An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine

Li, Shijin; Wu, Hao; Wan, Dingsheng; Zhu, Jiali

doi:10.1016/j.knosys.2010.07.003

Cited by 268 publications

(131 citation statements)

References 23 publications

Supporting

Mentioning

128

Contrasting

Unclassified

Order By: Relevance

“…Examples of such approaches can be found in (Estévez et al, 2009, Li et al, 2011 using SVM classifier, (Zhang et al, 2007) using maximum likelihood classifier, (Díaz-Uriarte and De Andres, 2006) using Random Forests.…”

Section: Feature Selection: State-of-the-artmentioning

confidence: 99%

Spectral Band Selection for Urban Material Classification Using Hyperspectral Libraries

Bris¹,

Laroui²,

Briottet³

et al. 2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:In urban areas, information concerning very high resolution land cover and especially material maps are necessary for several city modelling or monitoring applications. That is to say, knowledge concerning the roofing materials or the different kinds of ground areas is required. Airborne remote sensing techniques appear to be convenient for providing such information at a large scale. However, results obtained using most traditional processing methods based on usual red-green-blue-near infrared multispectral images remain limited for such applications. A possible way to improve classification results is to enhance the imagery spectral resolution using superspectral or hyperspectral sensors. In this study, it is intended to design a superspectral sensor dedicated to urban materials classification and this work particularly focused on the selection of the optimal spectral band subsets for such sensor. First, reflectance spectral signatures of urban materials were collected from 7 spectral libraires. Then, spectral optimization was performed using this data set. The band selection workflow included two steps, optimising first the number of spectral bands using an incremental method and then examining several possible optimised band subsets using a stochastic algorithm. The same wrapper relevance criterion relying on a confidence measure of Random Forests classifier was used at both steps. To cope with the limited number of available spectra for several classes, additional synthetic spectra were generated from the collection of reference spectra: intra-class variability was simulated by multiplying reference spectra by a random coefficient. At the end, selected band subsets were evaluated considering the classification quality reached using a rbf svm classifier. It was confirmed that a limited band subset was sufficient to classify common urban materials. The important contribution of bands from the Short Wave Infra-Red (SWIR) spectral domain (1000 -2400 nm) to material classification was also shown.

show abstract

Section: Feature Selection: State-of-the-artmentioning

confidence: 99%

Spectral Band Selection for Urban Material Classification Using Hyperspectral Libraries

Bris¹,

Laroui²,

Briottet³

et al. 2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The SVM is a popular supervised learning algorithm that has been employed in many real-world problems such as fault diagnosis [58], image classification [59], bioinformatics [60], geographical analysis [61] and hand-written character recognition [62]. Originally, the SVM is designed to solve binary classification problems, but multi-class extensions are also available [63].…”

Section: Svm In Qa and Data Classificationmentioning

confidence: 99%

Review of data mining applications for quality assessment in manufacturing industry: support vector machines

Rostami

Dantan

Homri

2015

Int. J. Metrol. Qual. Eng.

View full text Add to dashboard Cite

is an open access repository that collects the work of Arts et Métiers ParisTech researchers and makes it freely available over the web where possible. AbstractIn many modern manufacturing industries, data that characterize the manufacturing process are electronically collected and stored in the databases.Due to advances in data collection systems and analysis tools, data mining (DM)has widely been applied for quality assessment (QA) in manufacturing industries.In DM, the choice of technique to use in analyzing a dataset and assessing the quality depend on the understanding of the analyst. On the other hand, with the advent of improved and efficient prediction techniques, there is a need for an analyst to know which tool performs best for a particular type of data set.Although a few review papers have recently been published to discuss DM applications in manufacturing for QA, this paper provides an extensive review to investigate the application of a special DM technique, namely support vector machine (SVM) to solve QA problems. The review provides a comprehensive analysis of the literature from various points of view as DM preliminaries, data preprocessing, DM applications for each quality task, SVM preliminaries, and application results. Summary tables and figures are also provided besides to the analyses. Finally, conclusions and future research directions are provided.

show abstract

“…The proposed approach of band selection, especially regarding correlation-based band rejection, is closely related to band clustering (Li et al, 2011). While band clustering merges only adjacent bands in one cluster, the groups as used by the proposed approach do not follow any predefined order.…”

Section: Introductionmentioning

confidence: 99%

“…correlate less on the data level), the information contained in these bands might still be redundant given a specific classification task. Other works of band selection apply methods based on information theory such as mutual information (Martinez-Uso et al, 2006, Bigdeli et al, 2013, Li et al, 2011. The disadvantage of these approaches is, that two different methods are used to judge the descriptive power of a band and to actually use it to infer the classification decision.…”

Section: Introductionmentioning

confidence: 99%

Task-Dependent Band-Selection of Hyperspectral Images by Projection-Based Random Forests

Hänsch¹,

Hellwich²

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:The automatic classification of land cover types from hyperspectral images is a challenging problem due to (among others) the large amount of spectral bands and their high spatial and spectral correlation. The extraction of meaningful features, that enables a subsequent classifier to distinguish between different land cover classes, is often limited to a subset of all available data dimensions which is found by band selection techniques or other methods of dimensionality reduction. This work applies Projection-Based Random Forests to hyperspectral images, which not only overcome the need of an explicit feature extraction, but also provide mechanisms to automatically select spectral bands that contain original (i.e. non-redundant) as well as highly meaningful information for the given classification task. The proposed method is applied to four challenging hyperspectral datasets and it is shown that the effective number of spectral bands can be considerably limited without loosing too much of classification performance, e.g. a loss of 1% accuracy if roughly 13% of all available bands are used.

show abstract

An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine

Cited by 268 publications

References 23 publications

Spectral Band Selection for Urban Material Classification Using Hyperspectral Libraries

Spectral Band Selection for Urban Material Classification Using Hyperspectral Libraries

Review of data mining applications for quality assessment in manufacturing industry: support vector machines

Task-Dependent Band-Selection of Hyperspectral Images by Projection-Based Random Forests

Contact Info

Product

Resources

About