Multi-stage Feature Fusion Network for Edge Detection of Dunhuang Murals

被引:0
|
作者
Wang, Jianhua [1 ]
Liu, Baokai [1 ]
Li, Jiacheng [1 ]
Liu, Wenjie [1 ]
Du, Shiqiang [2 ]
机构
[1] Northwest Minzu Univ, Chinese Natl Informat Technol Res Inst, Lanzhou, Peoples R China
[2] Northwest Minzu Univ, Coll Math & Comp Sci, Lanzhou, Peoples R China
关键词
Dunhuang murals; Edge detection; Spatial attention; Multi-stage feature fusion;
D O I
10.1109/CCDC58219.2023.10327241
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Dunhuang murals have generally suffered serious damage due to natural disasters and human factors. As a result, the conservation and restoration of Dunhuang murals are becoming increasingly urgent, in which the line drawings of Dunhuang murals are an important work in the restoration of Dunhuang murals. The line drawings of the Dunhuang murals can be regarded as an image edge detection task. Although many CNN-based edge detection methods have made significant progress, they still produce thick edges and non-edges in the Dunhuang murals dataset. To solve this problem, we propose a novel edge detection method for generating line drawings of Dunhuang murals. Firstly, a novel loss function is proposed for edge detection, which uses focal Tversky loss to effectively suppress the background pixels near the edge pixels and allows CNN to produce sharp edges. Moreover, the proposed network introduces the dilated convolution modules and the spatial attention modules in each side output features to fully learn hierarchical features and obtain richer scale features. Finally, the results of experiments conducted on the BIPED dataset and the Dunhuang murals dataset show that the proposed method can generate richer and sharper edge maps.
引用
收藏
页码:4684 / 4689
页数:6
相关论文
共 50 条
  • [1] Inpainting of Dunhuang Murals Under Multi-Stage Stacking Fusion
    Wu, Kaijun
    Shan, Hongquan
    Tian, Bin
    Yu, Tianxiu
    Zhou, Yanlin
    [J]. Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2024, 53 (04): : 551 - 559
  • [2] Multi-stage feature-fusion dense network for motion deblurring
    Guo, Cai
    Wang, Qian
    Dai, Hong-Ning
    Li, Ping
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 90
  • [3] A multi-stage feature fusion defogging network based on the attention mechanism
    Song, Yuqin
    Zhao, Jitao
    Shang, Chunliang
    [J]. JOURNAL OF SUPERCOMPUTING, 2024, 80 (04): : 4577 - 4599
  • [4] Multi-Stage Feature Fusion Network for Video Super-Resolution
    Song, Huihui
    Xu, Wenjie
    Liu, Dong
    Liu, Bo
    Liu, Qingshan
    Metaxas, Dimitris N.
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 2923 - 2934
  • [5] A multi-stage feature fusion defogging network based on the attention mechanism
    Yuqin Song
    Jitao Zhao
    Chunliang Shang
    [J]. The Journal of Supercomputing, 2024, 80 (4) : 4577 - 4599
  • [6] Convolution Neural Network with Selective Multi-Stage Feature Fusion: Case Study on Vehicle Rear Detection
    Lee, Won-Jae
    Kim, Dong W.
    Kang, Tae-Koo
    Lim, Myo-Taeg
    [J]. APPLIED SCIENCES-BASEL, 2018, 8 (12):
  • [7] A Multi-Stage Progressive Network with Feature Transmission and Fusion for Marine Snow Removal
    Liu, Lixin
    Liao, Yuyang
    He, Bo
    Kwan, Chiman
    [J]. SENSORS, 2024, 24 (02)
  • [8] A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition
    Zou, Shinan
    Xiong, Jianbo
    Fan, Chao
    Yu, Shiqi
    Tang, Jin
    [J]. 2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB, 2023,
  • [9] Multi-Stage Feature Fusion Object Detection Method for Remote Sensing Image
    Chen, Li
    Zhang, Fan
    Guo, Wei
    Huang, Yun
    [J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2023, 51 (12): : 3520 - 3528
  • [10] Multi-Stage Multi-Scale Local Feature Fusion for Infrared Small Target Detection
    Wang, Yahui
    Tian, Yan
    Liu, Jijun
    Xu, Yiping
    [J]. REMOTE SENSING, 2023, 15 (18)