Centre de documentation
scientifique

Comparison of gray-level reduction and different texture spectrum encoding methods for land-use classification using a panchromatic Ikonos image / B. Xu in Photogrammetric Engineering & Remote Sensing, PERS, vol 69 n° 5 (May 2003)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 69 n° 5 (May 2003) . - pp 529 - 536 Titre : Comparison of gray-level reduction and different texture spectrum encoding methods for land-use classification using a panchromatic Ikonos image Type de document : Article/Communication Auteurs : B. Xu, Auteur ; E. Seto, Auteur ; P. Gong, Auteur ; R. Spear, Auteur Année de publication : 2003 Article en page(s) : pp 529 - 536 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse spectrale [Termes IGN] analyse texturale [Termes IGN] classification contextuelle [Termes IGN] compression d'image [Termes IGN] image à résolution métrique [Termes IGN] image Ikonos [Termes IGN] image panchromatique [Termes IGN] niveau de gris (image) [Termes IGN] texture d'image [Termes IGN] uniformisation d'histogramme [Termes IGN] utilisation du sol Résumé : (Auteur) In this paper, we evaluate the potential of a frequency-based contextual classifier (FBC) for landuse classification with a panchromatic Ikonos image. To capture the spatial arrangement of image graylevel values and use such information in image classification, we applied texture spectrum (TS) directly in the FBC. The effects of several data preprocessing and reduction methods on the performance of the FBC are also evaluated. The methods include four graylevel reduction (GLR) techniques and several modifications to the TS technique. The purpose of data reduction is to improve the classification efficiency of the FBC. The GLR schemes were minmax linear compression (LC), gray level binning (BN), histogram equalization (HE), and piecewise nonlinear compression (PC). Instead of using the texture measures derived from the texture spectrum, we directly applied texture spectra of various sizes in the classification. We modified the encoding algorithm in the TS and were able to reduce the number of texture units from its original 6561 to 256, 81, and 16, leading to as much as a 410 times computation efficiency. The original image and GLR images were subsequently classified with the FBC. We compared the classification accuracies and found that the GLR methods resulted in accuracies similar to that of the original image (within 0.03 kappa value). There was little difference in classification accuracy (within 0.03 kappa value) among the three modified TS methods, which were all outperformed by the original TS method. All TS methods performed considerably better than the use of the original image and the GLR methods. Numéro de notice : A2003-083 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.69.5.529 En ligne : http://dx.doi.org/10.14358/PERS.69.5.529 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22379 [article]