Directional Neighborhood Topologies Based Multi-Scale Quinary Pattern for Texture Classification

Rachdi, Elmokhtar; Merabet, Youssef El; Akhtar, Zahid; Messoussi, Rochdi

doi:10.1109/access.2020.3040136

Cited by 7 publications

(2 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The local quinary pattern descriptor was compared to the most advanced texture descriptors [ 49 ]. In research by Rachdi et al [ 50 ], the multiscale quinary pattern descriptor presented high capability over other local feature descriptors in extracting discriminative feature representation [ 50 ]. Ahmad et al [ 51 ] investigated the use of a feature descriptor, i.e., directional local quinary patterns (DLQP) for detecting plant leaf diseases.…”

Section: Introductionmentioning

confidence: 99%

MeQryEP: A Texture Based Descriptor for Biomedical Image Retrieval

Deep¹,

Kaur²,

Singh

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Image texture analysis is a dynamic area of research in computer vision and image processing, with applications ranging from medical image analysis to image segmentation to content-based image retrieval and beyond. “Quinary encoding on mesh patterns (MeQryEP)” is a new approach to extracting texture features for indexing and retrieval of biomedical images, which is implemented in this work. An extension of the previous study, this research investigates the use of local quinary patterns (LQP) on mesh patterns in three different orientations. To encode the gray scale relationship between the central pixel and its surrounding neighbors in a two-dimensional (2D) local region of an image, binary and nonbinary coding, such as local binary patterns (LBP), local ternary patterns (LTP), and LQP, are used, while the proposed strategy uses three selected directions of mesh patterns to encode the gray scale relationship between the surrounding neighbors for a given center pixel in a 2D image. An innovative aspect of the proposed method is that it makes use of mesh image structure quinary pattern features to encode additional spatial structure information, resulting in better retrieval. On three different kinds of benchmark biomedical data sets, analyses have been completed to assess the viability of MeQryEP. LIDC-IDRI-CT and VIA/I–ELCAP-CT are the lung image databases based on computed tomography (CT), while OASIS-MRI is a brain database based on magnetic resonance imaging (MRI). This method outperforms state-of-the-art texture extraction methods, such as LBP, LQEP, LTP, LMeP, LMeTerP, DLTerQEP, LQEQryP, and so on in terms of average retrieval precision (ARP) and average retrieval rate (ARR).

show abstract

Section: Introductionmentioning

confidence: 99%

MeQryEP: A Texture Based Descriptor for Biomedical Image Retrieval

Deep¹,

Kaur²,

Singh

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Von Neumann sociometry outperformed the conventional ones on a set of standard testing issues, hence it was selected out of the surrounding setups they evaluated. New techniques for an individual element to be impacted by its surroundings were developed by Rachdi et al [14]. Various topological structures have been shown in Fig.…”

Section: Neighborhood Topologiesmentioning

confidence: 99%

A Survey on Multi Objective Optimization Challenges in Swarm Intelligence

Caruana

Lou

2021

JCNS

View full text Add to dashboard Cite

Various challenges in real life are multi-objective and conflicting (i.e., alter concurrent optimization). This implies that a single objective is optimized based on another’s cost. The Multi-Objective Optimization (MOO) issues are challenging but potentially realistic, and due to their wide-range application, optimization challenges have widely been analyzed by research with distinct scholarly bases. Resultantly, this has yielded distinct approaches for mitigating these challenges. There is a wide-range literature concerning the approaches used to handle MOO challenges. It is important to keep in mind that each technique has its pros and limitations, and there is no optimum alternative for cure searchers in a typical scenario. The MOO challenges can be identified in various segments e.g., path optimization, airplane design, automobile design and finance, among others. This contribution presents a survey of prevailing MOO challenges and swarm intelligence approaches to mitigate these challenges. The main purpose of this contribution is to present a basis of understanding on MOO challenges.

show abstract

Learning search algorithm: framework and comprehensive performance for solving optimization problems

Qu,

Peng,

Zeng

2024

Artif Intell Rev

View full text Add to dashboard Cite

In this study, the Learning Search Algorithm (LSA) is introduced as an innovative optimization algorithm that draws inspiration from swarm intelligence principles and mimics the social learning behavior observed in humans. The LSA algorithm optimizes the search process by integrating historical experience and real-time social information, enabling it to effectively navigate complex problem spaces. By doing so, it enhances its global development capability and provides efficient solutions to challenging optimization tasks. Additionally, the algorithm improves the collective learning capacity by incorporating teaching and active learning behaviors within the population, leading to improved local development capabilities. Furthermore, a dynamic adaptive control factor is utilized to regulate the algorithm’s global exploration and local development abilities. The proposed algorithm is rigorously evaluated using 40 benchmark test functions from IEEE CEC 2014 and CEC 2020, and compared against nine established evolutionary algorithms as well as 11 recently improved algorithms. The experimental results demonstrate the superiority of the LSA algorithm, as it achieves the top rank in the Friedman rank-sum test, highlighting its power and competitiveness. Moreover, the LSA algorithm is successfully applied to solve six real-world engineering problems and 15 UCI datasets of feature selection problems, showcasing its significant advantages and potential for practical applications in engineering problems and feature selection problems.

show abstract

Directional Neighborhood Topologies Based Multi-Scale Quinary Pattern for Texture Classification

Cited by 7 publications

References 67 publications

MeQryEP: A Texture Based Descriptor for Biomedical Image Retrieval

MeQryEP: A Texture Based Descriptor for Biomedical Image Retrieval

A Survey on Multi Objective Optimization Challenges in Swarm Intelligence

Learning search algorithm: framework and comprehensive performance for solving optimization problems

Contact Info

Product

Resources

About