Processing

Please wait...

Settings

Settings

Goto Application

1. WO2014176641 - IMAGE CLUSTERING FOR ESTIMATION OF ILLUMINATION SPECTRA

Publication Number WO/2014/176641
Publication Date 06.11.2014
International Application No. PCT/AU2014/000491
International Filing Date 02.05.2014
IPC
G06K 9/36 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
CPC
G06K 9/0063
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
0063Recognising patterns in remote scenes, e.g. aerial images, vegetation versus urban areas
G06K 9/4661
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4661related to illumination properties, e.g. according to a reflectance or lighting model
G06K 9/52
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
52by deriving mathematical or geometrical properties from the whole image
G06K 9/6218
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6218Clustering techniques
Applicants
  • NATIONAL ICT AUSTRALIA LIMITED [AU]/[AU]
Inventors
  • GU, Lin
  • HUYNH, Cong Phuoc
  • ROBLES-KELLY, Antonio
Agents
  • FB RICE
Priority Data
201390156403.05.2013AU
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) IMAGE CLUSTERING FOR ESTIMATION OF ILLUMINATION SPECTRA
(FR) REGROUPEMENT D'IMAGES POUR ESTIMATION DE SPECTRES D'ÉCLAIRAGE
Abstract
(EN)
This disclosure concerns processing of electronic images, such as hyperspectral or multispectral images. A processor performs a method for estimating an illumination spectrum of an image which defines an input spectrum for each point of the image. The processor determines for each point of a first set of points a measure of variation in relation to the input spectrum of that point. The processor then selects one point from the first set based on the measure of variation. The processor determines a cluster of points based on the input spectrum of the selected point and determines an estimate for the illumination spectrum based on the input spectra of points in the cluster. Since the processor selects a point based on the measure of variation and then determines a cluster based on that point, it performs better than using other methods where the cluster is determined based on a random starting point, for example.
(FR)
La présente invention concerne le traitement d'images électroniques, telles que des images hyperspectrales ou multispectrales. Un processeur réalise un procédé d'estimation d'un spectre d'éclairage d'une image qui définit un spectre d'entrée pour chaque point de l'image. Le processeur détermine pour chaque point d'un premier ensemble de points une mesure de variation en relation avec le spectre d'entrée de ce point. Le processeur sélectionne ensuite un point du premier ensemble sur la base de la mesure de la variation. Le processeur détermine un groupe de points sur la base du spectre d'entrée du point sélectionné et détermine une estimation pour le spectre d'éclairage sur la base des spectres d'entrée de points dans le groupe. Etant donné que le processeur sélectionne un point sur la base de la mesure de variation et détermine ensuite un groupe sur la base de ce point, ceci fonctionne mieux que d'utiliser d'autres procédés dans lesquels le groupe est déterminé sur la base d'un point de départ aléatoire, par exemple.
Related patent documents
Latest bibliographic data on file with the International Bureau