Genetic algorithms and Linear Discriminant Analysis based dimensionality reduction for remotely sensed image analysis

Cui, Minshan; Prasad, Saurabh; Mahrooghy, Majid; Bruce, Lori; Aanstoos, James V.

doi:10.1109/igarss.2011.6049687

Cited by 18 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When it comes to filter-based approaches, there are some different criteria for the band selection, such as, distances measures (Keshava 2004), class separability measures (Cui et al 2011), information, dependence (Camps-Valls, Mooij, and Scholkopf 2010), correlation, searching strategies (Jahanshahi 2016;Su, Yong, and Du 2016) and classification measures (Habermann, Fremont, and Shiguemori 2017). For example, in (Damodaran, Courty, and Lefevre 2017), the authors propose a class separability-based approach.…”

Section: Literature Reviewmentioning

confidence: 99%

Supervised band selection in hyperspectral images using single-layer neural networks

Habermann

Frémont

Shiguemori

2018

International Journal of Remote Sensing

View full text Add to dashboard Cite

Hyperspectral images provide fine details of the scene under analysis in terms of spectral information. This is due to the presence of contiguous bands that make possible to distinguish different objects even when they have similar colour and shape. However, neighbouring bands are highly correlated, and, besides, the high dimensionality of hyperspectral images brings a heavy burden on processing and also may cause the Hughes phenomenon. It is therefore advisable to make a band selection pre-processing prior to the classification task. Thus, this paper proposes a new supervised filter-based approach for band selection based on neural networks. For each class of the data set, a binary single-layer neural network classifier performs a classification between that class and the remainder of the data. After that, the bands related to the biggest and smallest weights are selected, so, the band selection process is class-oriented. This process iterates until the previously defined number of bands is achieved. A comparison with three state-of-the-art band selection approaches shows that the proposed method yields the best results in 43.33% of the cases even with greatly reduced training data size, whereas the competitors have achieved between 13.33% and 23.33% on the Botswana, KSC and Indian Pines datasets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Supervised band selection in hyperspectral images using single-layer neural networks

Habermann

Frémont

Shiguemori

2018

International Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In order to select discrete wavelengths for classification, we use a genetic algorithm (GA) 38 to optimize feature selection based on a linear discriminant analysis (LDA) cost function. 39,40 A GA is an evolutionary optimization method inspired by natural selection. Since our goal is to maximize classification accuracy while minimizing DFIR image acquisition time, we use a GA to select optimal feature sets for a range of feature numbers.…”

Section: Methodsmentioning

confidence: 99%

Selecting optimal features from Fourier transform infrared spectroscopy for discrete-frequency imaging

Mankar

Bhargava

Prasad

et al. 2018

Analyst

Self Cite

View full text Add to dashboard Cite

Tissue histology utilizing chemical and immunohistochemical labels plays an important role in biomedicine and disease diagnosis. Recent research suggests that mid-infrared (IR) spectroscopic imaging may augment histology by providing quantitative molecular information. One of the major barriers to this approach is long acquisition time using Fourier-transform infrared (FTIR) spectroscopy. Recent advances in discrete frequency sources, particularly quantum cascade lasers (QCLs), may mitigate this problem by allowing selective sampling of the absorption spectrum. However, DFIR imaging only provides a significant advantage when the number of spectral samples is minimized, requiring a priori knowledge of important spectral features. In this paper, we demonstrate the use of a GPU-based genetic algorithm (GA) using linear discriminant analysis (LDA) for DFIR feature selection. Our proposed method relies on pre-acquired broadband FTIR images for feature selection. Based on user-selected criteria for classification accuracy, our algorithm provides a minimal set of features that can be used with DFIR in a time-frame more practical for clinical diagnosis.

show abstract

“…Zhang et al [4] implemented the SVM algorithm for the classification of polarimetric SAR images using scattering and textural features. Cui et al [5] have implemented a multi-classifier decision fusion framework for levee health monitoring using texture features derived from the grey level co-occurrence matrix.…”

Section: Surface Roughness Estimation With Different Radar Frequency mentioning

confidence: 99%

Comparison of L-band and X-band polarimetric SAR data classification for screening earthen levees

Dabbiru

Aanstoos²,

Younan³

2014

2014 IEEE Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

The main focus of this research is to detect vulnerabilities on the Mississippi river levees using remotely sensed Synthetic Aperture Radar (SAR) imagery. Unstable slope conditions can lead to small landslides which weaken the levees and increase the likelihood of failure during floods. This paper analyzes the ability of detecting the landslides on the levee with different frequency bands of synthetic aperture radar data using supervised machine learning algorithms. The two SAR datasets used in this study are: (1) the X-band satellitebased radar data from DLR's TerraSAR-X (TSX), and (2) the L-band airborne radar data from NASA JPL's Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). The Support Vector Machine (SVM) classification algorithm was implemented to detect the landslides on the levee. The results showed that higher accuracies have been attained using L-band radar data compared to the X-band data, likely due to the longer wavelength and deeper penetration capability of L-band data.

show abstract

Genetic algorithms and Linear Discriminant Analysis based dimensionality reduction for remotely sensed image analysis

Cited by 18 publications

References 7 publications

Supervised band selection in hyperspectral images using single-layer neural networks

Supervised band selection in hyperspectral images using single-layer neural networks

Selecting optimal features from Fourier transform infrared spectroscopy for discrete-frequency imaging

Comparison of L-band and X-band polarimetric SAR data classification for screening earthen levees

Contact Info

Product

Resources

About