Results 81 to 90 of about 321,454 (242)

Reversible implementation of a disrete linear transformation [PDF]

, 2010
Discrete linear transformations form important steps in processing information. Many such transformations are injective and therefore are prime candidates for a physically reversible implementation into hardware. We present here the first steps towards a
Burignat, Stéphane, De Vos, Alexis, Thomsen, Michael   +2 more
core   +1 more source

Haar Wavelet Neural Network Model

2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 2018
Convolutional neural networks, one of the most important methods of deep learning which is a popular and modern research topic. Nowadays, thismethod has been applied many problems in a short time and obtained successful results for science and the industry.
Pala, T., Yücedağ, I., Kahraman, H. T., Güvenç, U., Sönmez, Y.   +4 more
openaire   +2 more sources

Feature selection using Haar wavelet power spectrum [PDF]

BMC Bioinformatics, 2006
Feature selection is an approach to overcome the 'curse of dimensionality' in complex researches like disease classification using microarrays. Statistical methods are utilized more in this domain. Most of them do not fit for a wide range of datasets. The transform oriented signal processing domains are not probed much when other fields like image and ...
Sahu Rajendra, Subramani Prabakaran, Verma Shekhar   +2 more
openaire   +3 more sources

Multi‐Channel Fusion Residual Network for Robust Bone Fracture Classification From Radiographs

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This research introduces a multi‐channel fusion residual network (MFResNet18) to enhance bone fracture classification from radiographs. By integrating a multi‐modal channel filter with multi‐path early feature extraction, the model enriches fracture‐specific details before deep inference. Experimental results demonstrate a classification accuracy of 99.
Sivapriya T, K. R. Sri Preethaa, Yuvaraj Natarajan, M. Shyamala Devi   +3 more
wiley   +1 more source

AGFP: A Deep Attention‐Guided Framework for DWT‐Based Image Steganography

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This paper introduces Attention‐Guided Feature Perturbation (AGFP), a novel framework that combines deep learning‐based attention mechanisms with Discrete Wavelet Transform (DWT) embedding for image steganography. By selectively embedding data in perceptually and statistically safe regions, AGFP achieves high imperceptibility, robustness against ...
Taner Cevik, Nazife Cevik, Ali Pasaoglu, Fatih Sahin, Farzad Kiani, Muhammet Sait Ag   +5 more
wiley   +1 more source

Haar wavelet collocation method for the numerical solution of singular initial value problems

Ain Shams Engineering Journal, 2016
In this paper, numerical solutions of singular initial value problems are obtained by the Haar wavelet collocation method (HWCM). The HWCM is a numerical method for solving integral equations, ordinary and partial differential equations.
S.C. Shiralashetti, A.B. Deshi, P.B. Mutalik Desai   +2 more
doaj   +1 more source

Robust Facial Recognition Using Unified Optimised Feature Fusion and Selection of Handcrafted and Deep Learning Features

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This study presents a robust facial recognition framework based on a unified optimised feature vector that fuses handcrafted descriptors and deep learning embeddings. Using binary grey wolf optimisation for feature selection, the approach reduces redundancy while preserving discriminative power.
Farid Ayeche, Adel Alti
wiley   +1 more source

ANALISIS DEKOMPOSISI WAVELET PADA PENGENALAN POLA LURIK DENGAN METODE LEARNING VECTOR QUANTIZATION

Ilkom Jurnal Ilmiah, 2017
Indonesia merupakan negara yang terdiri dari banyak suku dan adat istiadat. Keragaman budaya di Indonesia juga dapat dilihat dari kerajinan tenun seperti songket dari daerah sumatra, ulos dari daerah batak, dan kain lurik dari daerah jawa tengah.
Bambang Robi'in
doaj   +1 more source

Wavelet Quadtree Contrast Limited Adaptive Histogram Equalisation Tablet Enhancement Method for Defect Detection in Low‐Contrast Tablets

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This paper proposes a novel image enhancement method, WCTE, which integrates Haar wavelet transform and adaptive CLAHE to improve the visibility of low‐contrast tablet images. Combined with the YOLOv11 model, this approach significantly boosts defect detection accuracy, especially for half‐grain and paste tabtal.
Zimei Tu, Qinna Wang, Zhicheng Jiang, Jinhua Jiang   +3 more
wiley   +1 more source

AHD‐YOLO: An Adaptive Hybrid Dynamic Network for Building Damage Detection

IET Image Processing, Volume 20, Issue 1, January/December 2026.
To address the issues of limited detection accuracy and high computational resource consumption in current deep learning‐based building damage detection, we propose a novel framework, AHD YOLO, built upon YOLOv11. AHD YOLO achieves an optimal balance between detection performance and computational resource efficiency, demonstrating strong potential for
Min Li, Tao Xu, Yinping Jiang, Peiyong Ji, Jingqi Hu, Wenlong Lui, Xuejian Ji, Ruiqiang Guo   +7 more
wiley   +1 more source