The image acquisition device may have a certain storage capacity, that is, it includes a storage unit. The original image data collected by the image acquisition device can be directly read from the storage unit of the data acquisition device into the content to perform desensitization processing according to various embodiments of the present invention, and then the desensitized original image data is sent and / or stored. Of course, it can also be imagined that the image acquisition device does not have storage capacity, but directly transmits the collected original image data to the memory for desensitization processing.

[0047] Figure 5 FIG. 5 is a block diagram of an electronic device 500 for executing a method for processing image data according to an embodiment of the present invention. Figure 5 As shown, the electronic device 500 may include at least one processor 510 (especially including a central processing unit (CPU) and a graphics processing unit (GPU)), an image acquisition device 520, a memory 540, a communication interface 550, and a memory (e.g., a non-volatile memory) 560, and the above-mentioned components are connected together via a bus 530. At least one processor 510 executes at least one computer-readable instruction (i.e., an element implemented in the form of software) stored or encoded in the memory 560, and the computer-readable instruction can be executed by at least one processor, thereby performing desensitization processing on the original image data in the memory 540 according to various embodiments of the present invention. The desensitized original image data can be sent to a remote storage via the communication interface 550, or can be stored in the local memory 560.

[0048] References Figure 1-5Various embodiments of the method and device of the present invention are described, and these embodiments can be combined with each other to obtain different effects without being limited by the subject type. Furthermore, the various units / steps / processes mentioned above are not restrictive, and the functions of the various units / steps / processes mentioned above can be merged / combined / changed / modified to obtain corresponding effects.

[0049] The functions of each unit of the method and system of the present invention can be implemented by software or corresponding hardware, and the functions of the above-mentioned units are implemented by means of a processor such as a GPU and / or a CPU. For example, the processor can read the computer program in the memory and run these computer programs to implement the functions of the above-mentioned units. In one embodiment, the above-mentioned electronic device of the present invention can also be implemented by a memory and a processor.

[0050] It can be understood that the methods of various embodiments of the present disclosure can be implemented by computer programs / software. These software can be loaded into the working memory of the processor and used to execute the methods according to various embodiments of the present disclosure when running.

[0051] Exemplary embodiments of the present disclosure cover both creating / using the computer program / software of the present disclosure from the outset and converting an existing program / software to use the computer program / software of the present disclosure by means of an update.

[0052] According to another embodiment of the present disclosure, a computer program product is provided, such as a machine (e.g., computer) readable medium, such as a CD-ROM, including a computer program code, which, when executed, causes a computer or a processor to perform a method according to each embodiment of the present disclosure. The machine readable medium is, for example, an optical storage medium or a solid-state medium supplied with or as part of other hardware.

[0053] The above describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0054] The present disclosure is described above with reference to specific embodiments. It should be understood by those skilled in the art that the technical solution of the present disclosure can be implemented in various ways without departing from the spirit and basic features of the present disclosure. The specific embodiments are merely illustrative and not restrictive. In addition, these embodiments can be arbitrarily combined to achieve the purpose of the present disclosure. The scope of protection of the present disclosure is defined by the attached claims.

[0055] The word "comprising" in the specification and claims does not exclude the existence of other elements or steps. The expressions "first", "second" and the order of the steps shown in the figures do not limit their order or quantity. The functions of the various elements described in the specification or recorded in the claims can also be split or combined and implemented by corresponding multiple elements or a single element.

Claims

1. A method for processing image data, comprising: Converting raw image data into viewable images; determining specific areas of the visual image that include sensitive information; Determining specific original image data corresponding to the specific area in the original image data; and The specific original image data in the original image data is desensitized.

2. The method according to claim 1, wherein: The original image data includes two-dimensional image data or three-dimensional image data.

3. The method according to claim 1, wherein: The original image data includes video image data, and the visible image includes multiple frames of visible images.

4. The method according to claim 3, wherein: For each visible image frame in the multiple visible image frames, determining in parallel the specific area in the visible image frame that includes the sensitive information and determining the specific original image data in the original image data that corresponds to the specific area in the visible image frame; The specific original image data for each visible image frame in the multiple visible image frames in the original image data is desensitized.

5. The method according to claim 1, wherein: The specific original image data corresponding to the specific area in the original image data is determined by mapping the coordinate positions between the visible image and the original image data.

6. The method according to any one of claims 1 to 5, further comprising: Acquire the original image data from an image acquisition device; and The desensitized original image data is sent and / or stored.

7. The method according to any one of claims 1 to 5, further comprising: The original image data is collected by an image collection device; and The desensitized original image data is sent and / or stored.

8. A device for processing image data, comprising: a conversion unit that converts raw image data into a viewable image; a positioning unit that determines a specific area of ​​the visible image that includes sensitive information; and A processing unit determines specific original image data corresponding to the specific area in the original image data and performs desensitization processing on the specific original image data in the original image data.

9. The device according to claim 8, wherein: The original image data includes video image data, and the visible image includes multiple frames of visible images.

10. The device according to claim 9, wherein: The processing unit includes a first processing unit and a second processing unit, For each visible image frame in the plurality of visible image frames, the positioning unit determines in parallel the specific region in the visible image frame that includes the sensitive information and the first processing unit determines in parallel the specific original image data in the original image data that corresponds to the specific region in the visible image frame; and The second processing unit performs desensitization processing on the specific original image data for each visible image frame in the multiple visible image frames in the original image data.

11. The device according to claim 8, wherein: The processing unit determines the specific original image data corresponding to the specific area in the original image data by mapping the coordinate positions between the visible image and the original image data.

12. The device according to any one of claims 8 to 11, further comprising: an acquisition unit, which acquires the original image data from an image acquisition device; and A sending unit and / or a storage unit, which respectively sends and / or stores the original image data that has been desensitized.

13. An electronic device, comprising: a memory storing at least one computer executable instruction; and one or more processors that execute the at least one computer executable instruction so that: Converting raw image data into viewable images; determining specific areas of the visual image that include sensitive information; determining specific original image data corresponding to the specific area in the original image data; and The specific original image data in the original image data is desensitized.

14. The electronic device according to claim 13, further comprising at least one of the following: An image acquisition device, which acquires raw image data; A communication interface for transmitting the desensitized original image data; and A memory is used to store the desensitized original image data.

15. A computer readable medium storing a computer program which, when executed by a processor or a computer, causes the processor or the computer to perform the method according to any one of claims 1 to 7.

Images