A Cnn Model for Improved Image Denoising With an Attention Guided Feature Selection

Résumé

Abstract Deep Convolutional Neural Networks, or DCNNs, have undergone numerous modifications to enhance their capabilities in image processing, including image restoration, but there is still room for improvement. They have been improved in a number of ways, including reducing information loss, increasing feature utilization , and reducing computational complexity. This study presents a network structure known as CNN with attention (CNWATT2) that can preserve detail and edge information while also making the denoised image easier to view. Multiple features from the input image are extracted and fed into a forward network structure by the CNWATT2 using convolutional kernels of varying sizes. It is made up of two CNNs, and an attention module is added to the output of each CNN so that it can choose the features that affect the model before the concate-nation operation (attention-guided concatenation) to combine these features into the final feature map. The feature selection mechanism is enhanced by incorporating an attention model at the output of each CNN model. The CNWATT2 denoising method outperforms recently used denoising models DnCNN, FFD-NET IRCNN, and BRDNET in terms of both objective and subjective quality and its ability to effectively remove Gaussian noise from both color and grayscale images.

Citer ce document

Accès au document

Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0