Share Email Print
cover

Proceedings Paper

Determining optimum pixel size for classification
Author(s): Nicole M. Rodríguez-Carrión; Shawn D. Hunt; Miguel A. Goenaga-Jimenez; Miguel Vélez-Reyez
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This work describes a novel method of estimating statistically optimum pixel sizes for classification. Historically more resolution, smaller pixel sizes, are considered better, but having smaller pixels can cause difficulties in classification. If the pixel size is too small, then the variation in pixels belonging to the same class could be very large. This work studies the variance of the pixels for different pixel sizes to try and answer the question of how small, (or how large) can the pixel size be and still have good algorithm performance. Optimum pixel size is defined here as the size when pixels from the same class statistically come from the same distribution. The work first derives ideal results, then compares this to real data. The real hyperspectral data comes from a SOC-700 stand mounted hyperspectral camera. The results compare the theoretical derivations to variances calculated with real data in order to estimate different optimal pixel sizes, and show a good correlation between real and ideal data.

Paper Details

Date Published: 13 June 2014
PDF: 10 pages
Proc. SPIE 9088, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XX, 90880X (13 June 2014); doi: 10.1117/12.2051089
Show Author Affiliations
Nicole M. Rodríguez-Carrión, Univ. de Puerto Rico Mayagüez (United States)
Shawn D. Hunt, Univ. de Puerto Rico Mayagüez (United States)
Miguel A. Goenaga-Jimenez, Univ. de Puerto Rico Mayagüez (United States)
Miguel Vélez-Reyez, The Univ. of Texas at El Paso (United States)


Published in SPIE Proceedings Vol. 9088:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XX
Miguel Velez-Reyes; Fred A. Kruse, Editor(s)

© SPIE. Terms of Use
Back to Top