Method and system for restoring high-level features of low-light images based on neural network

Abstract

The present application relates to the field of machine vision technology, and provides a method and system for recovering high-level features of low-light images based on a neural network. In this method, a low-light source image is processed based on a neural network model to obtain a first image, and the first image and a target image of normal light corresponding to the source image are Gaussian blurred by a multi-dimensional Gaussian function to extract high-level features of the first image and the target image; based on a deformed peak signal-to-noise ratio model, the differential loss value of the high-level features of the first image and the target image is determined, and the neural network model is updated to recover high-level features of the low-light image based on the updated neural network model. Therefore, in the process of backpropagation of the neural network model, the neural network model is updated by adding the deformed peak signal-to-noise ratio model to the loss function, so that the neural network model can better recover the high-level features in the image.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, system, computer-readable storage medium, and electronic device for restoring high-level features of low-light images based on a neural network. Background Art

[0002] Currently, commonly used methods for restoring low-light images include image enhancement, noise reduction, and Retinex theory. Image enhancement techniques often include histogram equalization, contrast-limited adaptive histogram equalization, and gamma correction. These methods can improve the contrast and brightness of low-light images, but they can also increase noise or distortion. Noise reduction techniques often include wavelet transforms, bilateral filters, and non-local means noise reduction. These methods restore images by reducing noise. However, simple pixel manipulation can also cause distortion and generate noise.

[0003] The Retinex theory improves image quality by separating the reflection component and the illumination component of the image. However, during the operation, only the single relationship of illumination between light rays is considered, and only one nonlinear mapping exists, which will also cause image distortion and generate a large amount of noise.

[0004] Therefore, there is an urgent need to provide a technical solution to the above-mentioned deficiencies in the existing technology. Summary of the Invention

[0005] The purpose of this application is to provide a method, system, computer-readable storage medium and electronic device for restoring high-level features of low-light images based on a neural network, so as to solve or alleviate the problems existing in the above-mentioned prior art.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The present application provides a method for restoring high-level features of low-illuminance images based on a neural network, including: step S101, processing a captured low-illuminance source image based on a preset neural network model to obtain a first image; step S102, Gaussian blurring the first image and a target image of normal illumination obtained corresponding to the source image through a high-dimensional Gaussian function, and extracting high-level features of the first image and high-level features of the target image respectively; step S103, determining differential loss values ​​of the high-level features of the first image and the high-level features of the target image based on a deformed peak signal-to-noise ratio model; step S104, updating the neural network model according to the differential loss values, so as to restore the high-level features of the low-illuminance image based on the updated neural network model.

[0008] Preferably, in step S101, characteristic illuminations of different levels of entity features in the source image are cyclically extracted and subjected to convolution operation, and the extracted characteristic illuminations are restored to obtain the first image.

[0009] Preferably, in step S102, based on the multidimensional Gaussian function, Gaussian blur is performed on the first image and the target image respectively to filter out low-level features in the first image and the target image to obtain high-level features of the first image and the target image.

[0010] Preferably, in step S103, according to the formula:

[0011]

[0012] Determine the differential loss value PNSR_DF of the high-level features of the first image and the high-level features of the target image; wherein, is the maximum pixel value of the target image; MSE_DF is the mean square error between the first image and the target image.

[0013] Preferably, in step S103, according to the formula:

[0014]

[0015] Determine the mean square error MSE_DF after deformation;

[0016] Among them, I DF(i,j) is the pixel value of the high-level feature of the first image at coordinate (i, j); K DF(i,j) is the pixel value of the high-level feature of the target image at coordinate (i, j); n and m are the length and width of the image after high-dimensional Gaussian blurring, where only the high-level features are retained; i, j, n, and m are all positive numbers.

[0017] Preferably, according to the formula:

[0018]

[0019] Determine the pixel value I of the high-level feature of the first image at coordinates (i, j) DF(i,j) , and the pixel value K of the high-level feature of the target image at coordinate (i, j) DF(i,j) ; Wherein, r is the radius of the Gaussian kernel of the multidimensional Gaussian function; σ is the intensity of Gaussian blur; N1 and N2 are the dimensions of the first image and the target image to be multidimensionally Gaussian blurred, respectively, and N1 and N2 are both positive integers.

[0020] Preferably, in step S104, the model parameter gradient of the neural network model corresponding to the differential loss value is calculated; and the model parameters in the neural network model are updated according to the model parameter gradient and the learning rate of the neural network model.

[0021] An embodiment of the present application also provides a system for restoring high-level features of low-illuminance images based on a neural network, comprising: an illumination extraction unit, configured to process a captured low-illuminance source image based on a preset neural network model to obtain a first image; a high-level feature extraction unit, configured to perform a Gaussian model on the first image and the acquired target object of normal illumination corresponding to the source image through a multi-dimensional Gaussian function, and extract high-level features of the first image and high-level features of the target image respectively; a differential calculation unit, configured to determine the differential loss values ​​of the high-level features of the first image and the high-level features of the target image based on a deformed peak signal-to-noise ratio model; and a model updating unit, configured to update the neural network model according to the differential loss value, and restore high-level features of the low-illuminance image based on the updated neural network model.

[0022] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements any of the above-described methods for restoring high-level features of low-light images based on a neural network.

[0023] An embodiment of the present application also provides an electronic device, comprising: a memory storing a computer program for a method for restoring high-level features of low-light images based on a neural network as described above; and a processor for retrieving and executing the computer program stored in the memory.

[0024] Beneficial effects:

[0025] The embodiment of the present application provides a method for restoring high-level features of low-light images based on a neural network. First, based on a preset neural network model, a captured low-light source image is processed to obtain a first image; then, the first image and a target image of normal light obtained corresponding to the source image are Gaussian blurred using a multi-dimensional Gaussian function to extract high-level features of the first image and high-level features of the target image, respectively; then, based on a deformed peak signal-to-noise ratio model, the differential loss values ​​of the high-level features of the first image and the high-level features of the target image are determined; finally, based on the differential loss values, the neural network model is updated, and high-level features of the low-light image are restored based on the updated neural network model. Thus, during the back-propagation process of the neural network model, the differential loss value of the image is calculated by adding the deformed peak signal-to-noise ratio model to the loss function, and the neural network model is updated, so that the neural network model can better restore high-level features in the image when calculating the target image and the low-light image. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings in the specification, which constitute a part of this application, are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0027] in:

[0028] Figure 1 A flowchart of a method for restoring high-level features of low-light images based on a neural network according to some embodiments of the present application is provided;

[0029] Figure 2 A schematic diagram of recovering high-level features of a low-light image according to some embodiments of the present application;

[0030] Figure 3 A schematic diagram of restoring high-level features of another low-light image according to some embodiments of the present application;

[0031] Figure 4 A schematic structural diagram of a system for restoring high-level features of low-light images based on a neural network according to some embodiments of the present application;

[0032] Figure 5 A schematic structural diagram of an electronic device provided according to some embodiments of the present application;

[0033] Figure 6 The present invention provides a hardware structure of an electronic device according to some embodiments of the present application. DETAILED DESCRIPTION

[0034] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments. Each example is provided by way of explanation of the present application and does not limit the present application. In fact, it will be clear to those skilled in the art that modifications and variations can be made in the present application without departing from the scope or spirit of the present application. For example, a feature shown or described as part of one embodiment can be used in another embodiment to produce yet another embodiment. Therefore, it is expected that the present application includes such modifications and variations within the scope of the appended claims and their equivalents.

[0035] In the fields of machine learning and deep learning, processing low-light images is a key research area, aiming to improve image visibility, detail, and color, enabling clear display even in low-light conditions. Deep neural networks are used to automatically learn the mapping relationship from low-light images to high-light images, automatically repairing the images and adjusting their brightness and color. However, image enhancement, noise reduction, and Retinex theory all result in distortion and noise when restoring the image's illumination.

[0036] Based on this, an embodiment of the present application provides a method for restoring high-level features of low-light images based on a neural network. During the back propagation process of training a neural network model (convolutional neural network or adversarial neural network), the deformed peak signal-to-noise ratio is added to the calculated loss function, thereby guiding the neural network model to better restore the high-level features of the image.

[0037] like Figures 1 to 3 As shown, the method for restoring high-level features of low-light images based on a neural network includes:

[0038] Step S101: Processing a collected low-illumination source image based on a preset neural network model to obtain a first image.

[0039] Low-light images are images with insufficient illumination (light intensity), appearing pitch black to the human eye. In this application, low-light images are defined as images with an average brightness below 50 lux, a peak brightness below 80 lux, an image contrast ratio below 30:1, and a color saturation below 70%.

[0040] The source image and target image are paired images of the same scene, captured under low illumination conditions and normal illumination conditions respectively. The training of the neural network model for restoring image illumination uses paired source images and target images to ensure that the training network can learn the mapping from low illumination conditions to normal illumination conditions.

[0041] In the present application, when processing the collected low-illuminance source image, the first image is obtained by cyclically extracting the characteristic illuminations of different levels of the entity features in the source image and performing a convolution operation, and restoring the extracted characteristic illuminations. That is to say, in the neural network model, the characteristic illuminations of different levels of the entity features in the source image are continuously extracted through the convolution operation, and then the extracted characteristic illuminations of different levels are again subjected to the convolution operation to restore the extracted characteristic illuminations of different levels. Since the loss function of the neural network model restores the illumination of the high-level features of the entity features, the second convolution operation only restores the illumination of the high-level features under the guidance of the loss function. Here, the high-level features of the image include but are not limited to the contours, materials, shapes, sizes, relative positional relationships between entity features (objects), and characteristic functions of the entity features (objects) in the image.

[0042] Step S102: Gaussian blur the first image and the target image with normal illumination obtained corresponding to the source image using a multi-dimensional Gaussian function to extract high-level features of the first image and high-level features of the target image respectively.

[0043] In the present application, the target image and the source image are paired images of different illuminations captured in the same scene, wherein the target image is an image captured under normal illumination conditions, and the source image is an image captured under low illumination conditions. When obtaining the high-level features of the first image and the high-level features of the target image, based on a multidimensional Gaussian function, Gaussian blur is performed on the first image and the target image respectively, and the low-level features in the first image and the target image are filtered out to obtain the high-level features of the first image and the high-level features of the target image. That is, the first image and the target image are filtered respectively by a multidimensional Gaussian function to filter out the high-frequency low-level features in the image and retain the high-level features in the image, thereby realizing the extraction of the high-level features of the image.

[0044] Specifically, a multidimensional Gaussian function is first generated by weighting the distances between pixels in the image and the central pixel. This multidimensional Gaussian function is then used as a weighting factor to reduce high-frequency components (i.e., details and noise) in the first and target images, thereby filtering out low-level features in the first and target images. Low-level features in these images include, but are not limited to, pixel values, saturation, brightness, hue, and value.

[0045] In the Gaussian blur process, a Gaussian kernel (two-dimensional array) is created based on a multidimensional Gaussian function. Then, on each color channel of the image, for each pixel, the Gaussian kernel is used to perform a weighted average of the pixels in its neighborhood. The value at each pixel position is replaced by the weighted average, thereby blurring the image.

[0046] Step S103: Determine differential loss values ​​of high-level features of the first image and high-level features of the target image based on the deformed peak signal-to-noise ratio model.

[0047] In this application, the difference between the high-level features of the first image and the high-level features of the target image is calculated by the peak signal-to-noise ratio, which is the differential loss value between the first image and the target image. Specifically, according to the formula:

[0048]

[0049] Determine a differential loss value of the high-level features of the first image and the high-level features of the target image.

[0050] in, is the maximum pixel value of the target image; MSE_DF is the mean square error after deformation, which is used to determine the L2 norm of the first image to the target image.

[0051] Here, according to the formula:

[0052]

[0053] Determine the mean square error MSE_DF between the first image and the target image.

[0054]

[0055] Where, I DF(i,j) is the pixel value of the high-level feature of the first image at coordinate (j, j); K DF(i,j) is the pixel value of the high-level feature of the target image at coordinates (i, j); n and m are the length and width of the image (first image, target image) that only retains the high-level features after multi-dimensional Gaussian blurring; i, j, n, and m are all positive numbers; r is the radius of the Gaussian kernel of the multi-dimensional Gaussian function; σ is the intensity of the Gaussian blurring; N1 and N2 are the dimensions of the first image and target image to be subjected to multi-dimensional Gaussian blurring, respectively, and both N1 and N2 are positive integers.

[0056] Step S104: updating the neural network model according to the differential loss value, and restoring the high-level features of the low-illumination image based on the updated neural network model.

[0057] In this application, the back propagation of differential loss values, specifically back propagation of a convolutional neural network or an adversarial neural network, is used to guide the neural network (convolutional neural network or adversarial neural network) model to learn to restore high-level features of low-light images. Specifically, first, the model parameter gradients of the neural network model corresponding to the differential loss value are calculated; then, based on the model parameter gradients and the learning rate of the neural network model, the model parameters in the neural network model are updated, thereby guiding the neural network model to learn to restore high-level features of low-light images.

[0058] Here, the differential loss value between the high-level features of the first image and the high-level features of the target image is calculated using a deformed peak signal-to-noise ratio model. This differential loss value is then used as the loss function, adding the deformed peak signal-to-noise ratio to the original loss function of the neural network model. Next, the gradient of the deformed loss function (differential loss value) relative to the model parameters of the neural network model is calculated. Finally, the gradient is multiplied by the learning rate of the neural network model to obtain the direction and magnitude of the gradient descent of the model parameters, thereby updating the model parameters. This means that the guidance weights of the loss function during the backpropagation process are updated based on the gradient descent method.

[0059] The neural network model accepts input data and passes it through a hierarchical structure, with each layer calculating its output until the last layer generates the final prediction result; the loss function calculates the difference between the predicted result and the actual label, generating a single loss value (differential loss value) to measure the performance of the current network.

[0060] The gradient of the loss function with respect to the model parameters (guidance weights) of the neural network model is calculated through backpropagation. Specifically, this is achieved by differentiating the network layer by layer, using the chain rule from the output layer back to the input layer. The gradient represents the rate of change of the differential loss value with respect to each weight.

[0061] Then, using gradient descent or another optimization algorithm, the guidance weights are updated based on the calculated gradients to reduce the loss function. Typically, the guidance weights are updated by subtracting the product of the learning rate and the gradient from the guidance weights. The difference is the updated guidance weight. The learning rate is a hyperparameter that determines the magnitude of each update during the optimization process.

[0062] Through iterative cycles and continuous optimization of the guidance weights, the neural network model's predictions will gradually approach the true labels, and the loss function value will decrease accordingly. In this process, the loss function provides a standard for measuring model performance and guides the direction and magnitude of weight updates through its gradient to train the model to make accurate predictions.

[0063] The neural network model with updated model parameters can be used to restore high-level features of low-light images. Here, the high-level features of the image include but are not limited to the outline of the object in the image, the material of the object, the color of the object, the shape of the object, the size of the object, the relative position relationship between objects, and the characteristic function of the object.

[0064] In this application, the acquired low-illumination source image is subjected to illumination restoration through a convolutional neural network or an adversarial neural network to obtain a first image; then, the first image and the target image are subjected to multi-dimensional Gaussian blur to extract high-level features of the first image and the target image, and the difference (differential loss value) between the high-level features of the first image and the target image is calculated through a deformed peak signal-to-noise ratio model. Through back propagation, the convolutional neural network or the adversarial neural network is guided to focus on restoring the high-level features of the low-illumination image, rather than simply restoring the illumination between pixels and pixel groups highlighted by low illumination, so that the illumination restoration effect of the low-illumination image is better.

[0065] like Figure 4 As shown, the embodiment of the present application further provides a system for restoring high-level features of low-light images based on a neural network, comprising:

[0066] The illumination extraction unit 401 is configured to process the collected low-illumination source image based on a preset neural network model to obtain a first image;

[0067] The high-level feature extraction unit 402 is configured to perform a Gaussian model on the first image and the target object with normal illumination corresponding to the source image using a multi-dimensional Gaussian function, and extract high-level features of the first image and high-level features of the target image respectively;

[0068] A differential calculation unit 403 is configured to determine differential loss values ​​of high-level features of the first image and high-level features of the target image based on the deformed peak signal-to-noise ratio model;

[0069] The model updating unit 404 is configured to update the neural network model according to the differential loss value, and perform high-level feature recovery on the low-light image based on the updated neural network model.

[0070] The system for restoring high-level features of low-light images based on a neural network provided in the embodiments of the present application can implement the steps and processes of any of the above-mentioned method embodiments for restoring high-level features of low-light images based on a neural network, and achieve the same technical effects, which will not be repeated here.

[0071] Figure 5 Schematic diagram of the structure of an electronic device according to some embodiments of the present application; Figure 5 As shown, the electronic device includes:

[0072] One or more processors 501;

[0073] The computer-readable medium can be configured to store one or more programs 502. When one or more processors 501 execute the one or more programs 502, the following steps are implemented: based on a preset neural network model, the collected low-light source image is processed to obtain a first image; through a multi-dimensional Gaussian function, the first image and the obtained target image with normal illumination corresponding to the source image are Gaussian blurred to extract the high-level features of the first image and the high-level features of the target image respectively; based on the deformed peak signal-to-noise ratio model, the differential loss values ​​of the high-level features of the first image and the high-level features of the target image are determined; according to the differential loss values, the neural network model is updated, and the high-level features of the low-light image are restored based on the updated neural network model.

[0074] Figure 6 The hardware structure of the electronic device provided according to some embodiments of the present application; Figure 6 As shown, the hardware structure of the electronic device may include: a processor 601 , a communication interface 602 , a computer-readable medium 603 and a communication bus 604 .

[0075] The processor 601 , the communication interface 602 , and the computer-readable storage medium 603 communicate with each other via a communication bus 604 .

[0076] Optionally, the communication interface 602 may be an interface of a communication module, such as an interface of a GSM module.

[0077] Among them, the processor 601 can be specifically configured as follows: based on a preset neural network model, processing the collected low-illuminance source image to obtain a first image; through a multi-dimensional Gaussian function, Gaussian blurring the first image and the acquired target image of normal illumination corresponding to the source image, and extracting the high-level features of the first image and the high-level features of the target image respectively; based on the deformed peak signal-to-noise ratio model, determining the differential loss values ​​of the high-level features of the first image and the high-level features of the target image; according to the differential loss values, updating the neural network model, and restoring the high-level features of the low-illuminance image based on the updated neural network model.

[0078] The processor 601 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor.

[0079] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

[0080] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and are primarily designed to provide voice and data communications. These terminals include smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones.

[0081] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0082] (3) Portable entertainment devices: These devices can display and play multimedia content. These devices include audio and video players (e.g., iPods), handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0083] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0084] (5) Other electronic devices with data interaction functions.

[0085] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0086] The above-described method according to the embodiment of the present application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code originally stored in a remote recording medium or non-transitory machine storage medium downloaded via a network and then stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It can be understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for restoring high-level features of low-light images based on a neural network described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown herein.

[0087] Those skilled in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of this application.

[0088] It should be noted that the various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from the other embodiments. In particular, the device and system embodiments are described briefly because they are generally similar to the method embodiments. For relevant parts, refer to the description of the method embodiments.

[0089] The device and system embodiments described above are merely illustrative. Units not described as separate may or may not be physically separate, and units not described as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiments. Persons of ordinary skill in the art will be able to understand and implement the present embodiments without inventive effort.

[0090] The foregoing description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

[0091] The foregoing description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for restoring high-level features of low-light images based on neural networks, characterized in that: include: Step S101: Based on a preset neural network model, cyclically extracting characteristic illuminations of different levels of entity features in a collected low-illumination source image, performing a convolution operation, and restoring the extracted characteristic illuminations to obtain a first image; Step S102: Gaussian blurring the first image and the target image with normal illumination obtained and corresponding to the source image using a multidimensional Gaussian function to extract high-level features of the first image and high-level features of the target image respectively; Step S103: Based on the deformed peak signal-to-noise ratio model, according to the formula: Determine a differential loss value of the high-level features of the first image and the high-level features of the target image ;in, is the maximum pixel value of the target image; is the mean square error between the first image and the target image; According to the formula: Determine the mean square error after deformation ; in, The high-level features of the first image are at coordinates The pixel value on ; The high-level features of the target image are in coordinates The pixel value on ; are the length and width of the image that retains only high-level features after multi-dimensional Gaussian blur; are all positive integers; Step S104: updating the neural network model according to the differential loss value, so as to restore high-level features of the low-illumination image based on the updated neural network model.

2. The method for restoring high-level features of low-light images based on a neural network according to claim 1, characterized in that: In step S102, Based on the multidimensional Gaussian function, Gaussian blur is performed on the first image and the target image respectively to filter out low-level features in the first image and the target image, thereby obtaining high-level features of the first image and the target image.

3. The method for restoring high-level features of low-light images based on a neural network according to claim 1, characterized in that: According to the formula: Determine the high-level features of the first image at coordinates The pixel value on , and the high-level features of the target image at coordinates The pixel value on ; in, is the radius of the Gaussian kernel of the multidimensional Gaussian function; is the intensity of Gaussian blur; are the dimensions of the first image and the target image to be subjected to multi-dimensional Gaussian blur, All are positive integers.

4. The method for restoring high-level features of low-light images based on a neural network according to claim 1, characterized in that: In step S104, Calculating the model parameter gradient of the neural network model corresponding to the differential loss value; The model parameters in the neural network model are updated according to the model parameter gradient and the learning rate of the neural network model.

5. A system for recovering high-level features of low-light images based on neural networks, characterized in that: include: an illumination extraction unit configured to extract characteristic illuminations of different levels of entity features in the collected low-illuminance source image through a convolution operation cycle based on a preset neural network model, perform convolution operations, and restore the extracted characteristic illuminations to obtain a first image; a high-level feature extraction unit configured to perform Gaussian blur on the first image and the acquired target image with normal illumination corresponding to the source image using a multidimensional Gaussian function, thereby extracting high-level features of the first image and high-level features of the target image respectively; The differential calculation unit is configured based on the deformed peak signal-to-noise ratio model according to the formula: Determine the differential loss value of the high-level features of the first image and the high-level features of the target image ;in, is the maximum pixel value of the target image; is the mean square error between the first image and the target image; according to the formula: Determine the mean square error after deformation ; in, The high-level features of the first image are at coordinates The pixel value on ; The high-level features of the target image are in coordinates The pixel value on ; are the length and width of the image that retains only high-level features after multi-dimensional Gaussian blur; are all positive integers; A model updating unit is configured to update the neural network model according to the differential loss value, and perform high-level feature recovery on the low-light image based on the updated neural network model.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for restoring high-level features of low-light images based on a neural network as described in any one of claims 1 to 4 is implemented.

7. An electronic device, characterized in that: include: A memory storing a computer program of the method for restoring high-level features of low-light images based on a neural network according to any one of claims 1 to 4; A processor is used to retrieve and execute the computer program stored in the memory.

Images