With the rapid increase in the variety and quantity of biomedical images in recent years, we see a steadily growing number of computer vision technologies applied to biomedical applications. The time is ripe for us to take a closer look at the accomplishments and experiences gained in this research subdomain, and to strategically plan the directions of our future research. The scientific goal of our workshop, "Computer Vision for Biomedical Image Applications: Current Techniques and Future Trends" (CVBIA), is to examine the diverse applications of computer vision to biomedical image applications, considering both current methods and promising new trends. An additional goal is to provide the opportunity for direct interactions between (1) prominent senior researchers and young scientists, including students, postdoctoral associates and junior faculty; (2) local researchers and international leaders in biomedical image analysis; and (3) computer scientists and medical practitioners. Our CVBIA workshop had two novel characteristics: each contributed paper was authored primarily by a young scientist, and the workshop attracted an unusually large number of well-respected invited speakers (and their papers). We had the good fortune of having Dr. Ayache of INRIA, France to talk about "Computational Anatomy and Computational Physiology," Prof. Grimson of MIT to discuss "Analyzing Anatomical Structures: Leveraging Multiple Sources of Knowledge," Dr. Jiang of the Chinese Academy of Sciences to present their work on "Computational Neuroanatomy and Brain Connectivity," Prof.

Thisvolumecollectsthepapersacceptedforpresentationatthe7thInternational Conferenceon Advanced Conceptsfor IntelligentVision Systems (ACIVS 2005). TheACIVS conference was established in 1999 in Baden-Baden (Germany) as part of a large multiconference.ACIVS has maintained the tradition of its ?rst edition of having 25-minute oral talks in a single track event, even though the number of participants has been steadily growing every year. The conference currently attracts computer scientists from more than 20 countries, mostly from Europe, Australia and Japan, but also from USA, Asia and the Middle East. ThoughACIVS is a conference on all areas in image processing, one of its major domains is image and video compression. A third of the selected papers dealt with compression, motion estimation, moving object detection and other video applications. This year, topics related to clustering, pattern recognition and biometrics constituted another third of the conference. The last third was more related to the fundamentals of image processing, namely noise reduction, ?ltering, restorationandimagesegmentation.We wouldliketothankthe invited speakers Fernando Pereira, Marc Op de Beeck and Rafael Molina for enhancing the technical program with their presentations

This volume presents the proceedings of the 11th International Conference on Computer Analysis of Images and Patterns (CAIP 2005). This conference - ries started about 20 years ago in Berlin. Initially, the conference served as a forum for meetings between scientists from Western and Eastern-block co- tries. Nowadays, the conference attracts participants from all over the world. The conference gives equal weight to posters and oral presentations, and the selected presentation mode is based on the most appropriate communication medium. The program follows a single-track format, rather than parallel s- sions. Non-overlapping oral and poster sessions ensure that all attendees have the opportunity to interact personally with presenters. As for the numbers, we received a total of 185 submissions. All papers were reviewed by two to four members of the Program Committee. The ?nal selection was carried out by the Conference Chairs. Out of the 185 papers, 65 were - lected for oral presentation and 43 as posters. CAIP is becoming well recognized internationally, and this year's presentations came from 26 di?erent countries. South Korea proved to be the most active scienti?cally with a total of 16 - cepted papers. At this point, we wish to thank the Program Committee and additional referees for their timely and high-quality reviews. The paper s- mission and review procedure was carried out electronically. We also thank the invited speakers Reinhardt Koch and Thomas Vetter for kindly accepting to present invited papers.

Correlation is a robust and general technique for pattern recognition and is used in many applications, such as automatic target recognition, biometric recognition and optical character recognition. The design, analysis and use of correlation pattern recognition algorithms requires background information, including linear systems theory, random variables and processes, matrix/vector methods, detection and estimation theory, digital signal processing and optical processing. This book provides a needed review of this diverse background material and develops the signal processing theory, the pattern recognition metrics, and the practical application know-how from basic premises. It shows both digital and optical implementations. It also contains state-of-the-art technology presented by the team that developed it and includes case studies of significant current interest, such as face and fingerprint recognition. Suitable for advanced undergraduate or graduate students taking courses in pattern recognition theory, whilst reaching technical levels of interest to the professional practitioner.

Inrecentresearchoncomputervisionsystems, attentionhasbeenplayingacrucialrolein mediatingbottom-upandtop-downpathsofinformationprocessing. Inappliedresearch, the development of enabling technologies such as miniaturized mobile sensors, video surveillance systems, and ambient intelligence systems involves the real-time analysis of enormous quantities of data. Knowledge has to be applied about what needs to be attendedto, andwhen, andwhattodoinameaningfulsequence, incorrespondencewith visual feedback. Methods on attention and control are mandatory to render computer vision systems more robust. The 2nd International Workshop on Attention and Performance in Computational Vision (WAPCV 2004) was held in the Czech Technical University of Prague, Czech Republic, as an associated workshop of the 8th European Conference on Computer - sion (ECCV 2004). The goal of this workshop was to provide an interdisciplinary forum tocommunicatecomputationalmodelsofvisualattentionfromvariousviewpoints, such as from computer vision, psychology, robotics and neuroscience. The motivation for - terdisciplinarity was communication and inspiration beyond the individual community, to focus discussion on computational modelling, to outline relevant objectives for p- formance comparison, to explore promising application domains, and to discuss these with reference to all related aspects of cognitive vision. The workshop was held as a single-day, single-track event, consisting of high-quality podium and poster presen- tions. Invited talks were given by John K. Tsotsos about attention and feature binding in biologically motivated computer vision and by Gustavo Deco about the context of attention, memory and reward from the perspective of computational neuroscience. The interdisciplinary program committee was composed of 21 internationally r- ognized researc

The 2004 International Conference on Parallel and Distributed Computing, - plications and Technologies (PDCAT 2004) was the ?fth annual conference, and was held at the Marina Mandarin Hotel, Singapore on December 8-10, 2004. Since the inaugural PDCAT held in Hong Kong in 2000, the conference has - come a major forum for scientists, engineers, and practitioners throughout the world to present the latest research, results, ideas, developments, techniques, and applications in all areas of parallel and distributed computing. The technical program was comprehensive and featured keynote speeches, te- nical paper presentations, and exhibitions showcased by industry vendors. The technical program committee was overwhelmed with submissions of papers for presentation, from countries worldwide. We received 242 papers and after - viewing them, based on stringent selection criteria, we accepted 173 papers. The papers in the proceedings focus on parallel and distributed computing viewed from the three perspectives of networking and architectures, software systems and technologies, and algorithms and applications. We acknowledge the great contribution from all of our local and international committee members and - perreviewerswhodevotedtheirtimeinthereviewprocessandprovidedvaluable feedback for the authors. PDCAT 2004 could never have been successful without the support and ass- tance of several institutions and many people. We sincerely appreciate the s- port from the National Grid O?ce and IEEE, Singapore for technical co-sponsorship.The?nancialsponsorshipsfromtheindustrialsponsors, Hewlett- Packard Singapore; IBM Singapore; Sun Microsystems; SANDZ Solutions; S- icon Graphics, and Advanced Digital Information Corporation, are gratefully acknowledged

The volume of data being collected in solar astronomy has exponentially increased over the past decade and we will be entering the age of petabyte solar data. Deep learning has been an invaluable tool exploited to efficiently extract key information from the massive solar observation data, to solve the tasks of data archiving/classification, object detection and recognition. Astronomical study starts with imaging from recorded raw data, followed by image processing, such as image reconstruction, inpainting and generation, to enhance imaging quality. We study deep learning for solar image processing. First, image deconvolution is investigated for synthesis aperture imaging. Second, image inpainting is explored to repair over-saturated solar image due to light intensity beyond threshold of optical lens. Third, image translation among UV/EUV observation of the chromosphere/corona, Ha observation of the chromosphere and magnetogram of the photosphere is realized by using GAN, exhibiting powerful image domain transfer ability among multiple wavebands and different observation devices. It can compensate the lack of observation time or waveband. In addition, time series model, e.g., LSTM, is exploited to forecast solar burst and solar activity indices. This book presents a comprehensive overview of the deep learning applications in solar astronomy. It is suitable for the students and young researchers who are major in astronomy and computer science, especially interdisciplinary research of them.

Medical imaging and medical image analysisare rapidly developing. While m- ical imaging has already become a standard of modern medical care, medical image analysis is still mostly performed visually and qualitatively. The ev- increasing volume of acquired data makes it impossible to utilize them in full. Equally important, the visual approaches to medical image analysis are known to su?er from a lack of reproducibility. A signi?cant researche?ort is devoted to developing algorithms for processing the wealth of data available and extracting the relevant information in a computerized and quantitative fashion. Medical imaging and image analysis are interdisciplinary areas combining electrical, computer, and biomedical engineering; computer science; mathem- ics; physics; statistics; biology; medicine; and other ?elds. Medical imaging and computer vision, interestingly enough, have developed and continue developing somewhat independently. Nevertheless, bringing them together promises to b- e't both of these ?elds. We were enthusiastic when the organizers of the 2004 European Conference on Computer Vision (ECCV) allowed us to organize a satellite workshop devoted to medical image analysis.

Welcome to the proceedings of the 8th European Conference on Computer - sion! Following a very successful ECCV 2002, the response to our call for papers was almost equally strong - 555 papers were submitted. We accepted 41 papers for oral and 149 papers for poster presentation. Several innovations were introduced into the review process. First, the n- ber of program committee members was increased to reduce their review load. We managed to assign to program committee members no more than 12 papers. Second, we adopted a paper ranking system. Program committee members were asked to rank all the papers assigned to them, even those that were reviewed by additional reviewers. Third, we allowed authors to respond to the reviews consolidated in a discussion involving the area chair and the reviewers. Fourth, thereports,thereviews,andtheresponsesweremadeavailabletotheauthorsas well as to the program committee members. Our aim was to provide the authors with maximal feedback and to let the program committee members know how authors reacted to their reviews and how their reviews were or were not re?ected in the ?nal decision. Finally, we reduced the length of reviewed papers from 15 to 12 pages. ThepreparationofECCV2004wentsmoothlythankstothee?ortsofthe- ganizing committee, the area chairs, the program committee, and the reviewers. We are indebted to Anders Heyden, Mads Nielsen, and Henrik J. Nielsen for passing on ECCV traditions and to Dominique Asselineau from ENST/TSI who kindly provided his GestRFIA conference software. We thank Jan-Olof Eklundh and Andrew Zisserman for encouraging us to organize ECCV 2004 in Prague.

Welcome to the proceedings of the 8th European Conference on Computer - sion! Following a very successful ECCV 2002, the response to our call for papers was almost equally strong - 555 papers were submitted. We accepted 41 papers for oral and 149 papers for poster presentation. Several innovations were introduced into the review process. First, the n- ber of program committee members was increased to reduce their review load. We managed to assign to program committee members no more than 12 papers. Second, we adopted a paper ranking system. Program committee members were asked to rank all the papers assigned to them, even those that were reviewed by additional reviewers. Third, we allowed authors to respond to the reviews consolidated in a discussion involving the area chair and the reviewers. Fourth, thereports,thereviews,andtheresponsesweremadeavailabletotheauthorsas well as to the program committee members. Our aim was to provide the authors with maximal feedback and to let the program committee members know how authors reacted to their reviews and how their reviews were or were not re?ected in the ?nal decision. Finally, we reduced the length of reviewed papers from 15 to 12 pages. ThepreparationofECCV2004wentsmoothlythankstothee?ortsofthe- ganizing committee, the area chairs, the program committee, and the reviewers. We are indebted to Anders Heyden, Mads Nielsen, and Henrik J. Nielsen for passing on ECCV traditions and to Dominique Asselineau from ENST/TSI who kindly provided his GestRFIA conference software. We thank Jan-Olof Eklundh and Andrew Zisserman for encouraging us to organize ECCV 2004 in Prague.

Many approaches have been proposed to solve the problem of finding the optic flow field of an image sequence. Three major classes of optic flow computation techniques can discriminated (see for a good overview Beauchemin and Barron IBeauchemin19951): gradient based (or differential) methods; phase based (or frequency domain) methods; correlation based (or area) methods; feature point (or sparse data) tracking methods; In this chapter we compute the optic flow as a dense optic flow field with a multi scale differential method. The method, originally proposed by Florack and Nielsen [Florack1998a] is known as the Multiscale Optic Flow Constrain Equation (MOFCE). This is a scale space version of the well known computer vision implementation of the optic flow constraint equation, as originally proposed by Horn and Schunck [Horn1981]. This scale space variation, as usual, consists of the introduction of the aperture of the observation in the process. The application to stereo has been described by Maas et al. [Maas 1995a, Maas 1996a]. Of course, difficulties arise when structure emerges or disappears, such as with occlusion, cloud formation etc. Then knowledge is needed about the processes and objects involved. In this chapter we focus on the scale space approach to the local measurement of optic flow, as we may expect the visual front end to do. 17. 2 Motion detection with pairs of receptive fields As a biologically motivated start, we begin with discussing some neurophysiological findings in the visual system with respect to motion detection.

Dieser Bericht behandelt die akustischen Aspekte der sprachlichen Kommunikation, insbesondere wenn sie durch Gerausche, Nachhall oder Schwerhorigkeit gestort ist. Produktion und Wahrnehmung von Sprache, also Sprechen und Horen, dienen wesentlich der Integration eines Menschen in das soziale und kulturelle Leben. Beides ist die Voraussetzung fur ein kompetentes Verhalten in der Familie, in der Offentlichkeit, am Arbeitsplatz und in der Ausbildung. Der Fortschritt der Technik verlangt notwendig nach mehr Kommunikation: u.a. aufgrund veranderter Betriebsablaufe (Teamarbeit zur Verbindung von Entwicklung, Konstruktion, Produktion, Verteilung der Arbeit an unterschiedlichen Standorten), an mobilen Arbeitsplatzen, bei der Benutzung akustischer Medien oder mobiler Telefone und beim weltweiten Kommunizieren in einer Zweitsprache. Die Auswirkungen reduzierter Kommunikation aufgrund von Larm oder Schwerhorigkeit sind deshalb betrachtlich. Durch akustisch schlecht gestaltete Raume, Arbeitsplatze und Kommunikationsgerate und durch zu hohe Sprechpegel, z.B. aus Lautsprechern, wird die Sprachkommunikation zusatzlich eingeschrankt. Damit ist nicht nur Wahrnehmen und Verstehen von Sprache reduziert, sondern zwingend auch der Informationsaustausch: die private, soziale und betriebliche Interaktion. Zu beachten sind ebenso auch langfristige Folgen, wie z.B. ein verzogerter Spracherwerb in Kindergarten und Schule, die Abnahme der Qualitat der Arbeit, die Zunahme von Konflikten und von Unfallen am Arbeitsplatz und eine Verminderung der physischen und psychischen Gesundheit. Ausgangspunkt der Analyse ist das Sprecher-Horer-Modell im Kontext der Psychoakustik. Einleitend werden wichtige Grundlagen des Sprechens, der Sprache, der Wahrnehmung und des Verstehens von Sprache dargestellt: der Sprecher produziert Sprache (Sprechweise, Artikulation), die zum Horer im Raum oder uber elektroakustische Anlagen ubertragen wird und gestort werden kann (Bandbegrenzung, Gerausche, Nachhall, Ubersteuerung etc.). Der Horer muss die Sprache wahrnehmen und verstehen, auch wenn er schwerhorig ist oder Gehorschutz tragt. Die Messung der Sprachverstandlichkeit wird anhand der Sprachindices erlautert. Die Methoden zur Bestimmung der Qualitat der Sprachkommunikation werden aufbauend auf der Verstandlichkeit durch Parameter wie Konzentration und Belastigung erganzt und neu formuliert. Die so entwickelten Qualitatsstufen werden ausfuhrlich diskutiert, dazu werden Kriterien fur die Raumgestaltung (u.a. Schulen) abgeleitet. Die Analyse soll es ermoglichen, den Umgebungsbereich fur sprachliche Kommunikation "barrierefrei" zu gestalten, so dass die Kommunikationspartner ungeachtet ihres Alters, individueller Handicaps (begrenzte Sprachkompetenz, Schwerhorigkeit) in offentlichen Bereichen und in der Arbeitswelt als gleichberechtigte Partner am Gesprach teilnehmen konnen. Ziel dieses Buches ist es auch uber die Akustik hinaus einen grossen Leserkreis unterschiedlicher Interessen und Berufsgruppen wie Ergonomen, Psychologen, Mediziner, Architekten, Medienexperten in die Diskussion uber die Sprachkommunikation aus wissenschaftlicher und angewandter Sicht einzufuhren und Hinweise fur eine optimale Gestaltung zu geben."

This book constitutes the refereed proceedings of the 4th International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR 2003, held in Lisbon, Portugal in July 2003. The 33 revised full papers presented were carefully reviewed and selected from 66 submissions. The papers are organized in topical sections on unsupervised learning and matching, probabilistic modeling, segmentation and grouping, shape modeling, restoration and reconstruction, and graphs and graph-based methods.

The refereed proceedings of the 4th International Conference on Scale Space Methods in Computer Vision, Scale-Space 2003, held at Isle of Skye, UK in June 2003. The 56 revised full papers presented were carefully reviewed and selected from 101 submissions. The book offers topical sections on deep structure representations, scale space mathematics, equivalences, implementing scale spaces, minimal approaches, evolution equations, local structure, image models, morphological scale spaces, temporal scale spaces, shape, and motion and stereo.

This book constitutes the thoroughly refereed post-proceedings of the 11th International Workshop on Theoretical Foundations of Computer Vision, held in Dagstuhl Castle, Germany in April 2002. The 27 revised full papers presented went through two rounds of reviewing and improvement and assess the state of the art in geometry, morphology, and computational imaging. The papers are organized  in sections on geometry - models and algorithms; property measurement in the grid and on finite samples; features, shape, and morphology; and computer vision and scene analysis.

  This book constitutes the refereed proceedings of the Third International Conference on Computer Vision Systems, ICVS 2003, held in Graz, Austria, in April 2003. The 51 revised full papers presented were carefully reviewed and selected from 109 submissions. The papers are organized in topical sections on cognitive vision, philosophical issues in cognitive vision, cognitive vision and applications, computer vision architectures, performance evaluation, implementation methods, architecture and classical computer vision, and video annotation.

This book focuses on end-to-end robotic applications using vision and control algorithms, exposing its readers to design innovative solutions towards sensors-guided robotic bin-picking and assembly in an unstructured environment. The use of sensor fusion is demonstrated through a bin-picking task of texture-less cylindrical objects. The system identification techniques are also discussed for obtaining precise kinematic and dynamic parameters of an industrial robot which facilitates the control schemes to perform pick-and-place tasks autonomously without any interference from the user. The uniqueness of this book lies in a judicious balance between theory and technology within the context of industrial application. Therefore, it will be valuable to researchers working in the area of vision- and force control- based robotics, as well as beginners in this inter-disciplinary area, as it deals with the basics and technologically advanced research strategies.

In the last decade unsupervised pattern discovery in time series, i.e. the problem of finding recurrent similar subsequences in long multivariate time series without the need of querying subsequences, has earned more and more attention in research and industry. Pattern discovery was already successfully applied to various areas like seismology, medicine, robotics or music. Until now an application to automotive time series has not been investigated. This dissertation fills this desideratum by studying the special characteristics of vehicle sensor logs and proposing an appropriate approach for pattern discovery. To prove the benefit of pattern discovery methods in automotive applications, the algorithm is applied to construct representative driving cycles.

Many robotics researchers consider high-level vision algorithms (computational) too expensive for use in robot guidance. This book introduces the reader to an alternative approach to perception for autonomous, mobile robots. It explores how to apply methods of high-level computer vision and fuzzy logic to the guidance and control of the mobile robot. The book introduces a knowledge-based approach to vision modeling for robot guidance, where advantage is taken of constraints of the robot's physical structure, the tasks it performs, and the environments it works in. This facilitates high-level computer vision algorithms such as object recognition at a speed that is sufficient for real-time navigation. The texts presents algorithms that exploit these constraints at all levels of vision, from image processing to model construction and matching, as well as shape recovery. These algorithms are demonstrated in the navigation of a wheeled mobile robot.

This book constitutes the refereed proceedings of the 5th International Conference on Visual Information Systems, VISUAL 2002, held in Hsin Chu, Taiwan, in March 2002.The 28 revised full papers presented together with one invited paper were carefully reviewed and selected for inclusion in the book. The papers are organized in topical sections on content-based indexing, search, and retrieval; visual information system architectures; image/video databases; networked video; and applications in various fields.

This volume consists of the 42 papers presented at the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR2001), whichwasheldatINRIA(InstitutNationaldeRechercheen Informatique et en Automatique) in Sophia Antipolis, France, from September 3 through September 5, 2001. This workshop is the third of a series, which was started with EMMCVPR'97, held in Venice in May 1997, and continued with EMMCVR'99, which took place in York, in July 1999. Minimization problems and optimization methods permeate computer vision (CV), pattern recognition (PR), and many other ?elds of machine intelligence. The aim of the EMMCVPR workshops is to bring together people with research interests in this interdisciplinary topic. Although the subject is traditionally well represented at major international conferences on CV and PR, the EMMCVPR workshops provide a forum where researchers can report their recent work and engage in more informal discussions. We received 70 submissions from 23 countries, which were reviewed by the members of the program committee. Based on the reviews, 24 papers were - cepted for oral presentation and 18 for poster presentation. In this volume, no distinction is made between papers that were presented orally or as posters. The book is organized into ?ve sections, whose topics coincide with the ?ve s- sionsoftheworkshop: "ProbabilisticModelsandEstimation,""ImageModelling and Synthesis," "Clustering, Grouping, and Segmentation," "Optimization and Graphs," and "Shapes, Curves, Surfaces, and Templates."

Following the highly successful International Conference on Computer Vision - stems held in Las Palmas, Spain (ICVS'99), this second International Workshop on Computer Vision Systems, ICVS 2001 was held as an associated workshop of the International Conference on Computer Vision in Vancouver, Canada. The organization of ICVS'99 and ICVS 2001 was motivated by the fact that the - jority of computer vision conferences focus on component technologies. However, Computer Vision has reached a level of maturity that allows us not only to p- form research on individual methods and system components but also to build fully integrated computer vision systems of signi cant complexity. This opens a number of new problems related to system architecture, methods for system synthesis and veri cation, active vision systems, control of perception and - tion, knowledge and system representation, context modeling, cue integration, etc. By focusing on methods and concepts for the construction of fully integrated vision systems, ICVS aims to bring together researchers interested in computer vision systems. Similar to the previous event in Las Palmas, ICVS 2001 was organized as a single-track workshop consisting of high-quality, previously unpublished papers on new and original research on computer vision systems. All contributions were presented orally. A total of 32 papers were submitted and reviewed thoroughly by program committee members. Twenty of them have been selected for p- sentation. We would like to thank all members of the organizing and program committee for their help in putting together a high-quality workshop.

This book constitutes the refereed proceedings of the Third International Conference on Scale-Space and Morphology in Computer Vision, Scale-Space 2001, held in Vancouver, Canada in July 2001.The 18 revised full papers presented together with 23 posters were carefully reviewed and selected from 60 submissions. The book addresses all current aspects of scale-space and morphology in the context of computer vision, in particular, vector distance functions, optic flow, image registration, curve evolution, morphological segmentation, scalar images, vector images, automatic scale selection, geometric diffusion, diffusion filtering, image filtering, inverse problems, active contours, etc.

This book provides the background and introduces a practical methodology for developing autonomous camera-equipped robot systems which solve deliberate tasks in open environments based on their competences acquired from training, interaction, and learning in the real task-relevant world; visual demonstration and neural learning for the backbone for acquiring the situated competences. The author verifies the practicability of the proposed methodology by presenting a structured case study including high-level sub-tasks such as localizing, approaching, grasping, and carrying objects.

This book constitutes the thoroughly refereed post-proceedings of the 10th International Workshop on Theoretical Foundations of Computer Vision, held at Dagstuhl Castle, Germany, in March 2000.
The 20 revised full papers presented have been through two rounds of reviewing, selection, and revision and give a representative assessment of the foundational issues in multiple-image processing. The papers are organized in topical sections on 3D data acquisition and sensor design, multi-image analysis, data fusion in 3D scene description, and applied 3D vision and virtual reality.