Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods
| Autor: | Ufuk Efe, A. Aydin Alatan, Kutalmis Gokalp Ince |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Matching (statistics) Pixel Computer science Image matching business.industry Nearest neighbor search Deep learning Ratio test Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Scale-invariant feature transform Pattern recognition Design for manufacturability Artificial intelligence business |
| DOI: | 10.48550/arxiv.2108.08179 |
| Popis: | 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. Comment: 8 pages, 2 figures, 3 tables, ICCV 2021 TradiCV Workshop |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|