FFD: Fast Feature Detector

Morteza Ghahremani, Yonghuai Liu*, Bernard Tiddeman

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)
125 Downloads (Pure)

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 languageEnglish
Article number9292438
Pages (from-to)1153-1168
Number of pages16
JournalIEEE Transactions on Image Processing
Volume30
Early online date14 Dec 2020
DOIs
Publication statusPublished - 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.

Cite this