Scale Normalized Radial Fourier Transform as a Robust Image Descriptor - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Scale Normalized Radial Fourier Transform as a Robust Image Descriptor


We present a new visual descriptor that combines a multi-scale Laplacian Profile with a Radial Discrete Fourier Transform. This descriptor exists at every position and scale in an image and provides a local feature vector that is both discriminant and robust to changes in orientation and scale. It has a variable description length, and thus can be easily adapted for a variety of applications, ranging from simple detection tasks on low power computing platforms to complex tasks requiring highly discriminant detectors. To demonstrate the discriminant power of this descriptor we employ it in its most compact form to construct a cascade of linear classifiers for detecting people in images. We compare this detector to cascades classifiers constructed using Haar wavelets, Gaussian derivatives and variable size block HOG descriptors. Our experiments show that a cascade with this descriptor performs well against the other three detectors when tested using a common publicly available data set. We examine the stability of the descriptor to changes in image rotation and scaling for different description lengths.
Fichier principal
Vignette du fichier
icpr2014_final.pdf (352.14 Ko) Télécharger le fichier
posterICPR2014_FINAL.pdf (522.6 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Format Other

Dates and versions

hal-01065463 , version 1 (18-09-2014)


  • HAL Id : hal-01065463 , version 1


Evanthia Mavridou, Manh-Dung Hoang, James L. Crowley, Augustin Lux. Scale Normalized Radial Fourier Transform as a Robust Image Descriptor. ICPR 2014, 22nd International Conference on Pattern Recognition, Aug 2014, Stockholm, Sweden. ⟨hal-01065463⟩
342 View
339 Download


Gmail Mastodon Facebook X LinkedIn More