Hyper Spectral Spatial Image Segmentation Using Machine Learning Algorithms

Designing active learning (AL) techniques to determine informative training samples for hyperspectral image (HSI) classification is an open research issue. In this chapter, several spectral–spatial AL techniques are designed by exploiting both, an interesting approach to fuse spectral and spatial information and different combinations of existing uncertainty and diversity criteria. In order to fuse spectral and spatial information, the dimensionality of HSI is reduced and mean filtering (for incorporation of spatial information) is applied to each component image in the reduced domain of HSI considering multiple windows of different sizes. The filtered images are concatenated with original component images to form an extended spatial profile for the HSI. These spectral–spatial features are used with different combinations of uncertainty and diversity criteria to design several spectral–spatial AL techniques for determining most informative pixels. The experiments carried out on two real HSI data sets show that the spectral–spatial AL methods are more robust than the AL methods based on spectral measurements only.

This paper proposes a fast approach to spectral image segmentation. In the algorithm, two popular techniques are extended and applied to spectral color images: the mean-shift filtering and the kernel-based clustering. We claim that segmentation should be completed under illuminant F11 rather than directly using the original spectral reflectance, because such illumination can reduce data variability and expedite the following filtering. The modes obtained in the mean-shift filtering represent the local features of spectral images, and will be applied to segmentation in place of pixels. Since the modes are generally small in number, the eigendecomposition of kernel matrices, the crucial step in the kernel-based clustering, becomes much easier. The combination of these two techniques can efficiently enhance the performance of segmentation. Experiments show that the proposed segmentation method is feasible and very promising for spectral color images. Keywords: spectral color image, illuminant F11, mean-shift filtering, spectrum extension, kernel-based clustering

The estimating the chlorophyll contents in the crops helps to identify the condition of crops and different classification of crops with soil characteristics in order to assist the farmer or others with agriculture growth. In this paper, a hybrid approach is introduced to estimate the Chlorophyll contents in the crops using hyperspectral image segmentation with active learning, which consists of two main steps. First, we use a sparse multinomial logistic regression (SMLR) model to learn the class posterior probability distributions with Quadratic Programming or joint probability distribution. Second, we use the information acquired in the previous step to segment the hyper spectral image using a Markov Random field segments to estimate the dependencies using spatial information and edge Information by minimum spanning forest rooted on markers. In order to reduce the cost of acquiring large training sets, PSO optimization is performed based on the SMLR posterior probabilities on the Normalized difference vegetation index (NDVI). The state-of-the-art performance of the proposed approach is illustrated using real hyper spectral data sets collected from the North Karnataka in a number of experimental comparisons with recently developed or statistical hyperspectral image analysis methods in terms of precision, recall and f—measure.

Hyperspectral image analysis method is widely used in all kinds of application including agriculture identification and forest investigation and atmospheric pollution monitoring. In order to accurately and steadily analyze hyperspectral image, considering the spectrum and spatial information which is provided by hyperspectral data together is necessary. The hyperspectral image has the characteristics of large amount of wave bands and information. Corresponding to the characteristics of hyperspectral image, a fast image fusion method that can fuse the hyperspectral image with high fidelity is studied and proposed in this paper. First of all, hyperspectral image is preprocessed before the morphological close operation. The close operation is used to extract wave band characteristic to reduce dimensionality of hyperspectral image. The spectral data is smoothed at the same time to avoid the discontinuity of the data by combination of spatial information and spectral information. On this basis, Mean-shift method is adopted to register key frames. Finally, the selected key frames by fused into one fusing image by the pyramid fusion method. The experiment results show that this method can fuse hyper spectral image in high quality. The fused image’s attributes is better than the original spectral images comparing to the spectral images and reach the objective of fusion.

There has been extensive research in the field of Hyperspectral Image Classification using deep neural networks. The deep learning based approaches requires huge amount of labelled data samples. But in the case of Hyperspectral Image, there are less number of labelled data samples. Therefore, we can adopt Active Learning combined with deep learning based approaches to be able to extract most informative data samples. By using this technique, we can train the classifier to achieve better classification accuracies with less number of labelled data samples. There is considerable amount of research carried out for selecting diverse data samples from the pool of unlabeled data samples. We present a novel diversity-based Active Learning approach utilizing the information of clustered data distribution. We incorporate diversity criteria with Active Learning selection criteria and combine it with Convolutional Neural Network for feature extraction and classification. This approach helps us in obtaining most informative and diverse data samples. We have compared our proposed approach with three other sampling methods in terms of classification accuracies, Cohen Kappa score, which shows that our approach gives better results with comparison to other sampling methods.

Hyperspectral Image (HSI) classification plays a key role remote sensing field. Recently, deep learning has demonstrated its effectiveness in HSI Classification field. This paper presents a spectral-spatial HSI classification technique established on the deep learning based deep belief network (DBN) for deep and abstract feature extraction and adaptive boundary adjustment based segmentation. Proposed approach focuses on integrating the deep learning based spectral features and segmentation based spatial features into a framework for improved performance. Specifically, first the deep DBN model is exploited as a spectral feature extraction based classifier to extract the deep spectral features. Second, spatial contextual features are obtained by utilizing effective adaptive boundary adjustment based segmentation technique. Finally, maximum voting based criteria is operated to integrate the results of extracted spectral and spatial information for improved HSI classification. In general, exploiting spectral features from DBN process and spatial features from segmentation and integration of spectral and spatial information by maximum voting based criteria, has a substantial effect on the performance of HSI classification. Experimental performance on real and widely used hyperspectral data sets with different contexts and resolutions demonstrates the accuracy of the proposed technique and performance is comparable to several recently proposed HSI classification techniques.

Abstract. Hyperspectral image enhancement has been a concern for the remote sensing society for detailed end member detection. Hyperspectral remote sensor collects images in hundreds of narrow, continuous spectral channels, whereas multispectral remote sensor collects images in relatively broader wavelength bands. However, the spatial resolution of the hyperspectral sensor image is comparatively lower than that of the multispectral. As a result, spectral signatures from different end members originate within a pixel, known as mixed pixels. This paper presents an approach for obtaining an image which has the spatial resolution of the multispectral image and spectral resolution of the hyperspectral image, by fusion of hyperspectral and multispectral image. The proposed methodology also addresses the band remapping problem, which arises due to different regions of spectral coverage by multispectral and hyperspectral images. Therefore we apply algorithms to restore the spatial information of the hyperspectral image by fusing hyperspectral bands with only those bands which come under each multispectral band range. The proposed methodology is applied over Henry Island, of the Sunderban eco-geographic province. The data is collected by the Hyperion hyperspectral sensor and LISS IV multispectral sensor.

Hyperspectral image classification with limited labeled samples is a challenging task and still an open research issue. In this article, a novel technique is presented to address such an issue by exploiting dimensionality reduction, spectral-spatial information, and classification with active learning. The proposed technique is based on two phases. Considering the importance of dimensionality reduction and spatial information for the analysis of hyperspectral images, Phase I generates the patterns corresponding to each pixel of the image using both spectral and spatial information. To this end, first, principal component analysis is used to reduce the dimensionality of an hyperspectral image, then extended morphological profiles are exploited. The spectral-spatial information based patterns generated by extended morphological profiles are used as input to the Phase II. Phase II performs the classification task guided by an active learning technique. This technique is based on a novel query function that uses uncertainty, diversity, and cluster assumption criteria by exploiting the properties of k-means clustering, K-nearest neighbors algorithm, support vector machines, and genetic algorithms. Experiments on three benchmark hyperspectral datasets demonstrate that the proposed method outperforms five state-of-the-art active learning methods.

The purpose of this study is to develop hyperspectral imaging (HSI) for automatic detection of head and neck cancer cells on histologic slides. A compact hyperspectral microscopic system is developed in this study. Histologic slides from 15 patients with squamous cell carcinoma (SCC) of the larynx and hypopharynx are imaged with the system. The proposed nuclei segmentation method based on principle component analysis (PCA) can extract most nuclei in the hyperspectral image without extracting other sub-cellular components. Both spectra-based support vector machine (SVM) and patch-based convolutional neural network (CNN) are used for nuclei classification. CNNs were trained with both hyperspectral images and pseudo RGB images of extracted nuclei, in order to evaluate the usefulness of extra information provided by hyperspectral imaging. The average accuracy of spectra-based SVM classification is 68%. The average AUC and average accuracy of the HSI patch-based CNN classification is 0.94 and 82.4%, respectively. The hyperspectral microscopic imaging and classification methods provide an automatic tool to aid pathologists in detecting SCC on histologic slides.

The hyperspectral and multispectral image fusion process, commonly known as the multisharpening process (also known as the hypersharpening process), results in the creation of unobservable high spectral and spatial resolution hyperspectral remote sensing data, by combining (or fusing) a hyperspectral image, characterized by a high spectral resolution, with, especially, a high spatial resolution multispectral one. There are several approaches in the literature performing such a process, in particular, those based on the spectral unmixing concept. The latter fusion methods aim to extract pure-material spectra from the high spectral resolution hyperspectral image and combine them with their corresponding proportions extracted from the high spatial resolution multispectral image. However, most of these methods, which mainly consider the standard linear mixing model, do not address the spectral variability phenomenon, precisely due to the considered data mixing model, which does not handle variations in illumination and atmospheric conditions or material composition inducing spectral variability. Neglecting such a phenomenon may lead to errors in the fusion process, thus decreasing the spatial and spectral qualities of sharpened products. In this paper, a new hyperspectral and multispectral data fusion method, based on the linear spectral unmixing concept that deals with spectral variability, is proposed. This approach, based on a multiplicative Nonnegative Matrix Factorization (NMF) technique, substantially extends the multiplicative Coupled NMF (CNMF) algorithm by considering a linear data mixing model that addresses the considered phenomenon. Indeed, the introduced approach minimizes new cost functions involving matrices with specific structures in order to deal with the spectral variability phenomenon. The proposed method is applied to synthetic and real data, and its effectiveness is evaluated with established performance criteria. Experimental results show that the designed algorithm globally yields sharpened hyperspectral data with fine spectral and spatial fidelities. Also, these results demonstrate that the proposed technique globally outperforms the tested literature approaches.

Analysis of hyperspectral images is of great importance in many scientific disciplines. Obtaining the spectral and spatial information simultaneously from time-varying hyperspectral images is a challenging task due to their high dimensionality. In this paper, we design an interface that allows users to study hyperspectral images interactively and obtain spectral features and enhanced images at the same time. The image fusion results change dynamically with the regions of interest selected by users and convey both the spatial and spectral information. We show the usefulness of our approach using time-varying hyperspectral plant images. We compare our method with existing hyperspectral image analysis techniques. Our evaluation indicates that our interface can help users determine important bands, identify regions of interest, and generate image fusion results for time-varying hyperspectral plant images.

Hyperspectral imaging is concerned with the measurement, analysis, and interpretation of spectra acquired from a given scene (or specific object) at a short, medium or long distance by an airbone or satellite sensor. Over the last few years, hyperspectral image data sets have been collected for a great amount of locations over the world, using a variety of instruments for Earth observation. Despite the increasing importance of hyperspectral images in remote sensing applications, there is no common repository of hyperspectral data intended to distribute and share hyperspectral data sets in the community. Quite opposite, the hyperspectral data sets which are available for public use are spread among different storage locations and present significant heterogeneity regarding the storage format, associated meta-data (if any), or ground-truth availability. As a result, the development of a standardized hyperspectral data repository is a highly desired goal in the remote sensing community. In this paper, we take a necessary first step towards the development of a digital repository for remotely sensed hyperspectral data. The proposed system allows uploading new hyperspectral data sets along with meta-data, ground-truth and analysis results, with the ultimate goal of sharing publicly available hyperspectral images within the remote sensing community. The database has been designed in order to allow storing relevant information for the hyperspectral data available through the system, including basic image characteristics (width, height, number of bands, format) and more advanced meta-data (ground-truth information, publications in which the data has been used). The current implementation consists of a front-end to ease the management of images through a web interface, thus containing both synthetic and real hyperspectral images from two highly representative instruments, such as NASAs Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the Cuprite Mining District in Nevada. Most importantly, the developed system includes a spectral unmixing-based content based image retrieval (CBIR) functionality which allows searching for images on the spectral unmixing information (spectrally pure components or endmembers and their associated abundances in the scene). This information is stored as meta-data associated to each hyperspectral image instance, and then used to search and retrieve images based on information content. This paper presents the design of the system and a preliminary validation of the unmixing-based retrieval functionality using both synthetic and real hyperspectral images stored in the database.

Rooibos (Aspalathus linearis) and Honeybush (Cyclopia species) are teas indigenous to South Africa that are popularly consumed locally as well as internationally for its purported health benefits. Studies have confirmed anti-oxidant, antimutagenic and anticancer activity mainly due to the presence of polyphenols. Hyperspectral imaging (HSI) integrates conventional spectroscopy and imaging to obtain spectral and spatial information from a sample. The potential of short wave infrared (SWIR) hyperspectral imaging in combination with chemometric data analysis as a rapid quality control method for commercially important herbal teas was investigated. Images were acquired with the sisuChema short wave infrared (SWIR) hyperspectral pushbroom imaging system at a spectral range of 920 – 2514nm. Principal Component Analysis (PCA) was performed to remove background pixels and to visualize the data. Classes (i.e. Rooibos or Honeybush) were interactively assigned using the score images and plots. Partial Least Squares Discriminant Analysis (PLS-DA) classification models developed were subsequently used to accurately predict the species identity of commercially available herbal tea samples introduced as an external dataset, producing a visually interpretable result. The results showed that the labeling information is correct but that Honeybush tea is in most cases present in very low amounts. It is evident that hyperspectral imaging is an objective and non-destructive quality control method that can be successfully used to determine the botanical species included in herbal teas in addition to giving an indication of the abundance of each species in polyherbal tea mixtures.

VTT Technical Research Centre of Finland has developed a Fabry-Perot Interferometer (FPI) based hyperspectral imager compatible with light weight UAV (Unmanned Aerial Vehicle) platforms (SPIE Proc. 7474¹, 8186B²). The FPI based hyperspectral imager was used in a UAV imaging campaign for forest and agriculture tests during the summer 2011 (SPIE Proc. 8174³). During these tests high spatial resolution Color-Infrared (CIR) images and hyperspectral images were recorded on separate flights. The spectral bands of the CIR camera were 500 - 580 nm for the green band, 580 - 700 nm for the red band and 700 - 1000 nm for the near infrared band. For the summer 2012 flight campaign a new hyperspectral imager is currently being developed. A custom made CIR camera will also be used. The system which includes both the high spatial resolution Color-Infrared camera and a light weight hyperspectral imager can provide all necessary data with just one UAV flight over the target area. The new UAV imaging system contains a 4 Megapixel CIR camera which is used for the generation of the digital surface models and CIR mosaics. The hyperspectral data can be recorded in the wavelength range 500 - 900 nm at a resolution of 10 - 30 nm at FWHM. The resolution can be selected from approximate values of 10, 15, 20 or 30 nm at FWHM.

Hyperspectral imaging provides complex image data with spectral information from many fluorescent species contained within the sample such as the fluorescent labels and cellular or pigment autofluorescence. To maximize the utility of this spectral imaging technique it is necessary to couple hyperspectral imaging with sophisticated multivariate analysis methods to extract meaningful relationships from the overlapped spectra. Many commonly employed multivariate analysis techniques require the identity of the emission spectra of each component to be known or pure component pixels within the image, a condition rarely met in biological samples. Multivariate curve resolution (MCR) has proven extremely useful for analyzing hyperspectral and multispectral images of biological specimens because it can operate with little or no a priori information about the emitting species, making it appropriate for interrogating samples containing autofluorescence and unanticipated contaminating fluorescence. To demonstrate the unique ability of our hyperspectral imaging system coupled with MCR analysis techniques we will analyze hyperspectral images of four-color in-situ hybridized rat brain tissue containing 455 spectral pixels from 550 - 850 nm. Even though there were only four colors imparted onto the tissue in this case, analysis revealed seven fluorescent species, including contributions from cellular autofluorescence and the tissue mounting media. Spectral image analysis will be presented along with a detailed discussion of the origin of the fluorescence and specific illustrations of the adverse effects of ignoring these additional fluorescent species in a traditional microscopy experiment and a hyperspectral imaging system.