Much of our understanding of the relationships among geometric struc tures in images is based on the shape of these structures and their relative orientations, positions and sizes. Thus, developing quantitative methods for capturing shape information from digital images is an important area for computer vision research. This book describes the theory, implemen tation, and application of two multi resolution image shape description methods. The author begins by motivating the need for quantitative methods for describing both the spatial and intensity variations of struc tures in grey-scale images. Two new methods which capture this informa tion are then developed. The first, the intensity axis of symmetry, is a collection of branching and bending surfaces which correspond to the skeleton of the image. The second method, multiresolution vertex curves, focuses on surface curvature properties as the image is blurred by a sequence of Gaussian filters. Implementation techniques for these image shape descriptions are described in detail. Surface functionals are mini mized subject to symmetry constraints to obtain the intensity axis of symmetry. Robust numerical methods are developed for calculating and following vertex curves through scale space. Finally, the author demon strates how grey-scale images can be segmented into geometrically coher ent regions using these shape description techniques. Building quantita tive analysis applications in terms of these visually sensible image regions promises to be an exciting area of biomedical computer vision research. v Acknowledgments This book is a corrected and revised version of the author's Ph. D.

This book results from a Workshop on Multiresolution Image Processing and Analysis, held in Leesburg, VA on July 19-21, 1982. It contains updated ver sions of most of the papers that were presented at the Workshop, as well as new material added by the authors. Four of the presented papers were not available for inclusion in the book: D. Sabbah, A computing with connections approach to visual recognition; R. M. Haralick, Fitting the gray tone intensity surface as a function of neighborhood size; E. M. Riseman, Hierarchical boundary formation; and W. L. Mahaffey, L. S. Davis, and J. K. Aggarwal, Region correspondence in multi-resolution images taken from dynamic scenes. The number and variety of papers indicates the timeliness of the H0rkshop. Multiresolution methods are rapidly gaining recognition as an important theme in image processing and analysis. I would like to express my thanks to the National Science Foundation for their support of the Workshop under Grant MCS-82-05942; to Barbara Hope for organizing and administering the Workshop; to Janet Salzman and Fran Cohen, for retyping the papers; and above all, to the speakers and other partici pants, for making the Workshop possible.

This volume contains papers presented at the Third International Workshop on Visual Form. It covers the most important topics of current interest in the field, presenting an updated collection of results achieved by leading academic and industrial research groups from several countries. The book contains invited lectures and research papers dealing with theoretical and applicative aspects of shape perception, representation, decomposition, description and recognition, as well as related topics.

Provides analytical theories offered by innovative artificial intelligence computing methods in the archaeological domain.

This book explores the application of deep learning techniques within a particularly difficult computational type of computer vision (CV) problem ─ super-resolution (SR). The authors present and discuss ways to apply computational intelligence (CI) methods to SR. The volume also explores the possibility of using different kinds of CV techniques to develop and enhance the tools/processes related to SR. The application areas covered include biomedical engineering, healthcare applications, medicine, histology, and material science. The book will be a valuable reference for anyone concerned with multiple multimodal images, especially professionals working in remote sensing, nanotechnology and immunology at research institutes, healthcare facilities, biotechnology institutions, agribusiness services, veterinary facilities, and universities.

This book constitutes the refereed proceedings of the First Brazilian Symposium on Document Image Analysis, BSDIA'97, held in Curitiba in November 1997. The volume presents 19 revised full papers selected from 30 submissions as well as eight full-paper invited contributions by internationally leading authorities. The invited papers give a unique survey of the state of the art in the area. The selected papers are organized in sections on low level processing, document processing and retrieval, handwriting recognition, signature verification, and application systems.

Welcome to the proceedings of the 5th Paci?c Rim Conference on Multimedia (PCM 2004) held in Tokyo Waterfront City, Japan, November 30–December 3, 2004. Following the success of the preceding conferences, PCM 2000 in Sydney, PCM 2001 in Beijing, PCM 2002 in Hsinchu, and PCM 2003 in Singapore, the ?fth PCM brought together the researchers, developers, practitioners, and educators in the ?eld of multimedia. Theoretical breakthroughs and practical systems were presented at this conference, thanks to the support of the IEEE Circuits and Systems Society, IEEE Region 10 and IEEE Japan Council, ACM SIGMM, IEICE and ITE. PCM2004featuredacomprehensiveprogramincludingkeynotetalks,regular paperpresentations,posters,demos,andspecialsessions.Wereceived385papers andthenumberofsubmissionswasthelargestamongrecentPCMs.Amongsuch a large number of submissions, we accepted only 94 oral presentations and 176 poster presentations. Seven special sessions were also organized by world-leading researchers. We kindly acknowledge the great support provided in the reviewing of submissions by the program committee members, as well as the additional reviewers who generously gave their time. The many useful comments provided by the reviewing process must have been very valuable for the authors’ work. Thisconferencewouldneverhavehappenedwithoutthehelpofmanypeople. We greatly appreciate the support of our strong organizing committee chairs and advisory chairs. Among the chairs, special thanks go to Dr. Ichiro Ide and Dr. Takeshi Naemura who smoothly handled publication of the proceedings with Springer. Dr. Kazuya Kodama did a fabulous job as our Web master.

This book constitutes the refereed proceedings of the 10th International Conference on Computer Analysis of Images and Patterns, CAIP 2003, held in Groningen, The Netherlands in August 2003. The 94 revised papers presented were carefully reviewed and selected from 160 submissions. The papers are organized in topical sections on analysis and understanding, video analysis, segmentation, shape, classification, face recognition, interpolation and spatial transformations, and filtering.

Die Cordillera Central der Dominikanischen Republik ist eine Quelle wichtiger natürlicher Ressourcen – vor allem Wasser – für dieses karibische Land. Im oberen Einzugsgebiet des Río Yaque del Norte wurde im Laufe des 20. Jahrhunderts ein großer Teil der natürlichen Wälder abgeholzt und durch Weide- und Ackerland sowie Sekundärvegetation ersetzt. Entwaldung und nicht nachhaltige Landnutzung auf den steilen Hängen dieses Gebietes haben zu Erosion und Landdegradierung geführt. Es gibt aber auch noch verschiedene primäre Bergwälder, darunter kleine Nebelwaldbereiche mit bedrohten endemischen Arten. Fernerkundungsdaten sind eine unverzichtbare Quelle für flächendeckende räumliche Informationen, die als Basis für Raumnutzungspläne und den Schutz bedrohter Ökosysteme benötigt werden. Die Nutzbarkeit von Satellitendaten mittlerer Auflösung (z.B. Landsat) für die Kartierung der Vegetationstypen des Untersuchungsgebietes ist begrenzt, weil das kleinräumige Mosaik verschiedener Landbedeckungstypen (wie in vielen tropischen Gebirgsbereichen) zu einem großen Anteil von Mischpixeln in diesen Daten führt. Die neue Generation kommerzieller hochauflösender Satelliten wie IKONOS (1 m bis 4 m Auflösung) ermöglicht eine detailliertere Kartierung von kleineren Interessensgebieten, aber die automatische Klassifizierung räumlich hochaufgelöster Daten beinhaltet auch neue Herausforderungen. Diese Arbeit beschäftigt sich daher hauptsächlich mit der Optimierung von Methoden zur Ausnutzung der räumlichen Information in hochauflösenden Satellitendaten für die Kartierung von tropischen Bergwäldern und anderen Landoberflächen.