Scale detection via keypoint density maps in regular or near-regular textures

Risultato della ricerca: Articlepeer review

10 Citazioni (Scopus)

Abstract

In this paper we propose a new method to detect the global scale of images with regular, near regular, orhomogenous textures. We define texture ‘‘scale’’ as the size of the basic elements (texels or textons) thatmost frequently occur into the image. We study the distribution of the interest points into the image, atdifferent scale, by using our Keypoint Density Maps (KDMs) tool. A ‘‘mode’’ vector is built computing themost frequent values (modes) of the KDMs, at different scales. We observed that the mode vector is quasilinear with the scale. The mode vector is properly subsampled, depending on the scale of observation, andcompared with a linear model. Texture scale is estimated as the one which minimizes an error functionbetween the related subsampled vector and the linear model. Results, compared with a state of the artmethod, are very encouraging.
Lingua originaleEnglish
pagine (da-a)2071-2078
Numero di pagine8
RivistaPattern Recognition Letters
Volume34
Stato di pubblicazionePublished - 2013

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint Entra nei temi di ricerca di 'Scale detection via keypoint density maps in regular or near-regular textures'. Insieme formano una fingerprint unica.

Cita questo