Azriel Rosenfeld

Ralph L. Hartley

Leslie J. Kitchen

Cheng-Ye Wang

MARYLAND UNIV COLLEGE PARK COMPUTER VISION LAB.

Several segmentation techniques were applied to a set of 51 FLIR (Forward-Looking Infrared) images of four different types, and the results were compared to hand segmentations. There were substantial differences in perfomance, indicating that the choice of proper technique is very important. The segmentation techniques used were 'superslice, ' 'pyramid spot detection', two versions of 'relaxation', pyramid linking', and 'superspike', One technique, 'superspike', outperformed all the others, detecting 88% of the targets and yielding only 1.6 false alarms per true target. (Author).

Segmentation of FLIR Images: A Comparative Study

Jean-Michel Jolion

Biological visual systems employ massively parallel processing to perform real-world visual tasks in real time. A key to this remarkable performance seems to be that biological systems construct representations of their visual image data at multiple scales. A Pyramid Framework for Early Vision describes a multiscale, or `pyramid', approach to vision, including its theoretical foundations, a set of pyramid-based modules for image processing, object detection, texture discrimination, contour detection and processing, feature detection and description, and motion detection and tracking. It also shows how these modules can be implemented very efficiently on hypercube-connected processor networks. A Pyramid Framework for Early Vision is intended for both students of vision and vision system designers; it provides a general approach to vision systems design as well as a set of robust, efficient vision modules.

Multiresolutional Computer Vision

A Pyramid Framework for Early Vision

David Doermann

Daniel DeMenthon

Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyzing image sequences, or video Video understanding deals with understanding of video understanding. sequences, e.g., recognition of gestures, activities, facial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvi ous overlap with computer vision. The main goal of computer graphics is to generate and animate realistic looking images, and videos. Re searchers in computer graphics are increasingly employing techniques from computer vision to generate the synthetic imagery. A good exam pIe of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is derived from real images using computer vision techniques. Here the shift is from synthesis to analy sis followed by synthesis. Image processing has always overlapped with computer vision because they both inherently work directly with images.

Video Mining

Peter Meer

Allen C. Sher

Hierarchical Contour Processing

The Chain Pyramid

Biological visual systems employ massively parallel processing to perform real-world visual tasks in real time. A key to this remarkable performance seems to be that biological systems construct representations of their visual image data at multiple scales. A Pyramid Framework for Early Vision describes a multiscale, or 'pyramid', approach to vision, including its theoretical foundations, a set of pyramid-based modules for image processing, object detection, texture discrimination, contour detection and processing, feature detection and description, and motion detection and tracking. It also shows how these modules can be implemented very efficiently on hypercube-connected processor networks. The volume is intended for both students of vision and vision system designers; it provides a general approach to vision systems design as well as a set of robust, efficient vision modules.

Petra Perner

TheInternationalConferenceonMachineLearningandDataMining(MLDM)is the third meeting in a series of biennial events, which started in 1999, organized by the Institute of Computer Vision and Applied Computer Sciences (IBaI) in Leipzig. MLDM began as a workshop and is now a conference, and has brought the topic of machine learning and data mining to the attention of the research community. Seventy-?ve papers were submitted to the conference this year. The program committeeworkedhardtoselectthemostprogressiveresearchinafairandc- petent review process which led to the acceptance of 33 papers for presentation at the conference. The 33 papers in these proceedings cover a wide variety of topics related to machine learning and data mining. The two invited talks deal with learning in case-based reasoning and with mining for structural data. The contributed papers can be grouped into nine areas: support vector machines; pattern dis- very; decision trees; clustering; classi?cation and retrieval; case-based reasoning; Bayesian models and methods; association rules; and applications. We would like to express our appreciation to the reviewers for their precise andhighlyprofessionalwork.WearegratefultotheGermanScienceFoundation for its support of the Eastern European researchers. We appreciate the help and understanding of the editorial sta? at Springer Verlag, and in particular Alfred Hofmann,whosupportedthepublicationoftheseproceedingsintheLNAIseries. Last, but not least, we wish to thank all the speakers and participants who contributed to the success of the conference.

Third International Conference, MLDM 2003, Leipzig, Germany, July 5-7, 2003, proceedings

Machine Learning and Data Mining in Pattern Recognition

Jacob Beck

Barbara Hope

Human and Machine Vision provides information pertinent to an interdisciplinary program of research in visual perception. This book presents a psychophysical study of the human visual system, which provides insights on how to model the flexibility required by a general-purpose visual system. Organized into 17 chapters, this book begins with an overview of how a visual display is segmented into components on the basis of textual differences. This text then proposes three criteria for judging representations of shape. Other chapters consider an increased use of machine vision programs as models of human vision and of data from human vision in developing programs for machine vision. This book discusses as well the diversity and flexibility of systems for representing visual information. The final chapter deals with dot patterns and discusses the process of interring orientation information from collections of them. This book is a valuable resource for psychologists, neurophysiologists, and computer scientists.

Human and Machine Vision

Reinhard Klette

Fridrich Sloboda

Digital geometry deals with geometric properties of subsets of digital images or, equivalently, with geometric properties of finite sets of lattice points. Digital geometry can anticipate progress in imaging technology allowing higher and higher spatial resolution. It seems that the input data in both fields will "converge" to data embedded in digital arrays of very high spatial resolution.

Azriel Rosenfeld

About

Books

Join the club