Interest Points Detection in Image Based on Topology Features of Multi-level Complex Networks

Zou, Qingyu; Bai, Jing

doi:10.1007/s11277-018-5472-4

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Referring to past research, metadata from the O*NET database were used to develop quantitative assessment scales, information technology, and algorithms, such as the prediction and construction of an evaluation system, to conduct research on teachers' professional competencies [2,[13][14][15]. This research used social network analysis (SNA) methods, approaches, and theoretical concepts, such as affiliation networks and bipartite graphs [16] that included occupational titles, Element Name and ID, and KSAOs [17] from the O*NET database, to design and implement CB-TPD curricula, as shown in Figure 1. In addition, ECPC keyword co-occurrences were analyzed by centrality metrics to construct e-learning curricula evaluation metrics for CB-TPD and verify their importance [18].…”

Section: Literature Reviewmentioning

confidence: 99%

The Construction and Application of E-Learning Curricula Evaluation Metrics for Competency-Based Teacher Professional Development

Chen¹,

Huang²,

Hsiao³

2022

Sustainability

View full text Add to dashboard Cite

Today, students at universities in advanced countries typically enroll in colleges, such as the College of Education, which offer interdisciplinary programs for undergraduates in their first and second years, allowing them to explore personal interests, experience educational research fields, complete their integrated curricula, and then choose a major in their third year. To cooperate with the government’s epidemic prevention policies and measures in the post-COVID-19 era, the trend of e-learning and distance teaching has accelerated the establishment of integrated online curricula with interdisciplinary programs for undergraduates in the College of Education to facilitate effective future teacher professional development (TPD). Therefore, it is very important to construct e-learning curricula evaluation metrics for competency-based teacher professional development (CB-TPD) and to implement them in teaching practice. This research used social network analysis (SNA) methods, approaches, and theoretical concepts, such as affiliation networks and bipartite graphs comprised of educational occupational titles and common professional competencies (i.e., Element Name and ID), as well as knowledge, skills, abilities, and other characteristics (KSAOs), from the U.S. occupational information network (O*NET) 26.1 OnLine database, to collect data on the occupations of educational professionals. This study also used Gephi network analysis and visualization software to carry out descriptive statistics of keyword co-occurrences to measure their centrality metrics, including weighted degree centrality, degree centrality, betweenness centrality, and closeness centrality, and to verify their importance and ranking in professional competency in eight categories of educational professionals (i.e., three categories of special education teachers and five categories of teachers, except special education). The analysis of the centrality metrics identified the educational common professional competency (ECPC) keyword co-occurrences, which were then used to design, develop, and apply e-learning curricula evaluation metrics for CB-TPD. The results of this study can be used as a reference for conducting related academic research and cultivating educational professionals’ online curricula, including ECPC keywords, integrated curricula design and the development of transdisciplinary programs, and teacher education, as well as to facilitate the construction and application of future e-learning curricula evaluation metrics for CB-TPD.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

The Construction and Application of E-Learning Curricula Evaluation Metrics for Competency-Based Teacher Professional Development

Chen¹,

Huang²,

Hsiao³

2022

Sustainability

View full text Add to dashboard Cite

show abstract

“…T He topological structure of images that does not change with parameters such as image size and direction is considered to be an important feature applied to image analysis and recognition [1]. Extracting topological structure from image shape is a process of feature extraction, which means transforming high-dimensional features of pattern space into the low-dimensional features of feature space through mapping or transformation, that is, using fewer new features to describe samples.…”

Section: Introductionmentioning

confidence: 99%

Scale-Adaptive Growing Neural Network Based on Distortion Error Stability and its Application in Image Topological Feature Extraction

2021

View full text Add to dashboard Cite

“…Image segmentation application area varies from the identification of objects from remote sensing data [1,42,43] to the detection of cancerous cells. For example, it can be used to diagnose medical imaging [2], or to extract interest points for images for identifying the local features of an image [3]. In the literature, a lot of image segmentation algorithms have been proposed.…”

Section: Introductionmentioning

confidence: 99%

A general framework for complex network-based image segmentation

Mourchid

Cherifi

2019

Multimed Tools Appl

View full text Add to dashboard Cite

With the recent advances in complex networks theory, graph-based techniques for image segmentation has attracted great attention recently. In order to segment the image into meaningful connected components, this paper proposes an image segmentation general framework using complex networks based community detection algorithms. If we consider regions as communities, using community detection algorithms directly can lead to an over-segmented image. To address this problem, we start by splitting the image into small regions using an initial segmentation. The obtained regions are used for building the complex network. To produce meaningful connected components and detect homogeneous communities, some combinations of color and texture based features are employed in order to quantify the regions similarities. To sum up, the network of regions is constructed adaptively to avoid many small regions in the image, and then, community detection algorithms are applied on the resulting adaptive similarity matrix to obtain the final segmented image. Experiments are conducted on Berkeley Segmentation Dataset and four of the most influential community detection algorithms are tested. Experimental results have shown that the proposed general framework increases the segmentation performances compared to some existing methods.

show abstract

Interest Points Detection in Image Based on Topology Features of Multi-level Complex Networks

Cited by 4 publications

References 15 publications

The Construction and Application of E-Learning Curricula Evaluation Metrics for Competency-Based Teacher Professional Development

The Construction and Application of E-Learning Curricula Evaluation Metrics for Competency-Based Teacher Professional Development

Scale-Adaptive Growing Neural Network Based on Distortion Error Stability and its Application in Image Topological Feature Extraction

A general framework for complex network-based image segmentation

Contact Info

Product

Resources

About