The comparison of PCA and discrete rough set for feature extraction of remote sensing image classification – A case study on rice classification, Taiwan

Abstract

Texture information offers an extensive solution for image classification by providing better accuracy of image information. However, huge amounts of improper additional texture information may result in a chaotic state, and this leads to uncertainty in the classification process. Considerable portion of earlier works have been carried out through the generally acknowledged procedure of Principal Components Analysis (PCA). However, the PCA method has flaws in the area of influenced and non-influenced attributes. On the whole, whether PCA provides an effective solution to determine the value of knowledge rule in image information still remains a question. This study proposes an innovative method, called Discrete Rough Set method, as a tool for image classification. This study focuses on two crucial issues: (1) The core attributes of the target categories in image classification are systematically analyzed while eliminating surplus attributes rationally; (2) The unique point of each attribute, which influenced the target categories, is successfully found. This is a crucial aspect that is very helpful for the construction of decision rule. Finally, in this study we utilized the expert knowledge classifier and the overall accuracy of Discrete Rough Set (96.67%) exceeds that of the conventional PCA (86.00%) of paddy rice area evaluation from Quickbird image. This result shows that the appropriate classification knowledge can be presented by Discrete Rough Set, and this information can effectively improve the accuracy of image classification.

An enhanced supervised spatial decision support system of image classification: consideration on the ancillary information of paddy rice area

“…In the original bands of Case (a), the producer accuracy and user accuracy are about 86% and 98.5%, respectively, for paddy rice identification. This result is very close to the conventional methods such as Maximum likelihood or PCA methods (Lei et al 2008). But for Cases (b) and (c) the accuracy is greatly improved; especially, the user accuracy is 100% (see Cases (b) and (c) in Table 1).…”

“…In fact, there are many other geostatistical measures such as covariance function, correlogram, general relative variogram, pairwise relative variogram, and rodogram. We used direct semi-variogram and semi-madogram as a reference which is fully tested for the best way to sieve out the image of paddy rice (Lei et al 2007(Lei et al , 2008.…”

A novel data mining technique of analysis and classification for landslide problems

“…In recent years, data mining approaches (Wan et al 2008;Lei et al 2007) offer a fresh approach to analyze landslides and geosciences. Our research used the Discrete Rough Set (DRS) method to tackle the difficult problem of landslide hazard prediction.…”

Development of a spatial decision support system for monitoring earthquake-induced landslides based on aerial photographs and the finite element method

“…For example, some researchers have focused on environmental variables versus statistical occurrence through the weights-of-evidence method (Van Westen et al, 2003), multi-variable statistical analysis with logistic regression (Santacana et al, 2003), and the frequency ratio method (Carrara et al, 1999;Lee and Sambath, 2006). On the other hand, data-mining approaches (Wan et al, , 2009aLei et al, 2008) have recently been seen as a solution for analyzing landslides and geodata.…”