Deblurring method, system and device based on conditional generative adversarial network and medium
A conditional generation and deblurring technology, applied in the fields of computer vision, image processing, and deep learning, can solve the problem of insignificant improvement in accuracy, prevent overfitting, improve feature extraction capabilities, and reduce the amount of calculation and parameters. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0071] Such as figure 1 As shown, this embodiment provides a defuzzification method based on a conditional generative adversarial network, which includes the following steps:
[0072] S101. Construct a generative adversarial network.
[0073] Generative Adversarial Networks (GAN) includes a generator G and a discriminator D. The structure of the generator G is as follows: figure 2 As shown, it is mainly composed of 32 Group-SE modules stacked, and the generator specifically includes sequentially connected input layers, the first standard convolution layer, the first activation function layer, and the first feature normalization (Activation and Normalization, AN) layer , 32 Group-SE modules, deconvolution layer (ConvTranspose), second standard convolution layer and output layer, the structure of the discriminator D is as follows image 3 As shown, it includes a DPN (Dual Path Network) network, and the DPN network includes a plurality of DPN blocks, wherein the first standard...
Embodiment 2
[0139] Such as Image 6 As shown, this embodiment provides a defuzzification system based on conditional generative adversarial network, which includes a construction unit 601, an acquisition unit 602, a processing unit 603, a feature extraction unit 604, an upsampling unit 605, an output unit 606, an iterative Unit 607 and deblurring processing unit 608, the specific functions of each unit are as follows:
[0140] A construction unit 601 is configured to construct a generative confrontation network.
[0141] The obtaining unit 602 is configured to obtain blurred images and clear images.
[0142] The processing unit 603 is configured to input the blurred image into the input layer of the generator, and sequentially process through the standard convolution layer, the first activation function layer and the first feature normalization layer.
[0143] A feature extraction unit 604, configured to input the processing results into multiple Group-SE modules to extract features.
...
Embodiment 3
[0150] This embodiment provides a computer device, which can be a computer, such as Figure 7 As shown, a processor 702, a memory, an input device 703, a display 704 and a network interface 705 are connected through a system bus 701, the processor is used to provide computing and control capabilities, and the memory includes a non-volatile storage medium 706 and an internal memory 707, the non-volatile storage medium 706 stores an operating system, a computer program, and a database, the internal memory 707 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium, and the processor 702 executes the During computer program, realize the deblurring method of above-mentioned embodiment 1, as follows:
[0151] Build a generative confrontation network;
[0152] Obtain blurred image and clear image;
[0153] Input the blurred image into the input layer of the generator, and process it sequentially through the stan...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More