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
  • [31] Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning-Based Methods
    Sen, Ovishake
    Fuad, Mohtasim
    Islam, Md Nazrul
    Rabbi, Jakaria
    Masud, Mehedi
    Hasan, Md Kamrul
    Awal, Md Abdul
    Fime, Awal Ahmed
    Fuad, Md Tahmid Hasan
    Sikder, Delowar
    Iftee, Md Akil Raihan
    IEEE ACCESS, 2022, 10 : 38999 - 39044
  • [32] Learning-Based Image Compression With Parameter-Adaptive Rate-Constrained Loss
    Guerin Jr, Nilson D.
    da Silva, Renam Castro
    Macchiavello, Bruno
    IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 1099 - 1103
  • [33] LEAPME: Learning-based Property Matching with Embeddings
    Ayala, Daniel
    Hernandez, Inma
    Ruiz, David
    Rahm, Erhard
    DATA & KNOWLEDGE ENGINEERING, 2022, 137
  • [34] Bangla natural language processing: A comprehensive analysis of classical, machine learning, and deep learning-based methods
    Sen, Ovishake
    Fuad, Mohtasim
    Islam, M.D. Nazrul
    Rabbi, Jakaria
    Masud, Mehedi
    Hasan, Kamrul
    Awal, M.D. Abdul
    Fime, Awal Ahmed
    Fuad, M.D. Tahmid Hasan
    Sikder, Delowar
    Iftee, M.D. Akil Raihan
    IEEE Access, 2022, 10 : 38999 - 39044
  • [35] Photovoltaic Cells Parameter Estimation Using an Enhanced Teaching–Learning-Based Optimization Algorithm
    Abdelhady Ramadan
    Salah Kamel
    Ahmed Korashy
    Juan Yu
    Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 2020, 44 : 767 - 779
  • [36] Transfer learning-based parameter optimization for improved 3D NAND performance
    Dibyadrasta Sahoo
    Ankit Gaurav
    Sanjeev Kumar Manhas
    Journal of Computational Electronics, 2025, 24 (2)
  • [37] Empirical Analysis of Learning-based Malware Detection Methods using Image Visualization
    Sheneamer, Abdullah
    Alhazmi, Essa
    Henrydoss, James
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2022, 13 (04) : 925 - 936
  • [38] Editorial: Weakly supervised deep learning-based methods for brain image analysis
    Zhu, Hancan
    Liu, Mingxia
    Tang, Zhenyu
    Wang, Shuai
    FRONTIERS IN NEUROINFORMATICS, 2022, 16
  • [39] DICTIONARY LEARNING-BASED IMAGE COMPRESSION
    Wang, Hao
    Xia, Yong
    Wang, Zhiyong
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3235 - 3239
  • [40] Learning-Based Conditional Image Compression
    Shen, Tianma
    Peng, Wen-Hsiao
    Shih, Huang -Chia
    Liu, Ying
    2024 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS 2024, 2024,