A Novel PDE-Based Single Image Super-Resolution Reconstruction Method

Zhao, Xiaodong; Cao, Jianzhong; Zhou, Zhiguang; Huang, Jijiang

doi:10.1142/s0218001417540106

Cited by 7 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image recognition has achieved great development with the help of deep learning technology and has been widely applied in various fields at home and abroad. Some scholars to apply image recognition technology content detection of image frames, in view of the existing retrieval scenario framework and clothing problems [4], the missing clothing information recognition for dress design optimization and scene design recognition problems, this paper proposes a new garment segmentation method and based on cross domain dictionary learning recognition of dress design. A new image information retrieval algorithm [5,6] based on scale-invariant feature transform features is proposed, which is applied to content-based image information retrieval and improves the traditional image similarity method to accurately and quickly scan the content of the image.…”

Section: Related Workmentioning

confidence: 99%

Application of Image Recognition Method Based on Diffusion Equation in Film and Television Production

Guo

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

On the basis of studying the basic theory of anisotropic diffusion equation, this paper focuses on the application of anisotropic diffusion equation in image recognition film production. In order to further improve the application performance of P-M (Perona-Malik) anisotropic diffusion model, an improved P-M anisotropic diffusion model is proposed in this paper, and its application in image ultrasonic image noise reduction is discussed. The experimental results show that the model can effectively suppress the speckle noise and preserve the edge features of the image. Based on the image recognition technology, an image frame testing system is designed and implemented. The method of image recognition diffusion equation is used to extract and recognize the multilayer feature points of the test object according to the design of artificial neural network. To a certain extent, it improves the accuracy of image recognition and the audience rating of film and television. Use visual features of the film and television play in similarity calculation for simple movement scene segmentation problem, at the same time, the camera to obtain information, use the lens frame vision measuring the change of motion of the camera, and use weighted diffusion equation and the visual similarity of lens similarity calculation and motion information, by considering the camera motion of image recognition, effectively solve the sports scene of oversegmentation problem such as fighting and chasing.

show abstract

Section: Related Workmentioning

confidence: 99%

Application of Image Recognition Method Based on Diffusion Equation in Film and Television Production

Guo

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

show abstract

“…In this model, a genetic algorithm was used to search the solution space to avoid a local minimum value; then, the regularization prior model was used to perform a single point search in the solution space, and a higher quality superresolution reconstruction estimation was obtained. Zhao et al [ 8 ] proposed a novel single image superresolution reconstruction method based on the unified partial differential equation, and the method achieved a good effect in enhancing the image edge and suppressing noise robustness. Zhang and He [ 9 ] proposed a single image superresolution reconstruction method based on mixed sparse representation, which was particularly effective for optimizing the reconstruction of noisy images.…”

Section: Introductionmentioning

confidence: 99%

Application of a Modified Generative Adversarial Network in the Superresolution Reconstruction of Ancient Murals

Cao

Zhang

Zhao

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Considering the problems of low resolution and rough details in existing mural images, this paper proposes a superresolution reconstruction algorithm for enhancing artistic mural images, thereby optimizing mural images. The algorithm takes a generative adversarial network (GAN) as the framework. First, a convolutional neural network (CNN) is used to extract image feature information, and then, the features are mapped to the high-resolution image space of the same size as the original image. Finally, the reconstructed high-resolution image is output to complete the design of the generative network. Then, a CNN with deep and residual modules is used for image feature extraction to determine whether the output of the generative network is an authentic, high-resolution mural image. In detail, the depth of the network increases, the residual module is introduced, the batch standardization of the network convolution layer is deleted, and the subpixel convolution is used to realize upsampling. Additionally, a combination of multiple loss functions and staged construction of the network model is adopted to further optimize the mural image. A mural dataset is set up by the current team. Compared with several existing image superresolution algorithms, the peak signal-to-noise ratio (PSNR) of the proposed algorithm increases by an average of 1.2–3.3 dB and the structural similarity (SSIM) increases by 0.04 = 0.13; it is also superior to other algorithms in terms of subjective scoring. The proposed method in this study is effective in the superresolution reconstruction of mural images, which contributes to the further optimization of ancient mural images.

show abstract

MRI Image Reconstruction Based on Artificial Intelligence

Liang¹

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Artificial intelligence is a new high and new technology, which has powerful functional advantages in processing big data, complex and non-deterministic data, and in-depth mining of hidden information behind the data. Magnetic resonance is a common diagnosis and treatment technology in medical clinics. The use of magnetic resonance imaging technology to construct medical images has a great auxiliary effect for doctors to make accurate medical diagnosis. This article proposes to combine artificial intelligence and magnetic resonance technology to construct magnetic resonance images based on artificial intelligence, in order to reconstruct high-quality magnetic resonance images, thereby improving the efficiency of doctors’ diagnosis and treatment and reducing misdiagnosis. This paper uses the deep learning algorithm of artificial intelligence to compare the analytic dictionary method, the synthetic dictionary method and the deep dictionary method based on convolutional neural network, and obtain the peak-to-noise ratio of the image reconstructed by the three algorithms under the same sampling rate. They are 42.56, 44.17 and 45.55 respectively; the structural similarity is 0.9387, 0.9536 and 0.9867, respectively. The study concluded that the deep dictionary method based on convolutional neural network has more advantages in reconstructing MRI images, and the effect is more obvious.

show abstract

A Novel PDE-Based Single Image Super-Resolution Reconstruction Method

Cited by 7 publications

References 30 publications

Application of Image Recognition Method Based on Diffusion Equation in Film and Television Production

Application of Image Recognition Method Based on Diffusion Equation in Film and Television Production

Application of a Modified Generative Adversarial Network in the Superresolution Reconstruction of Ancient Murals

MRI Image Reconstruction Based on Artificial Intelligence

Contact Info

Product

Resources

About