Image quality evaluation method and device, equipment, storage medium and chip
Through edge detection and gradient information, the black and white edge characteristics of the image are determined, which solves the problem of evaluation of black and white edge phenomena during image sharpening, and achieves efficient image quality evaluation.
Patent Information
- Application Number
- CN202410021522.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-05
- Publication Date
- 2025-07-08
AI Technical Summary
The prior art is difficult to effectively evaluate the black and white edge phenomenon introduced during image sharpening, affecting the visual effect of the image.
The black and white edge feature image of the image is determined through edge detection algorithm and gradient information, and edge expansion and gradient parameter update are used to achieve objective evaluation of the black and white edge phenomenon.
The evaluation efficiency of image black and white edge phenomena is improved, and the objective evaluation of image sharpening effect is ensured.
Smart Images
Figure CN120278940A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of image quality evaluation, and particularly to an image quality evaluation method, apparatus, device, storage medium, and chip. Background Art
[0002] Image quality assessment (IQA) is a classic computer vision task, that is, by giving an image, the visual quality of the image is calculated. When the obtained objective quality evaluation result is closer to the human eye evaluation result, the performance of the IQA algorithm is higher. In the early stage, IQA relied on manually designed image feature extractors and scorers. After the rise of machine learning, IQA relied on manually designed feature extractors and learning-based scorers such as SVR. Currently, deep learning has become the mainstream technology in computer vision, and IQA can also automatically learn feature extractors and scorers through neural networks. Summary of the Invention
[0003] The present disclosure provides an image quality evaluation method, apparatus, device, storage medium, and chip to implement the image quality evaluation of black and white edges of an image.
[0004] In a first aspect embodiment of the present disclosure, an image quality evaluation method is proposed. The method includes: using a first algorithm to determine an edge detection image of an input image; using a second algorithm to determine gradient information of the input image; based on the input image, the edge detection image, and the gradient information, determining a black and white edge feature image of the input image; and based on the black and white edge feature image, determining an evaluation result of the black and white edge phenomenon of the input image.
[0005] In some embodiments, based on the input image, the edge detection image, and the gradient information, determining the black and white edge feature image of the input image includes: based on the input image, determining a first intermediate image, and the first black and white edge feature parameter values of multiple first pixel points of the first intermediate image are the same; based on the first intermediate image, the edge detection image, and the gradient information, determining a second intermediate image; dilating the edge detection image with a preset size to obtain an edge dilated image; and based on the input image, the second intermediate image, and the edge dilated image, determining the black and white edge feature image.
[0006] In some embodiments, based on the first intermediate image, the edge detection image, and the gradient information, determining the second intermediate image includes: based on the edge detection image, determining a first edge detection result corresponding to a first pixel point in the first intermediate image; based on the first edge detection result and the gradient information, determining a second gradient parameter; and based on the second gradient parameter, determining the second intermediate image.
[0007] In some embodiments, determining the second gradient parameter based on the first edge detection result and the gradient information includes: when the first edge detection result is non-edge, determining the first black-and-white edge feature parameter as the second gradient parameter; when the first edge detection result is edge, determining the second gradient parameter based on the gradient information and the first black-and-white edge feature parameter.
[0008] In some embodiments, when the first edge detection result is edge, determining the second gradient parameter based on the gradient information and the first black-and-white edge feature parameter includes: determining the gradient mean value in the first neighborhood and the gradient mean value in the second neighborhood of the first pixel point, where the range of the first neighborhood is larger than and includes the range of the second neighborhood; when the gradient mean value in the second neighborhood is greater than the gradient mean value in the first neighborhood, updating the first black-and-white edge feature parameter to determine the updated first black-and-white edge feature parameter as the second gradient parameter; when the gradient mean value in the second neighborhood is less than or equal to the gradient mean value in the first neighborhood, determining the first black-and-white edge feature parameter as the second gradient parameter. In some embodiments, determining the handover target cell from candidate target cells with a second measurement value higher than a fourth preset value includes: determining the candidate target cell with the highest second measurement value as the handover target cell; or randomly determining the handover target cell from candidate target cells with a second measurement value higher than a fourth preset value.
[0009] In some embodiments, determining the black-and-white edge feature image based on the input image, the second intermediate image, and the edge dilation image includes: determining the second edge detection result corresponding to the second pixel point of the second intermediate image based on the edge dilation image; determining the gray value of the second pixel point based on the input image; determining the third gradient parameter of the black-and-white edge feature image based on the second edge detection result and the gray value; determining the black-and-white edge feature image based on the third gradient parameter.
[0010] In some embodiments, determining the third gradient parameter of the black-and-white edge feature image based on the second edge detection result includes: when the second edge detection result is non-edge, determining the second gradient parameter as the third gradient parameter; when the second edge detection result is edge, updating the second gradient parameter of the second pixel point whose gray value satisfies a preset condition to determine the updated second gradient parameter as the third gradient parameter, and determining the second gradient parameter of the second pixel point whose gray value does not satisfy the preset condition as the third gradient parameter.
[0011] In some embodiments, the preset condition is that the gray value is less than a preset black threshold or the gray value is greater than a preset white threshold.
[0012] In some embodiments, determining the black-and-white edge phenomenon evaluation result of the input image based on the black-and-white edge feature image includes: summing the third gradient parameters of the black-and-white edge feature image to determine the black-and-white edge phenomenon evaluation result.
[0013] A second aspect embodiment of the present disclosure provides an image quality evaluation device, which includes: a first processing unit for determining an edge detection image of an input image using a first algorithm; a second processing unit for determining gradient information of the input image using a second algorithm; a third processing unit for determining a black-and-white edge feature image of the input image based on the input image, the edge detection image, and the gradient information; and a fourth processing unit for determining an evaluation result of the black-and-white edge phenomenon of the input image based on the black-and-white edge feature image.
[0014] A third aspect embodiment of the present disclosure provides a communication device, which includes a processor and a memory. Among them, a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device executes the method described in the first aspect above.
[0015] A fourth aspect embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause a computer to execute the method described in the first aspect of the present disclosure.
[0016] A fifth aspect embodiment of the present disclosure provides a chip, which includes at least one processor and a communication interface; the communication interface is used to receive signals input to the chip or signals output from the chip, and the processor communicates with the communication interface and implements the method described in the first aspect of the present disclosure through logic circuits or by executing code instructions.
[0017] In summary, according to the image quality evaluation method proposed by the present disclosure, an edge detection image of an input image is determined using a first algorithm; gradient information of the input image is determined using a second algorithm; a black-and-white edge feature image of the input image is determined based on the input image, the edge detection image, and the gradient information; and an evaluation result of the black-and-white edge phenomenon of the input image is determined based on the black-and-white edge feature image. Thus, an objective evaluation of the black-and-white edge phenomenon of the input image is realized, and the evaluation efficiency of the black-and-white edge phenomenon of the input image is improved.
[0018] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure and do not constitute an improper limitation to the present disclosure.
[0020] Figure 1 It is an application scenario diagram of an image quality evaluation method provided by an embodiment of the present disclosure;
[0021] Figure 2Flow chart of an image quality evaluation method provided by an embodiment of the present disclosure;
[0022] Figure 3 Flow chart of another image quality evaluation method provided by an embodiment of the present disclosure;
[0023] Figure 4 Flow chart of another image quality evaluation method provided by an embodiment of the present disclosure;
[0024] Figure 5 Flow chart of yet another image quality evaluation method provided by an embodiment of the present disclosure;
[0025] Figure 6 Structural schematic diagram of an image quality evaluation device provided by an embodiment of the present disclosure;
[0026] Figure 7 Structural schematic diagram of a communication device provided by an embodiment of the present disclosure;
[0027] Figure 8 Structural schematic diagram of a chip provided by an embodiment of the present disclosure. Detailed implementation manners
[0028] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the embodiments of the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present disclosure as detailed in the appended claims.
[0029] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present disclosure. The singular forms "a" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.
[0030] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the embodiments of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "when" as used herein may be interpreted as "when" or "while" or "in response to determining".
[0031] For ease of understanding, the background and application scenarios related to this application are described.
[0032] During the process of image signal processing (ISP) of a mobile phone camera, the edge enhancement (EE) module sharpens the image to improve the visual effect of the image. However, excessive sharpening will exacerbate the black and white edge phenomenon of the image, affecting the visual effect of the image. For example Figure 1 As shown, where the left side is the original image and the right side is the sharpened image. Obviously, the sharpened image on the right has more black and white edges and its visual effect is poor. Therefore, a solution that can objectively evaluate the black and white edge effect of the image is needed to determine the sharpening effect of the image.
[0033] It can be understood that the description of the embodiments of the present disclosure is to more clearly illustrate the technical solutions of the embodiments of the present disclosure, and does not constitute a limitation on the image quality evaluation methods, devices, and storage media proposed by the embodiments of the present disclosure. Those of ordinary skill in the art know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions proposed by the embodiments of the present disclosure are equally applicable to similar technical problems.
[0034] Figure 2 This is a flowchart of an image quality evaluation method provided by an embodiment of the present disclosure. As Figure 2 shown, the image quality evaluation method includes steps 201-204.
[0035] Step 201, using a first algorithm, determine the edge detection image of the input image.
[0036] In some embodiments, by using a first algorithm to determine the edge detection image of the input image, it lays a foundation for determining the black and white edge feature image of the input image.
[0037] In some embodiments, by using a first algorithm, determine the edge detection results of each pixel point of the input image (that is, determine whether each pixel point of the input image is on the image edge), thereby generating an edge detection image. In other words, the edge detection image is an image composed of the edge detection results of each pixel point of the input image.
[0038] In some embodiments, the first algorithm may be an edge detection algorithm, such as algorithms that can determine whether a pixel point is located on the edge of a graph, such as the Canny algorithm, the Laplacian algorithm, etc. The present disclosure does not limit the first algorithm.
[0039] In some embodiments, the input image is an RGB format image. For an input image that is not in the RGB format, the format of the input image can be converted to the RGB format by methods such as format conversion.
[0040] Step 202: Use a second algorithm to determine the gradient information of the input image.
[0041] In some embodiments, by using a second algorithm to determine the gradient information of the input image, a basis is laid for determining the black-and-white edge feature image of the input image.
[0042] In some embodiments, the second algorithm can be an image gradient algorithm. For example, algorithms such as the Dsobel algorithm and the Robinson algorithm that can determine the gradient information of pixel positions are applicable. The present disclosure does not limit the second algorithm.
[0043] Step 203: Based on the input image, the edge detection image, and the gradient information, determine the black-and-white edge feature image of the input image.
[0044] In some embodiments, a first intermediate image can be determined based on the input image, where the first black-and-white edge feature parameter values of multiple first pixel points of the first intermediate image are the same. Then, the first black-and-white edge feature parameter is updated to a third black-and-white edge feature parameter through the input image, the edge detection image, and the gradient information, so as to determine the black-and-white edge feature image of the input image through the third black-and-white edge feature parameter.
[0045] Step 204: Based on the black-and-white edge feature image, determine the black-and-white edge quality evaluation result of the input image.
[0046] In some embodiments, the black-and-white edge quality evaluation result of the input image can be determined by summing the third black-and-white edge feature parameters of the black-and-white edge feature image. For example, the greater the sum of the third black-and-white edge feature parameters, the more obvious the black-and-white edge phenomenon of the input image.
[0047] In summary, the image quality evaluation method proposed according to the present disclosure includes: using a first algorithm to determine the edge detection image of the input image; using a second algorithm to determine the gradient information of the input image; based on the input image, the edge detection image, and the gradient information, determine the black-and-white edge feature image of the input image; based on the black-and-white edge feature image, determine the black-and-white edge phenomenon evaluation result of the input image. The method of the present disclosure realizes an objective evaluation of the black-and-white edge phenomenon of the input image through the edge information and gradient information of the input image by determining the black-and-white edge feature image of the input image, and improves the evaluation efficiency of the black-and-white edge phenomenon of the input image.
[0048] Figure 3 The flowchart of an image quality evaluation method proposed for an embodiment of the present disclosure is as Figure 3 shown inFigure 2 Based on the illustrated embodiments, step 203 is further explained, including steps 301-304.
[0049] Step 301: Based on the input image, determine a first intermediate image.
[0050] In some embodiments, the first intermediate image can be determined by assigning first black-and-white edge feature parameters to the pixel points of the input image. In other words, the first intermediate image can be an image composed of the first black-and-white edge feature parameters and their corresponding first pixel points.
[0051] In some embodiments, the values of the first black-and-white edge feature parameters of multiple first pixel points of the first intermediate image are the same. For example, the values of the first feature parameters can all be 0 or all be 1. The present disclosure does not limit the specific values of the first black-and-white edge feature parameters.
[0052] In some embodiments, the size of the first intermediate image is the same as or different from the size of the input image. When it is necessary to evaluate the black-and-white edge quality of the entire input image, the size of the first intermediate image is the same as the size of the input image; when only evaluating the black-and-white edge quality of a partial area of the input image, the size of the first intermediate image can only be the same as the size of the area of the input image that needs to be evaluated.
[0053] Step 302: Based on the first intermediate image, the edge detection image, and the gradient information, determine a second intermediate image.
[0054] In some embodiments, the first black-and-white edge feature parameters of the first intermediate image can be updated to second black-and-white edge feature parameters through the edge detection image and the gradient information, so as to determine the second intermediate image through the second black-and-white edge feature parameters. In other words, the second intermediate image can be an image composed of the second black-and-white edge feature parameters and their corresponding second pixel points.
[0055] Step 303: Dilate the edge detection image with a preset size to obtain an edge-dilated image.
[0056] In some embodiments, by dilating the edge detection image, the edge area in the edge detection image is expanded, thereby reducing the situation where pixel points in the non-edge area of the edge detection image are actually in the edge area, which helps to improve the accuracy of the black-and-white edge quality evaluation result.
[0057] In some embodiments, the preset size is not limited, for example, it is the size of a 3*3 pixel area, the size of a 5*5 pixel area.
[0058] Exemplarily, the edge detection image is dilated with a region size of 3×3 pixels, that is, the edge detection image is divided into regions of 3×3 pixels. If the edge detection result of at least one pixel in a 3×3 pixel region is at the image edge, the edge detection results of all pixels in the 3×3 pixel region are determined to be at the image edge, so as to realize the dilation of the edge detection image. It should be understood that the divided 3×3 pixel regions do not overlap with each other.
[0059] Step 304: Determine a black-and-white edge feature image based on the input image, the second intermediate image, and the edge dilation image.
[0060] In some embodiments, based on the input image and the edge detection image, the second black-and-white edge feature parameter of the second intermediate image is updated to a third black-and-white edge feature parameter, so as to determine the black-and-white edge feature image through the third black-and-white edge feature parameter. In other words, the black-and-white edge feature image may be an image composed of the third black-and-white edge feature parameter and its corresponding third pixel points.
[0061] In summary, the image quality evaluation method proposed according to the present disclosure includes: determining a first intermediate image based on the input image, where the first black-and-white edge feature parameter values of multiple first pixel points of the first intermediate image are the same; determining a second intermediate image based on the first intermediate image, the edge detection image, and the gradient information; dilating the edge detection image with a preset size to obtain an edge dilation image; and determining a black-and-white edge feature image based on the input image, the second intermediate image, and the edge dilation image. Thus, by using the edge detection information and gradient information of the input image to determine the black-and-white edge feature information of the input image, and then determining the black-and-white edge feature image of the input image, it lays a foundation for determining the black-and-white edge quality evaluation result of the input image.
[0062] Figure 4 It is a flowchart of an image quality evaluation method proposed in an embodiment of the present disclosure. As Figure 4 shown, on the basis of the embodiment shown in Figure 3 the step 302 is further explained, including steps 401-403.
[0063] Step 401: Determine the first edge detection result corresponding to the first pixel point in the first intermediate image based on the edge detection image.
[0064] In some embodiments, if the first pixel point of the first intermediate image corresponds to the pixel point of the edge detection image, the first edge detection result corresponding to the first pixel point in the first intermediate image may be determined based on the edge detection results of the pixel points in the edge detection image.
[0065] In some embodiments, the detection result of a pixel point in the edge detection image can be determined as the first edge detection result of the corresponding first pixel point in the first intermediate image. For example: the edge detection result of pixel point #1 in the edge detection image is in a non-edge area, and pixel point #1 corresponds to the first pixel point #1-1 in the first intermediate image, then the first edge detection result of the first pixel point #1-1 is in a non-edge area.
[0066] Step 402: Determine the second black-and-white edge feature parameter based on the first edge detection result and the gradient information.
[0067] In some embodiments, when the first edge detection result of the first pixel point is non-edge, the first black-and-white edge feature parameter of the first pixel point can be determined as the second black-and-white edge feature parameter of the first pixel point. For example: the first black-and-white edge feature parameter of the first pixel point #1-1 is 1, and the first edge detection result of the first pixel point #1-1 is in a non-edge area, then it can be determined that the second black-and-white edge feature parameter of the first pixel point #1-1 is 1.
[0068] In some embodiments, when the first edge detection result of the first pixel point is edge, determine the second black-and-white edge feature parameter based on the gradient information and the first black-and-white edge feature parameter.
[0069] Furthermore, the second black-and-white edge feature parameter of the first pixel point can be determined by determining the gradient mean value in the first neighborhood and the gradient mean value in the second neighborhood of the first pixel point, where the range of the first neighborhood is larger than and includes the range of the second neighborhood.
[0070] Furthermore, when the gradient mean value in the second neighborhood of the first pixel point is greater than the gradient mean value in the first neighborhood of the first pixel point, update the first black-and-white edge feature parameter of the first pixel point, and determine the updated first black-and-white edge feature parameter as the second black-and-white edge feature parameter. Taking the range of the first neighborhood as the area range of 5*5 pixel points centered on the first pixel point and the range of the second neighborhood as the area range of 3*3 pixel points centered on one pixel point as an example, the gradient mean value of the first pixel point in the 3*3 pixel point area range is greater than the gradient mean value in the 5*5 pixel point area range, update the first black-and-white edge feature parameter of the first pixel point, and determine the updated first black-and-white edge feature parameter as the second black-and-white edge feature parameter, where the update method is, for example, adding one to the value of the first black-and-white edge feature parameter of the first pixel point, but not limited thereto, and the present disclosure does not limit the specific method adopted for the update.
[0071] Furthermore, when the gradient mean value in the second neighborhood of the first pixel point is less than or equal to the gradient mean value in the first neighborhood of the first pixel point, determine the first black-and-white edge feature parameter of the first pixel point as the second black-and-white edge feature parameter.
[0072] Step 403: Determine a second intermediate image based on the second black-and-white edge feature parameter.
[0073] In some embodiments, a second intermediate image may be determined based on the second black-and-white edge feature parameter. In other words, the second intermediate image may be an image composed of the second black-and-white edge feature parameter and its corresponding second pixel points.
[0074] In summary, the image quality evaluation method proposed according to the present disclosure includes: determining a first edge detection result corresponding to a first pixel point in a first intermediate image based on an edge detection image; determining a second black-and-white edge feature parameter based on the first edge detection result and gradient information; and determining a second intermediate image based on the second black-and-white edge feature parameter. Thus, the first black-and-white edge feature image is updated through the edge detection result and gradient information, and then the second black-and-white edge feature parameter is determined, laying a foundation for determining the black-and-white edge feature image.
[0075] Figure 5 The flowchart of an image quality evaluation method proposed in an embodiment of the present disclosure is as Figure 5 shown. Based on the embodiment shown in Figure 3 Step 304 is further explained, including Steps 501-504.
[0076] Step 501: Determine a second edge detection result corresponding to a second pixel point of the second intermediate image based on an edge dilation image.
[0077] In some embodiments, if the pixel points in the edge dilation image correspond to the second pixel points of the second intermediate image, the edge detection result of the pixel points in the edge dilation image may be determined as the second edge detection result of the corresponding second pixel points. For example, if pixel point #2 in the edge dilation image corresponds to second pixel point #2-1 in the second intermediate image, and the edge detection result of pixel point #2 is in the edge region, it may be determined that the second edge detection result of second pixel point #2-1 is in the edge region.
[0078] Step 502: Determine the gray value of the second pixel point based on the input image.
[0079] In some embodiments, the gray values of the pixel points in the input image may be determined, and then the gray values of the pixel points in the input image may be determined as the gray values of the corresponding second pixel points. For example, if pixel point #1 in the input image corresponds to second pixel point #3-1 in the second intermediate image, the gray value of pixel point #1 may be determined as the gray value of second pixel point #3-1. It should be understood that the present disclosure does not limit the specific method for determining the gray value of the input image.
[0080] Step 503: Determine the third black-and-white edge feature parameter of the black-and-white edge feature image based on the second edge detection result and the grayscale value.
[0081] In some embodiments, when the second edge detection result is a non-edge, the second black-and-white edge feature parameter can be determined as the third black-and-white edge feature parameter.
[0082] In some embodiments, when the second edge detection result is an edge, update the second black-and-white edge feature parameter of the second pixel points whose grayscale values meet the preset conditions, so as to determine the updated second black-and-white edge feature parameter as the third black-and-white edge feature parameter, and determine the second black-and-white edge feature parameter of the second pixel points whose grayscale values do not meet the preset conditions as the third black-and-white edge feature parameter.
[0083] In some embodiments, the preset condition is that the grayscale value is less than the preset black threshold or the grayscale value is greater than the preset white threshold.
[0084] Exemplarily, if the second edge detection result of the second pixel point #3-1 is an edge and the grayscale value of the second pixel point #3-1 is less than the black threshold in the preset condition, the second black-and-white edge feature parameter of the second pixel point #3-1 can be determined as the third black-and-white edge feature parameter of this second pixel point #3-1.
[0085] Exemplarily, if the second edge detection result of the second pixel point #3-2 is an edge and the grayscale value of the second pixel point #3-1 is greater than the white threshold in the preset condition, the second black-and-white edge feature parameter of the second pixel point #3-2 can be updated so as to determine the updated second black-and-white edge feature parameter as the third black-and-white edge feature parameter, where the update method is, for example, adding one to the value of the second black-and-white edge feature parameter of this second pixel point, but is not limited thereto, and the present disclosure does not limit the specific method adopted for the update.
[0086] Step 504: Determine the black-and-white edge feature image based on the third black-and-white edge feature parameter.
[0087] In some embodiments, the black-and-white edge feature image can be an image composed of the third black-and-white edge feature parameter and its corresponding third pixel points.
[0088] In summary, the image quality evaluation method proposed according to the present disclosure includes: determining a second edge detection result corresponding to a second pixel point of a second intermediate image based on an edge dilated image; determining a gray value of the second pixel point based on an input image; determining a third black-and-white edge feature parameter of a black-and-white edge feature image based on the second edge detection result and the gray value; and determining the black-and-white edge feature image based on the third black-and-white edge feature parameter. Thus, by using the edge detection information and the gray information of the second pixel point of the second intermediate image, the third black-and-white edge feature parameter is determined, and then the determination of the black-and-white edge feature image is realized, laying a foundation for determining the black-and-white edge quality evaluation result of the input image.
[0089] Therefore, the present solution has the following beneficial effects:
[0090] 1. By determining the black-and-white edge feature image of the input image, an objective evaluation of the black-and-white edge phenomenon of the input image is realized through the edge information and gradient information of the input image, improving the evaluation efficiency of the black-and-white edge phenomenon of the input image.
[0091] Figure 6 FIG. 600 is a schematic structural diagram of an image quality evaluation device provided in an embodiment of the present disclosure. The communication device includes:
[0092] A first processing unit 610, configured to determine an edge detection image of an input image by using a first algorithm;
[0093] A second processing unit 620, configured to determine gradient information of the input image by using a second algorithm;
[0094] A third processing unit 630, configured to determine a black-and-white edge feature image of the input image based on the input image, the edge detection image, and the gradient information;
[0095] A fourth processing unit 640, configured to determine a black-and-white edge quality evaluation result of the input image based on the black edge feature image.
[0096] In some embodiments, the third processing unit 630 is further configured to determine a first intermediate image based on the input image, where the first black-and-white edge feature parameter values of multiple first pixel points of the first intermediate image are the same; determine a second intermediate image based on the first intermediate image, the edge detection image, and the gradient information; dilate the edge detection image with a preset size to obtain an edge dilated image; and determine the black-and-white edge feature image based on the input image, the second intermediate image, and the edge dilated image.
[0097] In some embodiments, the third processing unit 630 is further configured to determine a first edge detection result corresponding to a first pixel point in the first intermediate image based on the edge detection image; determine a second black-and-white edge feature parameter based on the first edge detection result and the gradient information; and determine the second intermediate image based on the second black-and-white edge feature parameter.
[0098] In some embodiments, when the first edge detection result is non-edge, the first black-and-white edge feature parameter is determined as the second black-and-white edge feature parameter; when the first edge detection result is edge, the second black-and-white edge feature parameter is determined based on the gradient information and the first black-and-white edge feature parameter.
[0099] In some embodiments, the third processing unit 630 is further configured to determine the gradient mean value in the first neighborhood and the gradient mean value in the second neighborhood of the first pixel point, and the range of the first neighborhood is larger than and includes the range of the second neighborhood.
[0100] In some embodiments, when the gradient mean value in the second neighborhood is greater than the gradient mean value in the first neighborhood, the first black-and-white edge feature parameter is updated, and the updated first black-and-white edge feature parameter is determined as the second black-and-white edge feature parameter; when the gradient mean value in the second neighborhood is less than or equal to the gradient mean value in the first neighborhood, the first black-and-white edge feature parameter is determined as the second black-and-white edge feature parameter.
[0101] In some embodiments, the third processing unit 630 is further configured to determine the second edge detection result corresponding to the second pixel point of the second intermediate image based on the edge dilation image; determine the gray value of the second pixel point based on the input image; determine the third black-and-white edge feature parameter of the black-and-white edge feature image based on the second edge detection result and the gray value; and determine the black-and-white edge feature image based on the third black-and-white edge feature parameter.
[0102] In some embodiments, when the second edge detection result is non-edge, the second black-and-white edge feature parameter is determined as the third black-and-white edge feature parameter; when the second edge detection result is edge, the second black-and-white edge feature parameter of the second pixel point whose gray value satisfies the preset condition is updated, and the updated second black-and-white edge feature parameter is determined as the third black-and-white edge feature parameter, and the second black-and-white edge feature parameter of the second pixel point whose gray value does not satisfy the preset condition is determined as the third black-and-white edge feature parameter.
[0103] In some embodiments, the preset condition is that the gray value is less than the preset black threshold or the gray value is greater than the preset white threshold.
[0104] In some embodiments, the third black-and-white edge feature parameters of the black edge feature image are summed to determine the black-and-white edge quality evaluation result.
[0105] In summary, the image quality evaluation device provided according to the present disclosure includes: a first processing unit that determines an edge detection image of an input image using a first algorithm; a second processing unit that determines gradient information of the input image using a second algorithm; a third processing unit that determines a black-and-white edge feature image of the input image based on the input image, the edge detection image, and the gradient information; and a fourth processing unit that determines an evaluation result of the black-and-white edge phenomenon of the input image based on the black-and-white edge feature image. The device of the present disclosure realizes an objective evaluation of the black-and-white edge phenomenon of the input image through the edge information and gradient information of the input image by determining the black-and-white edge feature image of the input image, thereby improving the evaluation efficiency of the black-and-white edge phenomenon of the input image.
[0106] Since the device provided in the embodiments of the present disclosure corresponds to the methods provided in the above several embodiments, the implementation manners of the methods are also applicable to the device provided in this embodiment and will not be described in detail in this embodiment.
[0107] In the above embodiments provided in the present application, the methods and devices provided in the embodiments of the present application are introduced. To implement each function in the methods provided in the embodiments of the present application, a communication device may include a hardware structure, software modules, and implement the above functions in the form of a hardware structure, software modules, or a combination of a hardware structure and software modules. A certain function among the above functions may be executed in the form of a hardware structure, software module, or a combination of a hardware structure and software module.
[0108] Figure 7 It is a schematic structural diagram of a communication device 700 provided in an embodiment of the present application. The communication device 700 may be a network device, a terminal device, a chip, a chip system, or a processor that supports the network device to implement the above method, or a chip, a chip system, or a processor that supports the terminal device to implement the above method. This device can be used to implement the method described in the above method embodiments, and specific reference can be made to the description in the above method embodiments.
[0109] The communication device 700 may include one or more processors 701. The processor 701 may be a general-purpose processor or a dedicated processor, etc. For example, it may be a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control a communication device (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU, or a CU, etc.), execute a computer program, and process data of the computer program.
[0110] Optionally, the communication device 700 may further include one or more memories 702, on which a computer program 704 may be stored, and the processor 701 executes the computer program 704 so that the communication device 700 performs the method described in the above method embodiment. Optionally, data may also be stored in the memory 702. The communication device 700 and the memory 702 may be provided separately or integrated together.
[0111] Optionally, the communication device 700 may further include a transceiver 705 and an antenna 706. The transceiver 705 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, etc., and is used to implement a transceiver function. The transceiver 705 may include a receiver and a transmitter, the receiver may be referred to as a receiver or a receiving circuit, etc., and is used to implement a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., and is used to implement a transmitting function.
[0112] Optionally, the communication device 700 may further include one or more interface circuits 707. The interface circuit 707 is used to receive code instructions and transmit them to the processor 701. The processor 701 executes the code instructions to enable the communication device 700 to execute the method described in the above method embodiment.
[0113] In one implementation, the processor 701 may include a transceiver for implementing the receiving and sending functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing the receiving and sending functions may be separate or integrated. The above-mentioned transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or the above-mentioned transceiver circuit, interface, or interface circuit may be used for transmitting or delivering signals.
[0114] In one implementation, the processor 701 may store a computer program 703, which runs on the processor 701 and enables the communication device 700 to perform the method described in the above method embodiment. The computer program 703 may be fixed in the processor 701, in which case the processor 701 may be implemented by hardware.
[0115] In one implementation, the communication device 700 may include circuitry that can implement the functions of transmitting, receiving, or communicating in the foregoing method embodiments. The processor and transceiver described in this application can be implemented on an integrated circuit (IC), analog IC, radio frequency integrated circuit (RFIC), mixed-signal IC, application specific integrated circuit (ASIC), printed circuit board (PCB), electronic device, etc. The processor and transceiver can also be fabricated using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (NMOS), P-type metal oxide semiconductor (PMOS), bipolar junction transistor (BJT), BiCMOS, silicon germanium (SiGe), gallium arsenide (GaAs), etc.
[0116] The communication device described in the above embodiments can be a network device or a terminal device, but the scope of the communication device described in this application is not limited thereto, and the structure of the communication device can be unrestricted by Figure 7 ... The communication device can be an independent device or can be part of a larger device. For example, the communication device can be:
[0117] (1) An independent integrated circuit (IC), or chip, or chip system or subsystem;
[0118] (2) A collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and computer programs;
[0119] (3) An ASIC, such as a modem;
[0120] (4) A module that can be embedded in other devices;
[0121] (5) A receiver, terminal device, smart terminal device, cellular phone, wireless device, handset, mobile unit, vehicle-mounted device, network device, cloud device, artificial intelligence device, etc.;
[0122] (6) Others, etc.
[0123] For the case where the communication device can be a chip or a chip system, reference can be made toFigure 8 Schematic structural diagram of the chip shown
[0124] An embodiment of the present disclosure also provides a chip, such as Figure 8 The chip shown includes at least one processor 801 and a communication interface 802. Among them, the communication interface 802 is used to receive signals input to the chip or signals output from the chip, and the processor 801 communicates with the communication interface 802 and implements the method described in the above embodiments of the present disclosure through logic circuits or by executing code instructions.
[0125] Optionally, the chip further includes a memory 803, and the memory 803 is used to store necessary computer programs and data.
[0126] An embodiment of the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method described in the above embodiments of the present disclosure.
[0127] Those skilled in the art can also understand that the various illustrative logical blocks and steps listed in the embodiments of the present application can be implemented by electronic hardware, computer software, or a combination of both. Whether such a function is implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art can use various methods to implement the functions for each specific application, but such implementation should not be construed as exceeding the scope protected by the embodiments of the present application.
[0128] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of the present disclosure are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0129] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0130] Any process or method description shown in a flowchart or described otherwise herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where functions may be executed in a manner not shown or discussed, including substantially concurrently according to the functions involved or in a reverse order, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.
[0131] The logic and / or steps represented in a flowchart or described otherwise herein, for example, may be considered as a sequenced list of executable instructions for implementing a logical function and may be specifically implemented in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processing module, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of the computer-readable medium include the following: an electrical connection with one or more wirings (control method), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable media on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.
[0132] It should be understood that each part of the embodiments of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
[0133] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.
[0134] In addition, each functional unit in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk, an optical disk, etc.
[0135] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.
Claims
1. An image quality evaluation method, characterized in that, The method includes: Using a first algorithm to determine an edge detection image of the input image; Using a second algorithm to determine the gradient information of the input image; Based on the input image, the edge detection image, and the gradient information, determining a black-and-white edge feature image of the input image; Based on the black-and-white edge feature image, determining an evaluation result of the black-and-white edge phenomenon of the input image.
2. The method according to claim 1, wherein The determining the black-and-white edge feature image of the input image based on the input image, the edge detection image, and the gradient information includes: Based on the input image, determining a first intermediate image, where the first black-and-white edge feature parameter values of multiple first pixel points of the first intermediate image are the same; Based on the first intermediate image, the edge detection image, and the gradient information, determining a second intermediate image; Dilating the edge detection image with a preset size to obtain an edge dilated image; Based on the input image, the second intermediate image, and the edge dilated image, determining the black-and-white edge feature image.
3. The method according to claim 2, wherein The determining the second intermediate image based on the first intermediate image, the edge detection image, and the gradient information includes: Based on the edge detection image, determining a first edge detection result corresponding to a first pixel point in the first intermediate image; Based on the first edge detection result and the gradient information, determining a second gradient parameter; Based on the second gradient parameter, determining the second intermediate image.
4. The method according to claim 3, wherein The determining the second gradient parameter based on the first edge detection result and the gradient information includes: When the first edge detection result is non-edge, determining the first black-and-white edge feature parameter as the second gradient parameter; When the first edge detection result is edge, based on the gradient information and the first black-and-white edge feature parameter, determining the second gradient parameter.
5. The method according to claim 4, characterized in that, The when the first edge detection result is edge, based on the gradient information and the first black-and-white edge feature parameter, determining the second gradient parameter includes: Determining the gradient mean value in a first neighborhood and the gradient mean value in a second neighborhood of the first pixel point, where the range of the first neighborhood is larger than and includes the range of the second neighborhood; When the gradient mean value in the second neighborhood is greater than the gradient mean value in the first neighborhood, updating the first black-and-white edge feature parameter to determine the updated first black-and-white edge feature parameter as the second gradient parameter; When the gradient mean value in the second neighborhood is less than or equal to the gradient mean value in the first neighborhood, determining the first black-and-white edge feature parameter as the second gradient parameter.
6. The method according to claim 2, wherein The determining the black-and-white edge feature image based on the input image, the second intermediate image, and the edge dilated image includes: Based on the edge dilated image, determining a second edge detection result corresponding to a second pixel point in the second intermediate image; Based on the input image, determining the gray value of the second pixel point; Based on the second edge detection result and the gray value, determining a third gradient parameter of the black-and-white edge feature image; Based on the third gradient parameter, determining the black-and-white edge feature image.
7. The method according to claim 6, characterized in that, Determining the third gradient parameter of the black-and-white edge feature image based on the second edge detection result includes: When the second edge detection result is non-edge, determining the second gradient parameter as the third gradient parameter; When the second edge detection result is edge, updating the second gradient parameter of the second pixel points whose gray values satisfy a preset condition, so as to determine the updated second gradient parameter as the third gradient parameter, and determining the second gradient parameter of the second pixel points whose gray values do not satisfy the preset condition as the third gradient parameter.
8. The method according to claim 7, wherein The preset condition is that the gray value is less than a preset black threshold or the gray value is greater than a preset white threshold.
9. The method according to claim 1, characterized in that, Determining the black-and-white edge phenomenon evaluation result of the input image based on the black-and-white edge feature image includes: Summing the third gradient parameters of the black-and-white edge feature image to determine the black-and-white edge phenomenon evaluation result.
10. An image quality evaluation device, characterized in that, Including: A first processing unit, configured to use a first algorithm to determine an edge detection image of an input image; A second processing unit, configured to use a second algorithm to determine the gradient information of the input image; A third processing unit, configured to determine a black-and-white edge feature image of the input image based on the input image, the edge detection image, and the gradient information; A fourth processing unit, configured to determine the black-and-white edge phenomenon evaluation result of the input image based on the black-and-white edge feature image.
11. A communication device, characterized in that, The device includes a processor and a memory. Among them, a computer program is stored in the memory, and the processor executes the computer program stored in the memory, so that the device executes: the method described in claims 1-9.
12. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instruction is used to make the computer execute the method described in claims 1-9.
13. A chip, characterized in that, Including at least one processor and a communication interface; the communication interface is used to receive a signal input to the chip or a signal output from the chip, and the processor communicates with the communication interface and implements the method described in claims 1-9 through a logic circuit or by executing code instructions.