Pedram Ghamisi

An efficient method for segmentation of images based on fractional calculus and natural selection

Image segmentation has been widely used in document image analysis for extraction of printed characters, map processing in order to find lines, legends, and characters, topological features extraction for extraction of geographical information, and quality inspection of materials where defective parts must be delineated among many other applications. In image analysis, the efficient segmentation of images into meaningful objects is important for classification and object recognition. This paper presents two novel methods for segmentation of images based on the Fractional-Order Darwinian Particle Swarm Optimization (FODPSO) and Darwinian Particle Swarm Optimization (DPSO) for determining the n-1 optimal n-level threshold on a given image. The efficiency of the proposed methods is compared with other well-known thresholding segmentation methods. Experimental results show that the proposed methods perform better than other methods when considering a number of different measures.

Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

Due to the advantages of deep learning, in this paper, a regularized deep feature extraction (FE) method is presented for hyperspectral image (HSI) classification using a convolutional neural network (CNN). The proposed approach employs several convolutional and pooling layers to extract deep features from HSIs, which are nonlinear, discriminant, and invariant. These features are useful for image classification and target detection. Furthermore, in order to address the common issue of imbalance between high dimensionality and limited availability of training samples for the classification of HSI, a few strategies such as L2 regularization and dropout are investigated to avoid overfitting in class data modeling. More importantly, we propose a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery. Finally, in order to further improve the performance, a virtual sample enhanced method is proposed. The proposed approaches are carried out on three widely used hyperspectral data sets: Indian Pines, University of Pavia, and Kennedy Space Center. The obtained results reveal that the proposed models with sparse constraints provide competitive results to state-of-the-art methods. In addition, the proposed deep FE opens a new window for further research.

A Survey on Spectral–Spatial Classification Techniques Based on Attribute Profiles

Just over a decade has passed since the concept of morphological profile was defined for the analysis of remote sensing images. Since then, the morphological profile has largely proved to be a powerful tool able to model spatial information (e.g., contextual relations) of the image. However, due to the shortcomings of using the morphological profiles, many variants, extensions, and refinements of its definition have appeared stating that the morphological profile is still under continuous development. In this case, recently introduced theoretically sound attribute profiles (APs) can be considered as a generalization of the morphological profile, which is a powerful tool to model spatial information existing in the scene. Although the concept of the AP has been introduced in remote sensing only recently, an extensive literature on its use in different applications and on different types of data has appeared. To that end, the great amount of contributions in the literature that address the application of the AP to many tasks (e.g., classification, object detection, segmentation, change detection, etc.) and to different types of images (e.g., panchromatic, multispectral, and hyperspectral) proves how the AP is an effective and modern tool. The main objective of this survey paper is to recall the concept of the APs along with all its modifications and generalizations with special emphasis on remote sensing image classification and summarize the important aspects of its efficient utilization while also listing potential future works.

Feature Selection Based on Hybridization of Genetic Algorithm and Particle Swarm Optimization

A new feature selection approach that is based on the integration of a genetic algorithm and particle swarm optimization is proposed. The overall accuracy of a support vector machine classifier on validation samples is used as a fitness value. The new approach is carried out on the well-known Indian Pines hyperspectral data set. Results confirm that the new approach is able to automatically select the most informative features in terms of classification accuracy within an acceptable CPU processing time without requiring the number of desired features to be set a priori by users. Furthermore, the usefulness of the proposed method is also tested for road detection. Results confirm that the proposed method is capable of discriminating between road and background pixels and performs better than the other approaches used for comparison in terms of performance metrics.

Multilevel Image Segmentation Based on Fractional-Order Darwinian Particle Swarm Optimization

Hyperspectral remote sensing images contain hundreds of data channels. Due to the high dimensionality of the hyperspectral data, it is difficult to design accurate and efficient image segmentation algorithms for such imagery. In this paper, a new multilevel thresholding method is introduced for the segmentation of hyperspectral and multispectral images. The new method is based on fractional-order Darwinian particle swarm optimization (FODPSO) which exploits the many swarms of test solutions that may exist at any time. In addition, the concept of fractional derivative is used to control the convergence rate of particles. In this paper, the so-called Otsu problem is solved for each channel of the multispectral and hyperspectral data. Therefore, the problem of n-level thresholding is reduced to an optimization problem in order to search for the thresholds that maximize the between-class variance. Experimental results are favorable for the FODPSO when compared to other bioinspired methods for multilevel segmentation of multispectral and hyperspectral images. The FODPSO presents a statistically significant improvement in terms of both CPU time and fitness value, i.e., the approach is able to find the optimal set of thresholds with a larger between-class variance in less computational time than the other approaches. In addition, a new classification approach based on support vector machine (SVM) and FODPSO is introduced in this paper. Results confirm that the new segmentation method is able to improve upon results obtained with the standard SVM in terms of classification accuracies.

Spectral–Spatial Classification of Hyperspectral Images Based on Hidden Markov Random Fields

Hyperspectral remote sensing technology allows one to acquire a sequence of possibly hundreds of contiguous spectral images from ultraviolet to infrared. Conventional spectral classifiers treat hyperspectral images as a list of spectral measurements and do not consider spatial dependences, which leads to a dramatic decrease in classification accuracies. In this paper, a new automatic framework for the classification of hyperspectral images is proposed. The new method is based on combining hidden Markov random field segmentation with support vector machine (SVM) classifier. In order to preserve edges in the final classification map, a gradient step is taken into account. Experiments confirm that the new spectral and spatial classification approach is able to improve results significantly in terms of classification accuracies compared to the standard SVM method and also outperforms other studied methods.

Automatic Spectral–Spatial Classification Framework Based on Attribute Profiles and Supervised Feature Extraction

A robust framework for the classification of hyperspectral images which takes into account both spectral and spatial information is proposed. The extended multivariate attribute profile (EMAP) is used for extracting spatial information. Moreover, for solving the so-called curse of dimensionality, supervised feature extraction is carried out on both the original hyperspectral data and the output of the EMAP. After performing the dimensionality reduction, two output vectors of the original data and attributes are concatenated into one stacked vector. The final classification map is achieved by using a random-forest classifier. The main difficulties of using an EMAP is to initialize the attribute parameters. Therefore, a fully automatic scheme of the proposed method is introduced to overcome the shortcomings of using EMAP. The proposed method is tested on two widely known data sets. Experimental results confirm that the proposed method provides an accurate classification map in an acceptable CPU processing time.

Automatic Framework for Spectral–Spatial Classification Based on Supervised Feature Extraction and Morphological Attribute Profiles

Supervised classification plays a key role in terms of accurate analysis of hyperspectral images. Many applications can greatly benefit from the wealth of spectral and spatial information provided by these kind of data, including land-use and land-cover mapping. Conventional classifiers treat hyperspectral images as a list of spectral measurements and do not consider spatial dependencies of the adjacent pixels. To overcome these limitations, classifiers need to use both spectral and spatial information. In this paper, a framework for automatic spectral-spatial classification of hyperspectral images is proposed. In order to extract the spatial information, Extended Multi-Attribute Profiles (EMAPs) are taken into account. In addition, in order to reduce the redundancy of features and address the so-called curse of dimensionality, different supervised feature extraction (FE) techniques are considered. The final classification map is provided by using a random forest classifier. The proposed automatic framework is tested on two widely used hyperspectral data sets; Pavia University and Indian Pines. Experimental results confirm that the proposed framework automatically provides accurate classification maps in acceptable CPU processing times.

A Novel Feature Selection Approach Based on FODPSO and SVM

A novel feature selection approach is proposed to address the curse of dimensionality and reduce the redundancy of hyperspectral data. The proposed approach is based on a new binary optimization method inspired by fractional-order Darwinian particle swarm optimization (FODPSO). The overall accuracy (OA) of a support vector machine (SVM) classifier on validation samples is used as fitness values in order to evaluate the informativity of different groups of bands. In order to show the capability of the proposed method, two different applications are considered. In the first application, the proposed feature selection approach is directly carried out on the input hyperspectral data. The most informative bands selected from this step are classified by the SVM. In the second application, the main shortcoming of using attribute profiles (APs) for spectral-spatial classification is addressed. In this case, a stacked vector of the input data and an AP with all widely used attributes are created. Then, the proposed feature selection approach automatically chooses the most informative features from the stacked vector. Experimental results successfully confirm that the proposed feature selection technique works better in terms of classification accuracies and CPU processing time than other studied methods without requiring the number of desired features to be set a priori by users.

Integration of Segmentation Techniques for Classification of Hyperspectral Images

A new spectral-spatial method for classification of hyperspectral images is introduced. The proposed approach is based on two segmentation methods, fractional-order Darwinian particle swarm optimization and mean shift segmentation. The output of these two methods is classified by support vector machines. Experimental results indicate that the integration of the two segmentation methods can overcome the drawbacks of each other and increase the overall accuracy in classification.