Zirui Guo, Huimin Lu, Qinghua Yu, Ruibin Guo, Junhao Xiao and Hongshan Yu
This paper aims to design a novel feature descriptor to improve the performance of feature matching in challenge scenes, such as low texture and wide-baseline scenes. Common…
Abstract
Purpose
This paper aims to design a novel feature descriptor to improve the performance of feature matching in challenge scenes, such as low texture and wide-baseline scenes. Common descriptors are not suitable for low texture scenes and other challenging scenes mainly owing to encoding only one kind of features. The proposed feature descriptor considers multiple features and their locations, which is more expressive.
Design/methodology/approach
A graph neural network–based descriptors enhancement algorithm for feature matching is proposed. In this paper, point and line features are the primary concerns. In the graph, commonly used descriptors for points and lines constitute the nodes and the edges are determined by the geometric relationship between points and lines. After the graph convolution designed for incomplete join graph, enhanced descriptors are obtained.
Findings
Experiments are carried out in indoor, outdoor and low texture scenes. The experiments investigate the real-time performance, rotation invariance, scale invariance, viewpoint invariance and noise sensitivity of the descriptors in three types of scenes. The results show that the enhanced descriptors are robust to scene changes and can be used in wide-baseline matching.
Originality/value
A graph structure is designed to represent multiple features in an image. In the process of building graph structure, the geometric relation between multiple features is used to establish the edges. Furthermore, a novel hybrid descriptor for points and lines is obtained using graph convolutional neural network. This enhanced descriptor has the advantages of both point features and line features in feature matching.
Details
Keywords
Yung-Ting Chuang and Hsi-Peng Kuan
This study applies D3.js and social network analysis (SNA) to examine the impact of collaboration patterns, research productivity patterns and publication patterns on the Ministry…
Abstract
Purpose
This study applies D3.js and social network analysis (SNA) to examine the impact of collaboration patterns, research productivity patterns and publication patterns on the Ministry of Education (MOE) evaluation policies across all Management Information Systems (MIS) departments in Taiwan.
Design/methodology/approach
This study first retrieved data from the Ministry of Science and Technology of Taiwan (MOST) website from 1982 to 2015, the Journal Citation Reports (JCR) website, the Web of Science (WOS) website and Google Scholar. Then it applied power-law degree distribution, cumulative distribution function, weighted contribution score, exponential weighted moving average and network centrality score to visualize the MIS collaborations and research patterns.
Findings
The analysis concluded that most MIS professors focused primarily on SCIE-/SSCI-/TSSCI-/core indexed journals after 2005. Professors from public universities were drawn to collaboration and publishing in high-quality-based journals, while professors from private universities focused more on quantity-based publications. Female professors, by contrast, have a slightly higher single-authorship publication rate in SCIE-/SSCI-/TSSCI-indexed journals than do male professors. Meanwhile, professors in northern Taiwan emphasized quantity-based journal publications, while a focus on quality was more typical in the south. Furthermore, National Cheng Kung University has the most single-authorship or intrauniversity publications in SCIE-/SSCI-/TSSCI-/core journals, and National Sun Yat-Sen University published more SSCI-indexed articles than SCIE-indexed articles. All of these findings show that there is an explicit relation between MOE evaluation policies and MIS faculty members' collaboration/publication strategies.
Originality/value
The above findings explain how MOE evaluation policies affected MIS faculty members' collaboration and publication strategies in Taiwan, and the authors hope that such findings can constitute a resource for understanding and characterizing networking with MIS departments in Taiwan.