A Bilateral Filter Based Post-Processing Approach for Supervised Spectral-Spatial Hyperspectral Image Classification

Abstract

To effectively improve the performance of representation based classifier, a spatial spectral joint classification post-processing approach is proposed, based on the application of edge preserving BF (Bilateral Filtering) method. The proposed framework includes two key processes: (1) the classifier (such as SRC, CRC, or KSRC) based on sparse representation of each pixel is used to obtain softclassified probabilities belonging to each information class for each pixel; (2) spatial spectral joint BF for the soft-classified probabilities map. It is aimed to integrate context-aware information for each pixel class labels. Under the spatial guidance image, extracted from the three principle component, a BF is employed to get the refined probability maps. The BF considers not only the spatial distance but it also considers the image context-aware distance which significantly improves the classification results. Finally, the class label is obtained by choosing the maximum probability criteria. The experimental results on three benchmark hyperspectral data sets showed that the “local smoothing” is efficient and has a potential to achieve high classification accuracy. All the algorithms are implemented with equal number of labeled samples and comparative results are presented in terms of visual classification map and numerical classification results. The major advantages of proposed method are: it is simple, noniterative and easy to implement. Hence, the advantages lead to significant usage in real applications.

Authors and Affiliations

B. N. Soomro, L. Xiou, M. M. Jawaid, S. H. Soomro, N. A. Jaffari

Keywords

Related Articles

Cyber Threats/Attacks and a Defensive Model to Mitigate Cyber Activities

Nowadays, every internet user is part of cyber world. In this way, millions of users, knowledge seekers, and service provider organizations are connected to each other, a vast number of common people shifted their everyd...

LTE and GPS based Deca Band Printed Antenna for Cellular Mobile Handset Communication Applications

This paper presents novel mobile phone antenna for radiations simultaneously in ten frequency bands for applications of LTE (Long-Term Evolution), GPS (Global Positioning System), GSM (Global System for Mobile Communicat...

Wind Potential Assessment Analysis of Jhampir, District Thatta Sindh, Pakistan

Wind potential analysis is analyzing how much wind energy is available in particular region. It is most important step because the economics of project depends on the site wind resources. Wind plant depends on the variat...

Early Skin Tumor Detection from Microscopic Images through Image Processing

The research is done to provide appropriate detection technique for skin tumor detection. The work is done by using the image processing toolbox of MATLAB. Skin tumors are unwanted skin growth with different causes and v...

Experimental Study on Gas Slippage of Tight Gas Sands in Kirthar Fold Belt Sindh, Pakistan

The laboratory experiments on samples from Kirthar fold belt of lower Indus basin Sindh Pakistan were carried out to investigate the effect of gas slippage under varying conditions of pore pressures and overburden stress...

Download PDF file
  • EP ID EP304822
  • DOI 10.22581/muet1982.1803.15
  • Views 94
  • Downloads 0

How To Cite

B. N. Soomro, L. Xiou, M. M. Jawaid, S. H. Soomro, N. A. Jaffari (2018). A Bilateral Filter Based Post-Processing Approach for Supervised Spectral-Spatial Hyperspectral Image Classification. Mehran University Research Journal of Engineering and Technology, 37(3), 615-630. https://europub.co.uk./articles/-A-304822