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

http://cvssp-data.eps.surrey.ac.uk/Personal/AdrianHilton/Publications_files/survey_techrep.pdf

A survey of advances in vision-based human motion capture and analysis

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

(1991). Applied Linear Regression Models. Journal of Quality Technology: Vol. 23, No. 1, pp. 76-77.

Applied Linear Regression Models

Computational geometry

From the Publisher:
This computer vision textbook describes the reconstruction of object surfaces and the analysis of distances between camera and objects. Main topics are static and dynamic stereo analysis, shape from shading, photometric stereo analysis, and structured lighting. The selected procedures, e.g., complex algorithms as Tsai calibration, Frankot-Chellapa depth map generation, or Lee-Rosenfeld shape from shading, are discussed at a detailed level such that implementations can follow the given descriptions. Fundamentals are given for these application oriented approaches with respect to camera modeling and calibration, to geometric surface modeling, and to surface reflectance models. New research and laboratory results in shape reconstruction and depth analysis, e.g., based on color images, have been included. The text is suitable for graduate courses in computer science, in several engineering disciplines, or in applied mathematics. Theoretical and applied exercises accompany each chapter.

Computer Vision: Three-Dimensional Data from Images

This paper describes a new software-based registration and fusion of visible and thermal infrared (IR) image data for face recognition in challenging operating environments that involve illumination variations. The combined use of visible and thermal IR imaging sensors offers a viable means for improving the performance of face recognition techniques based on a single imaging modality. Despite successes in indoor access control applications, imaging in the visible spectrum demonstrates difficulties in recognizing the faces in varying illumination conditions. Thermal IR sensors measure energy radiations from the object, which is less sensitive to illumination changes, and are even operable in darkness. However, thermal images do not provide high-resolution data. Data fusion of visible and thermal images can produce face images robust to illumination variations. However, thermal face images with eyeglasses may fail to provide useful information around the eyes since glass blocks a large portion of thermal energy. In this paper, eyeglass regions are detected using an ellipse fitting method, and replaced with eye template patterns to preserve the details useful for face recognition in the fused image. Software registration of images replaces a special-purpose imaging sensor assembly and produces co-registered image pairs at a reasonable cost for large-scale deployment. Face recognition techniques using visible, thermal IR, and data-fused visible-thermal images are compared using a commercial face recognition software (FaceIt®) and two visible-thermal face image databases (the NIST/Equinox and the UTK-IRIS databases). The proposed multiscale data-fusion technique improved the recognition accuracy under a wide range of illumination changes. Experimental results showed that the eyeglass replacement increased the number of correct first match subjects by 85% (NIST/Equinox) and 67% (UTK-IRIS).

https://imaging.utk.edu/publications/papers/2006/241_IJCV_Kong07.pdf

Multiscale Fusion of Visible and Thermal IR Images for Illumination-Invariant Face Recognition

Up to now, most of the color edge detection methods are monochromatic-based techniques, which produce, in general, better than when traditional gray-value techniques are applied. In this overview, we focus mainly on vector-valued techniques because it is easy to understand how to apply common edge detection schemes to every color component. Opposed to this, vector-valued techniques are new and different. The second part of the article addresses the topic of edge classification. While edges are often classified into step edges and ramp edges, we address the topic of physical edge classification based on their origin into shadow edges, reflectance edges, orientation edges, occlusion edges, and specular edges. In the rest of this article we discuss various vector-valued techniques for detecting discontinuities in color images. Then operators are presented based on vector order statistics, followed by presentation by examples of a couple of results of color edge detection. We then discuss different approaches to a physical classification of edges by their origin.

https://imaging.utk.edu/publications/papers/2005/koschan_spm05.pdf

Detection and classification of edges in color images

In this paper, we describe an algorithm called fast marching watersheds that segments a triangle mesh into visual parts. This computer vision algorithm leverages a human vision theory known as the minima rule. Our implementation computes the principal curvatures and principal directions at each vertex of a mesh, and then our hill-climbing watershed algorithm identifies regions bounded by contours of negative curvature minima. These regions fit the definition of visual parts according to the minima rule. We present evaluation analysis and experimental results for the proposed algorithm.

https://imaging.utk.edu/publications/papers/2003/page_cvpr03.pdf

Perception-based 3D triangle mesh segmentation using fast marching watersheds

An introduction to color in three-dimensional image processing and the emerging area of multi-spectral image processing The importance of color information in digital image processing is greater than ever. However, the transition from scalar to vector-valued image functions has not yet been generally covered in most textbooks. Now, Digital Color Image Processing fills this pressing need with a detailed introduction to this important topic. In four comprehensive sections, this book covers: The fundamentals and requirements for color image processing from a vector-valued viewpoint Techniques for preprocessing color images Three-dimensional scene analysis using color information, as well as the emerging area of multi-spectral imaging Applications of color image processing, presented via the examination of two case studies In addition to introducing readers to important new technologies in the field, Digital Color Image Processing also contains novel topics such as: techniques for improving three-dimensional reconstruction, three-dimensional computer vision, and emerging areas of safety and security applications in luggage inspection and video surveillance of high-security facilities. Complete with full-color illustrations and two applications chapters, Digital Color Image Processing is the only book that covers the breadth of the subject under one convenient cover. It is written at a level that is accessible for first- and second-year graduate students in electrical and computer engineering and computer science courses, and that is also appropriate for researchers who wish to extend their knowledge in the area of color image processing.

Andreas Koschan

Papers

Computer Vision: Three-Dimensional Data from Images

Multiscale Fusion of Visible and Thermal IR Images for Illumination-Invariant Face Recognition

Detection and classification of edges in color images

Perception-based 3D triangle mesh segmentation using fast marching watersheds

Digital Color Image Processing