Random projection-based dimensionality reduction method for hyperspectral target detection

Comparison among dimensionality reduction techniques based on Random Projection for cancer classification

“…Compared to other state-of-the-art methods for the background suppression of infrared smalltarget images, the proposed model outperforms max-median [79], morphological (top-hat) [80], phase spectrum of quaternion Fourier transform (PQFT) [81] and wavelet transform (WRX) [82] in terms of signal-to-clutter ratio gain (SCRG) and background suppression factor (BSF) [83]. Feng et al [20] developed a new approach to detect hyperspectral targets using the CEM method [42]. The objective of CEM is to design a finite impulse response (FIR) linear filter with L filter coefficients, and the FIR filter can be represented using an L-dimensional vector w = {w 1 , w 2 , .…”

“…where 1 p×1 is a p × 1 column vector with ones in its components that is used to constrain the desired targets in D. Similarly, 0 q×1 is a q × 1 column vector with zeros in all components that is used to suppress the undesired targets in U. Analogous to Feng et al [20], Du et al [21] conducted target detection by TCIMF, where RP is used for dimensionality reduction. Not only does RP reduce the computational complexity, but it improves the target-detection accuracy by decision fusion across multiple RP instances.…”

“…Feng et al [20] developed a new approach to detect hyperspectral targets using the CEM method [42]. The objective of CEM is to design a finite impulse response (FIR) linear filter with L filter coefficients, and the FIR filter can be represented using an L-dimensional vector w = {w 1 , w 2 , .…”