Abstract
Abstract. The aim of this article is to assess if the data provided by soft classifiers and uncertainty measures can be used to identify regions with different levels of accuracy in a classified image. To this aim a soft Bayesian classifier was used, which enables the assignment of classifications confidence levels to all pixels. Two uncertainty measures were also used, namely the Relative Maximum Deviation (RMD) uncertainty measure and the Normalized Entropy (NE). The approach was tested on a case study. A multispectral IKONOS image was classified and the classification uncertainty and confidence where computed and analysed. Regions with different levels of uncertainty and confidence were identified. Reference datasets were then used to assess the classification accuracy of the whole study area and also in the regions with different levels of uncertainty and confidence. A comparative analysis was made on the variation of accuracy and classification uncertainty and confidence along the map and per class. The results show that for the regions with more uncertainty or less confidence the spatially constrained confusion matrices always generate lower values of global accuracy than for global accuracy of the regions with less uncertainty or more confidence. The analysis of the user’s and producer’s accuracy also shows the same general tendency. Proposals are then made on methodologies to use the information provided by the uncertainty and confidence to identify less reliable regions and also to improve classification results using fully automated approaches.
Highlights
The production of Land Cover Maps (LCM) through the classification of multispectral images is fundamental for many applications
The accuracy assessment of the resulting maps is made by selecting reference data and creating a confusion matrix that allows the computation of accuracy indices, which are usually obtained for the whole map and do not show the spatial variation of the map accuracy
3.2.2 Uncertainty and confidence: Figure 3 shows the spatial distribution the uncertainty obtained with the two uncertainty measures and the classification confidence, and Table 2 the statistical information on the obtained uncertainty and confidence values
Summary
The production of Land Cover Maps (LCM) through the classification of multispectral images is fundamental for many applications. The classification of images into a set of classes is usually made with automatic classification approaches, which require the selection of classifiers and training data. This process is very sensitive to both these choices and the final product is subject to error and uncertainty. The accuracy assessment of the resulting maps is made by selecting reference data and creating a confusion matrix that allows the computation of accuracy indices, which are usually obtained for the whole map and do not show the spatial variation of the map accuracy. It was already shown that this additional information, obtained for each one of the pixels, may be used to compute classification uncertainty and to assess its spatial variation. The development of automated methodologies that enable to control the quality of the classification results is becoming increasingly important with the exponential increase of the available images, making the identification of reference data to create the traditional accuracy matrices difficult or event impractical when classification results are necessary in real or near real time
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
