Improved Superpixels Generation Algorithm for Qualified Graph-Based Technique

The international arab journal of information technology

article

Asma Fejjari¹  Karim Saheb Ettabaa²  Ouajdi Korbaa¹ 

[1] MARS Research Laboratory, ISITCom, 4011, Hammam Sousse, University of Sousse;IMT Atlantique, Iti Department

关键词: Hyperspectral images;    dimensionality reduction;    graph;    MSEP;    superpixels;    improved SLIC;   

DOI  :  10.34028/iajit/19/6/13

学科分类：计算机科学（综合）

来源: Zarqa University

【 摘 要 】

Hyperspectral Images (HSIs) represent an important source of information in the remote sensing field. Indeed,HSIs, which collect data in many spectral bands, are more simple interpretable and provide a detailed information aboutinterest areas. However, hyperspectral imaging systems generate a huge amount of redundant data and an important level ofnoise. Dimensionality reduction is an important task that attempts to reduce dimensionality and remove noise so as to enhancethe accuracy of remote sensing applications. The first dimensionality reduction approaches date back to 1970s, and variousmodel-based methods have been proposed since these years. This field has known an increasing attention by the suggestion ofgraph based models that have yielded promising results. While graph based approaches generate considerable outputs, thesemodels require often an important processing time to handle data. In this work, we aim to reduce the computational burden ofa promising graph based method called the Modified Schroedinger Eigenmap Projections (MSEP). In this respect, we suggestan efficient superpixel algorithm, called Improved Simple Linear Iterative Clustering (Improved SLIC), to lessen the heavycomputational load of the MSEP method. The proposed approach exploits the superpixels as inputs instead of pixels; and thenruns the MSEP algorithm. While respecting the HSIs properties, the proposed scheme illustrates that the MSEP method can beperformed with computational efficiency.

【 授权许可】

Unknown