Two-dimensional code image processing method and device, electronic equipment and storage medium

Abstract

This application provides a QR code image processing method and apparatus, electronic device, and storage medium. The QR code image processing method includes: acquiring a QR code RAW image; focusing the image on the QR code RAW image with the QR code area as the center to acquire a focused first QR code digital image; performing color equalization processing on the first QR code digital image to acquire a second QR code digital image; and performing image filtering on the second QR code digital image to extract the blue light channel, thereby generating a QR code imaging image containing the blue light channel. This application can save algorithm complexity and redundant computation, achieving a balance between image quality and computational cost.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to QR code image processing methods and apparatus, electronic devices and storage media. Background Technology

[0002] With the increasing prevalence of mobile shopping, mobile payments, and QR code payments, QR code technology has become integrated into most aspects of our lives. By scanning a QR code with our mobile phones, we can easily obtain information or make mobile payments, indirectly improving the efficiency of society as a whole. However, the scanning process is also affected by many physical factors, leading to a decrease in recognition rate, such as ambient light, scanning distance, scanning angle, incomplete information, and QR code image quality.

[0003] Digital imaging sensors have evolved from CCD to CMOS technology, and camera products have gradually evolved from SLR cameras, point-and-shoot cameras, compact cameras to smartphones. Digital imaging sensors capture raw image data, which differs greatly from the images seen by the human eye. This led to the development of Image Signal Processor (ISP) technology. ISPs can process very low-quality raw images (RAW images) into digital images that conform to the characteristics of human vision; RAW images are sometimes referred to as digital negatives. Typically, to obtain higher-quality QR code images, the computational cost of the ISP system will also increase.

[0004] Therefore, achieving a balance between QR code imaging quality and computational cost has become a pressing technical problem to be solved in this field. Summary of the Invention

[0005] This application provides a QR code image processing method and apparatus, electronic device and storage medium, which can solve the above-mentioned deficiencies in the prior art.

[0006] Firstly, this application provides a QR code image processing method. The method includes: acquiring a QR code RAW image; focusing the image on the QR code RAW image with the QR code region as the center to acquire a focused first QR code digital image; performing color equalization processing on the first QR code digital image to acquire a second QR code digital image; and performing image filtering on the second QR code digital image to extract the blue light channel, thereby generating a QR code imaging image having the blue light channel. In this application, image focusing is first performed to acquire a high-quality QR code image, and then the image is filtered to extract the blue light channel, reducing redundant data and thus saving algorithm complexity and redundant computation.

[0007] In one implementation of the first aspect, image filtering of the second QR code digital image to extract the blue light channel includes: determining whether the second QR code digital image meets the blue light priority condition; and if the blue light priority condition is met, enabling the blue light priority mode to perform image filtering processing to extract the blue light channel.

[0008] In one implementation of the first aspect, the method further includes: if the blue light priority condition is not met, the second QR code digital image is directly output as the QR code imaging image.

[0009] In one implementation of the first aspect, determining whether the second QR code digital image satisfies the blue light priority condition includes: obtaining the RGB histogram of the second QR code digital image; and determining whether the blue light component is dominant based on the RGB histogram. If so, the blue light priority condition is satisfied; otherwise, the blue light priority condition is not satisfied.

[0010] In this implementation, considering that existing QR code images are generally carried by electronic devices, and the screen medium of electronic devices generally has the characteristics of strong blue light and weak other components, the blue light channel component in the RGB histogram is statistically analyzed to determine whether it meets the blue light priority condition. If the blue light priority condition is met, image filtering is performed to retain the blue light channel data, which can indirectly reduce redundant data and reduce redundant calculations.

[0011] In one implementation of the first aspect, enabling a blue light priority mode for image filtering to extract the blue light channel includes: extracting the effective portion of the blue light spectrum from the second QR code digital image to separate the blue light components and form a blue light image; performing equalization processing on the blue light image; and outputting the equalized blue light image as the QR code imaging image. In this implementation, separating the blue light components to form a blue light image, followed by equalization processing, improves image contrast and increases the accuracy of subsequent QR code recognition.

[0012] In one implementation of the first aspect, image focusing on the QR code RAW image centered on the QR code region includes: identifying and marking the QR code region; adjusting optical system parameters to focus on the QR code region; performing photometry centered on the QR code region; and performing distance measurement centered on the QR code region to perform image focusing.

[0013] In one implementation of the first aspect, adjusting the optical system parameters includes adjusting the focal point and viewing angle of the image.

[0014] In one implementation of the first aspect, the method further includes: recognizing the output QR code image to obtain a feature code.

[0015] Secondly, this application provides a QR code image processing apparatus. The apparatus includes: an image acquisition module configured to acquire a QR code RAW image; an image focusing module configured to focus the image on the QR code RAW image with the QR code area as the center, to acquire a focused first QR code digital image; a color equalization processing module configured to perform color equalization processing on the first QR code digital image to acquire a second QR code digital image; and an image filtering module configured to perform image filtering on the second QR code digital image to extract the blue light channel, thereby generating a QR code imaging image having the blue light channel.

[0016] In this application, the proposed QR code image processing device addresses the QR code image quality problem by designing an image focusing module to focus the image and obtain a high-quality QR code image. Secondly, it designs an image filtering module that can simplify the image based on the color characteristics of the QR code image, achieving a balance between image quality and computational cost, while also simplifying the complexity of the image processing system.

[0017] In one implementation of the second aspect, the device further includes a QR code recognition module configured to recognize the QR code image to obtain a feature code.

[0018] Thirdly, this application provides an electronic device. The electronic device includes: a memory configured to store a computer program; and a processor configured to invoke the computer program to perform the QR code image processing method according to the first aspect of this application.

[0019] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon. The computer program is executed to implement the QR code image processing method according to the first aspect of this application.

[0020] As described above, the QR code image processing method, apparatus, electronic device, and storage medium of this application first perform an image focusing algorithm and then perform an image filtering algorithm, thereby reducing redundant data while obtaining high-quality QR code images, saving algorithm complexity and redundant computation, and achieving a balance between image quality and computational cost. Attached Figure Description

[0021] Figure 1 This is a schematic diagram illustrating a scenario where the QR code image processing method according to an embodiment of this application is applied to a barcode scanner.

[0022] Figure 2 This is a flowchart of a QR code image processing method according to an embodiment of this application.

[0023] Figure 3This is a flowchart of an image focusing algorithm centered on the QR code region in a QR code image processing method according to an embodiment of this application.

[0024] Figure 4 This is a flowchart of the blue light priority image filtering algorithm in the QR code image processing method according to an embodiment of this application.

[0025] Figure 5 To display a QR code and related histogram on a screen medium according to embodiments of this application.

[0026] Figure 6 This is a structural block diagram of a QR code image processing apparatus according to an embodiment of this application.

[0027] Figure 7 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0028] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0029] It should be noted that the illustrations provided in the following embodiments are merely schematic representations of the basic concept of this application. The illustrations only show components relevant to this application and are not drawn according to the actual number, shape, and size of components in implementation. In actual implementation, the form, quantity, and proportion of each component can be arbitrarily changed, and the component layout may also be more complex. Furthermore, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0030] The following embodiments of this application provide a QR code image processing method, an IPS system, an electronic device, and a medium, which are applied to terminal devices with scanning functions. The terminal devices include, but are not limited to, barcode scanners, smartphones, and tablets. The following description will take a barcode scanner as an example.

[0031] Figure 1This is a schematic diagram illustrating a scenario where the QR code image processing method according to an embodiment of this application is applied to a barcode scanner. The barcode scanner 1 includes a digital imaging sensor and an image processing system. The image processing system acquires a RAW image of the QR code from the imaging sensor, performs image processing, and identifies the QR code information. The image processing system can be an image signal processor (ISP). The QR code 2 can be a QR code printed on the surface of various objects or a QR code displayed on the screen of an electronic device.

[0032] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0033] Figure 2 This is a flowchart of a QR code image processing method according to an embodiment of this application. The QR code image processing method in this embodiment includes the following steps S1 to S4.

[0034] In step S1, a RAW image of the QR code is acquired. The RAW image of the QR code can be acquired by an imaging sensor.

[0035] In step S2, the image is focused on the QR code RAW image with the QR code area as the center to obtain the first focused QR code digital image.

[0036] Step S2 is used for image focusing, so that the QR code area can obtain more effective pixels, improve the imaging quality, and thus avoid the quality problems of the QR code image obtained due to the influence of many physical factors during the scanning process.

[0037] In this embodiment, the image is focused on the QR code area, which makes the QR code image clear enough and the QR code occupies more than the ideal threshold. In this embodiment, the ideal threshold is set to 50%. Those skilled in the art can adjust the size of the ideal threshold themselves.

[0038] In step S3, the first QR code digital image is subjected to color equalization processing to obtain the second QR code digital image.

[0039] Color equalization aims to increase the brightness intervals to create a more uniform distribution, reducing contrast and thus correcting certain deficiencies in an image, making image details clearer. The basic idea of ​​color equalization is to merge less frequent brightness levels into neighboring brightness levels, thereby increasing the brightness intervals, reducing the number of brightness levels, creating a more uniform distribution, and weakening contrast.

[0040] In step S4, the second QR code digital image is subjected to image filtering to extract the blue light channel, so as to generate a QR code imaging image with the blue light channel.

[0041] In the QR code image processing method described above in this application, the image is first focused to obtain a high-quality QR code image, and then it is determined whether the image meets the blue light priority condition. If the blue light priority condition is met, the blue light priority mode is enabled to filter the image, reducing redundant data, thereby saving algorithm complexity and redundant computation.

[0042] In another preferred embodiment, the QR code image processing method further includes step S5 in addition to the steps S1 to S4 described above.

[0043] In step S5, the QR code image is recognized to obtain the feature code. Since a high-quality QR code image is obtained through image focusing, the recognition accuracy can be greatly improved. Simultaneously, the image filtering in step S4 reduces redundant data, further improving the recognition speed.

[0044] The two key algorithms of the QR code image processing method in this application include an image focusing algorithm centered on the QR code region and a blue light-priority image filtering algorithm. These will be described in detail below.

[0045] Figure 3 This is a flowchart of an image focusing algorithm prioritizing the QR code region in a QR code image processing method according to an embodiment of this application. The image focusing algorithm centered on the QR code region includes steps S21 to S24.

[0046] In step S21, the QR code region is identified and marked. This step rapidly identifies and marks the QR code region based on primary and intermediate features. Primary features include eye-shaped features and dot-shaped features; intermediate features include eye-shaped patterns and dot-shaped model features. Eye-shaped patterns include right-angled triangle distributions; dot-shaped model features include dot consistency (same type), etc. Furthermore, the QR code region can be identified using a deep learning model network. The deep learning model network structure can adopt, but is not limited to, structures such as MobileNet, Deep Residual Network (ResNet), or VGGNet (Visual Geometry Group Network).

[0047] In step S22, the optical system parameters are adjusted to focus on the QR code area. Preferably, adjusting the optical system parameters includes adjusting the imaging focus and viewing angle.

[0048] In step S23, light measurement is performed with the QR code area as the center.

[0049] In step S24, distance measurement is performed with the QR code area as the center to focus the image.

[0050] During image focusing, rapid light and distance measurement are performed centered on the QR code area, and the optical system is then adjusted to automatically focus on the QR code area, so that the QR code area can obtain more effective pixels and improve image quality.

[0051] Figure 4 This is a flowchart of a blue-light-priority image filtering algorithm in a QR code image processing method according to an embodiment of this application. The blue-light-priority image filtering algorithm includes steps S41 to S42.

[0052] In step S41, it is determined whether the second QR code digital image meets the blue light priority condition. This step may specifically include steps S411 and S412.

[0053] In step S411, the RGB histogram of the second QR code digital image is obtained.

[0054] In step S412, it is determined whether the blue light component is dominant based on the RGB histogram. If so, the blue light priority condition is met; otherwise, the blue light priority condition is not met.

[0055] Among them, the preferred methods for determining whether the blue light component of an image is dominant are the blue light component correlation method and the blue light component weighted average method. These two methods are only typical examples and are not limited to these two methods.

[0056] The specific implementation method of the blue light component correlation method includes: first, calculating the histogram of the blue light component and the histogram of the grayscale image (Gray image) respectively; then calculating the correlation coefficient between the two histograms; if the correlation coefficient is greater than the significant correlation threshold, the two histograms are significantly correlated, and the blue light component of the image is considered to be dominant.

[0057] The specific implementation of the blue light component weighted averaging method includes: First, calculating the histogram of the blue light component and the histogram of the grayscale image (Gray image) separately. Then, determining the N salient feature colors of the blue light component and the Gray image histogram (the number of colors is considered salient when sampling at equal intervals is greater than a threshold). If the weighted average of the N feature colors of the blue light component is greater than the weighted average of the N feature colors of the Gray image, then the blue light component of the image is considered dominant. The method for determining the dominance of the blue light component preferentially uses the grayscale image as the reference image, but other image formats can also be used as reference images.

[0058] For examples where the blue light component is dominant, see [link to relevant documentation]. Figure 5 . Figure 5 This application describes the display of a QR code and its associated histogram on a screen medium according to embodiments of the present application. Screen media include tablet screens, watch screens, mobile phone screens, cash register screens, and television screens. A typical characteristic of an image displaying a QR code on a screen medium is that the blue light component is relatively more significant than other components. Figure 5 The first column is the original image; the second column is the blue light component histogram; the third column is the superposition of the blue light component and grayscale image histograms; and the fourth column is the superposition of the RGB component histograms.

[0059] In this application, we consider that existing QR code images are generally carried by electronic devices, and the screen media of electronic devices typically have strong blue light and weaker other components. Therefore, we statistically analyze the blue light channel components in the RGB histogram to determine whether they meet the blue light priority condition. If the blue light priority condition is met, we perform image filtering to retain the blue light channel data, which can indirectly reduce redundant data and reduce redundant computation.

[0060] In step S42, if the blue light priority condition is met, then the blue light priority mode is enabled for image filtering to extract the blue light channel. The image filtering in step S42 to extract the blue light channel may include steps S421 to S423.

[0061] In step S421, the effective portion of the blue light spectrum is extracted from the second QR code digital image to separate the blue light components and form a blue light image. This filters out redundant data in the second QR code digital image, retaining only the effective spectrum specified in the configuration file, indirectly reducing redundant data and computational load, thereby lowering computational costs.

[0062] In step S422, the blue light image is subjected to equalization processing. This step of equalizing the blue light channel can be understood as a process of value range compression and expansion. For example, the value range of the current blue light image, 50-100, is equalized to 0-255. This operation can improve the contrast of the image, thereby facilitating the subsequent recognition of the QR code feature.

[0063] In step S423, the equalized blue light image is output as the QR code imaging image. The QR code imaging image is used for QR code feature recognition.

[0064] In a preferred embodiment, the blue light-priority image filtering algorithm further includes the following step S43.

[0065] In step S43, for the second QR code digital image that does not meet the blue light priority condition, it is degraded to the normal mode and the second QR code digital image is directly output as the QR code imaging image. The QR code imaging image is used for QR code feature recognition.

[0066] The QR code image processing method of this application first executes an image focusing algorithm centered on the QR code region, and then executes a blue light-priority image filtering algorithm. This reduces redundant data while acquiring high-quality QR code images, saving algorithm complexity and redundant computation, achieving a balance between image quality and computational cost. Compared with the full color gamut approach, this solution saves algorithm complexity and computational resources, and while meeting the recognition rate requirements, it can satisfy the low power consumption and high frame rate requirements of QR code devices.

[0067] The scope of protection of the QR code image processing method described in this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0068] This application also provides a QR code image processing device. Figure 6 This is a structural block diagram of a QR code image processing apparatus according to an embodiment of the present application. The QR code image processing apparatus 6 is used for QR code image processing, and includes an image acquisition module 61, an image focusing module 62, a color balance processing module 63, and an image filtering module 64.

[0069] The image acquisition module 61 is configured to acquire a RAW image of a QR code.

[0070] The image focusing module 62 is configured to focus the image on the QR code RAW image with the QR code area as the center, so as to obtain the first focused QR code digital image.

[0071] The color equalization processing module 63 is configured to perform color equalization processing on the first QR code digital image to obtain the second QR code digital image.

[0072] The image filtering module 64 is configured to perform image filtering on the second QR code digital image to extract the blue light channel, so as to generate a QR code imaging image having the blue light channel.

[0073] The QR code image processing device 6 is coupled to the digital imaging sensor 0. The image focusing module 62 is used to perform image focusing processing centered on the QR code area, and the image filtering output module 64 is used to perform blue light priority image filtering processing. The image focusing centered on the QR code area and the blue light priority image filtering have been described in detail above and will not be repeated here.

[0074] In another preferred embodiment, the QR code image processing device, in addition to including the image acquisition module 61, the image focusing module 62, the color equalization processing module 63, and the image filtering output module 64, may also include a QR code recognition module 65. The QR code recognition module 65 is used to recognize the QR code imaging image output by the image filtering output module and obtain the feature code.

[0075] The QR code image processing device can be integrated into an image signal processor, i.e., an ISP. Currently available ISPs have various algorithms, which are strung together in a pipeline. Pipeline configuration follows best practices: generally, low-level information, including Bayer interpolation and image noise reduction, is processed first, followed by high-level information, including the 3A series algorithms: AWB (Auto White Balance), AE (Auto Exposure), AF (Auto Focus), and image correction, etc., and finally, transmission information, including format conversion and information compression, is processed. The QR code image processing device of this application follows the principle of obtaining a normal image before image processing. Therefore, it first focuses the image through an image focusing module, and then performs color equalization and image filtering. This saves algorithm complexity and computational resources, and while meeting the recognition rate requirements, it can satisfy the low power consumption and high frame rate requirements of QR code devices, achieving a balance between image quality and computational cost.

[0076] This application also provides an electronic device. Figure 7 This is a block diagram of an electronic device according to an embodiment of this application. (Reference) Figure 7 In one embodiment of this application, the electronic device 7 includes a memory 71 and a processor 72. The memory 71 is configured to store a computer program. The processor 72 is communicatively connected to the memory 71 and is configured to invoke the computer program to execute the QR code image processing method according to this application.

[0077] Optionally, the electronic device 7 also includes a display 73. The display 73 is communicatively connected to the memory 71 and the processor 72, and serves as a GUI interactive interface related to the QR code image processing method and / or the QR code image processing.

[0078] This application also provides a computer-readable storage medium storing a computer program thereon, which is executed by a processor to implement the QR code image processing method according to this application. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state hard disk, magnetic tape, floppy disk, optical disk, and any combination thereof. The above storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0079] This application embodiment may also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application embodiment are generated. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0080] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, the computer program product can be downloaded and executed on the computer.

[0081] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0082] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A two-dimensional code image processing method characterized by comprising: The method comprises: acquiring a two-dimensional code RAW image; focusing an image with respect to the two-dimensional code RAW image with a two-dimensional code region as a center to acquire a first two-dimensional code digital image after focusing; performing color equalization processing on the first two-dimensional code digital image to acquire a second two-dimensional code digital image; and performing image filtering on the second two-dimensional code digital image to extract a blue light channel to generate a two-dimensional code imaging image having the blue light channel, wherein performing image filtering on the second two-dimensional code digital image to extract a blue light channel comprises: acquiring an RGB histogram of the second two-dimensional code digital image; judging whether a blue light component is dominant based on the RGB histogram, if yes, a blue light priority condition is met, otherwise, the blue light priority condition is not met; if the blue light priority condition is met, a blue light priority mode is enabled to perform image filtering processing to extract a blue light channel; and if the blue light priority condition is not met, the second two-dimensional code digital image is directly output as the two-dimensional code imaging image.

2. The two-dimensional code image processing method according to claim 1, characterized by, Enabling the blue light priority mode to perform image filtering processing to extract the blue light channel comprises: extracting a blue light spectrum effective part from the second two-dimensional code digital image to separate the blue light component to form a blue light image; performing equalization processing on the blue light image; and outputting the equalization-processed blue light image as the two-dimensional code imaging image.

3. The two-dimensional code image processing method according to claim 1, characterized by, Focusing an image with respect to the two-dimensional code RAW image with the two-dimensional code region as the center comprises: identifying and marking a two-dimensional code region; adjusting optical system parameters so as to focus on the two-dimensional code region; performing light measurement with the two-dimensional code region as the center; and performing distance measurement with the two-dimensional code region as the center to perform the image focusing.

4. The two-dimensional code image processing method according to claim 3, characterized by, Adjusting the optical system parameters comprises: adjusting the focus and the angle of view of imaging.

5. The two-dimensional code image processing method according to claim 1, characterized by, Further comprising: identifying the two-dimensional code imaging image to acquire a feature code.

6. A two-dimensional code image processing apparatus characterized by comprising: The method comprises: an image acquisition module configured to acquire a two-dimensional code RAW image; an image focusing module configured to focus an image with respect to the two-dimensional code RAW image with a two-dimensional code region as a center to acquire a first two-dimensional code digital image after focusing; a color equalization processing module configured to perform color equalization processing on the first two-dimensional code digital image to acquire a second two-dimensional code digital image; and an image filtering module configured to perform image filtering on the second two-dimensional code digital image to extract a blue light channel to generate a two-dimensional code imaging image having the blue light channel, wherein the image filtering module is configured to: acquire an RGB histogram of the second two-dimensional code digital image; judge whether a blue light component is dominant based on the RGB histogram, if yes, a blue light priority condition is met, otherwise, the blue light priority condition is not met; if the blue light priority condition is met, a blue light priority mode is enabled to perform image filtering processing to extract a blue light channel; and if the blue light priority condition is not met, the second two-dimensional code digital image is directly output as the two-dimensional code imaging image. Further comprising:

7. The two-dimensional code image processing apparatus according to claim 6, characterized by a two-dimensional code identifying module configured to identify the two-dimensional code imaging image to acquire a feature code. The method comprises:

8. An electronic device, comprising: a memory configured to store a computer program; and ​ ​ A processor configured to invoke the computer program to perform the two-dimensional code image processing method according to any one of claims 1 to 5.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed to implement the two-dimensional code image processing method according to any one of claims 1 to 5.

Images