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
  • [21] A learning-based framework for graph matching
    Van Wyk, MA
    Van Wyk, BJ
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2004, 18 (03) : 355 - 374
  • [22] A Review of Dense Stereo Image Matching Methods Based on Deep Learning
    Ji S.
    Luo C.
    Liu J.
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2021, 46 (02): : 193 - 202
  • [23] An Improved Teaching–Learning-Based Optimization for Multilevel Thresholding Image Segmentation
    Ziqi Jiang
    Feng Zou
    Debao Chen
    Jiahui Kang
    Arabian Journal for Science and Engineering, 2021, 46 : 8371 - 8396
  • [24] Machine learning-based multi-objective parameter optimization for indium electrorefining
    Fan, Hong-Qiang
    Zhu, Xuan
    Zheng, Hong-Xing
    Lu, Peng
    Wu, Mei-Zhen
    Peng, Ju-Bo
    Zhang, He-Sheng
    Qian, Quan
    SEPARATION AND PURIFICATION TECHNOLOGY, 2024, 328
  • [25] Oppositional Harris Hawks Optimization with Deep Learning-Based Image Captioning
    Kavitha, V. R.
    Nimala, K.
    Beno, A.
    Ramya, K. C.
    Kadry, Seifedine
    Kang, Byeong-Gwon
    Nam, Yunyoung
    COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 2023, 44 (01): : 579 - 593
  • [26] Heuristic particle swarm optimization learning-based image compression system
    Feng, Hsuan-Ming
    Chen, Ching-Yi
    Ye, Fun
    CYBERNETICS AND SYSTEMS, 2008, 39 (05) : 520 - 537
  • [27] Teaching–Learning-Based Optimization for Parameter Identification of an Activated Sludge Process Model
    Khoja I.
    Ladhari T.
    M’sahli F.
    Sakly A.
    Mathematical Models and Computer Simulations, 2022, 14 (3) : 516 - 531
  • [28] Teaching–learning-based Optimization Algorithm for Parameter Identification in the Design of IIR Filters
    Singh R.
    Verma H.K.
    Verma, H.K. (vermaharishgs@gmail.com), 1600, Springer (94): : 285 - 294
  • [29] Efficient learning-based blur removal method based on sparse optimization for image restoration
    Yang, Haoyuan
    Su, Xiuqin
    Chen, Songmao
    Zhu, Wenhua
    Ju, Chunwu
    PLOS ONE, 2020, 15 (03):
  • [30] Multimodal Representation Learning-Based Product Matching
    Feng, Changkai
    Chen, Wei
    Chen, Chao
    Xu, Tong
    Chen, Enhong
    CCKS 2022 - EVALUATION TRACK, 2022, 1711 : 180 - 190