Projects per year
Abstract
Scale-invariance, good localization and robustness to noise and distortions are the main properties that a local feature detector should possess. Most existing local feature detectors find excessive unstable feature points that increase the number of keypoints to be matched and the computational time of the matching step. In this paper, we show that robust and accurate keypoints exist in the specific scale-space domain. To this end, we first formulate the superimposition problem into a mathematical model and then derive a closed-form solution for multiscale analysis. The model is formulated via difference-of-Gaussian (DoG) kernels in the continuous scale-space domain, and it is proved that setting the scale-space pyramid's blurring ratio and smoothness to 2 and 0.627, respectively, facilitates the detection of reliable keypoints. For the applicability of the proposed model to discrete images, we discretize it using the undecimated wavelet transform and the cubic spline function. Theoretically, the complexity of our method is less than 5% of that of the popular baseline Scale Invariant Feature Transform (SIFT). Extensive experimental results show the superiority of the proposed feature detector over the existing representative hand-crafted and learning-based techniques in accuracy and computational time. The code and supplementary materials can be found at https://github.com/mogvision/FFD.
Original language | English |
---|---|
Article number | 9292438 |
Pages (from-to) | 1153-1168 |
Number of pages | 16 |
Journal | IEEE Transactions on Image Processing |
Volume | 30 |
Early online date | 14 Dec 2020 |
DOIs | |
Publication status | Published - 2021 |
Keywords
- difference-of-Gaussian (DoG)
- Feature detection
- robustness
- scale-invariant
- undecimated wavelet transform
Fingerprint
Dive into the research topics of 'FFD: Fast Feature Detector'. Together they form a unique fingerprint.Profiles
-
Bernie Tiddeman
- Department of Computer Science - Professor in Computer Science
Person: Teaching And Research
Projects
- 1 Finished
-
A China-UK joint phenomics consortium to dissect the basis of crop stress resistance in the face of climate change
Doonan, J. (PI), Han, J. (CoI), Liu, Y. (CoI) & Mur, L. (CoI)
Biotechnology and Biological Sciences Research Council
01 Jul 2018 → 31 Dec 2023
Project: Externally funded research