Rounded Hartley Transform: A Quasi-involution
A new multiplication-free transform derived from DHT is introduced: the RHT. Investigations on the properties of the RHT led us to the concept of weak-inversion. Using new constructs, we show that RHT is not involutional like the DHT, but exhibits quasi-involutional property, a new definition derived from the periodicity of matrices. Thus instead of using the actual inverse transform, the RHT is viewed as an involutional transform, allowing the use of direct (multiplication-free) to evaluate the inverse. A fast algorithm to compute RHT is presented. This algorithm show embedded properties. We also extended RHT to the two-dimensional case. This permitted us to perform a preliminary analysis on the effects of RHT on images. Despite of some SNR loss, RHT can be very interesting for applications involving image monitoring associated to decision making, such as military applications or medical imaging.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSimilar Papers 제목 키워드 기반
Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolution
Single Image Super-Resolution (SISR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. Deep learning, especially Convolutional Neural Networks (CNNs), has advanced SISR. However, increasing…
Computational EfficiencyImage Super-ResolutionSSIMSuper-ResolutionHartley Spectral Pooling for Deep Learning
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging…
Deep LearningDimensionality ReductionHartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
With the introduction of Transformers, different attention-based models have been proposed for image segmentation with promising results. Although self-attention allows capturing of long-range dependencies, it suffers fr…
Image SegmentationSemantic SegmentationSuper-ResolutionInvolution: Inverting the Inherence of Convolution for Visual Recognition
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision. In this work, we rethink the inherent principles of standard convolution for vision tasks, specifically…
Image ClassificationMed-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation
The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution …
image-classificationImage ClassificationMedical Image Classification