Classification of priors and regularization techniques appurtenant to single image super-resolution

Pandey, Garima; Ghanekar, Umesh

doi:10.1007/s00371-019-01729-z

Cited by 13 publications

(5 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Normalization adjusts the data, while regularization adjusts the prediction function. [76][77][78] When the previously used layer parameter in the CNN is changed, the input of individual layer changes; therefore, the CNN model training is complex. Consequently, the activation function we have used in our model as ReLU quickly drops the gradient.…”

Section: Normalization and Regularizationmentioning

confidence: 99%

An intelligent hierarchical residual attention learning‐based conjoined twin neural network for Alzheimer's stage detection and prediction

Shankar

Sisodia

Chandrakar

2023

Computational Intelligence

View full text Add to dashboard Cite

Alzheimer's disorder (AD) causes permanent impairment in the brain's memory of the cellular system, leading to the initiation of dementia. Earlier detection of Alzheimer's disease in the initial stages is challenging for researchers. Deep learning and machine learning‐based techniques can help resolve many issues associated with brain imaging exploration. Brain MR Images (Brain‐MRI) are used to detect Alzheimer's in computable research work. To correctly categorize the stages of Alzheimer's disease, discriminative features need to be extracted from the MR images. Recently, many studies have used deep learning methods for the early detection of this disorder. However, overfitting degrades the deep learning method's performance because the dataset's selection images are smaller and imbalanced. Some studies could not reach more discriminative and effectual attention‐aware features for Alzheimer's stage classification to increase the model performance. In this paper, we develop a novel hierarchical residual attention learning‐inspired multistage conjoined twin network (HRAL‐CTNN) to classify the stages of Alzheimer's. We used augmentation approaches to scale insufficient and imbalanced data. The HRAL‐CTNN is efficiently overcoming the issues of not obtaining efficient attention‐aware and generative features for Alzheimer's stage classification. The proposed model solved the problem of redundant features by extracting attentive discriminant features, and scaling imbalance data by data augmentation, after that training and validation using HRAL‐CTNN. The execution of this proposed work has been performed on the ADNI MRI dataset. This work achieved outstanding accuracy of 99.97 0.01% and F1 score of 99.30 0.02% for Alzheimer's stage classification. This model proposed by our group outperformed the existing related studies in terms of the model's performance score.

show abstract

Section: Normalization and Regularizationmentioning

confidence: 99%

An intelligent hierarchical residual attention learning‐based conjoined twin neural network for Alzheimer's stage detection and prediction

Shankar

Sisodia

Chandrakar

2023

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Each group includes 12 256×256 grayscale images. Each image of each group extracts the salient features of contrast, edge density, directional difference, and symmetry according to the imaging model [8]. Then complete the "competition" of features.…”

Section: Single Feature Experimentsmentioning

confidence: 99%

Computer Vision Communication Technology in Mathematical Modeling

Xue¹,

Wu²,

Shorman

2022

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

We use mathematical modeling methods to incorporate new elements into the computer graphics technology and visual communication design process. This method realizes the design of a computer image visual communication system. This method uses artificial vision to model and extracts local features. The micro-partial equation obtains the background reference line of the target point in the image sequence to complete the background suppression in the image spatio-temporal domain. The experimental results show that the proposed algorithm has a better tracking effect of subsequent frames of video images and higher tracking efficiency.

show abstract

“…The left column of is wide-view image and the right column is tele-view image captured by IphoneX. The red frame is the super-resolution result we will show next FIGURE 11 Results on real images(×2) in red frame FIGURE 13 Results on real images(×4) in red frame FIGURE 14 The real images inputs. The left column is wide-view image and the right column is tele-view image captured by IphoneX image), we cannot find similar spot, so the visual improvement of the reconstructed image is not obvious.…”

Section: Figure 10mentioning

confidence: 99%

“…Pandey et al. [13] classified super‐resolution methods based on the priors used and they discussed image priors and regularization in detailed. But those methods are based on traditional ways, the results are worse than methods based on deep learning on visual and objective evaluation indicators.…”

Section: Related Workmentioning

confidence: 99%

“…This approach assumes that the LR and HR image patches share similar local geometry in two distinct feature spaces. Pandey et al [13] [14] proposed the first end-to-end neural network SRCNN, but the network only has three layers, so it is difficult to learn the complex structures. The low convergence rate and working on a single scale are the other limitations of SRCNN.…”

Section: Image Super-resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Continuous digital zooming using generative adversarial networks for dual camera system

Yang

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

This paper presents a generative adversarial network (GAN) with patch match algorithm to realize a high-quality digital zooming using two camera modules with different focal lengths. In dual camera system, shorter focal length module produces the wide-view image with the low resolution. On the other hand, the longer focal length module produces the tele-view image via optical zooming. The long-focal image contains more details than short-focal image and can be used to guide short-focal image to reconstruct high frequency part. Firstly, a feature extraction block (FEB) is advanced to extract feature of long-focal image and short focal-image to reconstruct a wide-view image with different resolutions. Next, a patch match algorithm is integrated into convolution neural networks (CNN) to fuse information of long-focal with short-focal image and generate a new fused image. Finally, the fused image and short-focal image are merged with a feature fusion block (FFB) to predict high-resolution images. In addition, generative adversarial networks are used for filtering information integrated by previous network and output the zoomed image. Extensive experiments on benchmark datasets show that our algorithm achieves favorable performance against state-of-the-art methods.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Classification of priors and regularization techniques appurtenant to single image super-resolution

Cited by 13 publications

References 108 publications

An intelligent hierarchical residual attention learning‐based conjoined twin neural network for Alzheimer's stage detection and prediction

An intelligent hierarchical residual attention learning‐based conjoined twin neural network for Alzheimer's stage detection and prediction

Computer Vision Communication Technology in Mathematical Modeling

Continuous digital zooming using generative adversarial networks for dual camera system

Contact Info

Product

Resources

About