Manifold regularization for sparse unmixing of hyperspectral images

Abstract

Background Recently, sparse unmixing has been successfully applied to spectral mixture analysis of remotely sensed hyperspectral images. Based on the assumption that the observed image signatures can be expressed in the form of linear combinations of a number of pure spectral signatures known in advance, unmixing of each mixed pixel in the scene is to find an optimal subset of signatures in a very large spectral library, which is cast into the framework of sparse regression. However, traditional sparse regression models, such as collaborative sparse regression, ignore the intrinsic geometric structure in the hyperspectral data.ResultsIn this paper, we propose a novel model, called manifold regularized collaborative sparse regression, by introducing a manifold regularization to the collaborative sparse regression model. The manifold regularization utilizes a graph Laplacian to incorporate the locally geometrical structure of the hyperspectral data. An algorithm based on alternating direction method of multipliers has been developed for the manifold regularized collaborative sparse regression model.ConclusionsExperimental results on both the simulated and real hyperspectral data sets have demonstrated the effectiveness of our proposed model.

Fabric Defect Detection Using Deep Convolution Neural Network

“…Frequency-based methods extract fabric defects by detecting abnormal values using Fourier transform, wavelet transform, Gabor transform, and filtering approaches 23 For example, Li and Zhang developed an embedded machine vision system using Gabor filters and Pulse Coupled Neural Network (PCNN) that can identify defects of warp-knitted fabrics automatically. 24 However, the selection of appropriate parameters for both wavelets transform coefficients and Gabor filters then becomes the most challenging task in defect detection.…”

“…For evaluation, we adopted the criteria used in previous work, 11,24 that is, evaluate the model performance from two aspects: image-level and pixel-level metrics.…”

Hyperspectral Unmixing Via Nonconvex Sparse and Low-Rank Constraint

“…where ∥X∥ w,Sp is defined by (9). It is worth noting that A is a full-rank matrix that can guarantee the validity of the lowrank model above (discussed in Section II-C).…”

“…8 shows a mineral map produced in 1995 by the USGS. The USGS map serves as a good indicator for qualitative assessment of the fractional abundance maps produced by the various unmixing algorithms [6], [9], [22]. And, the scene enclosed by the red rectangle is used in the real experiment (see Fig.…”

“…Spectral unmixing is an important technique for hyperspectral data exploitation [8], and it is divided into two parts: endmember extraction and abundance estimation. Endmember extraction infers the pure spectral signatures that constitute the mixed pixel, and abundance estimation calculates their corresponding fractions, called abundances [9]- [12]. The linear mixing model (LMM) is widely adopted for the spectral unmixing problem because of its computational tractability and flexibility [13]- [18].…”