WO2021134874A1 - 二维码去摩尔纹的深度残差网络的训练方法 - Google Patents

二维码去摩尔纹的深度残差网络的训练方法 Download PDF

Info

Publication number
WO2021134874A1
WO2021134874A1 PCT/CN2020/076819 CN2020076819W WO2021134874A1 WO 2021134874 A1 WO2021134874 A1 WO 2021134874A1 CN 2020076819 W CN2020076819 W CN 2020076819W WO 2021134874 A1 WO2021134874 A1 WO 2021134874A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
dimensional code
code image
moiré
residual
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/076819
Other languages
English (en)
French (fr)
Inventor
陈昌盛
陆涵
黄继武
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen University
Original Assignee
Shenzhen University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen University filed Critical Shenzhen University
Publication of WO2021134874A1 publication Critical patent/WO2021134874A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
    • G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
    • G06K19/06009—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code with optically detectable marking
    • G06K19/06037—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code with optically detectable marking multi-dimensional coding
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
    • G06K7/1417—2D bar codes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/146—Methods for optical code recognition the method including quality enhancement steps
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Definitions

  • the present disclosure generally relates to a training method of a deep residual network for removing moiré in a two-dimensional code.
  • Multiphase component layer decomposition technology is used to remove the moiré in the image captured by the camera; the wavelet domain filtering method is used to remove the moiré in the scanned image; The image restoration method realizes the moiré removal.
  • LDPC Multiphase component layer decomposition technology
  • Multi-phase component layer decomposition technology is used to solve the problem of moiré removal, the removal effect is not obvious and the details of the original image will be smoothed, that is, the restored image has a certain degree of distortion.
  • image restoration methods such as reference denoising adaptive encoder to remove moiré, while removing the moiré in the high-frequency range, the high-frequency components of the original image will also be removed. Because the image loses high-frequency information, there will also be a certain amount of blur. None of the above technologies can completely avoid the moiré removal without affecting the original image content.
  • the present invention aims to provide a training method for a deep residual network that can effectively remove moiré in a two-dimensional code.
  • the present disclosure provides a method for training a deep residual network for removing moiré in a two-dimensional code, which includes: preparing an original two-dimensional code image with moiré; preparing to process the original two-dimensional code
  • the network device includes a preprocessing module, a first residual module, a second residual module, and a third residual module; the original two-dimensional code image is input into the preprocessing module, and the original
  • the two-dimensional code image is blurred to increase the pixels in the two-dimensional code area in the simulated two-dimensional code image, and then down-sampling is performed to form a pre-processed image with reduced image; then the pre-processed image is input to the first residual image
  • the difference module performs up-sampling processing to form a first output image whose image size is enlarged to the size of the original two-dimensional code image; then the first output image is input to the second residual module to form a restoration of the first output image.
  • the residual module performs a purification process to form a moiré-removed image.
  • the pre-processed image is processed by the first residual module, the second residual module and the third residual module in the deep residual network, which can conveniently and effectively remove the moire in the original two-dimensional code image. Pattern.
  • the first residual module includes a convolution kernel connected in sequence with a size of 3 ⁇ 3 and 64
  • the third convolutional layer with a convolution kernel size of 3 ⁇ 3 and 256 feature maps, a fourth convolution layer with a convolution kernel size of 1 ⁇ 1 and 3 feature maps, and a tanh activation layer can be removed more effectively.
  • the second residual module includes 10 successively connected layers consisting of a convolution kernel with a size of 5 ⁇ 5.
  • the convolutional layer with 64 feature maps and the second ReLU activation layer are concatenated into the first combined layer and 10 layers are activated by the convolutional layer with a convolution kernel size of 3 ⁇ 3 and 64 feature maps and the third ReLU
  • the second combination layer formed by series connection. In this way, it is possible to restore the image information lost in the first output image.
  • the third residual module includes a convolution kernel connected in sequence with a size of 3 ⁇ 3 and 128
  • the original two-dimensional code image is a synthesized simulated two-dimensional code image.
  • the original two-dimensional code image can be generated more conveniently.
  • the formation of the simulated two-dimensional code image includes the following steps: re-sampling the input image to generate a A mosaic composed of RGB pixels and displayed on the display; random projection transformation is used to simulate the different relative positions and directions between the display and the camera; the radiation distortion function is used to simulate the distortion of the camera lens; a flat top is used Gaussian filter to simulate anti-aliasing filtering; re-sampling the input image to simulate the input of the camera sensor; adding Gaussian noise to the input image to simulate sensor noise; demosaicing processing; using a denoising filter for processing Denoising processing; compressing the input image; and outputting a decompressed image to form the simulated two-dimensional code image.
  • the simulated two-dimensional code image can be generated more conveniently.
  • the two-dimensional code image on the display corresponding to the input image uses the same The projection transformation and the lens distortion function are processed. As a result, it is possible to easily obtain the two-dimensional code image on the display corresponding to the input image one-to-one.
  • the mean square error function is used.
  • M and N are the height and width of the simulated two-dimensional code image
  • H(G(I)) is the two-dimensional code image output by the deep residual network
  • J is and The two-dimensional code image on the display corresponding to the simulated two-dimensional code image is stored, and the model and parameters of the deep residual network when the training loss is the least are stored. Therefore, the deep residual network can be effectively trained.
  • the training method of the deep residual network for removing the moiré of the two-dimensional code involved in the present disclosure optionally, it also includes a real two-dimensional code image with moiré, based on the minimum training loss.
  • the model and parameters of the deep residual network and use the real two-dimensional code image to perform a migration learning operation on the deep residual network. As a result, the deep residual network can be trained more effectively.
  • the angle transformation is performed on the real two-dimensional code image to obtain the same image as the real two-dimensional code image.
  • a corresponding two-dimensional code image on the display In this way, it is possible to obtain the two-dimensional code image on the display corresponding to the real two-dimensional code image one-to-one.
  • the pre-processed image is processed by the first residual module, the second residual module and the third residual module in the deep residual network, which can conveniently and effectively remove the moire in the original two-dimensional code image. Pattern.
  • FIG. 1 is a schematic diagram showing the modules of the deep residual network involved in this embodiment.
  • FIG. 2 is a schematic diagram showing the specific structure of the deep residual network involved in this embodiment.
  • FIG. 3 is a schematic flowchart showing a method for training a deep residual network for removing moiré in a two-dimensional code according to this embodiment.
  • FIG. 4(a) is a schematic diagram showing the synthesized simulated two-dimensional code image related to this embodiment
  • FIG. 4(b) is a diagram showing the de-moiré image related to FIG. 4(a) related to this embodiment. .
  • FIG. 5(a) is a schematic diagram showing a captured image according to this embodiment
  • FIG. 5(b) is a schematic diagram showing a reconstructed image according to this embodiment
  • FIG. 5(c) is a schematic diagram showing the image The embodiment relates to the de-moiré image of FIG. 5(a).
  • Network device preprocessing module...10, first residual module...20, second residual module...30, first combination layer...31, second combination layer...32, third residual module...40.
  • FIG. 1 is a schematic diagram showing a module of a network device 1 related to this embodiment.
  • FIG. 2 is a schematic diagram showing a specific structure of the network device 1 according to this embodiment.
  • FIG. 3 is a schematic flowchart showing a training method for removing moiré from a two-dimensional code based on the network device 1 according to this embodiment.
  • the present disclosure designs a training method of a deep residual network based on the two-dimensional code moiré removal of the network device 1.
  • the network device 1 of the present disclosure may include a preprocessing module 10, a first residual module 20, a second residual module 30, and a third residual module 40, the preprocessing module 10, the first residual module The module 20, the second residual module 30, and the third residual module 40 are connected in series in sequence.
  • the training method of the deep residual network for removing the moiré of the two-dimensional code of the present disclosure includes the following steps: preparing an original two-dimensional code image I with moiré (step S100); preparing a network device for processing the original two-dimensional code ,
  • the network device includes a preprocessing module, a first residual module, a second residual module, and a third residual module (step S200);
  • the original two-dimensional code image I is input into the preprocessing module 10
  • the original two-dimensional code image I perform blur processing to increase the pixels in the QR code area in the simulated two-dimensional code image, and then perform down-sampling processing to form a reduced image preprocessed image I'(step S300); then input the preprocessed image I'to the first
  • the residual module 20 performs up-sampling processing to form a first output image whose image size is enlarged to the size of the original two-dimensional code image I (step S400); then the first output image is input to the second residual module 30 to form a restored first
  • step S500 Output the second output image of the missing image information of the image (step S500); and then perform feature fusion of the second output image and the original two-dimensional code image I to form a feature fusion image, and then input the feature fusion image to the third residual module 40 performs a purification process to form a moiré-removed image (step S600).
  • the first residual module 20, the second residual module 30, and the third residual module 40 in the network device 1 process the preprocessed image I', which can easily and effectively remove the original two-dimensional code. Moiré in image I.
  • the lost image information of the first output image may be, for example, the lack of pixel points, the loss of pixel coordinates, and the like.
  • the first residual module 20 may include a first convolutional layer with a convolution kernel size of 3 ⁇ 3 and 64 feature maps, a first ReLU (modified linear unit) activation layer, and a concatenated 16 residual blocks, a second convolutional layer with a convolution kernel size of 3 ⁇ 3 and 64 feature maps, a batch normalization layer (Batch Norm), a convolution kernel size of 3 ⁇ 3 and 256 features
  • the first residual module 20 can be used to remove moiré in the pre-processed image I′ that is significantly different from the pre-processed image I′, such as some colored band-shaped moiré.
  • the size of the convolution kernel and the number of feature maps in the first residual module 20 are not fixed, and can be adjusted according to different network devices 1 to be trained, and there is no limitation here.
  • the second residual module 30 may include 10 successively connected layers, a first combination layer composed of a convolutional layer with a convolution kernel size of 5 ⁇ 5 and 64 feature maps and a second ReLU activation layer in series.
  • the 31 and 10 layers are a second combination layer 32 composed of a convolutional layer with a convolution kernel size of 3 ⁇ 3 and 64 feature maps and a third ReLU activation layer in series.
  • each layer of the 10-layer first combination layer 31 can be composed of a convolutional layer with a size of 5 ⁇ 5 and 64 feature maps and a second ReLU activation layer in series, and then 10 layers
  • each layer of the 10-layer second combination layer 32 can be composed of a convolutional layer with a size of 3 ⁇ 3 and 64 feature maps and a layer
  • the third ReLU activation layer is connected in series, and then each of the 10 layers is connected in series to form the second combined layer 32.
  • the second residual module 30 can be used to restore the lost detail information of the first output image.
  • the size of the convolution kernels and the number of feature maps in the first combination layer 31 and the second combination layer 32 are not fixed, and can be adjusted according to the network device 1 to be trained, and there is no limitation here.
  • the third residual module 40 may include a fifth convolution layer with a convolution kernel size of 3 ⁇ 3 and 128 feature maps, a fourth ReLU activation layer, and a convolution kernel size of 3 ⁇ 3. 3 and a sixth convolutional layer with 3 feature maps.
  • the input to the third residual module 40 is the second output image and the original two-dimensional code image I, that is, the second output image and the original two-dimensional code image I are feature-fused and input to the third residual module 40.
  • two convolutional layers can be used to purify the second output image and the original two-dimensional code image I to further remove some comparative rules and moiré that is not easily separated from the original two-dimensional code image I.
  • the final moiré-removed de-moiré image is obtained.
  • FIG. 4(a) is a schematic diagram showing a synthesized pseudo two-dimensional code image according to this embodiment
  • FIG. 4(b) is a diagram showing a de-moiré image related to figure (a) according to this embodiment.
  • the original two-dimensional code image I is a synthesized simulated two-dimensional code image. As a result, the original two-dimensional code image I can be generated more conveniently.
  • the formation of a simulated two-dimensional code image includes the following steps: re-sampling the input image to generate a mosaic composed of RGB pixels, and display it on the display; random projection transformation to simulate the difference between the display and the camera The relative position and direction of the camera; use the radiation distortion function to simulate the distortion of the camera lens; use a flat-top Gaussian filter to simulate anti-aliasing filtering; resample the input image to simulate the input of the camera sensor; add Gaussian noise to the input image To simulate sensor noise; demosaicing; using denoising filters for denoising; compressing the input image; and outputting the decompressed image to form a simulated two-dimensional code image.
  • the simulated two-dimensional code image can be generated more conveniently.
  • bayer CFA may be used to resample the input image to simulate the input of the camera sensor.
  • the input image may be compressed in JPEG, TIFF, RAW, and other formats.
  • the two-dimensional code image on the display corresponding to the input image can be processed using the same projection transformation and lens distortion function. Since it is necessary to simulate a one-to-one correspondence between the two-dimensional code image and the two-dimensional code image on the display to train the network device 1, the same projection transformation and lens distortion function can be used to process the two-dimensional code image on the display .
  • the mean square error function can be used Train the network device 1 as a loss function, where M and N are the height and width of the simulated two-dimensional code image, H(G(I')) is the two-dimensional code image output by the network device 1, and J is the same as the simulated two-dimensional code image Corresponding to the two-dimensional code image on the display, and save the model and parameters of the network device 1 when the training loss is the smallest. As a result, the network device 1 can be effectively trained.
  • the loss function can also be implemented by a loss function, or a cross-entropy loss function, an exponential loss function, or a Hinge loss function (SVM), which can be selected according to actual conditions in specific applications, and there is no limitation here.
  • a loss function or a cross-entropy loss function, an exponential loss function, or a Hinge loss function (SVM), which can be selected according to actual conditions in specific applications, and there is no limitation here.
  • SVM Hinge loss function
  • the simulated two-dimensional code image can be input to the network device 1 as the original image I for training, so as to obtain the corresponding moiré image (as shown in FIG. 4(b)).
  • the network device 1 As a result, it is possible to reduce the difficulty caused by a real two-dimensional code image using a large amount of data.
  • FIG. 5(a) is a schematic diagram showing a captured image according to this embodiment
  • FIG. 5(b) is a schematic diagram showing a reconstructed image according to this embodiment
  • FIG. 5(c) is a schematic diagram showing the image The embodiment relates to the de-moiré image of FIG. 5(a).
  • the network device 1 model proposed in the present disclosure can be divided into two stages: (a) A large number of simulated two-dimensional code images with synthetic moiré are used to pair the network. Carry out pre-training (refer to the training of the simulated two-dimensional code image as above), so that the network can play the performance of removing moiré for the two-dimensional code. (b) Considering the characteristics of the moiré in the real environment, a relatively small amount of real-photographed real two-dimensional code images with moiré can be used in training for migration learning (Fine-tune) based on the network device 1, so that the network can target the real image The moiré pattern has a more ideal removal effect. The network device 1 trained in two stages can achieve good de-moiring performance on real-photographed two-dimensional code images with moiré.
  • the present disclosure may also include a real two-dimensional code image with moiré, based on the model and parameters of the network device 1 when the training loss is minimal, and use the real two-dimensional code image to perform the network device 1 Transfer learning operation.
  • the network device 1 can be trained more effectively.
  • the migration learning operation is detailed below.
  • the network After pre-training the network with the simulated two-dimensional code image, the network has the function of removing moiré, but the simulated two-dimensional code image cannot fully simulate the situation in the real environment, so it is necessary to use the real two-dimensional code image captured
  • the network is fine-tuned to enable the network to exert practical effects while enhancing the robustness of the network.
  • the model and parameters at the time of the minimum loss during the pre-training process are saved, and on this basis, the real two-dimensional code image with moiré is used to perform the migration learning operation on the network.
  • the network device 1 Since the network device 1 is a supervised learning method, the input and output images of the network should have no other difference except whether there is moiré or not. However, it is difficult to find the matching label for the real two-dimensional code image that is actually shot, so it can be used
  • the fixed modules in the two-dimensional code: the positioning pattern, the calibration pattern and the detection pattern are used for angular transformation of the captured two-dimensional code image so that it can correspond one-to-one with the two-dimensional code image on the display.
  • the reconstructed image (as shown in Figure 5(b)) after the angle transformation is used as the network input of the migration learning stage, and the corresponding two-dimensional code image on the screen is used as the network output.
  • the transfer learning process still uses the mean square error (MSE) function as the loss function. After the transfer learning operation of the real data (real two-dimensional code image), the network can have a more ideal removal effect on the moiré in the real shooting environment.
  • MSE mean square error
  • the batchsize can be 4, the number of iterations can be 12 ⁇ 10 5 times, the learning rate can be 10 -5 , and the optimizer can be Adam.
  • the deep learning framework tensorflow can be used to implement the network device 1.
  • the training and testing environment of the present disclosure may be a server equipped with NVIDIA Tesla P100 GPU and Intel Xeon E5-2695 v4 CPU.
  • the Dell U2414H display can be used to display different QR code images, and three smart phones (Apple iPhone 8plus, Huawei MI 8, Meizu m1 metal, etc.) can be used to capture the QR code images.
  • Fig. 5(a) in some examples, 10,000 real moiré real two-dimensional code images can be collected to perform migration learning operations on the network device 1, so that the network can perform better demolition The effect of the pattern.
  • the corresponding reconstructed image is shown in Figure 5(b).
  • a real two-dimensional code image taken by a mobile phone and other devices can be used as input, and the reconstructed image can be obtained by performing perspective transformation, angle transformation, and other operations to obtain a reconstructed image, which can be used as the input of the network device 1 for migration learning .
  • the trained network device 1 can have a more ideal removal effect on the two-dimensional code image taken in the real environment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Electromagnetism (AREA)
  • Toxicology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Image Processing (AREA)

Abstract

一种二维码去摩尔纹的深度残差网络的训练方法，其包括：准备带有摩尔纹的原始二维码图像(S100)；将原始二维码图像输入预处理模块，接着进行下采样处理以形成图像缩小的预处理图像(S300)；接着将预处理图像输入至第一残差模块进行上采样处理以形成图像大小放大至原始二维码图像大小的第一输出图像(S400)；接着将第一输出图像输入至第二残差模块以形成恢复第一输出图像丢失的图像信息的第二输出图像(S500)；并且接着将第二输出图像和原始二维码图像进行特征融合以形成特征融合图像，接着将特征融合图像输入第三残差模块进行提纯处理以形成去除摩尔纹的去摩尔纹图像(S600)。由此，能够更有效的去除原始二维码图像中的摩尔纹。

Description

二维码去摩尔纹的深度残差网络的训练方法 技术领域
本公开大体涉及一种二维码去摩尔纹的深度残差网络的训练方法。
背景技术
目前，去除图像中的摩尔纹常用到三种方法，采用多相分量的层分解技术(LDPC)，来针对相机拍摄所得图像去摩尔纹；采用小波域滤波的方法对扫描图像去摩尔纹；采用图像还原方法实现去摩尔纹。
上述三种方法，都可以不同程度实现去除图像中的摩尔纹，但同时也存在以下三方面的局限性：
(1)降低了去摩尔纹技术在通用性上的优势。采用多相分量的层分解技可实现相机拍摄图像上摩尔纹的去除。但实际上这项技术只能去除少量的摩尔纹干扰，不能对存在大规模摩尔纹干扰的图像中发挥明显作用，尤其不能对摩尔纹彩色带起作用，且最终会平滑图像细节。采用小波域滤波可对扫描图像去摩尔纹，但针对的摩尔纹必须是网状结构的。采用传统的图像还原方法或者对DnCNN(去噪卷积神经网络)进行改进实现去摩尔纹，由于这些模型并非专门针对去摩尔纹问题进行设计，只能实现次优的性能。实际上的摩尔纹是各向异性且随机变化的，上述技术只能针对特定的摩尔纹式样解决去摩尔纹问题，存在一定的局限性。
(2)无法彻底避免对原图像造成的影响。采用多相分量的层分解技术解决去摩尔纹问题，去除效果不明显且会平滑原图像的细节，即恢复出来的图像存在一定的失真。采用图像还原方法例如参考去噪的自适应编码器进行去摩尔纹，在去除高频带范围的摩尔纹的同时，也会去除原图像的高频成分。由于图像丢失高频信息，也会存在一定的模糊。上述技术均无法彻底避免在去摩尔纹的同时不对原图像内容造成影响。
(3)增加了使用复杂度。由于摩尔纹是各向异性，且非均匀的。 对于一副摩尔纹多样的图像，我们得通过多种现有技术的结合，使它们分别针对不同的摩尔纹式样发挥作用。这种做法增加了去摩尔纹问题的复杂度，需要多个步骤才能实现去摩尔纹，且无法实现较好的去除效果。
发明内容
本发明有鉴于上述现有的状况，其目的在于提供一种能够有效去除二维码中摩尔纹的深度残差网络的训练方法。
为此，本公开提供一种二维码去摩尔纹的深度残差网络的训练方法，其包括：准备带有摩尔纹的原始二维码图像；准备用于对所述原始二维码进行处理的网络装置，所述网络装置包括预处理模块、第一残差模块、第二残差模块以及第三残差模块；将所述原始二维码图像输入所述预处理模块，对所述原始二维码图像进行模糊处理以增加仿真二维码图像中二维码区域的像素，接着进行下采样处理以形成图像缩小的预处理图像；接着将所述预处理图像输入至所述第一残差模块进行上采样处理以形成图像大小放大至所述原始二维码图像大小的第一输出图像；接着将所述第一输出图像输入至所述第二残差模块以形成恢复所述第一输出图像丢失的图像信息的第二输出图像；并且接着将所述第二输出图像和所述原始二维码图像进行特征融合以形成特征融合图像，接着将所述特征融合图像输入所述第三残差模块进行提纯处理以形成去除摩尔纹的去摩尔纹图像。
在本公开中，通过深度残差网络中的第一残差模块、第二残差模块和第三残差模块对预处理图像进行处理，能够方便且有效的去除原始二维码图像中的摩尔纹。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，所述第一残差模块包括依次连接的卷积核大小为3×3且具有64个特征映射的第一卷积层、第一ReLU激活层、串联的16个残差块、卷积核大小为3×3且具有64个特征映射的第二卷积层、批归一化层、卷积核大小为3×3且具有256个特征映射的第三卷积层、卷积核大小为1×1且具有3个特征映射的第四卷积层以及tanh激活层。由此，能够更有效地去除预处理图像中的摩尔纹。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，所述第二残差模块包括依次连接的10层由卷积核大小为5×5且具有64个特征映射的卷积层和第二ReLU激活层串联成的第一组合层以及10层由卷积核大小为3×3且具有64个特征映射的卷积层和第三ReLU激活层串联成的第二组合层。由此，能够回复第一输出图像丢失的图像信息。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，所述第三残差模块包括依次连接的卷积核大小为3×3且具有128个特征映射的第五卷积层、第四ReLU激活层、卷积核大小为3×3且具有3个特征映射的第六卷积层。由此，能够有效的去除第二输出图像中的摩尔纹。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，所述原始二维码图像为合成的仿真二维码图像。由此，能够更方便地生成原始二维码图像。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，所述仿真二维码图像的形成包括如下步骤：对输入图像重新采样以生成一个由RGB像素组成的嵌合体，并显示在显示器上；随机作投影变换来模拟所述显示器和相机之间不同的相对位置和方向；使用放射失真函数来模拟所述相机的镜头的失真；采用平顶高斯滤波器来模拟抗混叠滤波；对所述输入图像重新采样以模拟所述相机传感器的输入；在所述输入图像上增加高斯噪声来模拟传感器噪声；去马赛克处理；采用去噪滤波器进行去噪处理；压缩所述输入图像；以及输出解压缩图像以形成所述仿真二维码图像。由此，能够更方便的生成仿真二维码图像。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，与所述输入图像相对应的所述显示器上的二维码图像使用相同的所述投影变换和所述镜头失真函数进行处理。由此，能够方便得到与输入图像一一对应的显示器上的二维码图像。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，采用均方差函数
Figure PCTCN2020076819-appb-000001
作为损失函数训 练所述深度残差网络，其中M和N是所述仿真二维码图像的高和宽，H(G(I))是深度残差网络输出的二维码图像，J是与所述仿真二维码图像相对应的显示器上的二维码图像，且保存训练的损失最小时的所述深度残差网络的模型和参数。由此，能够有效的训练该深度残差网络。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，还包括带有摩尔纹的真实二维码图像，基于训练的损失最小时的所述深度残差网络的模型和参数，并利用所述真实二维码图像对所述深度残差网络进行迁移学习操作。由此，能够更有效地训练该深度残差网络。
另外，在本公开所涉及的二维码去摩尔纹的深度残差网络的训练方法中，可选地，对所述真实二维码图像进行角度变换，得到与所述真实二维码图像一一对应的显示器上的二维码图像。由此，能够得到与真实二维码图像一一对应的显示器上的二维码图像。
在本公开中，通过深度残差网络中的第一残差模块、第二残差模块和第三残差模块对预处理图像进行处理，能够方便且有效的去除原始二维码图像中的摩尔纹。
附图说明
现在将仅通过参考附图的例子进一步详细地解释本公开的实施例，其中：
图1是示出了本实施方式所涉及的深度残差网络的模块示意图。
图2是示出了本实施方式所涉及的深度残差网络的具体结构示意图。
图3是示出了本实施方式所涉及的二维码去摩尔纹的深度残差网络的训练方法的流程示意图。
图4(a)是示出了本实施方式所涉及的合成的仿真二维码图像的示意图，图4(b)是示出了本实施方式所涉及的关于图4(a)去摩尔纹图像。
图5(a)是示出了本实施方式所涉及的拍摄图像的示意图，图5(b)是示出了本实施方式所涉及的重建图像的示意图，图5(c)是示出了本实施方式所涉及的关于图5(a)的去摩尔纹图像。
符号说明：
网络装置…1，预处理模块…10，第一残差模块…20，第二残差模块…30，第一组合层…31，第二组合层…32，第三残差模块…40。
具体实施方式
以下，参考附图，详细地说明本公开的优选实施方式。在下面的说明中，对于相同的部件赋予相同的符号，省略重复的说明。另外，附图只是示意性的图，部件相互之间的尺寸的比例或者部件的形状等可以与实际的不同。
图1是示出了本实施方式所涉及的网络装置1的模块示意图。图2是示出了本实施方式所涉及的网络装置1的具体结构示意图。图3是示出了本实施方式所涉及的基于网络装置1的二维码去摩尔纹的训练方法的流程示意图。
采用数字相机或智能手机等对光电显示器(或显示屏)进行拍摄可方便我们记录和传输数据，然而，由于相机传感器和显示器设备之间的像素格子不能完全匹配，拍摄所得的图像往往存在摩尔纹样式的图样干扰。现有的去摩尔纹技术大都针对自然图像进行处理，且效果不是特别理想。基于图像二维码构建显示-拍摄通信信道是一个热点问题，然而摩尔纹失真严重阻碍了该类通信系统的有效性。经调研发现目前尚未有针对二维码提出的去摩尔纹技术。
针对上述问题，本公开设计了一个基于网络装置1的二维码去摩尔纹的深度残差网络的训练方法。参照图1至图3，本公开的网络装置1可以包括预处理模块10、第一残差模块20、第二残差模块30以及第三残差模块40，预处理模块10、第一残差模块20、第二残差模块30以及第三残差模块40依次串联。
本公开二维码去摩尔纹的深度残差网络的训练方法包括如下步骤：准备带有摩尔纹的原始二维码图像I(步骤S100)；准备用于对原始二维码进行处理的网络装置，该网络装置包括预处理模块、第一残差模块、第二残差模块以及第三残差模块(步骤S200)；将原始二维码图像I输入预处理模块10，对原始二维码图像I进行模糊处理以增加仿真二维码图像中二维码区域的像素，接着进行下采样处理以形成图像缩小 的预处理图像I'(步骤S300)；接着将预处理图像I'输入至第一残差模块20进行上采样处理以形成图像大小放大至原始二维码图像I大小的第一输出图像(步骤S400)；接着将第一输出图像输入至第二残差模块30以形成恢复第一输出图像丢失的图像信息的第二输出图像(步骤S500)；并且接着将第二输出图像和原始二维码图像I进行特征融合以形成特征融合图像，接着将特征融合图像输入第三残差模块40进行提纯处理以形成去除摩尔纹的去摩尔纹图像(步骤S600)。
在本公开中，通过网络装置1中的第一残差模块20、第二残差模块30和第三残差模块40对预处理图像I'进行处理，能够方便且有效的去除原始二维码图像I中的摩尔纹。
在一些示例中，第一输出图像丢失的图像信息例如可以是像素点的缺失、像素点坐标的丢失等。
在一些示例中，第一残差模块20可以包括依次连接的卷积核大小为3×3且具有64个特征映射的第一卷积层、第一ReLU(修正线性单元)激活层、串联的16个残差块、卷积核大小为3×3且具有64个特征映射的第二卷积层、批归一化层(Batch Norm)、卷积核大小为3×3且具有256个特征映射的第三卷积层、卷积核大小为1×1且具有3个特征映射的第四卷积层以及tanh(双曲正切)激活层。在这种情况下，可以利用第一残差模块20去除预处理图像I'中与预处理图像I'差异明显的摩尔纹，例如一些彩色的带状摩尔纹。当然，第一残差模块20中的卷积核的大小和特征映射的个数并不固定，可以根据训练的网络装置1的不同进行调整，此处不做限制。
在一些示例中，第二残差模块30可以包括依次连接的10层由卷积核大小为5×5且具有64个特征映射的卷积层和第二ReLU激活层串联成的第一组合层31以及10层由卷积核大小为3×3且具有64个特征映射的卷积层和第三ReLU激活层串联成的第二组合层32。也即，10层第一组合层31的每层都可以由一层大小为5×5且具有64个特征映射的卷积层和一层第二ReLU激活层串联而成，然后再将10层中的每一层串联起来形成第一组合层31；同样的，10层第二组合层32的每层都可以由一层大小为3×3且具有64个特征映射的卷积层和一层第三ReLU激活层串联而成，然后再将10层中的每一层串联起来形成 第二组合层32。在这种情况下，可以利用第二残差模块30来恢复第一输出图像丢失的细节信息。当然，第一组合层31和第二组合层32中卷积核的大小和特征映射的个数并不固定，可以根据训练的网络装置1的不同进行调整，此处不做限制。
在一些示例中，第三残差模块40可以包括依次连接的卷积核大小为3×3且具有128个特征映射的第五卷积层、第四ReLU激活层、卷积核大小为3×3且具有3个特征映射的第六卷积层。由此，能够有效的去除第二输出图像中的摩尔纹。输入第三残差模块40的为第二输出图像和原始二维码图像I，也即将第二输出图像和原始二维码图像I进行特征融合并输入第三残差模块40。在这种情况下，可以使用两个卷积层对第二输出图像和原始二维码图像I进行提纯处理，以进一步去除一些比较规律以及和原始二维码图像I不易分离的摩尔纹，以得到最终的去除摩尔纹的去摩尔纹图像。
图4(a)是示出了本实施方式所涉及的合成的仿真二维码图像的示意图，图4(b)是示出了本实施方式所涉及的关于图(a)去摩尔纹图像。
参照图4(a)和图4(b)，在一些示例中，原始二维码图像I为合成的仿真二维码图像。由此，能够更方便地生成原始二维码图像I。
可以理解的是，为了使本公开网络装置1更加精确地识别真实环境中的摩尔纹，理想情况下我们只能使用真实拍摄的图像和与之相对应的显示器上的图像构成的图像对来训练该网络装置1。然而获取在空间位置上完全匹配的图像对是比较困难的，网络很容易将不匹配的边缘错误识别成摩尔纹，而且真实拍摄的图像存在许多共同的问题：镜头失真、相机抖动等，这些都会严重影响到图像对的对齐。考虑到使用真实图像构建高质量的大型图像集的难度，我们采用带有真实摩尔纹的仿真二维码图像来训练网络。为了更加准确地模拟摩尔纹生成过程，我们严格执行从图像显示在LCD显示器上到使用相机拍摄图像再到相机内部的数字处理整个流程。
在一些实例中，仿真二维码图像的形成包括如下步骤：对输入图像重新采样以生成一个由RGB像素组成的嵌合体，并显示在显示器上；随机作投影变换来模拟显示器和相机之间不同的相对位置和方向；使 用放射失真函数来模拟相机的镜头的失真；采用平顶高斯滤波器来模拟抗混叠滤波；对输入图像重新采样以模拟相机传感器的输入；在输入图像上增加高斯噪声来模拟传感器噪声；去马赛克处理；采用去噪滤波器进行去噪处理；压缩输入图像；以及输出解压缩图像以形成仿真二维码图像。由此，能够更方便的生成仿真二维码图像。
在一些示例中，可以采用bayer CFA对输入图像重新采样以模拟相机传感器的输入。
另外，在一些示例中，可以采用JPEG、TIFF、RAW等格式压缩输入图像。
在一些示例中，与输入图像相对应的显示器上的二维码图像可以使用相同的投影变换和镜头失真函数进行处理。由于需要仿真二维码图像与显示器上的二维码图像一一对应的构成图像对来训练该网络装置1，因此可以使用相同的投影变换和镜头失真函数对显示器上的二维码图像进行处理。
在一些示例中，可以采用均方差函数
Figure PCTCN2020076819-appb-000002
作为损失函数训练网络装置1，其中M和N是仿真二维码图像的高和宽，H(G(I'))是网络装置1输出的二维码图像，J是与仿真二维码图像相对应的显示器上的二维码图像，且保存训练的损失(loss)最小时的网络装置1的模型和参数。由此，能够有效的训练该网络装置1。
在一些示例中，损失函数也可以用损失函数也可以用交叉熵损失函数、指数损失函数、Hinge损失函数(SVM)来实现，在具体应用中可以根据实际情况进行选择，此处不做限制。
在本实施方式中，如上所述，可以将仿真二维码图像作为原始图像I输入该网络装置1进行训练，以得到相应的去摩尔纹图像(如图4(b)所示)。由此，能够减小使用大量数据的真实二维码图像带来的难度。
图5(a)是示出了本实施方式所涉及的拍摄图像的示意图，图5(b)是示出了本实施方式所涉及的重建图像的示意图，图5(c)是示出了本实施方式所涉及的关于图5(a)的去摩尔纹图像。
在一些示例中，为了实现二维码的去摩尔纹，本公开提出的网络装置1模型可以分成两个阶段进行：(a)采用大量仿真生成的带合成摩尔纹的仿真二维码图像对网络进行预训练(参照如上对仿真二维码图像的训练)，使网络可以针对二维码发挥去摩尔纹的性能。(b)考虑真实环境中摩尔纹的特性，训练中可以采用相对少量的真实拍摄的带摩尔纹的真实二维码图像基于网络装置1进行迁移学习(Fine-tune)，使网络针对真实图像上的摩尔纹有更加理想的去除效果。经过两个阶段训练的网络装置1，可以对带摩尔纹的真实拍摄的二维码图像实现良好的去摩尔纹性能。
因此，在一些示例中，本公开还可以包括带有摩尔纹的真实二维码图像，基于训练的损失最小时的网络装置1的模型和参数，并利用真实二维码图像对网络装置1进行迁移学习操作。由此，能够更有效地训练该网络装置1。
以下详述迁移学习操作。
使用仿真二维码图像对网络进行预训练后，网络具有去除摩尔纹的功能，但仿真二维码图像并不能完全模拟出真实环境中的情况，所以需要利用真实拍摄的真实二维码图像对网络进行微调，使网络能够发挥实际效果，同时增强网络的鲁棒性。对预训练过程中损失最小时的模型和参数进行保存，在此基础上，利用真实拍摄带摩尔纹的真实二维码图像对网络进行迁移学习操作。
由于该网络装置1是有监督学习的方式，网络的输入输出图像应当除了有无摩尔纹之外无其他差别，但真实拍摄的真实二维码图像很难找到与之匹配的标签，所以可以利用二维码中固定的模块：定位图样、校准图样和探测图样对拍摄的二维码图像进行角度变换，使之可以与显示器上的二维码图像一一对应。经过角度变换后的重建图像(如图5(b)所示)作为迁移学习阶段的网络输入，而与之相对应的屏幕上的二维码图像作为网络输出。迁移学习过程仍然使用均方误差(MSE)函数作为损失函数，网络经过真实数据(真实二维码图像)的迁移学习操作，可以对真实拍摄环境中的摩尔纹有更加理想的去除效果。
在一些示例中，在具体的训练参数设置为batchsize可以为4，迭代次数可以为12×10 5次，学习率可以为10 -5，优化器可以为Adam。
在预训练阶段，可以利用MATLAB对展示在显示器上600张不同的二维码进行摩尔纹仿真处理以以生成60000张512×512带有摩尔纹的仿真二维码图像，其中可以将50000张用于训练，10000张用于测试。
在一些示例中，可以利用深度学习框架tensorflow来实现网络装置1。本公开的训练和测试环境可以为搭载NVIDIA Tesla P100GPU和Intel Xeon E5-2695 v4CPU的服务器。
在一些示例中，可以使用Dell U2414H显示器显示不同的二维码图像，并可以采用三台智能手机(苹果iPhone 8plus、小米MI 8、魅族m1 metal等)对二维码图像进行拍摄。
参照图5(a)，在一些示例中，在迁移学习阶段，可以采集10000张真实的带摩尔纹的真实二维码图像对网络装置1进行迁移学习操作，使网络可以发挥更好的去摩尔纹的效果。可以从手机的版本2到版本6每个版本各采集2000张，利用手机从不同角度，不同距离对屏幕上同一张二维码图像拍摄20次。接着可以对拍摄的10000张真实二维码图像进行重建，根据二维码中固定的模块：定位图样，校准图样和三个探测图样进行角度变换，得到与屏幕上显示的二维码图像一一对应的重建图像，如图5(b)所示。
另外，再次参照图1，可以将手机等设备拍摄的真实二维码图像作为输入，并经过透视变换、角度变换等操作进行图像的重建得到重建图像，以作为该网络装置1的输入进行迁移学习。在这种情况下，可以使该训练好的网络装置1对真实环境中拍摄好的二维码图像有更加理想的去除效果。
虽然以上结合附图和实施例对本公开进行了具体说明，但是可以理解，上述说明不以任何形式限制本公开。本领域技术人员在不偏离本公开的实质精神和范围的情况下可以根据需要对本公开进行变形和变化，这些变形和变化均落入本公开的范围内。

Claims (10)

  1. 一种二维码去摩尔纹的深度残差网络的训练方法，其特征在于，
    包括：
    准备带有摩尔纹的原始二维码图像；
    准备用于对所述原始二维码进行处理的网络装置，所述网络装置包括预处理模块、第一残差模块、第二残差模块以及第三残差模块；
    将所述原始二维码图像输入所述预处理模块，对所述原始二维码图像进行模糊处理以增加仿真二维码图像中二维码区域的像素，接着进行下采样处理以形成图像缩小的预处理图像；
    将所述预处理图像输入至所述第一残差模块进行上采样处理以形成图像大小放大至所述原始二维码图像大小的第一输出图像；
    将所述第一输出图像输入至所述第二残差模块以形成恢复所述第一输出图像丢失的图像信息的第二输出图像；并且
    将所述第二输出图像和所述原始二维码图像进行特征融合以形成特征融合图像，接着将所述特征融合图像输入所述第三残差模块进行提纯处理以形成去除摩尔纹的去摩尔纹图像。
  2. 如权利要求1所述的训练方法，其特征在于，
    所述第一残差模块包括依次连接的卷积核大小为3×3且具有64个特征映射的第一卷积层、第一ReLU激活层、串联的16个残差块、卷积核大小为3×3且具有64个特征映射的第二卷积层、批归一化层、卷积核大小为3×3且具有256个特征映射的第三卷积层、卷积核大小为1×1且具有3个特征映射的第四卷积层以及tanh激活层。
  3. 如权利要求1所述的训练方法，其特征在于，
    所述第二残差模块包括依次连接的10层由卷积核大小为5×5且具有64个特征映射的卷积层和第二ReLU激活层串联成的第一组合层以及10层由卷积核大小为3×3且具有64个特征映射的卷积层和第三ReLU激活层串联成的第二组合层。
  4. 如权利要求1所述的训练方法，其特征在于，
    所述第三残差模块包括依次连接的卷积核大小为3×3且具有128个特征映射的第五卷积层、第四ReLU激活层、卷积核大小为3×3且具有3个特征映射的第六卷积层。
  5. 如权利要求1所述的训练方法，其特征在于，
    所述原始二维码图像为合成的仿真二维码图像。
  6. 如权利要求5所述的训练方法，其特征在于，
    所述仿真二维码图像的形成包括如下步骤：
    对输入图像重新采样以生成一个由RGB像素组成的嵌合体，并显示在显示器上；
    随机作投影变换来模拟所述显示器和相机之间不同的相对位置和方向；
    使用放射失真函数来模拟所述相机的镜头的失真；
    采用平顶高斯滤波器来模拟抗混叠滤波；
    对所述输入图像重新采样以模拟所述相机传感器的输入；
    在所述输入图像上增加高斯噪声来模拟传感器噪声；
    去马赛克处理；
    采用去噪滤波器进行去噪处理；
    压缩所述输入图像；以及
    输出解压缩图像以形成所述仿真二维码图像。
  7. 如权利要求6所述的训练方法，其特征在于，
    与所述输入图像相对应的所述显示器上的二维码图像使用相同的所述投影变换和所述镜头失真函数进行处理。
  8. 如权利要求1所述的训练方法，其特征在于，
    采用均方差函数
    Figure PCTCN2020076819-appb-100001
    作为损失函数训练所述深度残差网络，其中M和N是所述仿真二维码图像的高和宽，H(G(I))是深度残差网络输出的二维码图像，J是与所述仿真二维码图像相对应的显示器上的二维码图像，且保存训练的损失最小时的所述深度残差网络的模型和参数。
  9. 如权利要求8所述的训练方法，其特征在于，
    还包括带有摩尔纹的真实二维码图像，基于训练的损失最小时的所述深度残差网络的模型和参数，并利用所述真实二维码图像对所述深度残差网络进行迁移学习操作。
  10. 如权利要求8所述的训练方法，其特征在于，
    对所述真实二维码图像进行角度变换，得到与所述真实二维码图像一一对应的显示器上的二维码图像。
PCT/CN2020/076819 2019-12-31 2020-02-26 二维码去摩尔纹的深度残差网络的训练方法 Ceased WO2021134874A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911414600.1 2019-12-31
CN201911414600 2019-12-31

Publications (1)

Publication Number Publication Date
WO2021134874A1 true WO2021134874A1 (zh) 2021-07-08

Family

ID=71185725

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/076819 Ceased WO2021134874A1 (zh) 2019-12-31 2020-02-26 二维码去摩尔纹的深度残差网络的训练方法

Country Status (2)

Country Link
CN (1) CN111340729B (zh)
WO (1) WO2021134874A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113723515A (zh) * 2021-08-31 2021-11-30 平安科技（深圳）有限公司 基于图像识别的摩尔纹识别方法、装置、设备及介质
CN114693558A (zh) * 2022-03-31 2022-07-01 福州大学 基于渐进融合多尺度策略的图像去摩尔纹方法及系统
CN114881888A (zh) * 2022-06-10 2022-08-09 福州大学 基于线性稀疏注意力Transformer的视频去摩尔纹方法
CN116070654A (zh) * 2023-01-04 2023-05-05 瑞芯微电子股份有限公司 二维码图像超分重建与识别方法和系统、电子设备及介质
CN116188279A (zh) * 2021-11-25 2023-05-30 华为技术有限公司 图像处理及模型训练方法及电子设备
CN119027338A (zh) * 2024-07-05 2024-11-26 杭州电子科技大学 一种基于选择性时域融合的视频去摩尔纹方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112465092B (zh) * 2020-10-29 2023-03-03 深圳大学 一种二维码样本的生成方法、装置、服务器和存储介质
CN112712467B (zh) * 2021-01-11 2022-11-11 郑州科技学院 基于计算机视觉与色彩滤波阵列的图像处理方法
CN113066027B (zh) * 2021-03-31 2022-06-28 天津大学 面向Raw域的屏摄图像摩尔纹去除方法
CN114418846B (zh) * 2021-12-30 2024-09-10 深圳市安健科技股份有限公司 一种滤线栅摩尔纹的去除方法及终端
CN114492643B (zh) * 2022-01-27 2025-05-13 维沃移动通信有限公司 模型的训练方法和电子设备
CN118887112B (zh) * 2024-07-08 2025-10-17 江苏信息职业技术学院 基于小波变换与深度学习的轻量级图像增强方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107358575A (zh) * 2017-06-08 2017-11-17 清华大学 一种基于深度残差网络的单幅图像超分辨率重建方法
US20180268533A1 (en) * 2017-03-14 2018-09-20 Adobe Systems Incorporated Digital Image Defect Identification and Correction
CN109345449A (zh) * 2018-07-17 2019-02-15 西安交通大学 一种基于融合网络的图像超分辨率及去非均匀模糊方法
CN109993698A (zh) * 2019-03-29 2019-07-09 西安工程大学 一种基于生成对抗网络的单幅图像超分辨纹理增强方法
CN110287969A (zh) * 2019-06-14 2019-09-27 大连理工大学 基于图残差注意力网络的摩尔文本图像二值化系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106709875B (zh) * 2016-12-30 2020-02-18 北京工业大学 一种基于联合深度网络的压缩低分辨率图像复原方法
CN109949235A (zh) * 2019-02-26 2019-06-28 浙江工业大学 一种基于深度卷积神经网络的胸部x光片去噪方法
CN110009615B (zh) * 2019-03-31 2020-06-19 深圳大学 图像角点的检测方法及检测装置
CN110020684B (zh) * 2019-04-08 2021-01-29 西南石油大学 一种基于残差卷积自编码网络的图像去噪方法
CN110599388B (zh) * 2019-08-26 2021-10-15 华中科技大学 一种基于定位点辅助的盲鲁棒数字水印嵌入和检测方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180268533A1 (en) * 2017-03-14 2018-09-20 Adobe Systems Incorporated Digital Image Defect Identification and Correction
CN107358575A (zh) * 2017-06-08 2017-11-17 清华大学 一种基于深度残差网络的单幅图像超分辨率重建方法
CN109345449A (zh) * 2018-07-17 2019-02-15 西安交通大学 一种基于融合网络的图像超分辨率及去非均匀模糊方法
CN109993698A (zh) * 2019-03-29 2019-07-09 西安工程大学 一种基于生成对抗网络的单幅图像超分辨纹理增强方法
CN110287969A (zh) * 2019-06-14 2019-09-27 大连理工大学 基于图残差注意力网络的摩尔文本图像二值化系统

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113723515A (zh) * 2021-08-31 2021-11-30 平安科技（深圳）有限公司 基于图像识别的摩尔纹识别方法、装置、设备及介质
CN113723515B (zh) * 2021-08-31 2023-08-18 平安科技（深圳）有限公司 基于图像识别的摩尔纹识别方法、装置、设备及介质
CN116188279A (zh) * 2021-11-25 2023-05-30 华为技术有限公司 图像处理及模型训练方法及电子设备
CN114693558A (zh) * 2022-03-31 2022-07-01 福州大学 基于渐进融合多尺度策略的图像去摩尔纹方法及系统
CN114881888A (zh) * 2022-06-10 2022-08-09 福州大学 基于线性稀疏注意力Transformer的视频去摩尔纹方法
CN116070654A (zh) * 2023-01-04 2023-05-05 瑞芯微电子股份有限公司 二维码图像超分重建与识别方法和系统、电子设备及介质
CN119027338A (zh) * 2024-07-05 2024-11-26 杭州电子科技大学 一种基于选择性时域融合的视频去摩尔纹方法

Also Published As

Publication number Publication date
CN111340729A (zh) 2020-06-26
CN111340729B (zh) 2023-04-07

Similar Documents

Publication Publication Date Title
CN111340729B (zh) 二维码去摩尔纹的深度残差网络的训练方法
CN114881888B (zh) 基于线性稀疏注意力Transformer的视频去摩尔纹方法
Liu et al. Demoir\'eing of Camera-Captured Screen Images Using Deep Convolutional Neural Network
CN110969668B (zh) 一种长焦双目相机的立体标定算法
CN109978788B (zh) 卷积神经网络生成方法、图像去马赛克方法及相关装置
CN114693558B (zh) 基于渐进融合多尺度策略的图像去摩尔纹方法及系统
JP5294343B2 (ja) 画像位置合わせ処理装置、領域拡張処理装置及び画質改善処理装置
CN111275626A (zh) 一种基于模糊度的视频去模糊方法、装置及设备
CN110969667A (zh) 基于边缘特征的多光谱相机外参自校正算法
Yang et al. Designing Display Pixel Layouts for Under-Panel Cameras.
CN112801870B (zh) 一种基于网格优化的图像拼接方法，拼接系统及可读存储介质
CN115578428B (zh) 一种考虑模态差异的红外与可见光图像配准方法及系统
Guan et al. Srdgan: learning the noise prior for super resolution with dual generative adversarial networks
CN110992244A (zh) 带有摩尔纹的图片生成方法、系统、设备和存储介质
CN105761236A (zh) 一种用于图像配准的图像预处理方法及装置
CN113066027A (zh) 面向Raw域的屏摄图像摩尔纹去除方法
Park et al. Color filter array demosaicking using densely connected residual network
CN115641260A (zh) 图像处理方法、模组、设备、存储介质及程序产品
Cristóbal et al. Superresolution imaging: a survey of current techniques
JP6236908B2 (ja) 撮像装置、撮像システムおよび撮像方法
CN114862711B (zh) 基于双重互补先验约束的低照度图像增强与去噪方法
CN108320267A (zh) 用于人脸图像的超分辨率处理方法
CN110752013A (zh) 一种宫颈癌激光图像的数据预处理系统
CN113012071B (zh) 一种基于深度感知网络的图像失焦去模糊方法
CN115018707B (zh) 基于九曲面片双四次拟合的图像放大方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20909937

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03.11.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20909937

Country of ref document: EP

Kind code of ref document: A1