Deep Convolutional Neural Network Based on Multi-Scale Feature Extraction for Image Denoising

Zhang, Jing; Liu, Sang; Wan, Zekang; Wang, Yuchen; Li, Yunsong

doi:10.1109/vcip49819.2020.9301843

Cited by 8 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Images' detail and important characteristics and information may be diminished by doing excessive scaling [11]. Although the convolutional network is deeper, it may be easy to lose the gradient of the network.…”

Section: Diamond De-noising Network (Dmdn)mentioning

confidence: 99%

“…Although the convolutional network is deeper, it may be easy to lose the gradient of the network. To address these issues, Diamond Shaped (DS) multi-scale feature extraction www.ijacsa.thesai.org has been utilized in this network to extract the information of the images' features [11]. This fixed scale-based network is called a Diamond De-noising network (DmDN) [11].…”

Section: Diamond De-noising Network (Dmdn)mentioning

confidence: 99%

“…Zhang in [10] proposed a Dn-CNN method consisting of two main stages, residual learning and batch normalization. Deeper networks also cause gradient dispersion in which residual learning has been utilized in Dn-CNNs to tackle this issue [11]. There are also some other issues which deep neural network-based methods are suffering from.…”

Section: Introductionmentioning

confidence: 99%

“…To address these issues Bin et al developed a flashlight CNN method based on deep residual and inception networks that is able to hold many parameters [12]. Additionally, J. Zhang in [11] developed a diamond denoiser to deal with the issue of losing network's gradient caused by deeper networks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison

Rahimi,

Golilarz

2024

IJACSA

View full text Add to dashboard Cite

Various types of noise may affect the visual quality of images during capturing and transmitting procedures. Finding a proper technique to remove the possible noise and improve both quantitative and qualitative results is always considered as one of the most important and challenging pre -processing tasks in image and signal processing. In this paper, we made a short comparison between two well-known approaches called thresholding neural network (TNN) and deep neural network (DNN) based methods for image de-noising. De-noising results of TNNs, Dn-CNNs, Flashlight CNN (FLCNN) and Diamond denoising networks (DmDN) have been compared with each other. In this regard, several experiments have been performed in terms of Peak S ignal to Noise Ratio (PS NR) to validate the performance analysis of various de-noising methods. The analysis indicates that DmDNs perform better than other learning-based algorithms for de -noising brain MR images. DmDN achieved a PS NR value of 29.85 dB, 30.74 dB, 29.15 dB, and 29.45 dB for denoising MR image 1, MR image 2, MR image 3 and MR Image 4, respectively for a standard deviation of 15.

show abstract

Section: Diamond De-noising Network (Dmdn)mentioning

confidence: 99%

Section: Diamond De-noising Network (Dmdn)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison

Rahimi,

Golilarz

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…3. Earlier methods [59] Suppose the input-output pairs to train the proposed network are (x j , y j ) N j=1 where x and y are related as y j = x j + n j . Here x j denotes ground truth image patch and y j represents noisy image patch.…”

Section: E Multi-scale Feature Extraction (Msfe) Blockmentioning

confidence: 99%

Gradient and Multi Scale Feature Inspired Deep Blind Gaussian Denoiser

Thakur

Maji

2022

IEEE Access

View full text Add to dashboard Cite

In this paper, a novel deep blind Gaussian denoising network is proposed utilizing the concepts of gradient information, multi-scale feature information and feature denoising for removing additive white Gaussian noise (AWGN) from images. The proposed network consists of two modules where in the first module generates an intermediate image whose gradient information is concatenated with the features of second module to generate the final residual image. Subtracting this residual image with the noisy image gives the desired denoised image. The feature denoising block used in the middle of the first module enhances the feature information of the intermediate image. The usage of gradient information of this intermediate denoised image, together with the multi scale feature information block, in the second module further contributes to the quality of the final denoised image. Experimental results show superior denoising performance of the proposed method in comparison to several state of the art classical and learning based blind denoising methods like EPLL, BM3D, WNNM, DnCNN, MemNet, BUIFD, Self2Self and ComplexNet by a decent margin (an improvement of up to 2.4dB in PSNR, 0.07 in SSIM and 0.03 in FOM index with the second best performing model) when experimented over BSD68, Set5, Set14, SunHays80 and Manga109 image databases.INDEX TERMS Gradient information, multi-scale feature information, additive white Gaussian noise, residual image, feature denoising block.

show abstract

Dual-quality map based no reference image quality assessment using deformable convolution

Shi

Wang

Kong

et al. 2022

Digital Signal Processing

View full text Add to dashboard Cite

Deep Convolutional Neural Network Based on Multi-Scale Feature Extraction for Image Denoising

Cited by 8 publications

References 8 publications

Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison

Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison

Gradient and Multi Scale Feature Inspired Deep Blind Gaussian Denoiser

Dual-quality map based no reference image quality assessment using deformable convolution

Contact Info

Product

Resources

About