|
|
|
|
|
Log Polar Magnitude (LPM) is a rotation, scale and illumination invariant feature descriptor that achieves comparable performance to SIFT on a large variety of image registration problems but with much shorter feature vectors. The descriptor is based on the Log Polar Transform followed by a Fourier Transform and selection of the magnitude spectrum components. Selecting different frequency components allows optimizing for image patterns specific for a particular application. In addition, by relying only on feature detector coordinates and (optionally) feature sizes LPM is completely detector independent. A shorter feature vector results in better memory usage and faster matching. This combined with the fact that LPM does not require a time-consuming feature orientation estimation (the rotation invariance is achieved solely by using the magnitude spectrum of the Log Polar Transform) makes it particularly attractive to applications with limited hardware capacity. Our evaluation (see the paper below for more information) showed that if performs better than SIFT on both fluorescence and transmission elctron microscopy datasets which shows that it is particularly useful in applications with this type of images. Cite this software as: Matuszewski, D.J., Hast, A., Wählby, C., Sintorn, I.-M. (2016) A short feature vector for image matching: the Log Polar Magnitude feature descriptor. PLOS ONE, [submitted]. The MATLAB source code and the image datasets used in the paper are available free of charge; download here. |
|