Results 81 to 90 of about 311,920 (239)
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 +3 more
wiley +1 more source
Image Compression using Haar and Modified Haar Wavelet Transform
Efficient image compression approaches can provide the best solutions to the recent growth of the data intensive and multimedia based applications. As presented in many papers the Haar matrix–based methods and wavelet analysis can be used in various areas of image processing such as edge detection, preserving, smoothing or filtering.
Mohannad Abid Shehab Ahmed +2 more
openaire +3 more sources
AHD‐YOLO: An Adaptive Hybrid Dynamic Network for Building Damage Detection
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 +7 more
wiley +1 more source
Relationships among Interpolation Bases of Wavelet Spaces and Approximation Spaces [PDF]
A multiresolution analysis is a nested chain of related approximation spaces.This nesting in turn implies relationships among interpolation bases in the approximation spaces and their derived wavelet spaces.
Kon, Mark A., Zhang, Zhiguo
core
This paper proposes a novel image steganographic method based on an enhanced Pyramid Integer Wavelet Transform (PIWT) combined with a Modified Optimal Pixel Adjustment Process (MOPAP). The PIWT enables integer‐to‐integer transformation, avoiding floating‐point computations and improving its suitability for efficient implementation.
Ali Yahya Al‐Ashwal +2 more
wiley +1 more source
MFR‐UNet: A Medical Image Segmentation Network With Fused Multi‐Scale Feature Refinement
Addressing the challenges of CNN‐based methods (especially U‐Net and its variants) in medical image segmentation—such as difficulties in capturing long‐range dependencies and insufficient refinement of multi‐scale features—this paper proposes the MFR‐UNet architecture integrated with a multi‐scale feature refinement mechanism, which enhances ...
Shaoqiang Wang +7 more
wiley +1 more source
This paper evaluates the performance of six different machine learning (ML) algorithms for classifying power quality disturbances (PQDs), with statistical features extracted using discrete wavelet transform (DWT) as feature input.
Uvesh Sipai +5 more
doaj +1 more source
Haar-LikeWavelets over Tetrahedra
In this paper we define a Haar-like wavelets basis that form a basis for L2(T,S,μ), μ being the Lebesgue measure and S the σ -algebra of all tetrahedra generated from a subdivision method of the T tetrahedron.
Liliana Beatriz Boscardín +2 more
doaj +1 more source
Lung Lesion Segmentation Using Gaussian Filter and Discrete Wavelet Transform
Lung cancer is the growth of a tumour, referred to as a nodule that arises from cells covering the airways of the respiratory arrangement. Effective detection of lung cancer at premature stages enables any cure options, and reduce risk of insidious ...
Dimililer Kamil +2 more
doaj +1 more source
A well-balanced adaptive Haar wavelet finite volume scheme for 1D free surface water flows
This paper studies a Haar-wavelet based finite volume method in terms of its capability of preserving a well-balanced property compared to the classical finite volume method, as well as with its application on the real case of the shallow water flow ...
Dilshad A. Haleem
doaj +1 more source

