Parameter adjustment method, device and system

Abstract

A parameter adjusting method, device and system, wherein the method comprises: a parameter adjuster obtaining a processed image obtained by processing a preset image using an image processing parameter, and a standard image corresponding to the preset image, the display effect of the standard image being better than that of the processed image, and adaptively adjusting the image processing parameter according to the standard image and the processed image, so that the adjusted image processing parameter can reduce the image difference between the processed image and the standard image. By adjusting the image processing parameter with reference to the standard image with better display effect, the processed image obtained by the adjusted image processing parameter is closer to the standard image, and the scheme can not depend on the subjective feeling of the human eye and can not additionally introduce a camera, thereby helping to reduce the cost while taking into account the accuracy of parameter adjustment.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a parameter adjustment method, apparatus and system. Background Technology

[0002] With the development of media playback and display technologies, the number of adjustable parameters in display devices is constantly increasing, and the display effect of video images is also continuously improving. Currently, a high-performance display device can even have tens of thousands of adjustable parameters. These parameters work together on the original image; adjusting them to appropriate values ​​helps to transform the original image into a better-looking one, enabling users to enjoy a high-definition and smooth video viewing experience.

[0003] Traditional parameter adjustment methods typically involve professionals actively observing the display and repeatedly adjusting parameters based on their subjective perception until the display effect is deemed optimal. This method relies entirely on subjective human judgment, resulting in high labor costs and an inability to adaptively adjust parameters accurately. In response, the industry has proposed... Figure 1 One solution, as shown, uses a camera instead of the human eye. The camera captures the current display image on the screen and transmits it to an image quality evaluator. The evaluator calculates the overall display effect of the current image according to a preset image quality evaluation algorithm and then notifies the corresponding control circuit of the screen. The control circuit adjusts parameters based on the overall display effect, and this process is repeated iteratively until the overall display effect of the image captured by the camera is optimal. Although this solution no longer relies on the subjective perception of the human eye, it introduces additional errors from the shooting environment and the camera itself, which is detrimental to improving the accuracy of parameter adjustment. Furthermore, the additional camera increases the cost of parameter adjustment. Summary of the Invention

[0004] In view of this, this application provides a parameter adjustment method, apparatus and system to solve the technical problems of high cost and poor accuracy of existing image parameter adjustment methods.

[0005] Firstly, this application provides a parameter adjustment method. This method is applicable to a parameter adjuster, which can be a fixed device installed in a display device, a separate device connected to the display device when parameter adjustment is required, or a chip or circuit. The method includes: the parameter adjuster acquiring a processed image obtained by processing a preset image using image processing parameters, and acquiring a standard image corresponding to the preset image, wherein the display effect of the standard image is better than that of the processed image; then, the parameter adjuster adaptively adjusts the image processing parameters according to the standard image and the processed image, so that the adjusted image processing parameters can reduce the difference between the processed image and the standard image.

[0006] In the above design, adjusting image processing parameters by referencing a standard image with superior display quality helps to produce a processed image that more closely resembles the standard image. This design does not rely solely on the display quality of the processed image itself, but also provides a standard image as a reference for parameter adjustment, thus improving the accuracy of parameter adjustment. Furthermore, this design uses both the processed image and the standard image for parameter adjustment, eliminating the need for subjective human perception and additional cameras. Therefore, it helps to achieve adjustment accuracy without incurring additional human or material costs.

[0007] In one possible design, before acquiring the processed image obtained by processing the preset image using image processing parameters, the parameter adjuster can further reduce the display quality of the standard image and use the reduced-quality standard image as the preset image. In this design, the parameter adjuster can automatically complete the parameter adjustment process using the labeled image input from the video source, without needing to perform the additional operation of acquiring the standard image. This saves the parameter adjuster's computational resources and improves the parameter adjuster's flexible management of the entire parameter adjustment process.

[0008] In one possible design, the parameter regulator adaptively adjusts image processing parameters based on the standard image and the processed image. This includes: determining the target image difference between the processed image and the standard image under a preset evaluation metric; judging whether the target image difference meets the evaluation conditions corresponding to the preset evaluation metric; and adjusting the image processing parameters related to the preset evaluation metric if not. In this design, by using the preset evaluation metric as the basic unit for parameter adjustment, the analysis of the entire dataset at once can be avoided, effectively reducing the amount of data analyzed per instance and improving the efficiency and real-time performance of parameter adjustment.

[0009] In one possible design, the evaluation conditions corresponding to the preset evaluation indicators may include any of the following: the adjustment time is not less than the preset time; the number of adjustments is not less than the preset number of adjustments; the difference of the target image is within the allowable difference range of the preset evaluation indicator; and the error between the difference of the target image and the difference of the optimal image is less than the allowable error threshold. By setting different evaluation conditions, the parameter adjuster can select the evaluation conditions that meet the actual needs to complete the evaluation of each preset evaluation indicator.

[0010] In one possible design, the parameter adjuster regulates image processing parameters related to a preset evaluation metric. This includes: the parameter adjuster first adjusts the image processing parameters along a first direction with a first adjustment granularity until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the original image processing parameters; then, along a second direction with a second adjustment granularity, the parameter adjusts the image processing parameters along a second direction until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the original image processing parameters. The second adjustment granularity is smaller than the first adjustment granularity, and either the first direction increases and the second direction decreases, or vice versa. In this design, by adjusting the parameters back and forth with a granularity that decreases gradually, a parameter range can be roughly selected first, followed by fine-grained parameter adjustment. This helps reduce the amount of data to be processed and effectively saves the processing resources of the parameter adjuster.

[0011] In one possible design, the preset evaluation metrics include one or more sub-metrics such as local sharpness, peak signal-to-noise ratio, average energy ratio, or structural similarity. For example, in one scenario, the parameter adjuster can set a sub-metric that is unrelated or weakly correlated with other sub-metrics as a separate preset evaluation metric. Thus, even if subsequent image processing parameters are adjusted based only on this single sub-metric, it is highly unlikely to affect the display effect of the processed image under other sub-metrics, helping to improve the display effect corresponding to this sub-metric while ensuring that the display effects corresponding to other sub-metrics remain unchanged. In another scenario, the parameter adjuster can integrate related sub-metrics into a single preset evaluation metric to achieve more refined parameter adjustment by comprehensively considering the related sub-metrics. This avoids isolated analysis of single sub-metrics, maximizes the accuracy of image processing parameter adjustment, and effectively improves the overall display effect of the processed image.

[0012] In one possible design, when the preset evaluation index includes at least two sub-indicators, the parameter adjuster can determine the target image difference degree between the processed image and the standard image under the preset evaluation index in the following way: The parameter adjuster first determines the image difference degree between the processed image and the standard image under at least two sub-indicators, and then uses the weighted average of the image difference degrees under at least two sub-indicators as the target image difference degree. Thus, by weighting the image difference degree of at least two related sub-indicators, the weighted target image difference degree can accurately characterize the comprehensive display effect of the same image processing parameter corresponding to these at least two sub-indicators. Adjusting the image processing parameter based on this comprehensive display effect can effectively improve the accuracy of the adjustment.

[0013] Secondly, this application provides a parameter adjustment device, comprising: an image processor for processing a preset image using image processing parameters to obtain a processed image; and a parameter adjuster coupled to the image processor for acquiring the processed image and a standard image corresponding to the preset image, and adaptively adjusting the image processing parameters based on the processed image and the standard image. The standard image has a better display effect than the processed image, and the adjusted image processing parameters are used to reduce the image difference between the processed image and the standard image.

[0014] In one possible design, the image processor may include an input interface, an image processing unit, and an output interface coupled sequentially. The input interface may also be coupled to a video source for outputting a standard image, and the output interface may also be coupled to a display screen for displaying the image. In implementation, the input interface receives a standard image from the video source, reduces the display quality of the standard image to obtain a preset image, and sends the preset image to the image processing unit. The image processing unit processes the preset image using image processing parameters to obtain a processed image, and sends the processed image to the output interface, which then sends the processed image to the display screen.

[0015] In one possible design, the parameter regulator may include coupled adjustment circuitry and evaluation circuitry. The adjustment circuitry may also be coupled to an image processing unit, and the evaluation circuitry may further be coupled to an input interface and an output interface. In implementation, after receiving a standard image from a video source, the input interface may also send the standard image to the evaluation circuitry. Similarly, after receiving a processed image from the image processing unit, the output interface may also send the processed image to the evaluation circuitry. The evaluation circuitry can determine the target image difference between the processed image and the standard image under a preset evaluation metric and send the target image difference to the adjustment circuitry. When the adjustment circuitry determines that the target image difference does not meet the evaluation conditions corresponding to the preset evaluation metric, it sends a parameter adjustment command to the image processing unit corresponding to the preset evaluation metric. The image processing unit then adjusts the image processing parameters according to the parameter adjustment command.

[0016] In one possible design, the evaluation conditions corresponding to the preset evaluation index may include any of the following: the adjustment time is not less than the preset time; the number of adjustments is not less than the preset number of adjustments; the difference of the target image is within the difference range allowed by the preset evaluation index; and the error between the difference of the target image and the difference of the optimal image is less than the allowed error threshold.

[0017] In one possible design, the adjustment circuit can adjust the image processing parameters as follows: The adjustment circuit, via a parameter adjustment command, adjusts the image processing parameters related to a preset evaluation index along a first direction with a first adjustment granularity until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the original image processing parameters. Then, it adjusts the image processing parameters related to the preset evaluation index along a second direction with a second adjustment granularity until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the original image processing parameters. Wherein, the second adjustment granularity is smaller than the first adjustment granularity, the first direction is increasing and the second direction is decreasing, or the first direction is decreasing and the second direction is increasing.

[0018] In one possible design, the preset evaluation metrics may include one or more sub-metrics such as local sharpness, peak signal-to-noise ratio, average energy ratio, or structural similarity.

[0019] In one possible design, when the preset evaluation index includes at least two sub-indicators, the evaluation circuit can determine the image difference degree of the processed image relative to the standard image under at least two sub-indicators, and take the weighted average of the image difference degree under at least two sub-indicators as the target image difference degree.

[0020] Thirdly, this application provides a parameter adjustment system, including a video source, a display screen, and a parameter adjustment device as described in any of the second aspects above. The video source can output video to the parameter adjustment device, which processes any frame of the video using image processing parameters and then sends the processed video to the display screen for display.

[0021] Fourthly, this application provides a chip including a processor and a communication interface, wherein the processor can read instructions through the communication interface to execute the method corresponding to any of the designs in the first aspect above.

[0022] Fifthly, this application provides a computer-readable storage medium storing program code that, when run on a computer, causes the computer to perform the method corresponding to any of the designs in the first aspect above.

[0023] Sixthly, this application provides a computer program product that, when run on a processor, implements the method corresponding to any of the designs in the first aspect above.

[0024] For details of the beneficial effects of aspects two through six above, please refer to the technical effects that can be achieved by the corresponding design in aspect one above, which will not be repeated here. Attached Figure Description

[0025] Figure 1 This example illustrates a flowchart of a parameter adjustment method commonly used in the industry.

[0026] Figure 2 An exemplary schematic diagram of a system architecture applicable to an embodiment of this application is shown;

[0027] Figure 3 An exemplary flowchart of a parameter adjustment method provided in an embodiment of this application is shown.

[0028] Figure 4 An exemplary diagram illustrates a method for adjusting image processing parameters provided in an embodiment of this application;

[0029] Figure 5 An exemplary diagram illustrates another method for adjusting image processing parameters provided in an embodiment of this application;

[0030] Figure 6 An exemplary flowchart of another parameter adjustment method provided in an embodiment of this application is shown;

[0031] Figure 7 An exemplary schematic diagram of a parameter regulator provided in an embodiment of this application is shown;

[0032] Figure 8 An exemplary schematic diagram of another parameter regulator provided in an embodiment of this application is shown. Detailed Implementation

[0033] The parameter adjustment method disclosed in this application can be applied to a parameter adjuster, which can be an electronic device or a standalone unit. When the parameter adjuster is a standalone unit, it can be embedded in the electronic device and execute the parameter adjustment method disclosed in the embodiments of this application when the electronic device displays images or videos, thereby improving the image display effect of the electronic device. In other embodiments of this application, the parameter adjuster can also be a unit packaged inside the electronic device, such as a control circuit packaged on the same chip as the image processor in the electronic device, used to implement the function of adjusting the image processing parameters in the image processor. The electronic device can be a home appliance with a display screen, such as an LCD TV, a smart washing machine, or a smart refrigerator. The electronic device can also be a portable electronic device containing functions such as a personal digital assistant and / or a music player, such as a mobile phone, tablet computer, camera, monitor, wearable device (such as a smartwatch), or in-vehicle device. Exemplary embodiments of portable electronic devices include, but are not limited to, devices equipped with... Alternatively, it can be a portable electronic device with another operating system. The aforementioned portable electronic device can also be a laptop computer, such as one with a touch-sensitive surface (e.g., a touch panel). It should also be understood that, in some other embodiments of this application, the aforementioned electronic device can also be a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0034] The present application will now be described in further detail with reference to the accompanying drawings. It should be noted that in the description of this application, "at least one" refers to one or more, where "multiple" refers to two or more. Therefore, in the embodiments of the present invention, "multiple" can also be understood as "at least two". "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / ", unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0035] Furthermore, it should be understood that in the description of this application, terms such as "first" and "second" are used only for descriptive purposes and should not be construed as indicating or implying relative importance or order. For example, "first image difference degree" and "second image difference degree" merely exemplarily indicate two different image difference degrees calculated for two different processed images and a standard image, and do not imply a difference in the importance or priority of these two image difference degrees. In addition, "connection" should be understood as electrical connection or electrical coupling, such as a direct connection via a wire or an indirect connection via one or more other devices, and this application does not specifically limit this.

[0036] Figure 2 An exemplary schematic diagram of a system architecture applicable to an embodiment of this application is shown, such as... Figure 2 As shown, the system architecture includes a video source 210, an image processor 220, and a display screen 230 connected in sequence. The video source 210 can be any device capable of outputting video, such as, but not limited to, a live webcast source, a broadcast television signal source, a camera, a video recorder, a DVD player, or various media players (MP players, such as streaming media players, MP3, MP4, or MP5 players). The video output by the video source 210 consists of multiple consecutive frames. The image processor 220 can be a device or chip with image processing capabilities, including an input interface 221 and at least one image processing unit (such as...). Figure 2 The diagram shows image processing units 2221, 2222, ..., 222n (where n is a positive integer) and an output interface 223. At least one image processing unit can be configured as follows: Figure 2The displays can be connected in series as shown, or in parallel, or partially in parallel and then in series; the specific connection is not limited. The display screen 230 can be any screen with display capabilities, such as a cathode ray tube (CTR) display screen, a light-emitting diode (LED) display screen, a liquid crystal display (LCD), or a three-dimensional (3D) display screen. The display screen 230 can be a touchscreen or a non-touchscreen; the specific connection is not limited.

[0037] In implementation, video source 210 can output video to input interface 221, and input interface 221 can send any frame of the received video to at least one image processing unit. The at least one image processing unit processes the image and sends it to output interface 223, which then sends the processed image to display screen 230 for display to the user. Each of the at least one image processing unit can include one or more parameter registers, each storing an image processing parameter. Each image processing unit processes the received image according to the image processing parameters stored in its internal parameter registers and then sends it to another connected image processing unit or output interface 223. For example, the same image processing unit can include parameter registers that adjust the same display effect, allowing for grouped management of parameter registers based on display effect, facilitating more targeted adjustment of the image processing parameters corresponding to each display effect.

[0038] Continue to refer to Figure 2As shown, the system architecture also includes a parameter regulator 240, which can be connected to the control terminals of various image processing units in the image processor 220, such as connecting the control terminals of image processing unit 2221 to image processing unit 222n. When it is necessary to adjust the image processing parameters of a certain image processing unit, the parameter regulator 240 can send a parameter adjustment command to the image processing unit through the control terminal of that image processing unit to control the image processing unit to adjust the image processing parameters in its internal parameter registers according to the parameter adjustment command. The parameter regulator 240 can be a device or chip with processing capabilities, such as a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD), or other integrated chips. This application does not specifically limit it in this regard.

[0039] It should be noted that one or more components in this system architecture can integrate their functions onto a single physical unit, or they can distribute their functions across multiple independent physical units. For example, in one scenario, the image processor 220 and the parameter adjuster 240 can be integrated onto the same chip to quickly complete the overall logic of parameter adjustment through an on-chip message transmission mechanism. Alternatively, in another scenario, the parameter adjuster 240 can be integrated separately onto the parameter processor chip, and the image processor 220 can be integrated separately onto the image processor chip. In this way, these two components can execute their respective functions on their respective chips, facilitating distributed management of different functions.

[0040] The following is based on Figure 2 The system architecture shown is illustrated, and the specific implementation of the parameter adjustment method in this application is described in detail.

[0041] Example 1

[0042] Figure 3This example illustrates a schematic diagram of the execution flow of the parameter adjustment method provided in Embodiment 1 of this application. This method is applicable to parameter adjusters, such as... Figure 2 The parameter adjuster 240 is shown in the image. Figure 3 As shown, the method includes:

[0043] Step 301: The parameter adjuster obtains the processed image obtained by processing the preset image using image processing parameters.

[0044] In step 301 above, the preset image can be any frame image before being processed by at least one image processing unit, and the processed image can be any frame image after being processed by at least one image processing unit. In implementation, the parameter adjuster can obtain the processed image in various ways, for example:

[0045] Method 1, continue to refer to Figure 2 As shown, the parameter regulator 240 can also be connected to the control terminal of the output interface 223. After receiving at least one frame of processed image output by the image processing unit, the output interface 223 can actively report the processed image to the parameter regulator 240 through its control terminal. Alternatively, the output interface 223 can first send a query message to the parameter regulator 240. After receiving the query message, if the parameter regulator 240 determines that it is currently performing parameter adjustment, it can return a first response message to the output interface 223 to instruct the output interface 223 to report the processed image to the parameter regulator 240. If it determines that it is not currently performing parameter adjustment, it can return a second response message to the output interface 223 to instruct the output interface 223 to send the processed image to the display screen 230 for display according to the normal image display process.

[0046] Method 2, continue to refer to Figure 2 As shown, the parameter regulator 240 can also be connected to the control terminal of the output interface 223. When the parameter regulator 240 performs parameter adjustment business, it can periodically send an acquisition request to the output interface 223 through the control terminal of the output interface 223. After receiving the acquisition message, if the output interface 223 determines that there is a newly received processed image in the current period, it can actively report the newly received processed image to the parameter regulator 240.

[0047] Method 3, continue to refer to Figure 2 As shown, assuming that the image processing unit 222n is the last image processing unit connected to the output interface 223, after processing the image sent by the previous image processing unit, the image processing unit 222n can also actively send the processed image to the parameter regulator 240 while sending the processed image to the output interface 223.

[0048] It should be understood that the above content is only an example of several possible ways to obtain the processed image. The parameter adjuster can also use other methods to obtain the processed image, which will not be listed in this application.

[0049] Step 302: The parameter adjuster obtains the standard image corresponding to the preset image. The display effect of the standard image is better than that of the processed image.

[0050] Continue to refer to Figure 2 As shown, in an optional embodiment, the parameter adjuster 240 can also be connected to the control terminal of the input interface 221. When performing parameter adjustment, the video source 210 can output a standard video to the input interface 221. A standard video refers to a video in which the display effect of each frame of the video meets the expected display effect, and each frame of the standard video can be used as a standard image. After receiving a standard image output by the video source 210, the input interface 221 can actively or under the control of the parameter adjuster 240 reduce the display effect of the standard image, and send the standard image with reduced display effect as a preset image to at least one image processing unit. The image is then processed by the at least one image processing unit to obtain the processed image. The reduction of display effect can be achieved by adjusting one or more image processing parameters that affect the display effect, such as including but not limited to: increasing the pixel pitch, reducing the image resolution, reducing the transparency, increasing the grayscale, reducing the brightness, increasing the sharpness, increasing the color temperature, or increasing the blur level. As for the specific percentage reduction in display effect, it can be set by those skilled in the art based on experience. For example, it can be a percentage randomly selected from the range of percentages without distortion, a percentage reduced according to a preset fixed percentage, or a percentage calculated according to a preset percentage algorithm before reduction, etc. There are no specific limitations.

[0051] It should be noted that the above content is only one optional implementation method. The parameter regulator can also obtain the standard image corresponding to the preset image through other methods. For example, in another optional implementation method, the parameter regulator can also pre-store some standard images in its local space. After obtaining the processed image, the parameter regulator can directly match the processed image with each of the locally stored standard images, and take the standard image with the highest matching degree with the processed image as the standard image corresponding to the preset image. As another example, in yet another optional implementation method, the parameter regulator can also connect to a video source. After obtaining the processed image corresponding to the preset image, the parameter regulator can also obtain the identifier of the preset image from the image processor and send a request message carrying the identifier to the video source. After receiving the request message, the video source can search for the standard image corresponding to the identifier in its local video library, or obtain the standard image corresponding to the identifier through interaction with other video sources, and then return the standard image to the parameter regulator in a response message. It should be understood that there are many possible ways to obtain the standard image, which will not be listed here.

[0052] Step 303: The parameter adjuster adaptively adjusts the image processing parameters based on the standard image and the processed image. The adjusted image processing parameters are used to reduce the image difference between the processed image and the standard image.

[0053] In step 303 above, the parameter adjuster can first calculate the image difference degree between the processed image and the standard image based on the processed image and the standard image. When the image difference degree is large, it means that the image features of the processed image deviate far from the image features of the standard image, and the display effect of the processed image is poor. In this case, the parameter adjuster can adjust the image processing parameters in the direction of reducing the image difference degree. Adjusting the image processing parameters in the direction of reducing the image difference degree means that the adjusted image processing parameters meet the following condition: assuming that the processed image obtained by processing the preset image using the image processing parameters before adjustment has a first image difference degree relative to the standard image, and the processed image obtained by processing the preset image using the adjusted image processing parameters has a second image difference degree relative to the standard image, then the second image difference degree is less than the first image difference degree. Thus, the adjusted image processing parameters can process the preset image into a processed image that is more similar to the standard image, which helps improve the display effect of the processed image. When the image difference degree is small, it means that the image features of the processed image are already relatively close to the image features of the standard image, and the display effect of the processed image itself is good. In this case, the parameter adjuster does not need to adjust the image processing parameters.

[0054] It should be noted that reducing the image difference between the processed image and the standard image can also be considered as increasing the image similarity between the processed image and the standard image. This application only uses image difference as an example to illustrate the specific implementation process of parameter adjustment. In specific implementations, image difference can also be replaced by image similarity. The difference is that when the image similarity between the processed image and the standard image is small, the parameter adjuster can adjust the image processing parameters in the direction of increasing image similarity; when the image similarity between the processed image and the standard image is large, the parameter adjuster may not need to adjust the image processing parameters. For the specific implementation process of parameter adjustment using image similarity as an example, please refer directly to the following text; this application will not repeat it here.

[0055] In an optional implementation, the parameter adjuster may further include at least one preset evaluation index and evaluation conditions corresponding to each preset evaluation index. Each preset evaluation index may correspond to one or more image processing parameters. The image processing parameters corresponding to two preset evaluation indices may include the same image processing parameters or different image processing parameters. In practice, after obtaining the processed image corresponding to the preset image and the standard image corresponding to the preset image, the parameter adjuster may calculate the target image difference between the processed image and the standard image under any preset evaluation index. If the target image difference under a certain preset evaluation index does not meet the evaluation conditions corresponding to that preset evaluation index, the parameter adjuster may adjust the image processing parameters corresponding to the preset evaluation index in the direction of reducing the target image difference, and obtain a new processed image obtained by reprocessing the preset image using the adjusted image processing parameters. This judgment and adjustment process is repeated until a certain image processing parameter is adjusted so that the target image difference under the preset evaluation index meets the evaluation conditions corresponding to the preset evaluation index, at which point the analysis of the preset evaluation index ends. Accordingly, if the difference in the target image under a certain preset evaluation index meets the evaluation conditions corresponding to the preset evaluation index, the parameter regulator can directly end the analysis of that preset evaluation index. Afterwards, if a single-threaded approach is used to analyze each preset evaluation index serially, the parameter regulator can move on to analyze the next preset evaluation index. If a multi-threaded approach is used to analyze each preset evaluation index in parallel, the parameter regulator can wait for other threads to complete their analyses before moving on to analyze the next preset image frame. In this implementation, by using preset evaluation indices as the basic unit of parameter adjustment, the analysis of the entire dataset at once can be avoided, effectively reducing the amount of data analyzed per session and improving the efficiency and real-time performance of parameter adjustment.

[0056] In this embodiment, the evaluation conditions corresponding to any preset evaluation index may include one or more of the following: the adjustment time of the image processing parameters is not less than a preset time, the number of adjustments to the image processing parameters is not less than a preset number, the difference in the target image corresponding to the adjusted image processing parameters is within the allowable difference range of the preset evaluation index, and the error between the difference in the target image corresponding to the adjusted image processing parameters and the minimum image difference is not greater than an allowable error threshold. Of course, other conditions that can adjust the image processing parameters to achieve a better display effect may also be included, without specific limitations.

[0057] In this embodiment, a preset evaluation index may include one or more sub-indices such as local sharpness, structural similarity (SSIM), mean squared error (MSE), or peak signal-to-noise ratio (PSNR). Local sharpness refers to the sharpness of an image in a local region, which can be represented by the proportion of high-frequency components with frequencies higher than a certain frequency in the spectrum of that local region. Structural similarity refers to the similarity between the original image and the noisy image, which can be represented by the average energy similarity of each pixel region in the original image and the noisy image. Mean squared error (MSE) is the average energy difference between the original image and the noisy image, which can be represented by the average of the squares of the energy differences at each pixel in the original image and the noisy image. Peak signal-to-noise ratio is the ratio of the energy of the peak signal in the original image to the average energy of the noisy image, which can be represented by the sum of the mean squared error and the average energy of the noisy image. Among these sub-indicators, the noisy image is obtained by processing the original image. The original image can correspond to the standard image in this application, while the noisy image can correspond to the processed image in this application.

[0058] The following example uses a preset evaluation index to illustrate two specific implementation methods for adjusting image processing parameters.

[0059] Example 1: Preset evaluation indicators include only one sub-indicator

[0060] Figure 4 This illustration shows a flowchart of a method for adjusting image processing parameters according to an embodiment of this application. This method is applicable to parameter adjusters, such as... Figure 2 The parameter adjuster 240 is shown in the image. Figure 4 As shown, the method includes:

[0061] Step 401: The parameter adjuster obtains the processed image obtained by processing the preset image using image processing parameters, and the standard image corresponding to the preset image.

[0062] Step 402: The parameter adjuster calculates the image difference between the processed image and the standard image under the unique sub-index corresponding to the preset evaluation index, based on the standard image and the processed image.

[0063] In step 402 above, the parameter adjuster can set a sub-index that is unrelated or weakly correlated with other sub-indexes as a preset evaluation index. Thus, even if the image processing parameters are subsequently adjusted based only on this single sub-index, it is highly unlikely to affect the display effect of the processed image under other sub-indexes, helping to improve the display effect of this sub-index while ensuring that the display effects of other sub-indexes remain unchanged.

[0064] For example, when local sharpness is used as a preset evaluation index, the parameter adjuster can first obtain the first spectrum of a local region in the processed image, find the first high-frequency component with a frequency greater than the high-frequency threshold from the first spectrum, calculate the first proportion of the first high-frequency component in the first spectrum based on the first high-frequency component and the first spectrum, then obtain the second spectrum of a local region in the standard image, find the second high-frequency component with a frequency greater than the high-frequency threshold from the second spectrum, calculate the second proportion of the second high-frequency component in the second spectrum based on the second high-frequency component and the second spectrum, and then calculate the difference between the first proportion and the second proportion, using this difference as the image difference degree of the processed image relative to the standard image in terms of local sharpness.

[0065] Step 403: The parameter adjuster determines whether the image difference under the unique sub-index is within the allowable difference range. If not, proceed to step 404; if yes, proceed to step 405.

[0066] In step 403 above, the allowable range of differences can be limited by positive and negative difference thresholds: when the image difference under the unique sub-index is not greater than the positive difference threshold and not less than the negative difference threshold, the parameter regulator determines that the image difference under the unique sub-index is within the allowable range of differences; when the image difference under the unique sub-index is greater than the positive difference threshold or less than the negative difference threshold, the parameter regulator determines that the image difference under the unique sub-index is outside the allowable range of differences. In this case, the image difference under the unique sub-index being within the allowable range of differences can include the following situations: the image difference under the unique sub-index is positive and less than the positive difference threshold, or the image difference under the unique sub-index is negative and greater than the negative difference threshold. Correspondingly, the image difference under the unique sub-index being outside the allowable range of differences can include the following situations: the image difference under the unique sub-index is positive and greater than the positive difference threshold, or the image difference under the unique sub-index is negative and less than the negative difference threshold.

[0067] The positive difference threshold and the negative difference threshold can be values ​​set by those skilled in the art based on experience, or values ​​obtained from experimental verification. They can be fixed values ​​or variable values, and there is no specific limitation.

[0068] Step 404: The parameter adjuster adjusts the image processing parameters corresponding to the unique sub-index in the direction of reducing the image difference under the unique sub-index, and then repeats the above steps 401 to 404.

[0069] In step 404 above, taking local sharpness as a separate preset evaluation index as an example, when the image difference between the processed image and the standard image in terms of local sharpness is negative and less than the negative difference threshold, it means that the local areas of the processed image are far less clear and sharp than the same local areas in the standard image, and the original image processing parameters are obviously insufficient in filtering the preset image. In this case, the parameter adjuster can increase the image processing parameters related to filtering, such as increasing the parameter value in the filter parameter register. Thus, the increased filter parameter register can perform deeper filtering on the local areas of the preset image, helping to make the local areas of the processed image clearer and sharper, effectively reducing the sharpness difference between the processed image and the standard image in local areas. Conversely, when the image difference between the processed image and the standard image in terms of local sharpness is positive and greater than the positive difference threshold, it means that the local areas of the processed image are too clear and sharp or even distorted, and the original image processing parameters are too excessive in filtering the preset image. In this case, the parameter adjuster can decrease the image processing parameters related to filtering, such as decreasing the parameter value in the filter parameter register. In this way, the reduced filter parameter register can perform gentler filtering on local areas of the preset image, which helps to reduce the probability of distortion in local areas of the processed image and effectively reduce the difference in sharpness between the processed image and the standard image in local areas.

[0070] Furthermore, after adjusting the image processing parameters corresponding to the unique sub-index, the parameter adjuster can also obtain a new processed image obtained by processing the preset image using the new image processing parameters, and recalculate the image difference between the new processed image and the standard image under the unique sub-index. If the image difference is still outside the allowable difference range, the parameter adjuster can continue to adjust the image processing parameters corresponding to the unique sub-index in the direction of reducing the image difference under the unique sub-index, until the image processing parameters are adjusted to make the image difference under the unique sub-index fall within the allowable difference range, so as to gradually adjust the image processing parameters to a better level through iteration.

[0071] It should be noted that in the aforementioned iterative process, the preset image can be the same frame processed by the original image processing parameters, or it can be the next frame from the video input from the video source. As the parameter adjuster continuously adjusts the parameters for each frame in the same video input from the video source, this method can adjust to obtain universal image processing parameters applicable to the current video. Subsequently, the parameter adjuster can establish a relationship between the current video and the universal image processing parameters, and perform the same adjustment process for the next video to obtain relationships between different videos and different image processing parameters. Alternatively, the parameter adjuster can continue to adjust the parameters for other videos based on these universal image processing parameters, thereby obtaining a set of universal image processing parameters applicable to multiple videos.

[0072] It should be noted that, in the embodiments of this application, when the number of image processing parameters is very large, the parameter adjuster can also construct different parameter sets based on these image processing parameters. Each parameter set may include at least one image processing parameter, and different parameter sets may include one or more of the same image processing parameters, or they may include completely different image processing parameters; the specifics are not limited. In this case, the parameter adjuster can also utilize a deep learning network to adjust different parameter sets for different videos, thereby obtaining the same or different parameter sets applicable to various videos and improving the versatility of video processing.

[0073] Step 405: The parameter adjuster ends the parameter adjustment of the preset evaluation index.

[0074] In Example 1 above, by comparing the image difference degree under each sub-index with the allowable difference degree range, the image processing parameters corresponding to each sub-index can be adjusted to a range that is not much different from the display effect of the standard image, effectively improving the display effect of the processed image.

[0075] Example 2: The pre-set evaluation indicators include at least two sub-indicators.

[0076] Figure 5 This invention provides an exemplary flowchart of another method for adjusting image processing parameters according to an embodiment of the present application. This method is applicable to parameter adjusters, such as those described above. Figure 2 The parameter adjuster 240 is shown in the image. Figure 5 As shown, the method includes:

[0077] Step 501: The parameter adjuster obtains the processed image obtained by processing the preset image using image processing parameters, and the standard image corresponding to the preset image.

[0078] Step 502: The parameter adjuster calculates the image difference degree of the processed image relative to the standard image under at least two sub-indicators based on the processed image and the standard image, and determines the target image difference degree under the preset evaluation index based on the image difference degree under at least two sub-indicators.

[0079] In step 502 above, the parameter adjuster can integrate the relevant sub-indicators of each sub-index into a preset evaluation index, so as to achieve more refined parameter adjustment by comprehensively considering the relevant sub-indicators, avoiding isolated analysis of a single sub-index, maximizing the accuracy of image processing parameter adjustment, and effectively improving the overall display effect of the processed image.

[0080] For example, increasing the local sharpness of a preset image usually increases the noise of the preset image as well. Increased noise in the preset image, in turn, reduces the peak signal-to-noise ratio (PSNR) of the preset image. Therefore, local sharpness and PSNR are correlated. In this case, the parameter regulator can integrate local sharpness and PSNR into a single preset evaluation metric. When analyzing this preset evaluation metric, the parameter regulator can first calculate the image difference between the processed image and the standard image at local sharpness according to the method in step 402 above. Then, it can calculate the ratio of the peak signal energy in the standard image to the average energy of the processed image, and use this ratio as the image difference between the processed image and the standard image at PSNR. Finally, based on the image difference under these two sub-metrics, the target image difference between the processed image and the standard image under the preset evaluation metric can be determined. For example, the average or weighted average of the image difference under these two sub-metrics can be used as the target image difference. When using the weighted average of the differences between two images as the difference of the target image, the weights of these two differences can be set by those skilled in the art based on experience, or can be obtained through experimental verification, and there is no specific limitation.

[0081] Step 503: The parameter adjuster adjusts the image processing parameters corresponding to at least two sub-indices along the first direction with a first adjustment granularity.

[0082] In step 503 above, taking the preset evaluation indicators of local sharpness and peak signal-to-noise ratio (PSNR) as examples, when the parameter adjuster determines that the weighted image difference between the processed image and the standard image under these two sub-indicators is large, it means that the processed image shows a worse degree of blurring in local sharpness than the degree of noise interference in PSNR compared to the standard image. The overall display effect of the processed image under local sharpness and PSNR indicates that the processed image should be adjusted to be clearer and sharper first. In this case, the parameter adjuster can increase the image processing parameters related to filtering, such as increasing the parameter value in the filter parameter register. In this way, the increased filter parameter register can perform deeper filtering on the local areas of the preset image, which helps to make the local areas of the processed image clearer and sharper. Although it will also increase the degree of noise interference in the processed image under PSNR, it will still reduce the target image difference between the processed image and the standard image overall. Thus, by considering the overall display effect of the processed image under the two sub-indicators of local sharpness and peak signal-to-noise ratio, adjusting the image processing parameters helps to achieve the best balance between the sharpness and noise interference of the processed image, thereby improving the overall display effect of the processed image.

[0083] Step 504: The parameter adjuster obtains the new processed image obtained by processing the preset image using the adjusted image processing parameters, calculates the new image difference degree of the new processed image relative to the standard image under at least two sub-indicators based on the new processed image and the standard image, and determines the new target image difference degree under the preset evaluation index based on the new image difference degree under at least two sub-indicators.

[0084] Step 505: The parameter adjuster determines whether the absolute value of the difference in the target image is decreasing. If yes, proceed to step 503; otherwise, proceed to step 506.

[0085] In step 505 above, when the target image difference corresponding to the adjusted image processing parameters is positive and less than the target image difference corresponding to the original image processing parameters, or when the target image difference corresponding to the adjusted image processing parameters is negative and greater than the target image difference corresponding to the original image processing parameters, the parameter adjuster can determine that the target image difference is decreasing. When the target image difference corresponding to the adjusted image processing parameters is positive and not less than the target image difference corresponding to the original image processing parameters, or when the target image difference corresponding to the adjusted image processing parameters is negative and not greater than the target image difference corresponding to the original image processing parameters, the parameter adjuster can determine that the target image difference is not decreasing.

[0086] Step 506: The parameter adjuster adjusts the image processing parameters corresponding to at least two sub-indices along the second direction with a second adjustment granularity, the second adjustment granularity being smaller than the first adjustment granularity.

[0087] Step 507: The parameter adjuster obtains the new processed image obtained by processing the preset image using the adjusted image processing parameters, calculates the new image difference degree of the new processed image relative to the standard image under at least two sub-indicators based on the new processed image and the standard image, and determines the new target image difference degree under the preset evaluation index based on the new image difference degree under at least two sub-indicators.

[0088] Step 508: The parameter adjuster determines whether the absolute value of the difference in the target image is decreasing. If yes, proceed to step 506; otherwise, proceed to step 509.

[0089] Step 509: The parameter adjuster ends the parameter adjustment of the preset evaluation index.

[0090] In this embodiment, the first direction and the second direction can be either an increasing first direction and a decreasing second direction, or a decreasing first direction and an increasing second direction. The implementation process of steps 503 to 509 will be described in detail below, exemplarily taking an increasing first direction and a decreasing second direction as an example:

[0091] Step a: After determining the target image difference, the parameter adjuster can first increase the image processing parameters corresponding to at least two sub-indicators by a larger first adjustment granularity (e.g., 5 unit parameter values). It then obtains a new processed image by processing the new preset image output from the video source using the increased image processing parameters. The weighted average of the image differences of the new processed image relative to the standard image corresponding to the new preset image under at least two sub-indicators is taken as the new target image difference. If the absolute value of the new target image difference is less than the absolute value of the previously calculated target image difference, it indicates that the increased image processing parameters make the processed image increasingly closer to the standard image, and the direction of this increase is correct. Therefore, the parameter adjuster can continue to increase the image processing parameters corresponding to at least two sub-indicators according to the first adjustment granularity until the absolute value of the new target image difference is greater than or equal to the absolute value of the previously calculated target image difference. If this occurs, it indicates that the increased image processing parameters may have caused the processed image to deviate further from the standard image, and the direction of this increase is incorrect. This means that the most accurate image processing parameters are within a range of 5 unit parameter values ​​between the previously increased image processing parameters and the currently increased image processing parameters.

[0092] In step b, the parameter adjuster can further reduce the image processing parameters corresponding to at least two sub-indices by a smaller second adjustment granularity (e.g., 2 unit parameter values), and obtain a new processed image obtained by processing the new preset image output from the video source using the reduced image processing parameters. The weighted average of the image differences between the new processed image and the standard image corresponding to the new preset image under at least two sub-indices is taken as the new target image difference. If the absolute value of the new target image difference is less than the absolute value of the target image difference calculated previously, it indicates that the reduced image processing parameters make the processed image closer to the standard image, and the direction of this reduction is correct. Therefore, the parameter adjuster can continue to perform the reduction operation on the image processing parameters corresponding to at least two sub-indices according to the second adjustment granularity until the absolute value of the new target image difference is greater than or equal to the absolute value of the target image difference calculated previously. This indicates that the reduced image processing parameters may have made the processed image far away from the standard image, and the direction of this reduction is incorrect. This means that the most accurate image processing parameters are within the range of 2 unit parameter values ​​between the previously reduced image processing parameters and the currently reduced image processing parameters.

[0093] Step c: If the value of the second adjustment granularity is small enough to ignore the error in processing the image within a range of the second adjustment granularity, the parameter regulator can directly end the parameter adjustment of at least two sub-indicators. It can then select an image processing parameter from a range of two unit parameter values ​​between the previously reduced image processing parameter and the currently reduced image processing parameter as the final image processing parameter. For example, it can directly use the previously reduced image processing parameter as the final image processing parameter, or use the average or weighted average of these two image processing parameters as the final image processing parameter. In this case, the parameter regulator can find a better image processing parameter through only one alternating adjustment in the above two directions. If the value of the second adjustment granularity is not small enough to ignore the error in processing the image within a range of the second adjustment granularity, the parameter regulator can repeat the alternating adjustment in the above two directions, gradually reducing the adjustment granularity during the repetition until the latest adjustment granularity is small enough to ignore the error in processing the image within the latest adjustment granularity. In this case, the parameter regulator can find a better image processing parameter in an iterative manner through multiple alternating adjustments in the above two directions.

[0094] It should be noted that the above example only illustrates one specific implementation process of parameter adjustment using alternating adjustments in two directions. In practice, the parameter adjuster can also use other methods for parameter adjustment. For example, in another example, the parameter adjuster can first adjust the parameters in one direction with a larger granularity until it finds image processing parameters that prevent the absolute value of the target image difference from decreasing further. Then, using the previously adjusted image processing parameters as a reference, it can continue to adjust the parameters in that direction with a smaller granularity, and so on, continuously adjusting the parameters in the same direction at multiple granularities until a better image processing parameter is found. As another example, the parameter adjuster can first adjust the parameters in one direction at multiple granularities, and then, using the image processing parameters after the last adjustment as a reference, adjust the parameters in another direction at multiple granularities until a better image processing parameter is found. Yet another example, the parameter adjuster can first adjust the parameters in one direction at multiple granularities, and then, using the previously adjusted image processing parameters as a reference, adjust the parameters in another direction and the first direction at multiple granularities alternately until a better image processing parameter is found. It should be understood that there are many possible implementation methods, which will not be listed here.

[0095] In Example 2, by adjusting parameters with a large-to-small granularity, a parameter range can be roughly selected first, and then fine-tuning can be performed. This helps to reduce the amount of data that needs to be processed and effectively saves the processing resources of the parameter adjuster.

[0096] It should be noted that the adjustment methods in Example 1 and Example 2 above can be combined to obtain new examples. For example, in another example, the parameter adjuster can first calculate the image difference between the processed image and the standard image under a preset evaluation index, and determine whether the image difference is within the allowable difference range in the manner described in Example 1 above. If not, the image processing parameters are adjusted along the first direction with the first adjustment granularity in the manner described in Example 2 above, until the absolute value of the image difference corresponding to the new image processing parameters is not less than the image difference corresponding to the previously adjusted image processing parameters. Then, the image difference corresponding to the previously adjusted image processing parameters is determined in the manner described in Example 1 above. If it is, the previously adjusted image processing parameters are directly used as the final image processing parameters. If not, the image processing parameters are adjusted along the second direction with the second adjustment granularity in the manner described in Example 2 above, until the absolute value of the image difference corresponding to the new image processing parameters is not less than the image difference corresponding to the previously adjusted image processing parameters. The previously adjusted image processing parameters are then used as the final image processing parameters. It should be understood that there are many possible implementation methods, which will not be listed here.

[0097] In the first embodiment described above, adjusting the image processing parameters by referring to a standard image with superior display effect helps to produce a processed image that more closely resembles the standard image. This design not only relies on the display effect of the processed image itself but also provides a reference standard image for the parameter adjustment process, effectively improving the accuracy of parameter adjustment. Furthermore, the first embodiment adjusts parameters by directly acquiring the processed image and the standard image, eliminating the need for subjective human perception and additional cameras. Therefore, it achieves accurate adjustment without incurring additional human or material costs.

[0098] In one alternative implementation, referencing Figure 2 As shown, the parameter adjuster 240 may include an adjustment circuit 241 and an evaluation circuit 242. The output of the adjustment circuit 241 is connected to the control terminal of the input interface 221, the control terminals of the image processing units 2221 to 222n, and the control terminal of the output interface 223, respectively. The input of the adjustment circuit 241 is connected to the output of the evaluation circuit 242, and the input of the evaluation circuit 242 is connected to the output of the input interface 221 and the output of the output interface 223, respectively. In implementation, the evaluation circuit 242 can calculate the image difference degree based on the standard image and the processed image and send it to the adjustment circuit 241. The adjustment circuit 241 can adjust the image processing parameters of the image processing units 2221 to 222n based on the image difference degree. In this embodiment, by setting two logic circuits to perform the functions of calculating the image difference degree and adjusting the parameters respectively, the workload of performing both operations simultaneously by a single component can be distributed.

[0099] The following describes the specific implementation process of the parameter adjustment method in the above embodiments based on Example 2.

[0100]

Example 2

[0101] Figure 6 This illustration shows a schematic diagram of the execution flow of a parameter adjustment method provided in Embodiment 2 of this application. The method is applicable to a video source, an input interface and an output interface in an image processor, at least one image processing unit, and adjustment and evaluation circuits in a parameter adjuster. For example, it can be as follows: Figure 2The illustrated components include a video source 210, an input interface 221 and an output interface 223 in the image processor 220, one or more image processing units 2221 to 222n, and an adjustment circuit 241 and an evaluation circuit 242 in the parameter adjuster 240. In this example, the adjustment circuit can also be connected to the evaluation circuit, the input interface, the output interface, and each image processing unit via a bus system to complete information interaction with each component and monitor the entire parameter adjustment process. Figure 6 As shown, the method includes:

[0102] Step 601: The video source outputs a standard image to the input interface.

[0103] Step 602: After receiving the standard image from the video source, the input interface sends a first notification message to the adjustment circuit.

[0104] The first notification message is used to notify the adjustment circuit that the input interface has received a standard image.

[0105] Step 603: After receiving the first notification message, if the adjustment circuit determines that a parameter adjustment service is currently being performed, it returns a first control message to the input interface.

[0106] The first control message is used to instruct the input interface to send a standard image to the evaluation circuit, and to instruct the input interface to obtain a preset image by reducing the display effect of the standard image.

[0107] Step 604: The input interface sends the standard image to the evaluation circuit according to the first control message.

[0108] Step 605: The input interface obtains a preset image by reducing the display effect of the standard image according to the first control message.

[0109] Step 606: The input interface sends the preset image to the image processing unit.

[0110] Step 607: The image processing unit processes the preset image using image processing parameters to obtain the processed image.

[0111] Step 608: The image processing unit sends the processed image to the output interface.

[0112] Step 609: After receiving the processed image from the image processing unit, the output interface sends a second notification message to the adjustment circuit.

[0113] The second notification message is used to notify the adjustment circuit that the output interface has received the processed image.

[0114] Step 610: After receiving the second notification message, if the adjustment circuit determines that a parameter adjustment service is currently being performed, it returns a second control message to the output interface.

[0115] The second control message is used to instruct the output interface to send the processed image to the evaluation circuit.

[0116] Step 611: The output interface sends the processed image to the evaluation circuit according to the second control message.

[0117] For example, the output interface can also send the processed image to the display screen for display, so as to achieve parallel operation of displaying and adjusting at the same time.

[0118] Step 612: The evaluation circuit calculates the difference between the processed image and the standard image under a preset evaluation index based on the standard image and the processed image.

[0119] For example, when the input interface sends a standard image to the evaluation circuit, it can also simultaneously send the identifier of the standard image. Similarly, when the output interface sends a processed image to the evaluation circuit, it can also simultaneously send the identifier of the standard image corresponding to the processed image before processing. In this way, the evaluation circuit can find the standard image and the processed image with the same identifier from the various standard images sent by the input interface and the various processed images sent by the output interface, and initiate parameter adjustment for that processed image.

[0120] Step 613: The evaluation circuit sends the difference between the processed image and the standard image under the preset evaluation index to the adjustment circuit.

[0121] In another optional embodiment of steps 612 and 613 above, the evaluation circuit may also only calculate the image difference degree of the processed image relative to the standard image under each sub-index and send it to the adjustment circuit. The adjustment circuit then determines the target image difference degree of the processed image relative to the standard image under any preset evaluation index based on the image difference degree of each sub-index. In this way, the adjustment circuit can also combine the sub-indexes required for different scenarios according to its own needs, so as to flexibly adjust the image processing parameters for each scenario in a more targeted manner.

[0122] Step 614: The adjustment circuit determines whether the difference between the processed image and the standard image under the preset evaluation index meets the evaluation conditions corresponding to the preset evaluation index. If it does not meet the conditions, then proceed to step 615; if it does meet the conditions, then proceed to step 617.

[0123] Step 615: The adjustment circuit sends a parameter adjustment instruction to the image processing unit corresponding to the preset evaluation index. The parameter adjustment instruction is used to reduce the difference between the processed image and the standard image under the preset evaluation index.

[0124] Step 616: The image processing unit adjusts the image processing parameters according to the parameter adjustment instruction, and then executes step 607.

[0125] In steps 615 and 616 above, the parameter adjustment instruction can include both the adjustment direction and the adjustment magnitude, such as indicating how many units to increase the parameter value or how many units to decrease it. In this case, after receiving the parameter adjustment instruction, the image processing unit corresponding to the preset evaluation index can directly adjust the parameter value of the internal parameter registers according to the adjustment direction indicated in the parameter adjustment instruction, with the adjustment magnitude indicated by the instruction. Alternatively, the parameter adjustment instruction can only include the adjustment direction, such as indicating only an increase without specifying how many units to increase the parameter value, or indicating only a decrease without specifying how many units to decrease the parameter value. In this case, after receiving the parameter adjustment instruction, the image processing unit corresponding to the preset evaluation index can decide how much parameter value to adjust according to the adjustment direction indicated by the parameter adjustment instruction, for example, by increasing or decreasing only a small unit parameter value to avoid over-adjustment.

[0126] Step 617: Adjust the circuit to end the parameter adjustment process.

[0127] In this embodiment of the application, during the process of outputting video from the video source, continuous standard images in the same video are continuously input into this entire system. According to the above-mentioned process, the image processing parameters adaptively adjusted by the adjustment circuit for any frame of standard image in the video are used to verify the applicability of the next frame of standard image. The image processing parameters are further adjusted according to the applicability of the next frame of standard image until a set of image processing parameters that is good for each frame of standard image in the current video is trained.

[0128] In the second embodiment described above, the adjustment circuit controls the input interface to send a standard image to the evaluation circuit, and controls the output interface to send a processed image to the evaluation circuit. This facilitates unified monitoring of the entire parameter adjustment process by the adjustment circuit. It should be understood that this is only one possible implementation. In another possible implementation, the input interface can also autonomously send the standard image to the evaluation circuit after receiving it, or the output interface can also autonomously send the processed image to the evaluation circuit after receiving it, without requiring unified monitoring by the adjustment circuit, thus reducing the workload of the adjustment circuit.

[0129] It should be noted that in the above embodiment 2, the adjustment circuit and the evaluation circuit can be set on the same physical unit (for example, simultaneously set in the central processing unit of the same system on a chip (SoC)), or they can be set on different physical units (for example, set in different SoCs, or set in different logic units of the same SoC), and there is no specific limitation.

[0130] It should be understood that the names of the above information are merely examples. As communication technology evolves, the names of any of the above information may change. However, regardless of how the names change, as long as their meaning is the same as the meaning of the above information in this application, they all fall within the protection scope of this application.

[0131] The above mainly describes the solution provided in this application from the perspective of interaction between various network elements. It is understood that, in order to achieve the above functions, each network element includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0132] According to the aforementioned method, Figure 7 This is a schematic diagram of a parameter regulator provided in an embodiment of this application. The parameter regulator 701 can be an electronic device, a chip, or a circuit, such as a chip or circuit that can be disposed in an electronic device. The parameter regulator 701 can correspond to the parameter regulator in the above-described method to achieve the above-mentioned functionality. Figures 2 to 6 The relevant schemes of parameter regulators in any one or more of the methods shown.

[0133] like Figure 7As shown, the parameter regulator 701 may include a processor 702, a transceiver 703, and a memory 704, and may further include a bus system, with the processor 702, transceiver 703, and memory 704 connected via the bus system. The memory 704 may be an on-chip storage unit, such as a register or cache, or it may be an external storage unit within the parameter regulator 701, such as a read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM). The memory 704 is used to store instructions, and the processor 702 is used to execute the instructions stored in the memory 704 to implement the relevant scheme of the parameter regulator as described in any of the embodiments one to two above. For example, when the parameter adjuster 701 executes Embodiment 1, the transceiver 703 can obtain the processed image obtained by processing the preset image using image processing parameters, and obtain the standard image corresponding to the preset image. The display effect of the standard image is better than that of the processed image. The processor 702 can adaptively adjust the image processing parameters according to the standard image and the processed image so that the adjusted image processing parameters can reduce the image difference between the processed image and the standard image.

[0134] The concepts, explanations, detailed descriptions, and other steps related to the parameter regulator 701 and the technical solutions provided in the embodiments of this application can be found in the descriptions of these contents in the foregoing methods or other embodiments, and will not be repeated here.

[0135] According to the aforementioned method, Figure 8 This is a schematic diagram of a parameter regulator provided in an embodiment of this application. The parameter regulator 801 can be an electronic device, a chip, or a circuit, such as a chip or circuit that can be disposed in an electronic device. The parameter regulator 801 can correspond to the parameter regulator in the above method and is used to implement the above-described functionality. Figures 2 to 6 The steps performed by the parameter regulator in any one or more of the methods shown.

[0136] like Figure 8As shown, the parameter regulator 801 may include an acquisition unit 802 and a processing unit 803. The acquisition unit 802, when acquiring information, may be a receiving unit, receiver, output interface, pin, or radio frequency circuit, etc. In implementation, the acquisition unit 802 and the processing unit 803 may respectively execute computer instructions stored in the storage unit, enabling the parameter regulator 801 to execute the method performed by the parameter regulator in any of the embodiments one to two described above. For example, when executing embodiment one, the acquisition unit 802 may acquire the processed image obtained by processing a preset image using image processing parameters, and acquire the standard image corresponding to the preset image. The display effect of the standard image is better than that of the processed image. The processing unit 803 may adaptively adjust the image processing parameters according to the standard image and the processed image, so that the adjusted image processing parameters can reduce the image difference between the processed image and the standard image.

[0137] For the concepts, explanations, detailed descriptions, and other steps related to the technical solutions provided in the embodiments of this application involving the parameter regulator 801, please refer to the descriptions of these contents in the foregoing methods or other embodiments, which will not be repeated here.

[0138] It should be understood that the division of the units in the parameter regulator 801 above is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated; no specific limitation is made. In this embodiment, the aforementioned acquisition unit 802 can be... Figure 7 The transceiver 703 shown is implemented, and the processing unit 803 can be implemented by... Figure 7 The processor 702 is shown in the diagram.

[0139] According to the method provided in the embodiments of this application, this application also provides a chip, including the aforementioned parameter adjuster, or further including the aforementioned image processor.

[0140] According to the method provided in the embodiments of this application, this application also provides an electronic device, including the aforementioned parameter adjuster, image processor and display screen, wherein the parameter adjuster and image processor are used to implement the image processing function of the electronic device, and the display screen is used to implement the display function of the electronic device.

[0141] According to the method provided in the embodiments of this application, this application also provides a parameter adjustment system, including the aforementioned video source, parameter adjuster, image processor, and display screen. The parameter adjuster, image processor, and display screen can be located in the same electronic device or in different electronic devices; for example, the image processor and display screen can be located in one electronic device, while the parameter adjuster is located in another electronic device.

[0142] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when run on a computer, causes the computer to perform... Figures 2 to 6 The method of any one of the embodiments shown.

[0143] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, 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. The computer-readable 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 media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state drives (SSDs)).

[0144] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A parameter adjustment method, characterized in that, The method includes: Reduce the display quality of standard images; The standard image with reduced display quality is used as the preset image; Obtain the processed image obtained by processing the preset image using image processing parameters; Obtain the standard image corresponding to the preset image, wherein the display effect of the standard image is better than the display effect of the processed image; The image processing parameters are adaptively adjusted based on the standard image and the processed image. The adjusted image processing parameters are used to reduce the image difference between the processed image and the standard image.

2. The method as described in claim 1, characterized in that, The step of adaptively adjusting the image processing parameters based on the standard image and the processed image includes: Determine the degree of difference between the processed image and the standard image under a preset evaluation index; When the difference of the target image does not meet the evaluation conditions corresponding to the preset evaluation index, the image processing parameters related to the preset evaluation index are adjusted.

3. The method as described in claim 2, characterized in that, The evaluation conditions corresponding to the preset evaluation indicators include the following: The adjustment duration should not be less than the preset duration; The number of adjustments should not be less than the preset number; The difference in the target image is within the allowable range of the preset evaluation index; or... The error between the target image difference and the optimal image difference is less than the allowable error threshold.

4. The method as described in claim 2 or 3, characterized in that, The adjustment of image processing parameters related to the preset evaluation index includes: Adjust the image processing parameters related to the preset evaluation index along the first direction with a first adjustment granularity until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the unadjusted image processing parameters. Adjust the image processing parameters related to the preset evaluation index along the second direction with a second adjustment granularity until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the unadjusted image processing parameters. Wherein, the second adjustment granularity is smaller than the first adjustment granularity, and the first direction is increasing while the second direction is decreasing, or the first direction is decreasing while the second direction is increasing.

5. The method as described in claim 2 or 3, characterized in that, The preset evaluation indicators include one or more sub-indicators such as local sharpness, peak signal-to-noise ratio, average energy ratio, or structural similarity.

6. The method as described in claim 5, characterized in that, When the preset evaluation index includes at least two sub-indicators: Determining the difference between the processed image and the standard image under a preset evaluation metric includes: Determine the image difference degree between the processed image and the standard image under at least two sub-indicators; The weighted average of the image differences under the at least two sub-indicators is taken as the target image difference.

7. A parameter adjustment device, characterized in that, include: An image processor is used to process a preset image using image processing parameters to obtain a processed image. A parameter adjuster coupled to the image processor is used to acquire the processed image and a standard image corresponding to the preset image, and adaptively adjust the image processing parameters according to the processed image and the standard image. The standard image displays better than the processed image, and the adjusted image processing parameters are used to reduce the image difference between the processed image and the standard image. The image processor includes an input interface, an image processing unit, and an output interface coupled in sequence; the input interface is also coupled to a video source, which is used to output a standard image; the output interface is also coupled to a display screen, which is used to display an image. The input interface is used to receive the standard image from the video source, reduce the display effect of the standard image to obtain the preset image, and send the preset image to the image processing unit; The image processing unit is used to process the preset image using the image processing parameters to obtain a processed image, and then send the processed image to the output interface. The output interface is used to send the processed image to the display screen.

8. The apparatus as claimed in claim 7, characterized in that, The parameter adjuster includes a coupled adjustment circuit and an evaluation circuit, the adjustment circuit is also coupled to the image processing unit, and the evaluation circuit is also coupled to the input interface and the output interface; The input interface is also used to send the standard image to the evaluation circuit; The output interface is also used to send the processed image to the evaluation circuit; The evaluation circuit is used to: determine the target image difference degree between the processed image and the standard image under a preset evaluation index, and send the target image difference degree to the adjustment circuit. The adjustment circuit is specifically used to: when it is determined that the difference of the target image does not meet the evaluation conditions corresponding to the preset evaluation index, send a parameter adjustment instruction to the image processing unit corresponding to the preset evaluation index. The image processing unit corresponding to the preset evaluation index is used to adjust the image processing parameters according to the parameter adjustment command.

9. The apparatus as claimed in claim 8, characterized in that, The evaluation conditions corresponding to the preset evaluation indicators include the following: The adjustment duration should not be less than the preset duration; The number of adjustments should not be less than the preset number; The difference in the target image is within the allowable range of the preset evaluation index; or... The error between the target image difference and the optimal image difference is less than the allowable error threshold.

10. The apparatus as claimed in claim 8 or 9, characterized in that, The adjustment circuit is specifically used for: By means of the parameter adjustment command, the image processing parameters related to the preset evaluation index are adjusted along the first direction with a first adjustment granularity until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the image processing parameters before adjustment. Then, the image processing parameters related to the preset evaluation index are adjusted along the second direction with a second adjustment granularity until the absolute value of the target image difference corresponding to the adjusted image processing parameters is not less than the absolute value of the target image difference corresponding to the image processing parameters before adjustment. Wherein, the second adjustment granularity is smaller than the first adjustment granularity, and the first direction is increasing while the second direction is decreasing, or the first direction is decreasing while the second direction is increasing.

11. The apparatus as claimed in claim 8 or 9, characterized in that, The preset evaluation indicators include one or more sub-indicators such as local sharpness, peak signal-to-noise ratio, average energy ratio, or structural similarity.

12. The apparatus as claimed in claim 11, characterized in that, When the preset evaluation index includes at least two sub-indicators: The evaluation circuit is specifically used for: Determine the image difference degree between the processed image and the standard image under at least two sub-indicators; The weighted average of the image differences under the at least two sub-indicators is taken as the target image difference.

13. A parameter adjustment system, characterized in that, Includes a video source, a display screen, and a parameter adjustment device as described in any one of claims 7 to 12; The video source is used to output video to the parameter adjustment device; The parameter adjustment device is used to process any frame of the video using image processing parameters and then send it to the display screen. The display screen is used to display the processed video.

14. A chip, characterized in that, It includes a processor and a communication interface, wherein the processor reads instructions through the communication interface and executes the method as described in any one of claims 1 to 6.

15. A computer-readable storage medium, characterized in that, The computer-readable medium stores program code that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 6.

Images