PAMSGAN: Pyramid Attention Mechanism-Oriented Symmetry Generative Adversarial Network for Motion Image Deblurring

Zhang, Zhenfeng

doi:10.1109/access.2021.3099803

Cited by 3 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the great success of deep learning in computer vision, some deep learning deblurring methods have been proposed. By combining multi-scale pyramid feature and attention mechanism, Zhang et al [33] constructed a generative adversarial network to obtain latent images. Esmaeilzehi et al [34] proposed a two-stage convolutional network to carry out the processes of up-sampling and deblurring.…”

Section: Related Workmentioning

confidence: 99%

Blind Text Image Deblurring Algorithm Based on Multi-Scale Fusion and Sparse Priors

Yang

Cheng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The goal of blind text image deblurring is to obtain a clean text image from the given blurry text image without knowing the blur kernel. Sparsity-based methods have been shown their effectiveness in various blind text image deblurring models. However, the blur kernel estimation methods based on sparse priors lack of the consideration for the brightness information about the blur kernel, which will affect the restoration effect of the blur kernel. Besides, previous methods seldom apply sparse priors to both spatial domain and transform domain information. We propose a novel blind text image deblurring model based on multi-scale fusion and sparse priors. Besides the sparse gradient prior on the latent clean text image, we add the sparse prior on the high-frequency wavelet coefficients of the latent text image, which will better constrain the solution space and obtain good clean images. The semi-quadratic splitting method is used to alternately optimize the blur kernel and the latent clean image. Meanwhile, we consider the influence of the brightness feature of the restored blur kernel. By multi-scale fusion technique on the basis of Laplacian weight and saliency weight, we fuse the computed blur kernels in three channels to improve the quality of blur kernel. The experimental results show that our algorithm has good results in the restoration of blur kernels and text images.INDEX TERMS Blind text image deblurring, sparse priors, multi-scale fusion, wavelet transform.

show abstract

Section: Related Workmentioning

confidence: 99%

Blind Text Image Deblurring Algorithm Based on Multi-Scale Fusion and Sparse Priors

Yang

Cheng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Accuracy/% LeNet-FC 98.9 AlexNet [20] 98.1 ResNet [21] 95.6 DCGAN [22] 92.5 SCNN [23] 94.7 PAMSGAN [24] 95.1…”

Section: Modelmentioning

confidence: 99%

A novel deep LeNet-5 convolutional neural network model for image recognition

Zhang

Lei

et al. 2022

COMSIS J

View full text Add to dashboard Cite

At present, the traditional machine learning methods and convolutional neural network (CNN) methods are mostly used in image recognition. The feature extraction process in traditional machine learning for image recognition is mostly executed by manual, and its generalization ability is not strong enough. The earliest convolutional neural network also has many defects, such as high hardware requirements, large training sample size, long training time, slow convergence speed and low accuracy. To solve the above problems, this paper proposes a novel deep LeNet-5 convolutional neural network model for image recognition. On the basis of Lenet-5 model with the guaranteed recognition rate, the network structure is simplified and the training speed is improved. Meanwhile, we modify the Logarithmic Rectified Linear Unit (L_ReLU) of the activation function. Finally, the experiments are carried out on the MINIST character library to verify the improved network structure. The recognition ability of the network structure in different parameter s is analyzed compared with the state-of-the-art recognition algorithms. In terms of the recognition rate, the proposed method has exceeded 98%. The results show that the accuracy of the proposed structure is significantly higher than that of the other recognition algorithms, which provides a new reference for the current image recognition.

show abstract