Saak-Transform based Method for Image Noise Reduction
This research proposes a novel approach to reduce noise in an image. In this study, the input image is considered being shot with high ISO in the low light condition and the noise is modeled as the additive white Gaussian noise. The Subspace Approximation with Augmented Kernels (Saak) transform, a state-of-the-art spatial-spectral representation, is used for extracting the local characteristics of an image. The clean coefficients are estimated based on optimal linear minimum mean square error (LMMSE) estimation with a shrinkage on Saak coefficients. The processed image provides subjectively satisfactory quality improvement and an increase in peak signal to noise ratio (PSNR) without harming edges or other image details. It shows that Saak transform is a promising tool for noise reduction.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Defense Against Adversarial Attacks with Saak Transform
Deep neural networks (DNNs) are known to be vulnerable to adversarial perturbations, which imposes a serious threat to DNN-based decision systems. In this paper, we propose to apply the lossy Saak transform to adversaria…
Adversarial DefenseA Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognition
An efficient, scalable and robust approach to the handwritten digits recognition problem based on the Saak transform is proposed in this work. First, multi-stage Saak transforms are used to extract a family of joint spat…
On Data-Driven Saak Transform
Being motivated by the multilayer RECOS (REctified-COrrelations on a Sphere) transform, we develop a data-driven Saak (Subspace approximation with augmented kernels) transform in this work. The Saak transform consists of…
Robustness Of Saak Transform Against Adversarial Attacks
Image classification is vulnerable to adversarial attacks. This work investigates the robustness of Saak transform against adversarial attacks towards high performance image classification. We develop a complete image cl…
Adversarial RobustnessClassificationDenoisingGeneral Classification+2Visualization, Discriminability and Applications of Interpretable Saak Features
In this work, we study the power of Saak features as an effort towards interpretable deep learning. Being inspired by the operations of convolutional layers of convolutional neural networks, multi-stage Saak transform wa…
General Classificationimage-classificationImage Classification