Sensor-induced image noise reduction processing method, system, device and storage medium

Abstract

The present invention discloses a method, system, device, and storage medium for denoising sensor-induced images. The method comprises: obtaining first array data of a sensor-induced image, adding Gaussian noise to the first array data to obtain second array data; performing functional relationship conversion on the second array data to obtain a pixel capacitance array, and inputting the pixel capacitance array into a pre-trained convolutional neural network; performing convolution calculation on the pixel capacitance array through a convolution layer to obtain a sensor charge array; performing data scaling on the sensor charge array to obtain third array data, performing nonlinear transformation on the third array data through an activation function to obtain fourth array data, and normalizing the fourth array data to obtain fifth array data; and decoding the fifth array data through a decoding layer to obtain a denoised sensor-induced image. The present invention improves the efficiency of denoising sensor-induced images and can be widely applied in the field of artificial intelligence technology.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a sensor-induced image noise reduction processing method, system, device and storage medium. Background Art

[0002] Sensors based on capacitive pixel arrays typically utilize the parasitic capacitance generated by capacitive pixels under external perception, which changes the capacitance value. A measurement circuit then measures the changed capacitance value and converts it into a digital value. This value is then passed to a processor, which processes the digital data representing the capacitance value information obtained for each capacitive pixel using an image algorithm to obtain the result. Autoencoder algorithms can be used to implement processing methods such as style learning and image denoising. Convolutional neural network-based encoders have better two-dimensional representation capabilities and are suitable for images. However, the data obtained by sensors in nature is often noisy, and measuring the capacitance value of each pixel requires multiple reading steps and corresponding circuits. Obtaining the data in digital form requires a lot of computing time and a large amount of storage space. Calculating the capacitance value of the entire image through a neural network algorithm also requires a large amount of computing power. Therefore, how to combine convolutional autoencoders with capacitive sensors to achieve noise reduction processing of sensor-perceived images and improve the efficiency of noise reduction processing is an urgent problem that needs to be solved. Summary of the Invention

[0003] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0004] To this end, one purpose of an embodiment of the present invention is to provide a sensor-sensed image noise reduction processing method, which utilizes the electrical characteristics of the capacitor and uses analog capacitance values ​​to participate in the calculation, which can effectively simplify circuit resources, speed up the calculation process in the neural network, and realize the noise reduction processing of the sensor-sensed image. It is also beneficial to speed up the calculation speed, reduce data bandwidth and simplify hardware resources during hardware mapping, reduce the requirements for system storage space and computing power, and improve the noise reduction processing efficiency of the sensor-sensed image.

[0005] Another object of an embodiment of the present invention is to provide a sensor-induced image noise reduction processing system.

[0006] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0007] In a first aspect, an embodiment of the present invention provides a method for denoising a sensor-induced image, comprising the following steps:

[0008] Acquire first array data of a sensor-sensed image, and add Gaussian noise to the first array data to obtain second array data;

[0009] Performing a functional relationship conversion on the second array data to obtain a pixel capacitance array, and then inputting the pixel capacitance array into a pre-trained convolutional neural network;

[0010] Performing convolution calculation on the pixel capacitance array through the convolution layer of the convolutional neural network to obtain a sensor charge array;

[0011] performing data scaling on the sensor charge array to obtain third array data, performing nonlinear transformation on the third array data using the activation function of the convolutional neural network to obtain fourth array data, and further performing normalization processing on the fourth array data to obtain fifth array data;

[0012] The fifth array data is decoded by the decoding layer of the convolutional neural network to obtain a sensor-sensed image after noise reduction.

[0013] Furthermore, in one embodiment of the present invention, the second array data is calculated by the following formula:

[0014] P(ij)=[1+σ(Noise)×randn(0,1)]Q(ij)

[0015] Wherein, P(ij) represents the data in the i-th row and j-th column of the second array data, Q(ij) represents the data in the i-th row and j-th column of the first array data, σ(Noise) represents the preset noise coefficient, and randn(0,1) represents a random number generated by a Gaussian function with a center of 0 and a variance of 1.

[0016] Furthermore, in one embodiment of the present invention, the pixel capacitance array is calculated by the following formula:

[0017] C(ij)=[P(ij)×C0] / [P(ij)+C0]

[0018] Wherein, C(ij) represents the data of the i-th row and j-th column in the pixel capacitance array, P(ij) represents the data of the i-th row and j-th column in the second array data, and C0 represents the original capacitance of the sensor.

[0019] Furthermore, in one embodiment of the present invention, the step of performing convolution calculation on the pixel capacitance array through the convolution layer of the convolutional neural network to obtain the sensor charge array is specifically:

[0020] Performing convolution calculation on the pixel capacitance array according to a preset first weight parameter to obtain the sensor charge array;

[0021] The first weight parameter is used to represent the voltage value applied to the sensor pixel capacitance.

[0022] Furthermore, in one embodiment of the present invention, the step of performing data scaling on the sensor charge array to obtain third array data, performing nonlinear transformation on the third array data using the activation function of the convolutional neural network to obtain fourth array data, and then normalizing the fourth array data to obtain fifth array data specifically includes:

[0023] The sensor charge array is divided by a preset scaling factor to obtain a third array data, where the scaling factor is C k ×V LSB , where C k Indicates the capacitance value of the preset equivalent capacitor structure, V LSB Indicates the preset analog-to-digital converter accuracy;

[0024] Performing a nonlinear transformation on the third array data using a preset activation function to obtain fourth array data, wherein the activation function is one of a Sigmoid function, a Tanh function, and a ReLU function;

[0025] The fourth array data is normalized by a batch normalization method to obtain fifth array data.

[0026] Furthermore, in one embodiment of the present invention, the step of decoding the fifth array data by the decoding layer of the convolutional neural network to obtain the denoised sensor-sensed image specifically includes:

[0027] Performing preliminary decoding processing on the fifth array data using a deconvolution algorithm according to a preset second weight parameter to obtain sixth array data;

[0028] Performing a nonlinear transformation on the sixth array data using a preset activation function to obtain seventh array data;

[0029] The seventh array data is subjected to a depth decoding process by a deconvolution algorithm according to a preset third weight parameter to obtain a sensor-sensed image after noise reduction.

[0030] Furthermore, in one embodiment of the present invention, the sensor-induced image denoising processing method further includes the step of training a convolutional neural network, which specifically includes:

[0031] Determining a training data set, inputting the training data set into the convolutional neural network to obtain a noise reduction processing result;

[0032] Determining a loss value of the convolutional neural network according to the denoising result and the training data set;

[0033] Updating weight parameters of the convolutional layer and the decoding layer through a back propagation algorithm according to the loss value;

[0034] When the loss value reaches a preset first threshold or the number of iterations reaches a preset second threshold, the training is stopped and a trained convolutional neural network is obtained.

[0035] In a second aspect, an embodiment of the present invention provides a sensor-induced image noise reduction processing system, comprising:

[0036] a noise adding module, configured to obtain first array data of an image sensed by a sensor, and add Gaussian noise to the first array data to obtain second array data;

[0037] a pixel capacitance array determination module, configured to perform functional relationship conversion on the second array data to obtain a pixel capacitance array, and then input the pixel capacitance array into a pre-trained convolutional neural network;

[0038] A convolution calculation module, configured to perform convolution calculation on the pixel capacitance array through a convolution layer of the convolutional neural network to obtain a sensor charge array;

[0039] a data conversion module, configured to perform data scaling on the sensor charge array to obtain third array data, perform nonlinear transformation on the third array data using the activation function of the convolutional neural network to obtain fourth array data, and further perform normalization processing on the fourth array data to obtain fifth array data;

[0040] A decoding module is used to decode the fifth array data through the decoding layer of the convolutional neural network to obtain a sensor-sensed image after noise reduction.

[0041] In a third aspect, an embodiment of the present invention provides a sensor-induced image noise reduction processing device, comprising:

[0042] at least one processor;

[0043] at least one memory for storing at least one program;

[0044] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned sensor-induced image noise reduction processing method.

[0045] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to execute the above-mentioned sensor-induced image noise reduction processing method when executed by the processor.

[0046] The advantages and benefits of the present invention will be described in part in the following description and will become apparent from the following description or learned through practice of the present invention:

[0047] The embodiment of the present invention adds Gaussian noise to the first array data of the sensor-sensed image to obtain the second array data, then performs functional relationship conversion on the second array data to obtain the pixel capacitance array, then inputs the pixel capacitance array into the trained convolutional neural network, performs convolution calculation on the pixel capacitance array through the convolution layer to obtain the sensor charge array, then performs data scaling on the sensor charge array to obtain the third array data, performs nonlinear transformation and normalization processing on the third array data to obtain the fifth array data, and finally decodes the sensor-sensed image after noise reduction through the decoding layer. The embodiment of the present invention utilizes the electrical characteristics of the capacitor and uses analog capacitance values ​​to participate in the calculation, which can effectively simplify circuit resources, speed up the calculation process in the neural network, and realize the noise reduction processing of the sensor-sensed image. It is also beneficial to speed up the calculation speed, reduce data bandwidth and simplify hardware resources during hardware mapping, reduce the requirements for system storage space and computing power, and improve the noise reduction processing efficiency of the sensor-sensed image. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 A flowchart of a method for denoising a sensor-induced image provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the convolutional neural network training and noise reduction process provided by an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of a capacitive sensor provided by an embodiment of the present invention introducing parasitic capacitance due to external stimulation;

[0052] Figure 4 A schematic diagram of a calculation process of a pixel capacitance array provided by an embodiment of the present invention;

[0053] Figure 5 A schematic diagram of the convolution calculation process provided by an embodiment of the present invention;

[0054] Figure 6 A schematic diagram of the encoding and decoding process provided by an embodiment of the present invention;

[0055] Figure 7 A structural block diagram of a sensor-induced image noise reduction processing system provided by an embodiment of the present invention;

[0056] Figure 8 This is a structural block diagram of a sensor-induced image noise reduction processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0058] In the description of the present invention, "a plurality" means two or more. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly indicating the number of the indicated technical features, or as implicitly indicating the order of the indicated technical features. Furthermore, unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art.

[0059] In capacitive pixel array sensors, parasitic capacitance is typically generated by external induction, causing the capacitance value of the capacitive pixels to change. A characteristic circuit measures the capacitance value of each pixel, converts it into digital data, and transmits it to the processor as the input feature image. The processor then runs a series of neural network algorithms to generate an optimized output image. Reading and converting each capacitance value into a digital value requires a significant amount of time, storing the capacitive array image data requires significant storage space, and performing image data recognition involves numerous convolution operations.

[0060] The embodiment of the present invention uses a capacitive fingerprint sensor as an example to describe the algorithm and circuit mapping. The capacitive fingerprint sensor is composed of a capacitor array, each unit is called a pixel, and the initial capacitance value of each capacitor is C0. When the fingerprint is pressed on the sensor, the finger brings parasitic capacitance to each capacitor, where the size of the parasitic capacitance is related to the distance from the epithelial cell layer of the finger to the sensor, that is, the groove fingerprint information of the finger will bring parasitic capacitance information to the sensor. The parasitic capacitance is connected in series with the initial capacitance, thereby changing the capacitance value of each pixel. Figure 3Figure 2 shows a schematic diagram of a capacitive sensor provided by an embodiment of the present invention that introduces parasitic capacitance in response to external stimuli. The wavy curve represents the skin of a finger, the capacitor Ci within the dashed box represents the parasitic capacitance introduced by the finger, and the capacitor C0 outside the dashed box represents the original capacitance. The capacitors form a series structure, and the non-series nodes of the parasitic capacitance are connected to the ground.

[0061] Reference Figure 1 The embodiment of the present invention provides a method for denoising a sensor-induced image, which specifically includes the following steps:

[0062] S101 , obtaining first array data of a sensor-sensed image, and adding Gaussian noise to the first array data to obtain second array data.

[0063] Specifically, the first array data is two-dimensional array data, which is used to simulate and represent the parasitic capacitance introduced by the capacitance array sensor when sensing the outside world.

[0064] As an optional embodiment, the second array data is calculated by the following formula:

[0065] P(ij)=[1+σ(Noise)×randn(0,1)]Q(ij)

[0066] Wherein, P(ij) represents the data in the i-th row and j-th column of the second array data, Q(ij) represents the data in the i-th row and j-th column of the first array data, σ(Noise) represents the preset noise coefficient, and randn(0,1) represents a random number generated by a Gaussian function with a center of 0 and a variance of 1.

[0067] Specifically, Gaussian noise is added to the first array data by multiplying each data point of the first array data by [1+(Noise)×randn(0,1)]. This can simulate the noise existing when the capacitor array in the real circuit receives external information, so that the parasitic capacitance value has a slight noise fluctuation.

[0068] S102 , performing functional relationship conversion on the second array data to obtain a pixel capacitance array, and then inputting the pixel capacitance array into a pre-trained convolutional neural network.

[0069] Specifically, the second array data is converted using the capacitance series formula. The output pixel capacitance array corresponds to the total capacitance after the parasitic capacitance and the original capacitance are connected in series. When mapped to the circuit, the capacitance array sensor generates parasitic capacitance when receiving external information. The parasitic capacitance and the original capacitance form a series structure. Therefore, the capacitance series formula is applied to calculate the total pixel capacitance.

[0070] As a further optional implementation, the pixel capacitance array is calculated using the following formula:

[0071] C(ij)=[P(ij)×C0] / [P(ij)+C0]

[0072] Wherein, C(ij) represents the data of the i-th row and j-th column in the pixel capacitance array, P(ij) represents the data of the i-th row and j-th column in the second array data, and C0 represents the original capacitance of the sensor.

[0073] Specifically, each data in the calculated pixel capacitance array corresponds to the series capacitance value of the parasitic capacitance and the original capacitance. Figure 4 A schematic diagram of a calculation process of a pixel capacitance array provided by an embodiment of the present invention is provided. Second array data is obtained by adding noise to first array data, and then data transformation is performed on the second array data to obtain a pixel capacitance array.

[0074] S103 , performing convolution calculation on the pixel capacitance array through the convolution layer of the convolutional neural network to obtain a sensor charge array.

[0075] Specifically, the convolution layer input is the pixel capacitance array converted using the capacitor series formula. The convolution kernel weight corresponds to the voltage applied to the pixel capacitance array, and the output corresponds to the charge on the pixel capacitance array. The convolution process is equivalent to applying a voltage to the capacitor and then obtaining the charge value. Convolution calculations are used to encode the sensor-sensed image.

[0076] As a further optional implementation, the step of performing convolution calculation on the pixel capacitance array through the convolution layer of the convolutional neural network to obtain the sensor charge array is specifically as follows:

[0077] Performing convolution calculation on the pixel capacitance array according to a preset first weight parameter to obtain a sensor charge array;

[0078] The first weight parameter is used to represent the voltage value applied to the sensor pixel capacitance.

[0079] Specifically, applying voltage to the pixel capacitor can collect charge. Collecting the pixel charge into a unified circuit structure can obtain the total charge. In this embodiment of the present invention, the convolution layer performs a convolution calculation on the capacitance data using the voltage data as the weight. When this process is performed on m×n pixels, the charge amount obtained is:

[0080]

[0081] Wherein, V represents the first weight parameter, which can also be in array form.

[0082] The above formula can simulate the calculation of the convolution window, such as Figure 5 FIG2 is a schematic diagram of a convolution calculation process provided by an embodiment of the present invention, wherein a sensor charge array is obtained through convolution calculation.

[0083] S104. Perform data scaling on the sensor charge array to obtain third array data, perform nonlinear transformation on the third array data through an activation function of a convolutional neural network to obtain fourth array data, and then perform normalization on the fourth array data to obtain fifth array data.

[0084] Specifically, the charge reading method can transfer the charge to a capacitor C_k of known capacity. At this time, the analog voltage across the capacitor is:

[0085] V A =Q / C_k

[0086] In order to read this voltage, an analog-to-digital converter is needed to convert the voltage into a digital value. The accuracy of the analog-to-digital converter is V LSB , the converted digital voltage data is:

[0087] V D =V A / V LSB

[0088] In this embodiment, the conversion of digital voltage is achieved by data scaling, and then nonlinear transformation is performed by activation function. Step S104 specifically includes the following steps:

[0089] S1041, divide the sensor charge array by a preset scaling factor to obtain third array data, where the scaling factor is C k ×V LSB ,in, k Indicates the capacitance value of the preset equivalent capacitor structure, V LSB Indicates the preset analog-to-digital converter accuracy;

[0090] S1042. Perform a nonlinear transformation on the third array data using a preset activation function to obtain fourth array data, where the activation function is one of a Sigmoid function, a Tanh function, and a ReLU function;

[0091] S1043 . Normalize the fourth array data using a batch normalization method to obtain fifth array data.

[0092] Specifically, the sensor charge array is divided by the scaling factor and then output. The scaling factor is C k ×V LSB , where the left term corresponds to the capacitance C k The equivalent capacitor structure, the charge divided by the capacitance corresponds to the voltage across the equivalent capacitor; the right-hand term corresponds to the use of the accuracy of V LSB The analog-to-digital converter reads the voltage across the equivalent capacitor to obtain binary data.

[0093] The obtained binary data of the voltage is passed to a digital processor for calculation of the activation function. At this time, no analog calculation and circuit parameter mapping are involved. The third array data is nonlinearly transformed by the activation function to obtain the fourth array data, and then the fourth array data is normalized by the batch normalization method to prevent the data range from being too large, which makes it difficult to converge during network training.

[0094] S105 , decoding the fifth array data through a decoding layer of a convolutional neural network to obtain a sensor-sensed image after noise reduction.

[0095] Specifically, steps S101 to S104 can be used to encode the sensor-sensed image. The decoding part uses a structure with two decoding layers and one activation layer to perform preliminary decoding, activation function conversion, and deep decoding on the fifth array data to obtain the sensor-sensed image after noise reduction. The output image size is the same as the original sensor-sensed image. Step S105 specifically includes the following steps:

[0096] S1051, performing preliminary decoding processing on the fifth array data using a deconvolution algorithm according to a preset second weight parameter to obtain sixth array data;

[0097] S1052, performing a nonlinear transformation on the sixth array data using a preset activation function to obtain seventh array data;

[0098] S1053 : Performing depth decoding processing on the seventh array data by using a deconvolution algorithm according to a preset third weight parameter to obtain a sensor-sensed image after noise reduction.

[0099] Specifically, the fifth array data is preliminarily decoded using the second weight parameter preset by the decoding layer, and the deconvolution algorithm, the upsampling layer (or the anti-pooling layer) and the convolution layer can be used as a combination algorithm to obtain the sixth array data after the preliminary decoding processing; the sixth array data is again converted to an activation function to obtain the seventh array data, wherein the activation function can be one of the ReLU function, the tanh function, and the Sigmoid function; the seventh array data is deeply decoded using the third weight parameter preset by the decoding layer, and the deconvolution algorithm, the upsampling layer (or the anti-pooling layer) and the convolution layer can be used as a combination algorithm to obtain the sensor-sensed image after noise reduction.

[0100] As an optional embodiment, the sensor-induced image noise reduction processing method further includes the step of training a convolutional neural network, which specifically includes:

[0101] A1. Determine the training data set and input it into the convolutional neural network to obtain the noise reduction result.

[0102] A2. Determine the loss value of the convolutional neural network based on the denoising results and the training dataset;

[0103] A3. Update the weight parameters of the convolutional layer and decoding layer through the back propagation algorithm according to the loss value;

[0104] A4. When the loss value reaches a preset first threshold or the number of iterations reaches a preset second threshold, training is stopped to obtain a trained convolutional neural network.

[0105] Specifically, a complete convolutional neural network encoding and decoding denoising process can be completed through the aforementioned steps S101 to S105, and to implement the training process of the convolutional neural network, it is also necessary to calculate the loss value and update the weight parameters. Figure 2 The figure shows a schematic diagram of the training and denoising process of the convolutional neural network provided by an embodiment of the present invention. In the embodiment of the present invention, the data processing process when training the convolutional neural network is similar to the data processing process during denoising, which will not be described in detail here. The difference is that when training the model, the loss value of the obtained denoising result and the original training data set is calculated, and then the gradient of the loss value to the weight parameter is calculated using the original weight parameter. The weight parameter is updated while adjusting the learning rate, and is output to the convolution layer and the decoding layer to replace the original weight parameter. The training is completed until the loss value reaches the preset first threshold or the number of iterations reaches the preset second threshold.

[0106] like Figure 6 The figure shows a schematic diagram of the encoding and decoding process provided by an embodiment of the present invention. The first array data of the original sensor-sensed image is converted into a pixel capacitance array by adding Gaussian noise and functional relationship. The pixel capacitance array is converted into a third array data by convolution calculation and data scaling. The third array data is converted into a fourth array data by nonlinear transformation, thereby completing the encoding process of the sensor-sensed image. The fourth array data is converted into a sixth array data by normalization processing and preliminary decoding processing. The sixth array data can obtain the noise-reduced sensor-sensed image by nonlinear transformation and deep decoding.

[0107] The above describes the method steps of the present invention. It can be recognized that the embodiments of the present invention utilize the electrical characteristics of capacitors and use analog capacitance values ​​to participate in calculations, which can effectively simplify circuit resources, speed up the calculation process in the neural network, and realize the noise reduction processing of sensor-sensed images. In addition, during hardware mapping, it is beneficial to speed up the calculation speed, reduce the data bandwidth, and simplify the hardware resources, thereby reducing the requirements for system storage space and computing power, and improving the noise reduction processing efficiency of sensor-sensed images.

[0108] Reference Figure 7 , an embodiment of the present invention provides a sensor-induced image noise reduction processing system, comprising:

[0109] a noise adding module, configured to obtain first array data of an image sensed by a sensor, and add Gaussian noise to the first array data to obtain second array data;

[0110] a pixel capacitance array determination module, configured to perform functional relationship conversion on the second array data to obtain a pixel capacitance array, and then input the pixel capacitance array into a pre-trained convolutional neural network;

[0111] A convolution calculation module is used to perform convolution calculation on the pixel capacitance array through the convolution layer of the convolutional neural network to obtain a sensor charge array;

[0112] a data conversion module, configured to perform data scaling on the sensor charge array to obtain third array data, perform nonlinear transformation on the third array data using an activation function of a convolutional neural network to obtain fourth array data, and further perform normalization processing on the fourth array data to obtain fifth array data;

[0113] The decoding module is used to decode the fifth array data through a decoding layer of a convolutional neural network to obtain a sensor-sensed image after noise reduction.

[0114] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0115] Reference Figure 8 , an embodiment of the present invention provides a sensor-induced image noise reduction processing device, comprising:

[0116] at least one processor;

[0117] at least one memory for storing at least one program;

[0118] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned sensor-induced image noise reduction processing method.

[0119] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0120] An embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor. When the program is executed by the processor, it is used to perform the above-mentioned sensor-induced image noise reduction processing method.

[0121] A computer-readable storage medium according to an embodiment of the present invention can execute a sensor-induced image noise reduction processing method provided by an embodiment of the method of the present invention, can execute any combination of implementation steps of the embodiment of the method, and has the corresponding functions and beneficial effects of the method.

[0122] The embodiment of the present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs Figure 1 The method shown.

[0123] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0124] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present invention set forth in the claims using ordinary skills without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0125] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0126] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0127] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable media on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0128] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0129] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0130] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0131] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for reducing noise in sensor-induced images, characterized in that: The following steps are involved: Acquire first array data of a sensor-sensed image, and add Gaussian noise to the first array data to obtain second array data; Performing a functional relationship conversion on the second array data to obtain a pixel capacitance array, and then inputting the pixel capacitance array into a pre-trained convolutional neural network; Performing convolution calculation on the pixel capacitance array through the convolution layer of the convolutional neural network to obtain a sensor charge array; performing data scaling on the sensor charge array to obtain third array data, performing nonlinear transformation on the third array data using the activation function of the convolutional neural network to obtain fourth array data, and further performing normalization processing on the fourth array data to obtain fifth array data; Decoding the fifth array data through a decoding layer of the convolutional neural network to obtain a sensor-sensed image after noise reduction; The pixel capacitance array is calculated by the following formula: in, represents the data of the i-th row and j-th column in the pixel capacitor array, represents the data in the i-th row and j-th column of the second array data, Represents the sensor raw capacitance.

2. The method for denoising a sensor-induced image according to claim 1, wherein: The second array data is calculated by the following formula: in, represents the data in the i-th row and j-th column of the second array data, represents the data in the i-th row and j-th column of the first array data, represents the preset noise figure, Represents a random number generated by a Gaussian function with center 0 and variance 1.

3. The method for denoising a sensor-induced image according to claim 1, wherein: The step of performing convolution calculation on the pixel capacitance array through the convolution layer of the convolutional neural network to obtain a sensor charge array is specifically as follows: Performing convolution calculation on the pixel capacitance array according to a preset first weight parameter to obtain the sensor charge array; The first weight parameter is used to represent the voltage value applied to the sensor pixel capacitance.

4. The method for denoising a sensor-induced image according to claim 1, wherein: The step of performing data scaling on the sensor charge array to obtain third array data, performing nonlinear transformation on the third array data using the activation function of the convolutional neural network to obtain fourth array data, and then normalizing the fourth array data to obtain fifth array data specifically includes: The sensor charge array is divided by a preset scaling factor to obtain a third array data, where the scaling factor is ,in, Indicates the capacitance value of the preset equivalent capacitance structure, Indicates the preset analog-to-digital converter accuracy; Performing a nonlinear transformation on the third array data using a preset activation function to obtain fourth array data, wherein the activation function is one of a Sigmoid function, a Tanh function, and a ReLU function; The fourth array data is normalized by a batch normalization method to obtain fifth array data.

5. The method for denoising a sensor-induced image according to claim 1, wherein: The step of decoding the fifth array data through the decoding layer of the convolutional neural network to obtain a noise-reduced sensor-sensed image specifically includes: Performing preliminary decoding processing on the fifth array data using a deconvolution algorithm according to a preset second weight parameter to obtain sixth array data; Performing a nonlinear transformation on the sixth array data using a preset activation function to obtain seventh array data; The seventh array data is subjected to a depth decoding process by a deconvolution algorithm according to a preset third weight parameter to obtain a sensor-sensed image after noise reduction.

6. A sensor-induced image noise reduction processing method according to any one of claims 1 to 5, characterized in that: The sensor-induced image noise reduction processing method further includes the step of training a convolutional neural network, which specifically includes: Determining a training data set, inputting the training data set into the convolutional neural network to obtain a noise reduction processing result; Determining a loss value of the convolutional neural network according to the denoising result and the training data set; Updating weight parameters of the convolutional layer and the decoding layer through a back propagation algorithm according to the loss value; When the loss value reaches a preset first threshold or the number of iterations reaches a preset second threshold, the training is stopped and a trained convolutional neural network is obtained.

7. A sensor-induced image noise reduction processing system, characterized in that: include: a noise adding module, configured to obtain first array data of an image sensed by a sensor, and add Gaussian noise to the first array data to obtain second array data; a pixel capacitance array determination module, configured to perform functional relationship conversion on the second array data to obtain a pixel capacitance array, and then input the pixel capacitance array into a pre-trained convolutional neural network; A convolution calculation module, configured to perform convolution calculation on the pixel capacitance array through a convolution layer of the convolutional neural network to obtain a sensor charge array; a data conversion module, configured to perform data scaling on the sensor charge array to obtain third array data, perform nonlinear transformation on the third array data using the activation function of the convolutional neural network to obtain fourth array data, and further perform normalization processing on the fourth array data to obtain fifth array data; a decoding module, configured to decode the fifth array data through a decoding layer of the convolutional neural network to obtain a sensor-sensed image after noise reduction; The pixel capacitance array is calculated by the following formula: in, represents the data of the i-th row and j-th column in the pixel capacitor array, represents the data in the i-th row and j-th column of the second array data, Represents the sensor raw capacitance.

8. A sensor-induced image noise reduction processing device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the sensor-induced image noise reduction processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to perform a sensor-induced image noise reduction processing method according to any one of claims 1 to 6 when executed by the processor.

Images