Search

Advances in hyperspectral remote sensing have instigated multitude of applications for better understanding of our planet through remote data acquisition and observation of natural phenomena such as weather monitoring and prediction to include tornado, wild fires, global warming, etc. For this, data analysis methods that exploit the rich spectral and spatial information in hyperspectral data are often employed to gain insights about the natural phenomenon. This work presents a new deep learning based hyperspectral data analysis framework, which efficiently utilizes both spatial and spectral information present in the data to achieve superior classification performance. Gabor filtering is used for spatial feature extraction in conjunction with sparse random projections for spectral feature extraction and dimensionality reduction. Finally, supervised classification using a 3-D convolutional neural network was employed to perform a volumetric hyperspectral data analysis. Experimental results reveal that the proposed spatial–spectral hyperspectral data analysis frameworks outperform the conventional 2-D convolution neural network-based spectral–spatial feature extraction techniques.

Spectral–spatial Gabor filtering, which is based on 3-D local harmonic analysis, has been a powerful spectral–spatial feature extraction tool for hyperspectral image (HSI) classification. However, existing spectral–spatial Gabor approaches are prone to oversmoothing, neglecting the existences of edges and negatively affecting the classification. In this article, we propose a new HSI Gabor filtering concept, called spectral–spatial-range Gabor filtering, which intends to restrain edge interference from disturbing local spectral–spatial harmonic components. Contributions and novelties of our work can be identified as follows: 1) an HSI filtering framework is created, which can accommodate various Gabor filtering procedures and hence offer the potential to guide the design of new Gabor filters; 2) following such a unified filtering framework and taking into consideration both local spectral–spatial harmonic characteristics and range domain variations, we develop a new concept of spectral–spatial-range Gabor filtering; and 3) utilizing this proposed Gabor prototype and elaborating mathematical derivations, we achieve a novel discriminative spectral–spatial-range Gabor filtering method, which can deal with discriminative local harmonics and edge interference simultaneously along the spectral–spatial-range domain, obtaining highly discriminative Gabor features while yielding linear computational complexity. Our novel method is evaluated on four real HSI data sets and achieves excellent performances. [ABSTRACT FROM AUTHOR]

In this paper, a new hyperspectral image classification method based on 2-dimensional complex Gabor filtering and deep convolutional neural networks is proposed. Specifically, as a deep learning model, convolutional neural network is aimed to extract distinctive high-level features. Deep-learned and Gabor feature extraction methodologies are simultaneously performed on the input hyperspectral samples. Gabor features are calculated by implementing complex Gabor filtering only on the first three principal components of the hyperspectral image. The proposed hybrid model uses Gabor transform to obtain local image features, such as edges, corners and texture. The Gabor features of the images are calculated at multiple orientations and frequencies. Then, deep features and Gabor features are fused to obtain a more robust and discriminative feature vector. Hybrid feature vector is used as input to a softmax classifier for hyperspectral image classification. The parameters of the proposed deep learning architecture are optimized using a small training set. Thus, the over-fitting problem of the proposed convolutional neural network has been reduced to some extent. Experiments performed on two popular hyperspectral datasets show that the proposed method can achieve better classification performance than some conventional methods. Classification results demonstrates that the proposed hybrid model is an efficient method for feature extraction and classification of hyperspectral images. [ABSTRACT FROM AUTHOR]

Texture classification plays an important role in computer vision, and Gabor filtering (GF) is a promising direction of texture classification for its desirable characteristics. However, traditional GF methods are too coarse to achieve satisfactory classification performance. To address this problem, this paper presents an effective texture classification method by combing multi-resolution global and local Gabor features in pyramid space. First, a pyramid space for each image is constructed via upsampling and downsampling to represent the images with different resolutions. Second, GF is applied to each image at different scales and orientations, and then the magnitude and phase components of filtered images are calculated. Third, the global and local Gabor features are extracted, where the global Gabor feature is represented by the mean and variance of the magnitude component, and the local Gabor feature is represented by the joint coding of both magnitude and phase components in a histogram form. Finally, the fusion of global and local Gabor features and the texture classification are implemented in the framework of nearest subspace classifier. Experimental results on CUReT and KTH-TIPS databases demonstrate that the proposed method significantly improves the performance of GF-based texture classification methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Active learning (AL) has obtained a great success in supervised remotely sensed hyperspectral image classification, since it is able to select highly informative training samples. As an intrinsically biased sampling approach, AL generally favors the selection of samples following discriminative distributions, which are located in low-density areas. However, hyperspectral data are often highly class-mixed, i.e., most samples fluctuate in the overlapping regions of distributions of different classes. In this case, the potential of AL to select effective training samples is more limited. As AL strongly depends on the features, a possibility to increase its capabilities is to transfer the data into a highly discriminative feature space, in which the mixture of distributions that different classes of data follow tends to reduce. Based on this observation, in this paper, we introduce the concept of feature-driven AL, namely, the sample selection is going to be conducted in a given optimized feature space whose superiority is measured by an overall error probability. For illustrative purposes, we used Gabor filtering and morphological profiles for instantiation. Our experimental results, obtained on three real hyperspectral data sets, indicate that the proposed approach can significantly improve the potential of AL for hyperspectral image classification. [ABSTRACT FROM AUTHOR]

Recently, the capability of deep learning-based approaches, especially deep convolutional neural networks (CNNs), has been investigated for hyperspectral remote sensing feature extraction (FE) and classification. Due to the large number of learnable parameters in convolutional filters, lots of training samples are needed in deep CNNs to avoid the overfitting problem. On the other hand, Gabor filtering can effectively extract spatial information including edges and textures, which may reduce the FE burden of the CNNs. In this letter, in order to make the most of deep CNN and Gabor filtering, a new strategy, which combines Gabor filters with convolutional filters, is proposed for hyperspectral image classification to mitigate the problem of overfitting. The obtained results reveal that the proposed model provides competitive results in terms of classification accuracy, especially when only a limited number of training samples are available. [ABSTRACT FROM PUBLISHER]

Ocular biometrics refers to the use of features of the eye for person recognition. For instance, the unique and stable texture of the iris has been recognised as a powerful ocular biometric characteristic. In this study, the authors propose to improve biometric authentication with a multimodal ocular biometric system based on the iris pattern and the three‐dimensional shape of the cornea. They show how the cornea can be used as a biometric trait for person recognition and then, they propose an intra‐ocular fusion with iris features to improve the overall performance of the system. Feature extraction was done by modelling the shape of the cornea with a Zernike polynomial expansion. Then the best linear combinations of Zernike coefficients were found with linear discriminant analysis and used as biometric identifier. The iris texture was analysed with a typical methodology using Gabor filtering and phase encoding. The fusion was performed at the matching score level using min, max, sum and weighted‐sum rule. The experimental results on a new database constructed for this bi‐modal study showed impressive performance of the proposed ocular biometric system with equal error rate decreasing to 0% with the weighted‐sum rule. [ABSTRACT FROM AUTHOR]

Spectral–spatial classification of remotely sensed hyperspectral images has attracted a lot of attention in recent years. Although Gabor filtering has been used for feature extraction from hyperspectral images, its capacity to extract relevant information from both the spectral and the spatial domains of the image has not been fully explored yet. In this paper, we present a new discriminative low-rank Gabor filtering (DLRGF) method for spectral–spatial hyperspectral image classification. A main innovation of the proposed approach is that our implementation is accomplished by decomposing the standard 3-D spectral–spatial Gabor filter into eight subfilters, which correspond to different combinations of low-pass and bandpass single-rank filters. Then, we show that only one of the subfilters (i.e., the one that performs low-pass spatial filtering and bandpass spectral filtering) is actually appropriate to extract suitable features based on the characteristics of hyperspectral images. This allows us to perform spectral–spatial classification in a highly discriminative and computationally efficient way, by significantly decreasing the computational complexity (from cubic to linear order) compared with the 3-D spectral–spatial Gabor filter. In order to theoretically prove the discriminative ability of the selected subfilter, we derive an overall classification risk bound to evaluate the discriminating abilities of the features provided by the different subfilters. Our experimental results, conducted using different hyperspectral images, indicate that the proposed DLRGF method exhibits significant improvements in terms of classification accuracy and computational performance when compared with the 3-D spectral–spatial Gabor filter and other state-of-the-art spectral–spatial classification methods. [ABSTRACT FROM PUBLISHER]

In this paper, we apply and evaluate a modified Gaussian-test-based hierarchical clustering method for high-resolution satellite images. The purpose is to obtain homogeneous clusters within each hierarchy level which later allow the classification and annotation of image data ranging from single scenes up to large satellite data archives. After cutting a given image into small patches and feature extraction from each patch, $k$-means are used to split sets of extracted image feature vectors to create a hierarchical structure. As image feature vectors usually fall into a high-dimensional feature space, we test different distance metrics, to tackle the “curse of dimensionality” problem. By using three different synthetic aperture radar (SAR) and optical image datasets, Gabor texture and Bag-of-Words (BoW) features are extracted, and the clustering results are analyzed via visual and quantitative evaluations. We also compared our approach with other classic unsupervised clustering methods. The most important contributions of this paper are the discussion and evaluation of cluster homogeneity by comparing various datasets, feature descriptors, evaluation measures, and clustering methods, as well as the analysis of the clustering performances under various distance metrics. The results show that the Gaussian-test-based hierarchical patch clustering method is able to obtain homogeneous clusters, while Gabor texture features perform better than the BoW features. In addition, it turns out that a distance parameter ranging from 1.2 to 2 performs best. Also indicated by [1], our modified G-means algorithm is faster than the original algorithm. [ABSTRACT FROM PUBLISHER]

Due to the development of digital microscopy technologies there are huge quantity of histology images are collected and stored in database. The capability to handle and access these collections of histology images is considered as a key constituent for next generation of medical systems. These types of image retrieval system are the combination of different features play major key responsibility to retrieve images. It aims at attractive the expressive authority of visual and salient features equivalent to semantically consequential queries. Most of the existing work doesn't go behind with different combination of features to retrieve digital images along with salient features and visual feature still becomes major problem, extraction of these features also not major problem. To overcome these issue in this paper presents a improved Gaussian mixture model that routinely extracts both salient and visual representation of features from histology image database. A Gabor filtering framework is proposed, which makes the salient regions further radiant in the saliency maps to retrieve histology images with enhanced image quality results. The major objective of the work is to found the most significant visual representation of features and salient features for a specific keyword that is connected with numerous query image retrieval processes for exact matching of results. The proposed work uses an Enhanced Artificial Fish Swarm Algorithm (AFSA) method, which aims to appreciate an best possible visual-semantic matching purpose by together allowing for the different preference of the collection of query images. It is capable to discover different types of features that summarize diverse portions of the majority representative of visual patterns and salient features for every conception. Experimental results demonstrate that proposed EAFSA system for content-based histology image retrieval system, high retrieval accurateness other than existing methods. [ABSTRACT FROM AUTHOR]

Saliency detection for images and videos has become increasingly popular due to its wide applicability. In this paper, we present a new method that takes advantage of region-based visual dynamic contrast to generate temporally coherent video saliency maps. The concept of visual dynamics is formulated to represent both visual and motional variabilities of video content. Moreover, the regions are regarded as primitives for saliency computation by using spatiotemporal appearance contrasts. Then, region matching is performed across successive video frames to form temporally coherent regions, which are computed on the basis of spatiotemporal similarity in the visual dynamics of the different regions along the optical flow in the video. The region matching can effectively eliminate saliency discontinuities, particularly in the areas of oversegmentation that are otherwise highly problematic. The proposed approach is tested on a challenging set of video sequences and is compared with contemporary methods to demonstrate its superior performance in terms of its computational efficiency and ability to detect salient video content. [ABSTRACT FROM AUTHOR]

Local-feature-based face recognition (FR) methods, such as Gabor features encoded by local binary pattern, could achieve state-of-the-art FR results in large-scale face databases such as FERET and FRGC. However, the time and space complexity of Gabor transformation are too high for many practical FR applications. In this paper, we propose a new and efficient local feature extraction scheme, namely monogenic binary coding (MBC), for face representation and recognition. Monogenic signal representation decomposes an original signal into three complementary components: amplitude, orientation, and phase. We encode the monogenic variation in each local region and monogenic feature in each pixel, and then calculate the statistical features (e.g., histogram) of the extracted local features. The local statistical features extracted from the complementary monogenic components (i.e., amplitude, orientation, and phase) are then fused for effective FR. It is shown that the proposed MBC scheme has significantly lower time and space complexity than the Gabor-transformation-based local feature methods. The extensive FR experiments on four large-scale databases demonstrated the effectiveness of MBC, whose performance is competitive with and even better than state-of-the-art local-feature-based FR methods. [ABSTRACT FROM PUBLISHER]

Abstract: A multi-scale supervised neural architecture, called Multi-Scale SOON, is proposed for natural texture classification. This architecture recognizes the input textured image through a hierarchical categorization structure in multiple scales. This process consists of three sequential phases: a multi-scale feature extraction, a scale prototype pattern generation, and a multi-scale prototype fusion pattern classification. First phase extracts scale textural features using the Gabor filtering. Then, a hierarchical categorization shapes the classification. First categorization level generates the scale prototypes and an upper level categorizes the prototypes fusion. Three increasing complexity tests over the well-known Brodatz database are performed in order to quantify the Multi-Scale SOON behavior. The comparison to other standout methods proves Multi-Scale SOON behavior to be satisfactory. The tests, including the entire texture album, show the stability and robustness of the Multi-Scale SOON response. [Copyright &y& Elsevier]

The performance of speech recognition systems relies on the consistency and adaptation of the speech feature in complex conditions during the training and testing stages. Traditional systems usually perform poorly under adverse noisy conditions and are not applicable to most real world problems. In this paper, we investigate the speech feature extraction problem in a noisy environment and propose a novel approach based on Gabor filtering and tensor factorization. Recent physiological and psychoacoustic experimental results suggest that the localized spectro-temporal features are essential for auditory perception. To explore this property, we represent the speech signal by using a general higher order tensor and employ two-dimensional Gabor functions with different scales and directions to analyze the localized patches of the power spectrogram. Then the Nonnegative Tensor PCA with sparse constraints is proposed to learn the projection matrices from multiple interrelated feature subspaces. The objective of the sparse constraints is to preserve the statistical characteristic of clean speech data by finding projection matrices of speech subspaces and reduce the noise components which have distributions different from those of clean speech. A multifactor analysis method is proposed to extract robust sparse features by processing the data samples in tensor structure. The simulation results indicate that our proposed method is able to improve the speech recognition performance, especially in noisy environments, compared with the traditional speech feature extraction methods. [ABSTRACT FROM PUBLISHER]