Use of weighting algorithms to improve traditional support vector machine based classifications of reflectance data

A Spectral Encoding Simulator for Broadband Active Illumination and Reconstruction-Based Spectral Measurement

Spectral reflectance or transmittance measurements provide intrinsic information on the material of an object and are widely used in remote sensing, agriculture, diagnostic medicine, etc. Most reconstruction-based spectral reflectance or transmittance measurement methods based on broadband active illumination use narrow-band LEDs or lamps combined with specific filters as spectral encoding light sources. These light sources cannot achieve the designed spectral encoding with a high resolution and accuracy due to their low degree of freedom for adjustment, leading to inaccurate spectral measurements. To address this issue, we designed a spectral encoding simulator for active illumination. The simulator is composed of a prismatic spectral imaging system and a digital micromirror device. The spectral wavelengths and intensity are adjusted by switching the micromirrors. We used it to simulate spectral encodings according to the spectral distribution on micromirrors and solved the DMD patterns corresponding to the spectral encodings with a convex optimization algorithm. To verify the applicability of the simulator for spectral measurements based on active illumination, we used it to numerically simulate existing spectral encodings. We also numerically simulated a high-resolution Gaussian random measurement encoding for compressed sensing and measured the spectral reflectance of one vegetation type and two minerals through numerical simulations. We reconstructed the spectral transmittance of a calibrated filter through an experiment. The results show that the simulator can measure the spectral reflectance or transmittance with a high resolution and accuracy.

Spectral reflectance recovery using optimal illuminations

The spectral reflectance of objects provides intrinsic information on material properties that have been proven beneficial in a diverse range of applications, e.g., remote sensing, agriculture and diagnostic medicine, to name a few. Existing methods for the spectral reflectance recovery from RGB or monochromatic images either ignore the effect from the illumination or implement/optimize the illumination under the linear representation assumption of the spectral reflectance. In this paper, we present a simple and efficient convolutional neural network (CNN)-based spectral reflectance recovery method with optimal illuminations. Specifically, we design illumination optimization layer to optimally multiplex illumination spectra in a given dataset or to design the optimal one under physical restrictions. Meanwhile, we develop the nonlinear representation for spectral reflectance in a data-driven way and jointly optimize illuminations under this representation in a CNN-based end-to-end architecture. Experimental results on both synthetic and real data show that our method outperforms the state-of-the-arts and verifies the advantages of deeply optimal illumination and nonlinear representation of the spectral reflectance.

ISBDD Model for Classification of Hyperspectral Remote Sensing Imagery

The diverse density (DD) algorithm was proposed to handle the problem of low classification accuracy when training samples contain interference such as mixed pixels. The DD algorithm can learn a feature vector from training bags, which comprise instances (pixels). However, the feature vector learned by the DD algorithm cannot always effectively represent one type of ground cover. To handle this problem, an instance space-based diverse density (ISBDD) model that employs a novel training strategy is proposed in this paper. In the ISBDD model, DD values of each pixel are computed instead of learning a feature vector, and as a result, the pixel can be classified according to its DD values. Airborne hyperspectral data collected by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor and the Push-broom Hyperspectral Imager (PHI) are applied to evaluate the performance of the proposed model. Results show that the overall classification accuracy of ISBDD model on the AVIRIS and PHI images is up to 97.65% and 89.02%, respectively, while the kappa coefficient is up to 0.97 and 0.88, respectively.

Support subspaces method for recognition of the synthetic aperture radar images using fractal compression

The goal of this work is to develop a technology that can reduce recognition computational complexity with the rise of recognition quality. We use an approach based on implementation of the conjugation indices of the vectors with the class feature spaces. We suggest a new criterion of class separability based on the conjugation index and use it to form so-called support subspaces from the training vectors. This procedure decreases computing complexity at training stage about 1000 times in comparison with previous algorithm implementation and improves recognition quality. The most significant decrease of the computational complexity of the proposed technology is achieved by implementing the fractal compression to radar images. The results prove that using this technology leads to an increase of the recognition quality.

A Real-Time Infrared Ultra-Spectral Signature Classification Method via Spatial Pyramid Matching

The state-of-the-art ultra-spectral sensor technology brings new hope for high precision applications due to its high spectral resolution. However, it also comes with new challenges, such as the high data dimension and noise problems. In this paper, we propose a real-time method for infrared ultra-spectral signature classification via spatial pyramid matching (SPM), which includes two aspects. First, we introduce an infrared ultra-spectral signature similarity measure method via SPM, which is the foundation of the matching-based classification method. Second, we propose the classification method with reference spectral libraries, which utilizes the SPM-based similarity for the real-time infrared ultra-spectral signature classification with robustness performance. Specifically, instead of matching with each spectrum in the spectral library, our method is based on feature matching, which includes a feature library-generating phase. We calculate the SPM-based similarity between the feature of the spectrum and that of each spectrum of the reference feature library, then take the class index of the corresponding spectrum having the maximum similarity as the final result. Experimental comparisons on two publicly-available datasets demonstrate that the proposed method effectively improves the real-time classification performance and robustness to noise.

Importance of spatial and spectral data reduction in the detection of internal defects in food products

Despite the importance of data reduction as part of the processing of reflection-based classifications, this study represents one of the first in which the effects of both spatial and spectral data reductions on classification accuracies are quantified. Furthermore, the effects of approaches to data reduction were quantified for two separate classification methods, linear discriminant analysis (LDA) and support vector machine (SVM). As the model dataset, reflection data were acquired using a hyperspectral camera in 230 spectral channels from 401 to 879 nm (spectral resolution of 2.1 nm) from field pea (Pisum sativum) samples with and without internal pea weevil (Bruchus pisorum) infestation. We deployed five levels of spatial data reduction (binning) and eight levels of spectral data reduction (40 datasets). Forward stepwise LDA was used to select and include only spectral channels contributing the most to the separation of pixels from non-infested and infested field peas. Classification accuracies obtained with LDA and SVM were based on the classification of independent validation datasets. Overall, SVMs had significantly higher classification accuracies than LDAs (P < 0.01). There was a negative association between pixel resolution and classification accuracy, while spectral binning equivalent to up to 98% data reduction had negligible effect on classification accuracies. This study supports the potential use of reflection-based technologies in the quality control of food products with internal defects, and it highlights that spatial and spectral data reductions can (1) improve classification accuracies, (2) vastly decrease computer constraints, and (3) reduce analytical concerns associated with classifications of large and high-dimensional datasets.

Use of customizing kernel sparse representation for hyperspectral image classification

Sparse representation-based classification (SRC) has attracted increasing attention in remote-sensed hyperspectral communities for its competitive performance with available classification algorithms. Kernel sparse representation-based classification (KSRC) is a nonlinear extension of SRC, which makes pixels from different classes linearly separable. However, KSRC only considers projecting data from original space into feature space with a predefined parameter, without integrating a priori domain knowledge, such as the contribution from different spectral features. In this study, customizing kernel sparse representation-based classification (CKSRC) is proposed by incorporating kth nearest neighbor density as a weighting scheme in traditional kernels. Analyses were conducted on two publicly available data sets. In comparison with other classification algorithms, the proposed CKSRC further increases the overall classification accuracy and presents robust classification results with different selections of training samples.

Feature weighting algorithms for classification of hyperspectral images using a support vector machine

The support vector machine (SVM) is a widely used approach for high-dimensional data classification. Traditionally, SVMs use features from the spectral bands of hyperspectral images with each feature contributing equally to the classification. In practical applications, although affected by noise, slight contributions can also be obtained from deteriorated bands. Thus, compared with feature reduction or equal assignment of weights to all the features, feature weighting is a trade-off choice. In this study, we examined two approaches to assigning weights to SVM features to increase the overall classification accuracy: (1) "CSC-SVM" refers to a support vector machine with compactness and a separation coefficient feature weighting algorithm, and (2) "SE-SVM" refers to a support vector machine with a similarity entropy feature weighting algorithm. Analyses were conducted on a public data set with nine selected land-cover classes. In comparison with traditional SVMs and other classical feature weighting algorithms, the proposed weighting algorithms increase the overall classification accuracy, and even better results could be obtained with few training samples.