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

Impact of Storage Time, Rain and Quality of Molasses in the Production of Bioethanol

Due to environmental concerns and the rising prices of petroleum products, usually bio-ethanol is being produced in greater amount from sugar cane molasses in Pakistan. In this work various properties related to molasses...

Characterization of Solid Concrete Block Masonry

Masonry walls constituted of solid concrete blocks are used very commonly in the framed structures as well as in the load bearing structures in various parts of Pakistan. However, very limited understanding on the charac...

Calibration and Validation of an Experimental Setup for the Measurement of the Cylindrical Body Shapes and Curvatures of the Objects and Subjects through the Techniques of Rasterstereography

The intent of study is to establish a criterion for the experimental setup of rasterstereography, one that is more efficient, simple, accurate and precise to examine and analyse the curvature of the object or the subject...

Analysis of Improving the Power out of a Piezoelectric Energy Harvester Using Segmented Electrodes

Vibration-based EH (Energy Harvesting) using piezoelectric materials have been investigated by several research groups with the aim of harvesting maximum energy and providing power to low-powered wireless electronic syst...

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...

Download PDF file
  • EP ID EP304822
  • DOI 10.22581/muet1982.1803.15
  • Views 78
  • 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