Target detection of hyperspectral images based on their Fourier spectral features

Saipullah, Khairul Muzzammil; Kim, Deok‐Hwan

doi:10.1117/1.oe.51.11.111704

Cited by 8 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The higher overall accuracy shows the more precise in target and background pixels’ identification. Inspired by Khazai et al [38],

z_{α}

in (13) is regarded to be 3 and CFAR, which introduced in [31], was set to 0.001, inspired by Saipullah and Kim [39]. Table 5 shows the performance comparison of the proposed threshold estimation method and the two conventional methods on the fabric targets and the exposed soil in HyMap and Hyperion datasets, respectively, using the overall accuracy statistic.…”

Section: Resultsmentioning

confidence: 99%

Selecting optimal bands for sub‐pixel target detection in hyperspectral images based on implanting synthetic targets

Hashjin

Boloorani

Khazai

et al. 2019

IET Image Processing

View full text Add to dashboard Cite

Target detection at sub-pixel abundances is in fact one of the challenging issues of hyperspectral image processing. Selection of optimal bands to improve sub-pixel target detection (STD) performance is one of the common solutions, applied by many researchers. Nevertheless, absence of sufficient training data is the main weakness of selecting optimal bands with regards to this approach. The present research introduces a new band selection method for STD in hyperspectral images, based on creating training data, in which the desired target spectrum is implanted randomly in a series of host pixels from the entire hyperspectral image. Afterward, via running an optimization algorithm twice, with the aim of minimizing the false alarm rate (FAR) in local Adaptive Coherence Estimator (ACE) target detection algorithm, the number of optimal bands and optimal spectral bands are selected. In this study, the performance of three optimization methods, including Genetic Algorithm (GA), Grey Wolf Optimization (GWO), and Particle Swarm Optimization (PSO), are compared. Experimental results on Hymap and Hyperion datasets show that, the proposed method obtains the minimum FAR compared to the rest of evaluated methods. Also, based on the results obtained, GWO outperforms GA and PSO optimization methods in the STD domain.

show abstract

“…The higher overall accuracy shows the more precise in target and background pixels’ identification. Inspired by Khazai et al [38],

z_{α}

Section: Resultsmentioning

confidence: 99%

Selecting optimal bands for sub‐pixel target detection in hyperspectral images based on implanting synthetic targets

Hashjin

Boloorani

Khazai

et al. 2019

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Spatial features are not explored in this study but will be included in our future work. The extracted spectral features included (1) first-order derivatives of each spectral curve, which reflect the variations of spectral information across the wavelength range; (2) second-order derivatives of each spectral curve, which reflect the concavity of the spectral curve; (3) mean, std, and total reflectance at each pixel, which summarize the statistical characteristics of the spectral fingerprint; and (4) Fourier coefficients (FCs), which were initially found to be effective for target detection in the remote sensing field 26 and later were adopted for breast cancer margin classification from ex-vivo breast cancer hyperspectral images. Different features may have very different numerical ranges, so each feature was standardized into its z-score (MATLAB function) by subtracting the mean from each feature and then dividing by its std.…”

Section: Feature Extraction From Hyperspectral Datamentioning

confidence: 99%

Framework for hyperspectral image processing and quantification for cancer detection during animal tumor surgery

Wang

Qin

et al. 2015

J. Biomed. Opt

View full text Add to dashboard Cite

Abstract. Hyperspectral imaging (HSI) is an imaging modality that holds strong potential for rapid cancer detection during image-guided surgery. But the data from HSI often needs to be processed appropriately in order to extract the maximum useful information that differentiates cancer from normal tissue. We proposed a framework for hyperspectral image processing and quantification, which includes a set of steps including image preprocessing, glare removal, feature extraction, and ultimately image classification. The framework has been tested on images from mice with head and neck cancer, using spectra from 450-to 900-nm wavelength. The image analysis computed Fourier coefficients, normalized reflectance, mean, and spectral derivatives for improved accuracy. The experimental results demonstrated the feasibility of the hyperspectral image processing and quantification framework for cancer detection during animal tumor surgery, in a challenging setting where sensitivity can be low due to a modest number of features present, but potential for fast image classification can be high. This HSI approach may have potential application in tumor margin assessment during image-guided surgery, where speed of assessment may be the dominant factor.

show abstract

Striver: an image descriptor for fingerprint liveness detection

Li,

Wang,

Zhang

2024

SIViP

View full text Add to dashboard Cite

Target detection of hyperspectral images based on their Fourier spectral features

Cited by 8 publications

References 13 publications

Selecting optimal bands for sub‐pixel target detection in hyperspectral images based on implanting synthetic targets

Selecting optimal bands for sub‐pixel target detection in hyperspectral images based on implanting synthetic targets

Framework for hyperspectral image processing and quantification for cancer detection during animal tumor surgery

Striver: an image descriptor for fingerprint liveness detection

Contact Info

Product

Resources

About