IEEE Transactions on Pattern Analysis and Machine Intelligence · 1986 · 110 citations · 7 references
ComputingComputer ScienceBiomedical ImagingComputer VisionDigital ImagingCamera ProjectionDigital Image ProcessingImage ProcessingImage Registration
In many fields such as aerospace and biomedical imaging, image sequences suffer from unpredictable camera and scene movements that require displacement estimation for stable display, typically demanding computationally intensive two‑dimensional algorithms. The study proposes a novel image registration algorithm that relies solely on one‑dimensional Fourier transforms. This algorithm achieves registration by applying one‑dimensional Fourier transforms to determine image displacements, thereby reducing computational complexity compared to conventional two‑dimensional methods. Preliminary experimental results confirm the feasibility of the proposed one‑dimensional Fourier‑based registration algorithm.
In many application fields (e.g., aerospace and biomedical image processing), one has to deal with a sequence of images whose observation is made difficult by unpredictable relative movements of the camera and the scene. In order to obtain a stable display, the displacement of each image in the sequence with respect to one chosen as a reference must be preliminarily determined. This would usually require two-dimensional algorithms, involving a considerable computational effort. This work discusses a new algorithm for image registration, which requires only one-dimensional Fourier transformations. Preliminary experimental results are reported.
7
The phase correlation image alignment method
C. D. Kuglin · Medical Entomology and Zoology · 1975 · 1.1K citations
On the Hough Technique for Curve Detection
Sklansky · IEEE Transactions on Computers · 1978 · 217 citations