Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods

被引:4
|
作者
Efe, Ufuk [1 ]
Ince, Kutalmis Gokalp [1 ]
Alatan, A. Aydin [1 ]
机构
[1] Middle East Tech Univ, Dept Elect & Elect Engn, Ctr Image Anal OGAM, Ankara, Turkey
关键词
D O I
10.1109/ICCVW54120.2021.00283
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning-based image matching methods are improved significantly during the recent years. Although these methods are reported to outperform the classical techniques, the performance of the classical methods is not examined in detail. In this study, we compare classical and learning-based methods by employing mutual nearest neighbor search with ratio test and optimizing the ratio test threshold to achieve the best performance on two different performance metrics. After a fair comparison, the experimental results on HPatches dataset reveal that the performance gap between classical and learning-based methods is not that significant. Throughout the experiments, we demonstrated that SuperGlue is the state-of-the-art technique for the image matching problem on HPatches dataset. However, if a single parameter, namely ratio test threshold, is carefully optimized, a well-known traditional method SIFT performs quite close to SuperGlue and even outperforms in terms of mean matching accuracy (MMA) under 1 and 2 pixel thresholds. Moreover, a recent approach, DFM, which only uses pre-trained VGG features as descriptors and ratio test, is shown to outperform most of the well-trained learning-based methods. Therefore, we conclude that the parameters of any classical method should be analyzed carefully before comparing against a learning-based technique.
引用
收藏
页码:2506 / 2513
页数:8
相关论文
共 50 条
  • [41] Low Pixel Resolution Hyperspectral Image Mosaics Generation Using Learning-Based Feature Matching
    Perera, Chamika Janith
    Premachandra, Chinthaka
    Kawanaka, Hiroharu
    IEEE ACCESS, 2023, 11 : 104084 - 104093
  • [42] Learning-based Declarative Query Optimization
    Tripathi, Shivani
    CODS-COMAD 2021: PROCEEDINGS OF THE 3RD ACM INDIA JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE & MANAGEMENT OF DATA (8TH ACM IKDD CODS & 26TH COMAD), 2021, : 416 - 416
  • [43] Learning-based versus established image registration methods for paediatric voxel-based analysis
    Henderson, Edward G. A.
    Osorio, Eliana M. Vasquez
    Davey, Angela
    Aznar, Marianne C.
    RADIOTHERAPY AND ONCOLOGY, 2024, 197 : S315 - S317
  • [44] Learning-based parameter prediction for quality control in three-dimensional medical image compression
    Hou, Yuxuan
    Ren, Zhong
    Tao, Yubo
    Chen, Wei
    FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2021, 22 (09) : 1169 - 1178
  • [45] A powerful Peripheral Arterial Disease detection using machine learning-based severity level classification model and hyper parameter optimization methods
    Sasikala, P.
    Mohanarathinam, A.
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 90
  • [46] Learning-based natural geometric matching with homography prior
    Xu, Yifang
    Liao, Tianli
    Chen, Jing
    ELECTRONICS LETTERS, 2018, 54 (23) : 1328 - 1329
  • [47] Rapid Learning-Based and Geologically Consistent History Matching
    Pejman Tahmasebi
    Muhammad Sahimi
    Mehrdad G. Shirangi
    Transport in Porous Media, 2018, 122 : 279 - 304
  • [48] Deep Learning-Based Corresponding Points Fast Matching
    Orumi, Mohammad Ali Bagheri
    Famouri, Mahmoud
    Azimifar, Zohreh
    Nazemi, Azadeh
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE (ICPRAI 2018), 2018, : 256 - 260
  • [49] Learning-Based Template Matching for Robot Arm Grasping
    Le, Minh-Tri
    Lien, Jenn-Jier James
    2021 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2021, : 1763 - 1768
  • [50] Learning-based Relational Object Matching Across Views
    Elich, Cathrin
    Armeni, Iro
    Oswald, Martin R.
    Pollefeys, Marc
    Stueckler, Joerg
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA, 2023, : 5999 - 6005