Results 81 to 90 of about 5,665 (212)

A Hybrid Signal Processing and Deep Learning Framework for Accurate Transformer Fault Identification [PDF]

E3S Web of Conferences
Accurate discrimination among magnetizing inrush currents and internal fault currents is still a major problem in power transformer protection. Conventional time domain analysis gives little or no insight into transient characteristics and stimulates ...
Krishna Rao Y.V. Balarama, Swathi G.V., V Pandurangachari, Suresh Shamnty, Rao G. Madhusudhana   +4 more
doaj   +1 more source

Detection and Characterisation of Atypical Harmonic Patterns in Big Power Quality Data

IET Generation, Transmission &Distribution, Volume 19, Issue 1, January/December 2025.
This paper proposes a new algorithm to identify and assess properties of atypical harmonic patterns in long‐term monitoring data adaptively. The well‐known challenges of field application, such as data accuracy validation, missing data handling, adaptability to dynamic data nature (seasonality and trends), and data mining results interpretation, are ...
Olga Zyabkina, Max Domagk, Jan Meyer, Peter Schegner, Marco Lindner, Heiko Mayer, Christoph Butterer   +6 more
wiley   +1 more source

Sparse representation for restoring images by exploiting topological structure of graph of patches

IET Image Processing, Volume 19, Issue 1, January/December 2025.
To elevate sparse representation learning, this study leverages a graph learning model to delineate similarity relationships among image patches, utilizing this model for the initial image reconstruction phase. To capitalize on inter‐patch relationships while preserving individual patch characteristics, low‐rank constraints are integrated during the ...
Yaxian Gao, Zhaoyuan Cai, Xianghua Xie, Jingjing Deng, Zengfa Dou, Xiaoke Ma   +5 more
wiley   +1 more source

An Unsupervised Image Enhancement Method Based on Adaptation Region Divisions

IET Image Processing, Volume 19, Issue 1, January/December 2025.
This paper proposes an image enhancement method that combines traditional techniques with deep learning. It converts images to Lab color space, calculates texture complexity, adaptation region divisions and uses a convolutional autoencoder for noise reduction.
Kaijun Zhou, Weiyi Yuan, Yemei Qin
wiley   +1 more source

FAST DISCRETE CURVELET TRANSFORM BASED ANISOTROPIC FEATURE EXTRACTION FOR IRIS RECOGNITION [PDF]

ICTACT Journal on Image and Video Processing, 2010
The feature extraction plays a very important role in iris recognition. Recent researches on multiscale analysis provide good opportunity to extract more accurate information for iris recognition.
Amol D. Rahulkar, Dattatraya V. Jadhav, Raghunath S. Holambe   +2 more
doaj  

Histopathology Image Enhancement Using Multi‐Resolution Deep Learning Techniques

IET Image Processing, Volume 19, Issue 1, January/December 2025.
Accurate analysis of histopathology images is critical for reliable disease diagnosis and effective treatment planning. However, the resolution limitations of digital pathology scanners can hinder the visibility of fine cellular details, potentially impacting diagnostic accuracy and patient outcomes. In this study, we present a comprehensive comparison
Meriem Touhami, Zaka Ur Rehman, Md Jahid Hasan, Mohammad Faizal Ahmad Fauzi, Sarina Binti Mansor   +4 more
wiley   +1 more source

Three-dimensional curvelet-based dictionary learning for speckle noise removal of optical coherence tomography.

Biomedical Optics Express, 2020
Optical coherence tomography (OCT) is a recently emerging non-invasive diagnostic tool useful in several medical applications such as ophthalmology, cardiology, gastroenterology and dermatology.
Mahad Esmaeili, A. M. Dehnavi, Fedra Hajizadeh, H. Rabbani   +3 more
semanticscholar   +1 more source

Iris recognition based on generalized Gaussian distribution FDCT_Wrap and FSVM

Dianxin kexue, 2016
In order to improve the accuracy rate of iris recognition,an improved curvelet transform algorithm for iris recognition was proposed.Firstly,the iris image was decomposed with fast discrete curvelet transform by wrapping algorithm.Mean variance and ...
Zhenhong HE
doaj   +2 more sources

Improving face recognition by elman neural network using curvelet transform and HSI color space

Periodicals of Engineering and Natural Sciences (PEN), 2019
In this paper, a suggested algorithm was proposed to increase the efficiency of the Elman neural algorithm in face recognition. The proposed algorithm was studied on the images of 20 students from the Department of Computer Science, Tikrit University ...
A. S. Abdullah, M. A. Abed, I. AlBarazanchi   +2 more
semanticscholar   +1 more source

Face Recognition Using Curvelet Transform

, 2010
This paper presents a new method for the problem of human face recognition from still images. This is based on a multiresolution analysis tool called Digital Curvelet Transform. Curvelet transform has better directional and edge representation abilities than wavelets.
Hana Hejazi, Mohammed Alhanjouri
openaire   +2 more sources