مقاله انگلیسی رایگان در مورد طبقه بندی تصویر ابر طیفی نیمه نظارت شده – IEEE 2019

In hyperspectral image classification, the foremost task is that: how can we apply limited labeled samples to achieve good classification results? Spatial–spectral classification methods, which assign a label to each pixel regarding both spatial and spectral information, are effective to improve classification performance. Moreover, semisupervised learning (SSL) focuses on the scenario that the number of labeled data is rather small while a large number of unlabeled data are available. To complement spatial–spectral classification methods and semisupervised learning for each other, we propose a novel learning landscape features semisupervised framework (LLFSF) based on M-training algorithm and weighted spatial-spectral double layer SVM classifiers module (WSS-DSVM). In this novel framework, we first propose a SLIC (simple linear iterative clustering) based non-local superpixel segmentation algorithm to initially learn landscape feature and spatial composition. Then, we apply WSS-DSVM module to obtain initial classification maps. To better characterize complex scenes of hyperspectral images, we quantizes both the landscape diversity and separability from the initial classification map, which increase availability of spatial details and structural information of objects. Finally, we put some patches with lower accuracy into Multiple-training algorithm for further classification. In order to achieve an unbiased evaluation, we have evaluated the performance of LLFSF on three different scene hyperspectral data sets and compare it with that of three state-of-the-art hyperspectral image classification methods. The experimental results confirm the efficacy of the proposed framework.

Introduction

Recently, in pace with the rapid development of imaging technology, hyperspectral imagery can obtain a large amount of information about an object via hundreds of contiguous and narrow spectral bands. Hyperspectral imagery (HSI) has emerged as a significant data in a variety of scientific fields, including medical imaging [1], chemical analysis [2], and remote sensing [3], agricultural monitoring [4], ecosystem monitoring [5] and endmember extraction [6]. The crucial component in these applications is classification. The classification techniques are divided into supervised classification algorithms and unsupervised classification algorithms based on whether a prior knowledge is needed. Some conventional supervised classifiers can obtain satisfactory classification results, such as support vector machines [7], [8], neural networks [9], [10] and regression methods [11]. Recently, as the supervised models, deep learning networks have attracted much attention, due to the fact that the advantages of deep learning models. Firstly, the fundamental philosophy of deep learning is that let the trained model itself select more important features with fewer constraints imposed by human experts.