Image quality evaluation method and device, electronic equipment and medium

Abstract

The invention relates to an image quality evaluation method and device, electronic equipment and a medium, and the method comprises the steps: obtaining a to-be-processed image; performing feature extraction processing on the image to obtain original image features and low-frequency image features in the image; according to the original image features and low-frequency image features, determining a quality evaluation result of the image, the low-frequency image features being related features of semantic content in the image; according to the original image features and the low-frequency image features, related features of noise in the image can be determined, interference of semantic content in image quality evaluation is avoided, the accuracy of a quality evaluation result obtained through evaluation is ensured, and the accuracy of image quality evaluation is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technologies, and in particular, to an image quality evaluation method, apparatus, electronic device, and medium. Background Art

[0002] Currently, for image quality evaluation methods, for example, a face image is input into a feature extraction network to obtain feature data; the feature data is input into a fully connected layer for processing to obtain the face quality score of the face image.

[0003] In the above solution, the face image includes noise and semantic content, resulting in the face quality score being determined by combining the noise and semantic content, making it difficult to accurately reflect the noise situation in the face image, resulting in poor accuracy of the evaluated face quality score and poor accuracy of image quality evaluation. Summary of the Invention

[0004] The present disclosure provides an image quality evaluation method, apparatus, electronic device, and medium.

[0005] According to a first aspect of an embodiment of the present disclosure, an image quality evaluation method is provided. The method includes: obtaining an image to be processed; performing feature extraction processing on the image to obtain the original image features and low-frequency image features in the image; and determining the quality evaluation result of the image according to the original image features and the low-frequency image features.

[0006] In an embodiment of the present disclosure, the original image features include original image sub-features at multiple scales; the low-frequency image features include low-frequency image sub-features at the multiple scales.

[0007] In an embodiment of the present disclosure, the image feature extraction network for extracting the original image features includes image feature sub-extraction networks at multiple scales; the image feature sub-extraction network includes a first convolutional layer, a ReLU activation network, a second convolutional layer, and an L2 pooling layer connected in sequence.

[0008] In an embodiment of the present disclosure, performing feature extraction processing on the image to obtain the low-frequency image features in the image includes: performing at least one of max-pooling feature extraction processing, average-pooling feature extraction processing, image content feature extraction processing, and perceptual content feature extraction processing on the image to obtain at least one intermediate low-frequency image feature; the intermediate low-frequency image feature includes intermediate low-frequency image sub-features at the multiple scales; and performing fusion processing on the intermediate low-frequency image sub-features at the multiple scales in at least one intermediate low-frequency image feature to obtain the low-frequency image features.

[0009] In one embodiment of the present disclosure, the low-frequency feature extraction network for extracting the low-frequency image features includes a feature fusion network, a max-pooling feature extraction network, an average-pooling feature extraction network, an image content feature extraction network, and a perceptual content feature extraction network that are respectively connected to the feature extraction network; the perceptual content feature extraction network is the deep convolutional neural network VGG-19.

[0010] In one embodiment of the present disclosure, determining the quality assessment result of the image according to the original image features and the low-frequency image features includes: for each scale in the multiple scales, determining the mean square error between the original image sub-features and the low-frequency image sub-features at the scale; according to the weights of each scale in the multiple scales, performing weighted summation processing on the mean square error at each scale to obtain a quality score; using the quality score as the quality assessment result of the image.

[0011] In one embodiment of the present disclosure, the weights of each scale in the multiple scales and the feature extraction network for performing feature extraction processing on the image are trained according to multiple sample noise images and the sample quality scores of the sample noise images.

[0012] In one embodiment of the present disclosure, the quality assessment result is a quality score; the quality score indicates the noise situation in the image; the processing scenario to which the image belongs includes at least one of the following: an image shooting scenario, an image sorting and recommendation scenario, and an image generation scenario; the quality score is used to guide the processing algorithm or processing parameters in the processing scenario.

[0013] According to the second aspect of the embodiments of the present disclosure, there is also provided an image quality assessment device, including: an acquisition module for acquiring an image to be processed; a feature extraction module for performing feature extraction processing on the image to obtain the original image features and the low-frequency image features in the image; a determination module for determining the quality assessment result of the image according to the original image features and the low-frequency image features.

[0014] In one embodiment of the present disclosure, the original image features include original image sub-features at multiple scales; the low-frequency image features include low-frequency image sub-features at the multiple scales.

[0015] In one embodiment of the present disclosure, the image feature extraction network for extracting the original image features includes image feature sub-extraction networks at multiple scales; the image feature sub-extraction network includes a first convolutional layer, a ReLU activation network, a second convolutional layer, and an L2 pooling layer connected in sequence.

[0016] In one embodiment of the present disclosure, the feature extraction module is specifically configured to perform at least one of maximum pooling feature extraction processing, average pooling feature extraction processing, image content feature extraction processing, and perceptual content feature extraction processing on the image to obtain at least one intermediate low-frequency image feature; the intermediate low-frequency image feature includes intermediate low-frequency image sub-features at multiple scales; and perform a fusion process on the intermediate low-frequency image sub-features at multiple scales in at least one intermediate low-frequency image feature to obtain the low-frequency image feature.

[0017] In one embodiment of the present disclosure, the low-frequency feature extraction network for extracting the low-frequency image feature includes a feature fusion network, and a maximum pooling feature extraction network, an average pooling feature extraction network, an image content feature extraction network, and a perceptual content feature extraction network respectively connected to the feature extraction network; the perceptual content feature extraction network is the deep convolutional neural network VGG-19.

[0018] In one embodiment of the present disclosure, the determination module is specifically configured to, for each scale in the multiple scales, determine the mean square error between the original image sub-feature and the low-frequency image sub-feature at the scale; perform a weighted summation process on the mean square errors at each scale according to the weights of each scale in the multiple scales to obtain a quality score; and use the quality score as the quality assessment result of the image.

[0019] In one embodiment of the present disclosure, the weights of each scale in the multiple scales and the feature extraction network for performing feature extraction processing on the image are trained according to multiple sample noise images and the sample quality scores of the sample noise images.

[0020] In one embodiment of the present disclosure, the quality assessment result is a quality score; the quality score indicates the noise situation in the image; the processing scenario to which the image belongs includes at least one of the following: an image shooting scenario, an image sorting and recommendation scenario, and an image generation scenario; and the quality score is used to guide the processing algorithm or processing parameters in the processing scenario.

[0021] According to a third aspect of the embodiments of the present disclosure, there is also provided an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to: implement the steps of the image quality assessment method as described above.

[0022] According to a fourth aspect of the embodiments of the present disclosure, there is also provided a non-transitory computer-readable storage medium, which when the instructions in the storage medium are executed by the processor, enables the processor to execute the image quality assessment method as described above.

[0023] According to a fifth aspect of the embodiments of the present disclosure, there is also provided a chip, including one or more interface circuits and one or more processors; the interface circuit is configured to receive a signal from a memory of an electronic device and send the signal to the processor, the signal including computer instructions stored in the memory, and when the processor executes the computer instructions, the electronic device is caused to execute the image quality assessment method as described above.

[0024] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects:

[0025] By obtaining an image to be processed; performing feature extraction processing on the image to obtain the original image features and low-frequency image features in the image; determining the quality assessment result of the image according to the original image features and the low-frequency image features, wherein the low-frequency image features are the relevant features of the semantic content in the image; according to the original image features and the low-frequency image features, the relevant features of the noise in the image can be determined, avoiding the interference of the semantic content in the image quality assessment, ensuring the accuracy of the quality assessment result obtained by the assessment, and improving the accuracy of the image quality assessment.

[0026] 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

[0027] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure and do not constitute an improper limitation of the present disclosure.

[0028] Figure 1 It is a flowchart of an image quality assessment method according to an embodiment of the present disclosure;

[0029] Figure 2 It is a flowchart of an image quality assessment method according to another embodiment of the present disclosure;

[0030] Figure 3 It is a schematic structural diagram of an image feature extraction network;

[0031] Figure 4 It is a schematic structural diagram of a low-frequency feature extraction network;

[0032] Figure 5 It is a schematic structural diagram of an image quality assessment device according to an embodiment of the present disclosure;

[0033] Figure 6 It is a structural block diagram of an electronic device shown according to an exemplary embodiment of the present disclosure;

[0034] Figure 7 It is a schematic structural diagram of a chip according to an embodiment of the present disclosure. Detailed implementation manners

[0035] To enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data used in appropriate cases can be interchanged so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation manners described in the following exemplary embodiments do not represent all implementation manners 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.

[0037] The current image quality assessment method, for example, inputs a face image into a feature extraction network to obtain feature data; inputs the feature data into a fully connected layer for processing to obtain the face quality score of the face image.

[0038] In the above solution, the face image includes noise and semantic content, resulting in the face quality score being determined by combining the noise and semantic content, making it difficult to accurately reflect the noise situation in the face image, resulting in poor accuracy of the evaluated face quality score and poor accuracy of the image quality assessment.

[0039] Figure 1 It is a flowchart of the image quality assessment method according to an embodiment of the present disclosure. Among them, it should be noted that the image quality assessment method of this embodiment can be applied to an image quality assessment device, and this device can be configured in an electronic device or a chip so that the electronic device or the chip can perform the image quality assessment function.

[0040] Among them, the electronic device can be any device with computing capabilities, such as a personal computer (PC for short), a mobile terminal, a server, a controller in a vehicle, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc., which are hardware devices with various operating systems, touch screens, and / or display screens.

[0041] In addition, the image quality assessment device can also be software in an electronic device, etc. Among them, in the following embodiments, the execution subject is taken as an electronic device for illustration.

[0042] As Figure 1 shown, the method includes the following steps:

[0043] Step 101: Obtain the image to be processed.

[0044] In the embodiments of the present disclosure, the scene to which the image belongs may include at least one of the following: an image capture scene, an image sorting and recommendation scene, and an image generation scene. Among them, in the image capture scene, the image to be processed may be an image obtained by shooting. In the image sorting and recommendation scene, the image to be processed may be an image to be sorted and recommended. In the image generation scene, the image to be processed may be a generated image.

[0045] Step 102: Perform feature extraction processing on the image to obtain the original image features and low-frequency image features in the image.

[0046] In the embodiments of the present disclosure, the process of the electronic device executing Step 102 may be, for example, performing image feature extraction processing on the image to obtain the original image features in the image; performing low-frequency feature extraction processing on the image to obtain the low-frequency image features in the image.

[0047] Among them, the image may include noise and semantic content. Correspondingly, the original image features may include the relevant features of the noise in the image and the relevant features of the semantic content. Among them, semantic content is generally low-frequency content. Therefore, the relevant features of semantic content can be obtained by performing low-frequency feature extraction processing on the image. Therefore, the low-frequency image features in the image can be extracted to distinguish the relevant features of the noise in the image and the relevant features of the semantic content.

[0048] Among them, the original image features in the image can be extracted by an image feature extraction network. The low-frequency image features in the image can be extracted by a low-frequency feature extraction network. Among them, the electronic device may set a quality evaluation model, which includes an image feature extraction network, a low-frequency feature extraction network, and a quality evaluation network. The quality evaluation network is used to determine the quality evaluation result of the image according to the original image features and the low-frequency image features.

[0049] Among them, the quality evaluation model can be trained according to multiple sample noise images and the sample quality evaluation results of the sample noise images. Among them, the sample noise image may be an image carrying noise; or it may be obtained by adding noise to an image without noise. The quality evaluation result may be, for example, a quality score.

[0050] Step 103: Determine the quality evaluation result of the image according to the original image features and the low-frequency image features.

[0051] In an embodiment of the present disclosure, the process of the electronic device executing step 103 may be, for example, to determine the mean square error between the original image features and the low-frequency image features; use this mean square error as the quality score; and use this quality score as the image quality evaluation result. Among them, the quality score can indicate the noise situation in the image. For example, it can indicate the intensity and / or type of noise in the image, etc. Among them, the types of noise are, for example, Gaussian noise, Poisson noise, impulse noise, etc.

[0052] Among them, the original image features may include features in multiple dimensions; the low-frequency image features may also include features in multiple dimensions. The process for the electronic device to determine the mean square error between the original image features and the low-frequency image features may be, for example, for each dimension in the original image features, determine the squared difference value between the feature in this dimension and the feature in the corresponding dimension of the low-frequency image features; sum and average the squared difference values in multiple dimensions to obtain a calculation result; and determine this calculation result as the mean square error between the original image features and the low-frequency image features.

[0053] In an embodiment of the present disclosure, when the scene to which the image belongs is an image capture scene, the image capture parameters may be adjusted according to the image quality evaluation result of the captured image to improve the quality of the captured image. Among them, when the scene to which the image belongs is an image sorting and recommendation scene, multiple images may be sorted according to the quality evaluation results of the multiple images, and the images with higher quality evaluation results may be recommended.

[0054] Among them, when the scene to which the image belongs is an image generation scene, the image generation parameters may be adjusted according to the image quality evaluation result to improve the quality of the generated image.

[0055] In the image quality evaluation method of the embodiment of the present disclosure, by obtaining the image to be processed; performing feature extraction processing on the image to obtain the original image features and the low-frequency image features in the image; determining the image quality evaluation result according to the original image features and the low-frequency image features, where the low-frequency image features are the relevant features of the semantic content in the image; according to the original image features and the low-frequency image features, the relevant features of the noise in the image can be determined, avoiding the interference of semantic content in the image quality evaluation, ensuring the accuracy of the evaluated quality evaluation result, and improving the accuracy of the image quality evaluation.

[0056] Figure 2 It is a flowchart of the image quality evaluation method according to another embodiment of the present disclosure. Among them, it should be noted that the image quality evaluation method of this embodiment can be applied to an image quality evaluation device, and this device can be configured in an electronic device or a chip so that the electronic device or the chip can perform the image quality evaluation function.

[0057] Among them, the electronic device can be any device with computing capabilities, such as a personal computer (PC), a mobile terminal, a server, a controller in a vehicle, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc., which are hardware devices with various operating systems, touch screens, and / or display screens.

[0058] In addition, the image quality evaluation device can also be software in the electronic device, etc. Among them, in the following embodiments, the execution subject is taken as an example of an electronic device for description.

[0059] As Figure 2 shown, the method includes the following steps:

[0060] Step 201, obtain the image to be processed.

[0061] Step 202, perform feature extraction processing on the image to obtain the original image features in the image; the original image features include original image sub-features at multiple scales.

[0062] In the embodiments of the present disclosure, the image feature extraction network for extracting the original image features includes image feature sub-extraction networks at multiple scales; the image feature sub-extraction network includes a first convolutional layer, a ReLU activation network, a second convolutional layer, and an L2 pooling layer (L2 Pooling) connected in sequence. Among them, the structural schematic diagram of the image feature extraction network can be, for example, as Figure 3 shown. Among them, the first convolutional layer and the second convolutional layer can be 3×3 convolutional networks.

[0063] Step 203, perform at least one of maximum pooling feature extraction processing, average pooling feature extraction processing, image content feature extraction processing, and perceptual content feature extraction processing on the image to obtain at least one intermediate low-frequency image feature; the intermediate low-frequency image feature includes intermediate low-frequency image sub-features at multiple scales.

[0064] In the embodiments of the present disclosure, the maximum pooling feature extraction network includes maximum pooling feature sub-extraction networks at multiple scales. The maximum pooling sub-feature network includes a third convolutional layer, a ReLU activation network, a fourth convolutional layer, and a maximum pooling layer (Max Pooling) connected in sequence. Among them, the third convolutional layer and the fourth convolutional layer can be 3×3 convolutional networks.

[0065] Among them, the average pooling feature network includes average pooling feature sub - extraction networks at multiple scales. The average pooling feature sub - extraction network includes a fifth convolutional layer, a ReLU activation network, a sixth convolutional layer, and an average pooling layer (Avg Pooling) connected in sequence. Among them, the fifth convolutional layer and the sixth convolutional layer can be 3×3 convolutional networks.

[0066] Among them, the structure of the image content feature extraction network is the same as that of the image feature extraction network. Among them, the perceptual content feature extraction network can be the deep convolutional neural network VGG - 19.

[0067] Among them, the low - frequency feature extraction network for extracting low - frequency image features includes a feature fusion network, and a max - pooling feature extraction network, an average - pooling feature extraction network, an image content feature extraction network, and a perceptual content feature extraction network respectively connected to the feature extraction network. Among them, the feature fusion network can include a seventh convolutional layer, a ReLU activation network, an eighth convolutional layer, and a spatial attention mechanism network connected in sequence. Among them, the spatial attention mechanism network can be composed of two convolutional layers, a ReLU activation network, and a Sigmoid activation network. The first convolutional layer reduces the number of channels to 1 / 4 of the original, and the second convolutional layer restores the original number of channels; a ReLU activation network is used between the two convolutional layers; a Sigmoid activation network is used after the second convolutional layer to obtain the output result of the spatial attention mechanism network.

[0068] Step 204: Perform fusion processing on the intermediate low - frequency image sub - features at multiple scales in at least one intermediate low - frequency image feature to obtain a low - frequency image feature.

[0069] Among them, performing fusion processing on the intermediate low - frequency image sub - features at multiple scales in at least one intermediate low - frequency image feature can be achieved through the feature fusion network in the low - frequency feature extraction network. The structural schematic diagram of the low - frequency feature extraction network can be, for example, as Figure 4 shown. In Figure 4 , the max - pooling feature extractor refers to the max - pooling feature extraction network; the average - pooling feature extractor refers to the average - pooling feature extraction network; the image content feature extractor refers to the image content feature extraction network; the perceptual content feature extractor refers to the perceptual content feature extraction network.

[0070] Step 205: Determine the image quality assessment result according to the original image feature and the low - frequency image feature.

[0071] In an embodiment of the present disclosure, the process of the electronic device executing step 205 may be, for example, for each scale among multiple scales, determining the mean square error between the original image sub-feature and the low-frequency image sub-feature at the scale; performing a weighted sum processing on the mean square error at each scale according to the weight of each scale among the multiple scales to obtain a quality score; and using the quality score as the quality assessment result of the image.

[0072] Among them, taking the number of scales as 5 as an example, the calculation formula of the quality score may be as shown in the following formulas (1), (2), and (3).

[0073] F e1 ,...,F e5 =f E (I) (1)

[0074] F l1 ,...,F l5 =f L (I) (2)

[0075]

[0076] Among them, I represents an image; f E (I) represents the original image feature; F e1 represents the original image sub-feature at the first scale; f L (I) represents the low-frequency image feature; F l1 represents the low-frequency image sub-feature at the first scale; score represents the quality score; w i represents the weight of the i-th scale; MSE(F ei -F li ) represents the mean square error at the i-th scale.

[0077] Among them, the weight of each scale among the multiple scales, and the feature extraction network for performing feature extraction processing on the image are trained according to multiple sample noise images and the sample quality scores of the sample noise images. The feature extraction network may include an image feature extraction network and a low-frequency feature extraction network.

[0078] Among them, it should be noted that for the detailed descriptions of step 201 and step 205, reference may be made to Figure 1 step 101 and step 103 in the embodiments shown, and no detailed description will be given here.

[0079] In the image quality assessment method according to the embodiments of the present disclosure, an image to be processed is obtained; feature extraction processing is performed on the image to obtain the original image features in the image; the original image features include original image sub-features at multiple scales; at least one of maximum pooling feature extraction processing, average pooling feature extraction processing, image content feature extraction processing, and perceptual content feature extraction processing is performed on the image to obtain at least one intermediate low-frequency image feature; the intermediate low-frequency image feature includes intermediate low-frequency image sub-features at multiple scales; the intermediate low-frequency image sub-features at multiple scales in at least one intermediate low-frequency image feature are fused to obtain a low-frequency image feature; the quality assessment result of the image is determined according to the original image features and the low-frequency image feature; wherein, at least one of the extraction processes of the intermediate low-frequency image features can obtain a sufficient number of low-frequency image features through various low-frequency image feature extraction methods, and then, by combining the low-frequency image features and the original image features, the relevant features of the noise in the image can be further accurately determined, thereby further improving the accuracy of image quality assessment.

[0080] Figure 5 It is a schematic structural diagram of an image quality assessment device according to an embodiment of the present disclosure.

[0081] As Figure 5 shown, the image quality assessment device may include: an acquisition module 501, a feature extraction module 502, and a determination module 503.

[0082] Among them, the acquisition module 501 is configured to acquire an image to be processed; the feature extraction module 502 is configured to perform feature extraction processing on the image to obtain the original image features and the low-frequency image features in the image; the determination module 503 is configured to determine the quality assessment result of the image according to the original image features and the low-frequency image features.

[0083] In an embodiment of the present disclosure, the original image features include original image sub-features at multiple scales; the low-frequency image features include the low-frequency image sub-features at the multiple scales.

[0084] In an embodiment of the present disclosure, the image feature extraction network for extracting the original image features includes image feature sub-extraction networks at multiple scales; the image feature sub-extraction network includes a first convolutional layer, a ReLU activation network, a second convolutional layer, and an L2 pooling layer connected in sequence.

[0085] In one embodiment of the present disclosure, the feature extraction module 502 is specifically configured to perform at least one of maximum pooling feature extraction processing, average pooling feature extraction processing, image content feature extraction processing, and perceptual content feature extraction processing on the image to obtain at least one intermediate low-frequency image feature; the intermediate low-frequency image feature includes intermediate low-frequency image sub-features at multiple scales; perform fusion processing on the intermediate low-frequency image sub-features at multiple scales in at least one intermediate low-frequency image feature to obtain the low-frequency image feature.

[0086] In one embodiment of the present disclosure, the low-frequency feature extraction network for extracting the low-frequency image feature includes a feature fusion network, and a maximum pooling feature extraction network, an average pooling feature extraction network, an image content feature extraction network, and a perceptual content feature extraction network respectively connected to the feature extraction network; the perceptual content feature extraction network is the deep convolutional neural network VGG-19.

[0087] In one embodiment of the present disclosure, the determination module 503 is specifically configured to, for each scale in the multiple scales, determine the mean square error between the original image sub-feature and the low-frequency image sub-feature at the scale; perform weighted summation processing on the mean square error at each scale according to the weights of each scale in the multiple scales to obtain a quality score; use the quality score as the quality assessment result of the image.

[0088] In one embodiment of the present disclosure, the weights of each scale in the multiple scales and the feature extraction network for performing feature extraction processing on the image are trained according to multiple sample noise images and the sample quality scores of the sample noise images.

[0089] In one embodiment of the present disclosure, the quality assessment result is a quality score; the quality score indicates the noise situation in the image; the processing scenario to which the image belongs includes at least one of the following: an image shooting scenario, an image sorting and recommendation scenario, and an image generation scenario; the quality score is used to guide the processing algorithm or processing parameters in the processing scenario.

[0090] In the image quality assessment device according to the embodiments of the present disclosure, by obtaining an image to be processed; performing feature extraction processing on the image to obtain the original image feature and the low-frequency image feature in the image; determining the quality assessment result of the image according to the original image feature and the low-frequency image feature, wherein the low-frequency image feature is a feature related to the semantic content in the image; according to the original image feature and the low-frequency image feature, the feature related to the noise in the image can be determined, avoiding the interference of the semantic content in the image quality assessment, ensuring the accuracy of the obtained quality assessment result, and improving the accuracy of the image quality assessment.

[0091] According to a third aspect of the embodiments of the present disclosure, an electronic device is further provided, including: a processor; a memory for storing instructions executable by the processor, wherein the processor is configured to: implement the image quality assessment method as described above.

[0092] To implement the above embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium.

[0093] Wherein, when the instructions in the storage medium are executed by the processor, the processor is enabled to execute the image quality assessment method as described above.

[0094] To implement the above embodiments, the present disclosure also provides a computer program product.

[0095] Wherein, when the computer program product is executed by the processor of the electronic device, the electronic device is enabled to execute the above method.

[0096] Figure 6 FIG. is a block diagram of an electronic device according to an exemplary embodiment. Figure 6 The illustrated electronic device is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0097] As Figure 6 shown, the electronic device 1000 includes a processor 111, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM, Read Only Memory) 112 or the program loaded from the memory 116 into the random access memory (RAM, Random Access Memory) 113. In the RAM 113, various programs and data required for the operation of the electronic device 1000 are also stored. The processor 111, the ROM 112, and the RAM 113 are connected to each other via a bus 114. The input / output (I / O, Input / Output) interface 115 is also connected to the bus 114.

[0098] The following components are connected to the I / O interface 115: a memory 116 including a hard disk, etc.; and a communication part 117 including a network interface card such as a local area network (LAN) card, a modem, etc., and the communication part 117 performs communication processing via a network such as the Internet; a driver 118 is also connected to the I / O interface 115 as required.

[0099] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program carried on a computer-readable medium, the computer program including program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 117. When the computer program is executed by the processor 111, the above-described functions defined in the method of the present disclosure are performed.

[0100] In an exemplary embodiment, a storage medium including instructions is also provided, such as a memory including instructions, and the above instructions can be executed by the processor 111 of the electronic device 1000 to complete the above method. Optionally, the storage medium may be a non-transitory computer-readable storage medium. For example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0101] In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0102] Figure 7 Schematic diagram of the structure of a chip according to an embodiment of the present disclosure. As Figure 7 shown, the chip includes a processor 701 and an interface circuit 702. Among them, the number of processors 701 can be one or more, and the number of interface circuits 702 can be one or more.

[0103] Optionally, the chip further includes a memory 703 for storing necessary computer programs and data; the interface circuit 702 is configured to receive signals from the memory 703 and send signals to the processor 701, and the signals include computer instructions stored in the memory 703. When the processor 701 executes the computer instructions, the electronic device is caused to execute the image quality evaluation method described in the above embodiments of the present disclosure.

[0104] In addition, the word "exemplary" is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as "exemplary" is not necessarily to be construed as advantageous over other aspects or designs. Instead, the word exemplary is intended to present concepts in a concrete fashion. As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless specified otherwise, or clear from the context, "X applies A or B" is intended to mean any of the natural inclusive permutations. That is, if X applies A; X applies B; or X applies both A and B, then "X applies A or B" is satisfied under any of the foregoing instances. Additionally, unless specified otherwise or clear from the context that it refers to the singular form, the articles "a" and "an" as used in this application and the appended claims are generally understood to mean "one or more".

[0105] Likewise, although the present disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the drawings. The present disclosure includes all such modifications and variations and is limited only by the scope of the claims. Specifically with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terms used to describe such components are intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if not structurally equivalent to the disclosed structure. Additionally, although a particular feature of the present disclosure may have been disclosed with respect to only one of several implementations, such a feature may, as may be desired and advantageous for any given or particular application, be combined with one or more other features of other implementations. Further, with respect to the use of "comprises", "comprising", "has", "having", "includes", or variants thereof in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term "including".

[0106] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known or customary techniques in the art that are not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0107] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An image quality assessment method, characterized in that, The method includes: Obtaining an image to be processed; Performing feature extraction processing on the image to obtain the original image features and low-frequency image features in the image; Determining a quality assessment result of the image according to the original image features and the low-frequency image features.

2. The method according to claim 1, characterized in that, The original image features include original image sub-features at multiple scales; The low-frequency image features include low-frequency image sub-features at the multiple scales.

3. The method according to claim 2, wherein The image feature extraction network for extracting the original image features includes image feature sub-extraction networks at multiple scales; The image feature sub-extraction network includes a first convolutional layer, a ReLU activation network, a second convolutional layer, and an L2 pooling layer connected in sequence.

4. The method according to claim 2, wherein Performing feature extraction processing on the image to obtain the low-frequency image features in the image includes: Performing at least one of maximum pooling feature extraction processing, average pooling feature extraction processing, image content feature extraction processing, and perceptual content feature extraction processing on the image to obtain at least one intermediate low-frequency image feature; the intermediate low-frequency image feature includes intermediate low-frequency image sub-features at the multiple scales; Performing a fusion process on the intermediate low-frequency image sub-features at multiple scales in at least one intermediate low-frequency image feature to obtain the low-frequency image features.

5. The method according to claim 4, characterized in that The low-frequency feature extraction network for extracting the low-frequency image features includes a feature fusion network, and a maximum pooling feature extraction network, an average pooling feature extraction network, an image content feature extraction network, and a perceptual content feature extraction network respectively connected to the feature extraction network; The perceptual content feature extraction network is the deep convolutional neural network VGG-19.

6. The method according to claim 2, wherein Determining the quality assessment result of the image according to the original image features and the low-frequency image features includes: For each scale in the multiple scales, determining the mean square error between the original image sub-features and the low-frequency image sub-features at the scale; Performing a weighted sum process on the mean square errors at each scale according to the weights of each scale in the multiple scales to obtain a quality score; Using the quality score as the quality assessment result of the image.

7. The method according to claim 6, wherein The weights of each scale in the multiple scales and the feature extraction network for performing feature extraction processing on the image are trained according to multiple sample noise images and the sample quality scores of the sample noise images.

8. The method according to claim 1, wherein The quality assessment result is a quality score; the quality score indicates the noise condition in the image; The processing scenario to which the image belongs includes at least one of the following: an image shooting scenario, an image sorting and recommendation scenario, and an image generation scenario; the quality score is used to guide the processing algorithm or processing parameters in the processing scenario.

9. An image quality assessment device, characterized in that, The device includes: An acquisition module for acquiring an image to be processed; A feature extraction module for performing feature extraction processing on the image to obtain the original image features and the low-frequency image features in the image; A determination module for determining a quality assessment result of the image according to the original image features and the low-frequency image features.

10. An electronic device, characterized in that, Includes: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to: Implement the steps of the image quality assessment method according to any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor, enabling the processor to execute the image quality assessment method according to any one of claims 1 to 8.

12. A chip, characterized in that, Comprising one or more interface circuits and one or more processors; the interface circuits are used to receive signals from the memory of the electronic device and send the signals to the processor, the signals including computer instructions stored in the memory, and when the processor executes the computer instructions, enabling the electronic device to execute the image quality assessment method according to any one of claims 1 to 8.

Images