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

08/18/2021
by   Ufuk Efe, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/08/2023

Deep Learning based Image Watermarking: A Brief Survey

The act of secretly embedding and extracting a watermark on a cover imag...
research
06/06/2021

Deep Matching Prior: Test-Time Optimization for Dense Correspondence

Conventional techniques to establish dense correspondences across visual...
research
10/22/2018

A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards

We present new methods for apple detection and counting based on recent ...
research
08/26/2018

Single Image Dehazing Based on Generic Regularity

This paper proposes a novel technique for single image dehazing. Most of...
research
07/20/2019

Evaluation of Distance Measures for Feature based Image Registration using AlexNet

Image registration is a classic problem of computer vision with several ...
research
07/28/2021

Subjective evaluation of traditional and learning-based image coding methods

We conduct a subjective experiment to compare the performance of traditi...
research
06/14/2021

DFM: A Performance Baseline for Deep Feature Matching

A novel image matching method is proposed that utilizes learned features...

Please sign up or login with your details

Forgot password? Click here to reset