Data Mining - Concepts and Techniques.

Statistics for Spatial Data.

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

We propose a methodology for making optimal registration decisions during 3D volume reconstruction in terms of (a) anticipated accuracy of aligned images, (b) uncertainty of obtained results during the registration process, (c) algorithmic repeatability of alignment procedure, and (d) computational requirements. We researched and developed a web-enabled, web services based, data-driven, registration decision support system. The registration decisions include (1) image spatial size (image sub-area or entire image), (2) transformation model (e.g., rigid, affine or elastic), (3) invariant registration feature (intensity, morphology or a sequential combination of the two), (4) automation level (manual, semi-automated, or fully-automated), (5) evaluations of registration results (multiple metrics and methods for establishing ground truth), and (6) assessment of resources (computational resources and human expertise, geographically local or distributed). Our goal is to provide mechanisms for evaluating the tradeoffs of each registration decision in terms of the aforementioned impacts. First, we present a medical registration methodology for making registration decisions that lead to registration results with well-understood accuracy, uncertainty, consistency and computational complexity characteristics. Second, we have built software tools that enable geographically distributed researchers to optimize their data-driven registration decisions by using web services and supercomputing resources. The support developed for registration decisions about 3D volume reconstruction is available to the general community with the access to the NCSA supercomputing resources. We illustrate performance by considering 3D volume reconstruction of blood vessels in histological sections of uveal melanoma from serial fluorescent labeled paraffin sections labeled with antibodies to CD34 and laminin. The specimens are studied by fluorescence confocal laser scanning microscopy (CLSM) images.

/pdf/supporting-registration-decisions-during-3d-medical-volume-52ujmbeedg.pdf

Supporting Registration Decisions during 3D Medical Volume Reconstructions

This paper addresses the problem of mapping application specific requirements on image similarity metrics to the plethora of existing image similarity computations. The work is motivated by the fact that there is no method for choosing a similarity metric that is suitable for a given application. We approached the problem by designing a theoretical and experimental framework for creating sensitivity signatures of similarity metrics. In this paper, we outline the classifications of image similarity metrics found in the literature, the space of application parameters and requirements, derivations of similarity dependencies on application parameters, and experimentally obtained sensitivity signatures of similarity metrics using image simulations. These sensitivity signatures provide a way for users to query a reference database of sensitivity signatures and retrieve a recommendation for an image similarity metric. We illustrate the use of the prototype recommendation system by considering spectral calibration and spatial registration application requirements.

Toward a Recommendation System for Image Similarity Metrics

In this dissertation, I present a problem of three-dimensional volume reconstruction from florescent confocal laser scanning microscopy (CLSM) imagery. I overview a three-dimensional volume reconstruction framework which consists of (a) volume reconstruction procedures using multiple automation levels, feature types, and feature dimensionalities, (b) a data-driven registration decision support system, (c) an evaluation study of registration accuracy, and (d) a novel intensity enhancement technique for 3D CLSM volumes. 
The motivation for developing the framework came from the lack of 3D volume reconstruction techniques for CLSM image modality. The 3D volume reconstruction problem is challenging due to significant variations of intensity and shape of cross sectioned structures, unpredictable and inhomogeneous geometrical warping during medical specimen preparation, and an absence of external fiduciary markers. The framework addresses the problem of automation in the presence of the above challenges as they are frequently encountered during CLSM-based 3D volume reconstructions used for cell biology investigations. 
The objectives of the presented three-dimensional volume reconstruction framework are summarized as follows: (1) automate alignment of sub-volumes (physical sections) from multiple cross sections, (2) obtain high resolution image frames by mosaicking (i.e., stitching together), (3) quantify the accuracy of volume reconstruction using multiple techniques, and (4) visualize the reconstructed volumes in three-dimensional environments for visual inspection and quantitative interpretation. 
The primary contribution of this dissertation is the presentation of a new theoretical model for three-dimensional volume reconstruction that includes reconstruction methodology, a data-driven registration decision support, automation, intensity enhancement for processing volumetric image data from fluorescent confocal laser scanning microscopes (CLSM). Researched methods have been fully implemented in the Image to Knowledge (12K) software package developed at the National Center for Supercomputing Applications (NCSA). 
The broader impact of my work is in providing the algorithms in a form of web-enabled tools to the medical community so that medical researchers can minimize laborious and time intensive 3D volume reconstructions using the tools and computational resources at NCSA.

Three-dimensional volume reconstruction from fluorescent confocal laser scanning microscopy imagery

Motivation: Automated microscopy enables scientists to image an area of an experimental sample that is much larger than the microscope's Field of View (FOV) and to carry out time-lapse studies of cell cultures. An automated microscope acquires these images by generating a grid of partially overlapping images. This process generates hundreds to hundreds of thousands of image tiles that need to be stitched into a wide image. We address the problem of creating image mosaics from a grid of overlapping tiles constrained to only translational offsets. The challenges of creating a large mosaic image are: (1) sensitivity to image features in the overlapping regions of adjacent tiles (e.g., during the early period of cell colony growth), (2) computational requirements needed to assemble the resulting mosaic image, and (3) absence of ground truth needed for evaluating the accuracy of a stitching method.

MIST: Microscopy Image Stitching Tool

We present a novel methodology for evaluating statistically predicted versus measured multi-modal imagery, such as Synthetic Aperture Radar (SAR), Electro-Optical (EO), Multi-Spectral (MS) and Hyper-Spectral (HS) modalities. While several scene modeling approaches have been proposed in the past for multi-modal image predictions, the problem of evaluating synthetic and measured images has remained an open issue. Although analytical prediction models would be appropriate for accuracy evaluations of man-made objects, for example, SAR target modeling based on Xpatch, the analytical models cannot be applied to prediction evaluation of natural scenes because of their randomness and high geometrical complexity imaged by any of the aforementioned sensor modality. Thus, statistical prediction models are frequently chosen as more appropriate scene modeling approaches and there is a need to evaluate the accuracy of statistically predicted versus measured imagery. This problem poses challenges in terms of selecting quantitative and qualitative evaluation techniques, and establishing a methodology for systematic comparisons of synthetic and measured images. In this work, we demonstrate clutter accuracy evaluations for modified measured and predicted synthetic images with statistically modeled clutter. We show experimental results for color (red, green and blue) and HS imaging modalities, and for statistical clutter models using Johnson's family of probability distribution functions (PDFs). The methodology includes several evaluation techniques for comparing image samples and their similarity, image histograms, statistical central moments, and estimated probability distribution functions (PDFs). Particularly, we assess correlation, histogram, chi-squared, pixel and PDF parameter based error metrics quantitatively, and relate them to a human visual perception of predicted image quality. The work is directly applicable to multi-sensor phenomenology modeling for exploitation, recognition and identification.

/pdf/methodology-for-evaluating-statistically-predicted-versus-4r06pd63lv.pdf

Peter Bajcsy

Papers

Supporting Registration Decisions during 3D Medical Volume Reconstructions

Toward a Recommendation System for Image Similarity Metrics

Three-dimensional volume reconstruction from fluorescent confocal laser scanning microscopy imagery

MIST: Microscopy Image Stitching Tool

Methodology for evaluating statistically predicted versus measured imagery