CIELab Color Moments: Alternative Descriptors for LANDSAT Images Classification System
Abstract: This study compares
the image classification system based
on normalized difference
vegetation index (NDVI) and Latent
Dirichlet Allocation (LDA)
using CIELab color
moments as image
descriptors. It was
implemented for LANDSAT images
classification by evaluating the accuracy values of classification systems. The
aim of this study is to evaluate whether the
CIELab color moments
can be used
as an alternatif
descriptor replacing NDVI
when it is implemented using LDA-based classification
model. The result shows that the
LDA-based image classification system using CIELab color moments provides
better performance accuracy than the NDVI-based image classification system, i.e 87.43%
and 86.25% for
LDA-based and NDVI-based respectively.
Therefore, we conclude that the CIELab color moments which
are implemented under the
LDA-based image classification system
can be assigned
as alternative image descriptors
for the remote sensing image classification systems with the limited data
availability, especially when the data only available in true color composite
images.
Keywords: Normalized
Difference Vegetation Index, CIELab,
color moments, Latent
Dirichlet Allocation, LANDSAT, remote sensing image classification
Author: Retno Kusumaningrum,
Hisar Maruli Manurung, Aniati Murni Arymurthy
Journal Code: jptinformatikagg140004
