Lingjie Yu

Prof. Dr. Lingjie Yu

Xi'an Polytechnic University, Xi'an, China
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in Computers in Industry
Verified
Journal Article
Closed access
MCMengqi Chen
Mengqi Chen
LYLingjie Yu
Lingjie Yu
CZChao Zhi
Chao Zhi
RSRunjun Sun
Runjun Sun
SZShuangwu Zhu
Shuangwu Zhu
YZYuming Zhang
Yuming Zhang

18 February 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MZMengqiu Zhu
Mengqiu Zhu
LYLingjie Yu
Lingjie Yu
ZWZongbiao Wang
Zongbiao Wang
ZKZhenxia Ke
Zhenxia Ke
CZChao Zhi
Chao Zhi
Establishing an accurate objective evaluation metric of image sharpness is crucial for image analysis, recognition and quality measurement. In this review, we highlight recent advances in no-reference image quality assessment research, divide the reported algorithms into four groups (spatial domain-based methods, spectral domain-based methods, learning-based methods and combination methods) and outline the advantages and disadvantages of each method group. Furthermore, we conduct a brief bibliometric study with which to provide an overview of the current trends from 2013 to 2021 and compare the performance of representative algorithms on public datasets. Finally, we describe the shortcomings and future challenges in the current studies.

20 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YZYouyong Zhou
Youyong Zhou
LYLingjie Yu
Lingjie Yu
CZChao Zhi
Chao Zhi
CHChuwen Huang
Chuwen Huang
SWShuai Wang
Shuai Wang
SFSida Fu
Sida Fu
As an important branch in the field of image fusion, the multi-focus image fusion technique can effectively solve the problem of optical lens depth of field, making two or more partially focused images fuse into a fully focused image. In this paper, the methods based on boundary segmentation was put forward as a group of image fusion method. Thus, a novel classification method of image fusion algorithms is proposed: transform domain methods, boundary segmentation methods, deep learning methods, and combination fusion methods. In addition, the subjective and objective evaluation standards are listed, and eight common objective evaluation indicators are described in detail. On the basis of lots of literature, this paper compares and summarizes various representative methods. At the end of this paper, some main limitations in current research are discussed, and the future development of multi-focus image fusion is prospected.

1 February 2023 in Textile Research Journal
Verified
Journal Article
Closed access
JNJingjing Nan
Jingjing Nan
CZChao Zhi
Chao Zhi
JMJiaguang Meng
Jiaguang Meng
MMMenghe Miao
Menghe Miao
LYLingjie Yu
Lingjie Yu
Fiber-reinforced polymer (FRP) composites are widely used in marine engineering fields, such as coastal construction, offshore bridges, submarines, and warships, owing to their light weight, high strength, and corrosion resistance. However, owing to the harsh marine environment, FRP composites used in the ocean are inevitably affected by seawater aging. Therefore, it is necessary to investigate the seawater aging properties of FRP composites. In this study, the seawater aging mechanism of FRP composites is summarized, and the influence factors (matrix type, fiber type, immersion temperature, loading mode, and aging method) of seawater aging on the mechanical properties of FRP composites are further reviewed in detail. Based on this, the method for improving the seawater resistance of FRP composites is summarized. In addition, the research schemes of accelerated aging of FRP composites and commonly used life prediction models are summarized, and the methods and suggestions for improving the accuracy of life prediction are further discussed.

1 February 2020 in Polymers
Verified
Journal Article
Open access
PDF file
CZChao Zhi
Chao Zhi
MDMingjuan Du
Mingjuan Du
ZSZhaoling Sun
Zhaoling Sun
MWMengjie Wu
Mengjie Wu
XHXiaoyi He
Xiaoyi He
LYLingjie Yu
Lingjie Yu
In this study, a new type ternary composite, called warp-knitted spacer fabric reinforced syntactic foam (WKSF-SF), with the advantages of high mechanical properties and a lower density, was proposed. Then, a meso-mechanics theoretical model based on the Eshelby–Mori–Tanaka equivalent inclusion method, average stress method and composite hybrid theory was established to predict the compression modulus of WKSF-SF. In order to verify the validity of this model, compression modulus values of theoretical simulations were compared with the quasi-static compression experiment results. The results showed that the addition of suitable WKSF produces at least 15% improvement in the compressive modulus of WKSF-SF compared with neat syntactic foam (NSF). Meanwhile, the theoretical model can effectively simulate the values and variation tendency of the compression modulus for different WKSF-SF samples, and is especially suitable for the samples with smaller wall thickness or a moderate volume fraction of microballoons (the deviations is less than 5%). The study of the meso-mechanical properties of WKSF-SF will help to increase understanding of the compression properties of this new type composite deeply. It is expected that WKSF-SF can be used in aerospace, marine, transportation, construction, and other fields.

15 March 2024 in Textile Research Journal
Verified
Journal Article
Closed access
YXYiqin Xu
Yiqin Xu
CZChao Zhi
Chao Zhi
SWShuai Wang
Shuai Wang
JCJianglong Chen
Jianglong Chen
RSRunjun Sun
Runjun Sun
LYLingjie Yu
Lingjie Yu
When deep learning is applied to intelligent textile defect detection, the insufficient training data may result in low accuracy and poor adaptability of varying defect types of the trained defect model. To address the above problem, an enhanced generative adversarial network for data augmentation and improved fabric defect detection was proposed. Firstly, the dataset is preprocessed to generate defect localization maps, which are combined with non-defective fabric images and input into the network for training, which helps to better extract defect features. In addition, by utilizing a Double U-Net network, the fusion of defects and textures is enhanced. Next, random noise and the multi-head attention mechanism are introduced to improve the model’s generalization ability and enhance the realism and diversity of the generated images. Finally, we merge the newly generated defect image data with the original defect data to realize the data enhancement. Comparison experiments were performed using the YOLOv3 object detection model on the training data before and after data enhancement. The experimental results show a significant accuracy improvement for five defect types – float, line, knot, hole, and stain – increasing from 41%, 44%, 38%, 42%, and 41% to 78%, 76%, 72%, 67%, and 64%, respectively.