Processing Of Hyperspectral Medical Images

This book presents new methods of analyzing and processing hyperspectral medical images, which can be used in diagnostics, for example for dermatological images. The algorithms proposed are fully automatic and the results obtained are fully reproducible. Their operation was tested on a set of several thousands of hyperspectral images and they were implemented in Matlab. The presented source code can be used without licensing restrictions. This is a valuable resource for computer scientists, bioengineers, doctoral students, and dermatologists interested in contemporary analysis methods.

This book includes some very recent applications and the newest emerging trends of hyper-spectral imaging (HSI). HSI is a very recent and strange beast, a sort of a melting pot of previous techniques and scientific interests, merging and concentrating the efforts of physicists, chemists, botanists, biologists, and physicians, to mention just a few, as well as experts in data crunching and statistical elaboration. For almost a century, scientific observation, from looking to planets and stars down to our own cells and below, could be divided into two main categories: analyzing objects on the basis of their physical dimension (recording size, position, weight, etc. and their variations) or on how the object emits, reflects, or absorbs part of the electromagnetic spectrum, i.e., spectroscopy. While the two aspects have been obviously entangled, instruments and skills have always been clearly distinct from each other. With HSI now available, this is no longer the case. This instrument can return specimen dimensionalities and spectroscopic properties to any single pixel of your specimen, in a single set of data. HSI modality is ubiquitous and scale-invariant enough to be used to mark terrestrial resources on the basis of a land map obtained from satellite observation (actually, the oldest application of this type) or to understand if the cell you are looking at is cancerous or perfectly healthy. For all these reasons, HSI represents one of the most exciting methodologies of the new millennium.

Advances in Hyperspectral Image Processing Techniques Authoritative and comprehensive resource covering recent hyperspectral imaging techniques from theory to applications Advances in Hyperspectral Image Processing Techniques is derived from recent developments of hyperspectral imaging (HSI) techniques along with new applications in the field, covering many new ideas that have been explored and have led to various new directions in the past few years. The work gathers an array of disparate research into one resource and explores its numerous applications across a wide variety of disciplinary areas. In particular, it includes an introductory chapter on fundamentals of HSI and a chapter on extensive use of HSI techniques in satellite on-orbit and on-board processing to aid readers involved in these specific fields. The book’s content is based on the expertise of invited scholars and is categorized into six parts. Part I provides general theory. Part II presents various Band Selection techniques for Hyperspectral Images. Part III reviews recent developments on Compressive Sensing for Hyperspectral Imaging. Part IV includes Fusion of Hyperspectral Images. Part V covers Hyperspectral Data Unmixing. Part VI offers different views on Hyperspectral Image Classification. Specific sample topics covered in Advances in Hyperspectral Image Processing Techniques include: Two fundamental principles of hyperspectral imaging Constrained band selection for hyperspectral imaging and class information-based band selection for hyperspectral image classification Restricted entropy and spectrum properties for hyperspectral imaging and endmember finding in compressively sensed band domain Hyperspectral and LIDAR data fusion, fusion of band selection methods for hyperspectral imaging, and fusion using multi-dimensional information Advances in spectral unmixing of hyperspectral data and fully constrained least squares linear spectral mixture analysis Sparse representation-based hyperspectral image classification; collaborative hyperspectral image classification; class-feature weighted hyperspectral image classification; target detection approach to hyperspectral image classification With many applications beyond traditional remote sensing, ranging from defense and intelligence, to agriculture, to forestry, to environmental monitoring, to food safety and inspection, to medical imaging, Advances in Hyperspectral Image Processing Techniques is an essential resource on the topic for industry professionals, researchers, academics, and graduate students working in the field.

Hyperspectral Imaging: Techniques for Spectral Detection and Classification is an outgrowth of the research conducted over the years in the Remote Sensing Signal and Image Processing Laboratory (RSSIPL) at the University of Maryland, Baltimore County. It explores applications of statistical signal processing to hyperspectral imaging and further develops non-literal (spectral) techniques for subpixel detection and mixed pixel classification. This text is the first of its kind on the topic and can be considered a recipe book offering various techniques for hyperspectral data exploitation. In particular, some known techniques, such as OSP (Orthogonal Subspace Projection) and CEM (Constrained Energy Minimization) that were previously developed in the RSSIPL, are discussed in great detail. This book is self-contained and can serve as a valuable and useful reference for researchers in academia and practitioners in government and industry.

Hyperspectral Data Processing: Algorithm Design and Analysis is a culmination of the research conducted in the Remote Sensing Signal and Image Processing Laboratory (RSSIPL) at the University of Maryland, Baltimore County. Specifically, it treats hyperspectral image processing and hyperspectral signal processing as separate subjects in two different categories. Most materials covered in this book can be used in conjunction with the author’s first book, Hyperspectral Imaging: Techniques for Spectral Detection and Classification, without much overlap. Many results in this book are either new or have not been explored, presented, or published in the public domain. These include various aspects of endmember extraction, unsupervised linear spectral mixture analysis, hyperspectral information compression, hyperspectral signal coding and characterization, as well as applications to conceal target detection, multispectral imaging, and magnetic resonance imaging. Hyperspectral Data Processing contains eight major sections: Part I: provides fundamentals of hyperspectral data processing Part II: offers various algorithm designs for endmember extraction Part III: derives theory for supervised linear spectral mixture analysis Part IV: designs unsupervised methods for hyperspectral image analysis Part V: explores new concepts on hyperspectral information compression Parts VI & VII: develops techniques for hyperspectral signal coding and characterization Part VIII: presents applications in multispectral imaging and magnetic resonance imaging Hyperspectral Data Processing compiles an algorithm compendium with MATLAB codes in an appendix to help readers implement many important algorithms developed in this book and write their own program codes without relying on software packages. Hyperspectral Data Processing is a valuable reference for those who have been involved with hyperspectral imaging and its techniques, as well those who are new to the subject.

Hyperspectral Imaging, Volume 32, presents a comprehensive exploration of the different analytical methodologies applied on hyperspectral imaging and a state-of-the-art analysis of applications in different scientific and industrial areas. This book presents, for the first time, a comprehensive collection of the main multivariate algorithms used for hyperspectral image analysis in different fields of application. The benefits, drawbacks and suitability of each are fully discussed, along with examples of their application. Users will find state-of-the art information on the machinery for hyperspectral image acquisition, along with a critical assessment of the usage of hyperspectral imaging in diverse scientific fields. Provides a comprehensive roadmap of hyperspectral image analysis, with benefits and considerations for each method discussed Covers state-of-the-art applications in different scientific fields Discusses the implementation of hyperspectral devices in different environments

The book covers the most crucial parts of real-time hyperspectral image processing: causality and real-time capability. Recently, two new concepts of real time hyperspectral image processing, Progressive HyperSpectral Imaging (PHSI) and Recursive HyperSpectral Imaging (RHSI). Both of these can be used to design algorithms and also form an integral part of real time hyperpsectral image processing. This book focuses on progressive nature in algorithms on their real-time and causal processing implementation in two major applications, endmember finding and anomaly detection, both of which are fundamental tasks in hyperspectral imaging but generally not encountered in multispectral imaging. This book is written to particularly address PHSI in real time processing, while a book, Recursive Hyperspectral Sample and Band Processing: Algorithm Architecture and Implementation (Springer 2016) can be considered as its companion book.

This book focuses on architecture and implementation of algorithms, specifically on their real-time and causal processing implementation, architectures of FPGA design and parallel processing. It concludes with applications to multispectral imaging and medical imaging. All these topics have great potential in and impact on hyperspectral data communications and hardware implementation.