This book constitutes the refereed proceedings of the 13th IFIP TC 6/TC 11 International Conference on Communications and Multimedia Security, CMS 2012, held in Canterbury, UK, in September 2012. The 6 revised full papers presented together with 8 short papers, 8 extended abstracts describing the posters that were discussed at the conference, and 2 keynote talks were carefully reviewed and selected from 43 submissions. The papers are organized in topical sections on image and handwriting analysis, authentication and performance, biometrics, forensics and watermarking, and communications security.

The two volume set LNCS 7491 and 7492 constitutes the refereed proceedings of the 12th International Conference on Parallel Problem Solving from Nature, PPSN 2012, held in Taormina, Sicily, Italy, in September 2012. The total of 105 revised full papers were carefully reviewed and selected from 226 submissions. The meeting began with 6 workshops which offered an ideal opportunity to explore specific topics in evolutionary computation, bio-inspired computing and metaheuristics. PPSN 2012 also included 8 tutorials. The papers are organized in topical sections on evolutionary computation; machine learning, classifier systems, image processing; experimental analysis, encoding, EDA, GP; multiobjective optimization; swarm intelligence, collective behavior, coevolution and robotics; memetic algorithms, hybridized techniques, meta and hyperheuristics; and applications.

The two volume set LNCS 7491 and 7492 constitutes the refereed proceedings of the 12th International Conference on Parallel Problem Solving from Nature, PPSN 2012, held in Taormina, Sicily, Italy, in September 2012. The total of 105 revised full papers were carefully reviewed and selected from 226 submissions. The meeting began with 5 workshops which offered an ideal opportunity to explore specific topics in evolutionary computation, bio-inspired computing and metaheuristics. PPSN 2012 also included 8 tutorials. The papers are organized in topical sections on evolutionary computation; machine learning, classifier systems, image processing; experimental analysis, encoding, EDA, GP; multiobjective optimization; swarm intelligence, collective behavior, coevolution and robotics; memetic algorithms, hybridized techniques, meta and hyperheuristics; and applications.

Computer processing and image analysis technologies have improved substantially over the course of the past decade. This rapidly advancing technology along with the emphasis on video surveillance since 911 has propelled the development of effective video image detection (VID) systems for ?re. Fire protection system designers initially employed these VID systems for use in large facilities, outdoor locations and tunnels. However, video-based detection is being used for a broadening range of applications [e. g. , 1]. For example, these systems are c- rently installed in electrical power plants, paper mills, document storage facilities, historic municipal buildings, nuclear research facilities, automotive plants, wa- house/distribution centers, and onshore and offshore oil platforms. The 2007 edition of NFPA 72, National Fire Alarm Code [2], recognized the use of VID systems for ?ame and smoke detection. Although recognized, there is limited prescriptive installation and use requirements and there is a general desire by many for the development of performance criteria that ultimately could be utilized for the design of systems or the creation of standards. Since the underlying VID technology and development of standard and network-based camera systems are in a period of fairly rapid advancement [3-5], it is not possible to de?ne a comprehensive set of stand-alone prescriptive requirements. The performance of VID systems depends on both the video hardware and the software algorithms; there is no basic underlying principle, such as there is for ionization or pho- electric detection for smoke detectors. Consequently, performance-based inst- lation and operation requirements are needed.

This book constitutes the refereed proceedings of the 8th International Conference, MLDM 2012, held in Berlin, Germany in July 2012. The 51 revised full papers presented were carefully reviewed and selected from 212 submissions. The topics range from theoretical topics for classification, clustering, association rule and pattern mining to specific data mining methods for the different multimedia data types such as image mining, text mining, video mining and web mining.

The two-volume set LNCS 7324/7325 constitutes the refereed proceedings of the 9th International Conference on Image and Recognition, ICIAR 2012, held in Aveiro, Portugal, in June 2012. The 107 revised full papers presented were carefully reviewed and selected from 207 submissions. The papers are organized in topical sections on clustering and classification; image processing; image analysis; motion analysis and tracking; shape representation; 3D imaging; applications; biometrics and face recognition; human activity recognition; biomedical image analysis; retinal image analysis; and call detection and modeling.

The two-volume set LNCS 7324/7325 constitutes the refereed proceedings of the 9th International Conference on Image and Recognition, ICIAR 2012, held in Aveiro, Portugal, in June 2012. The 107 revised full papers presented were carefully reviewed and selected from 207 submissions. The papers are organized in topical sections on clustering and classification; image processing; image analysis; motion analysis and tracking; shape representation; 3D imaging; applications; biometrics and face recognition; human activity recognition; biomedical image analysis; retinal image analysis; and call detection and modeling.

The two-volume set LNCS 7367 and 7368 constitutes the refereed proceedings of the 9th International Symposium on Neural Networks, ISNN 2012, held in Shenyang, China, in July 2012. The 147 revised full papers presented were carefully reviewed and selected from numerous submissions. The contributions are structured in topical sections on mathematical modeling; neurodynamics; cognitive neuroscience; learning algorithms; optimization; pattern recognition; vision; image processing; information processing; neurocontrol; and novel applications.

The development of new-generation micro-manufacturing technologies and systems has revolutionised the way products are designed and manufactured today with a s- nificant impact in a number of key industrial sectors. Micro-manufacturing techno- gies are often described as disruptive, enabling and interdisciplinary leading to the creation of whole new classes of products that were previously not feasible to ma- facture. While key processes for volume manufacture of micro-parts such as mach- ing and moulding are becoming mature technologies, micro-assembly remains a key challenge for the cost-effective manufacture of complex micro-products. The ability to manufacture customizable micro-products that can be delivered in variable volumes within relatively short timescales is very much dependent on the level of development of the micro-assembly processes, positioning, alignment and measurement techniques, gripping and feeding approaches and devices. Micro-assembly has developed rapidly over the last few years and all the pred- tions are that it will remain a critical technology for high-value products in a number of key sectors such as healthcare, communications, defence and aerospace. The key challenge is to match the significant technological developments with a new gene- tion of micro-products that will establish firmly micro-assembly as a mature manuf- turing process. th The book includes the set of papers presented at the 5 International Precision - sembly Seminar IPAS 2010 held in Chamonix, France from the 14th to the 17th February 2010.

This book constitutes selected best papers from the 10th International Conference on Artificial Evolution, EA 2011, held in Angers, France, in October 2011. Initially, 33 full papers and 10 post papers were carefully reviewed and selected from 64 submissions. This book presents the 19 best papers selected from these contributions. The papers are organized in topical sections on ant colony optimization; multi-objective optimization; analysis; implementation and robotics; combinatorial optimization; learning and parameter tuning; new nature inspired models; probabilistic algorithms; theory and evolutionary search; and applications.

During the past two decades there has been a considerable growth in interest in problems of pattern recognition and image processing (PRIP). This inter est has created an increasing need for methods and techniques for the design of PRIP systems. PRIP involves analysis, classification and interpretation of data. Practical applications of PRIP include character recognition, re mote sensing, analysis of medical signals and images, fingerprint and face identification, target recognition and speech understanding. One difficulty in making PRIP systems practically feasible, and hence, more popularly used, is the requirement of computer time and storage. This situation is particularly serious when the patterns to be analyzed are quite complex. Thus it is of the utmost importance to investigate special comput er architectures and their implementations for PRIP. Since the advent of VLSI technology, it is possible to put thousands of components on one chip. This reduces the cost of processors and increases the processing speed. VLSI algorithms and their implementations have been recently developed for PRIP. This book is intended to document the recent major progress in VLSI system design for PRIP applications."

This book constitutes the thoroughly refereed post-workshop proceedings of the First IAPR TC3 Workshop on Pattern Recognition of Social Signals in Human-Computer-Interaction (MPRSS2012), held in Tsukuba, Japan in November 2012, in collaboration with the NLGD Festival of Games. The 21 revised papers presented during the workshop cover topics on facial expression recognition, audiovisual emotion recognition, multimodal Information fusion architectures, learning from unlabeled and partially labeled data, learning of time series, companion technologies and robotics.

This book constitutes the thoroughly refereed proceedings of the first International Conference on Context-Aware Systems and Applications, ICCASA 2012, held in Ho Chi Minh City, Vietnam, in November 2012. The 34 revised full papers presented were carefully selected and reviewed from over 100 submissions. The papers cover a wide spectrum of issues in the area of Context-Aware Systems (CAS). CAS are going to shape networked computing systems of the future

This book constitutes the proceedings of the third Sino-foreign-interchange Workshop on Intelligence Science and Intelligent Data Engineering, IScIDE 2012, held in Nanjing, China, in October 2012. The 105 papers presented were carefully peer-reviewed and selected from 429 submissions. Topics covered include pattern recognition; computer vision and image processing; machine learning and computational intelligence; knowledge discovery, data mining, and web mining; graphics and computer visualization; and multimedia processing and applications.

"Time-of-Flight Cameras and Microsoft Kinect " closely examines the technology and general characteristics of time-of-flight range cameras, and outlines the best methods for maximizing the data captured by these devices. This book also analyzes the calibration issues that some end-users may face when using these type of cameras for research, and suggests methods for improving the real-time 3D reconstruction of dynamic and static scenes.

"Time-of-Flight Cameras and Microsoft Kinect "is intended for researchers and advanced-level students as a reference guide for time-of-flight cameras.Practitioners working in a related field will also find the book valuable. "

Entropy Guided Transformation Learning: Algorithms and Applications (ETL) presents a machine learning algorithm for classification tasks. ETL generalizes Transformation Based Learning (TBL) by solving the TBL bottleneck: the construction of good template sets. ETL automatically generates templates using Decision Tree decomposition.

The authors describe ETL Committee, an ensemble method that uses ETL as the base learner. Experimental results show that ETL Committee improves the effectiveness of ETL classifiers. The application of ETL is presented to four Natural Language Processing (NLP) tasks: part-of-speech tagging, phrase chunking, named entity recognition and semantic role labeling. Extensive experimental results demonstrate that ETL is an effective way to learn accurate transformation rules, and shows better results than TBL with handcrafted templates for the four tasks. By avoiding the use of handcrafted templates, ETL enables the use of transformation rules to a greater range of tasks.

Suitable for both advanced undergraduate and graduate courses, Entropy Guided Transformation Learning: Algorithms and Applications provides a comprehensive introduction to ETL and its NLP applications.

This book constitutes the refereed proceedings of the International Conference, VISIGRAPP 2011, the Joint Conference on Computer Vision, Theory and Applications (VISAPP), on Imaging Theory and Applications (IMAGAPP), on Computer Graphics Theory and Applications (GRAPP), and on Information Visualization Theory and Applications (IVAPP), held in Vilamoura, Portugal, in March 2011. The 15 revised full papers presented together with one invited paper were carefully reviewed and selected. The papers are organized in topical sections on computer graphics theory and applications; imaging theory and applications; information visualization theory and applications; and computer vision theory and applications.

Why are We Writing This Book? Visual data (graphical, image, video, and visualized data) affect every aspect of modern society. The cheap collection, storage, and transmission of vast amounts of visual data have revolutionized the practice of science, technology, and business. Innovations from various disciplines have been developed and applied to the task of designing intelligent machines that can automatically detect and exploit useful regularities (patterns) in visual data. One such approach to machine intelligence is statistical learning and pattern analysis for visual data. Over the past two decades, rapid advances have been made throughout the ?eld of visual pattern analysis. Some fundamental problems, including perceptual gro- ing,imagesegmentation, stereomatching, objectdetectionandrecognition,and- tion analysis and visual tracking, have become hot research topics and test beds in multiple areas of specialization, including mathematics, neuron-biometry, and c- nition. A great diversity of models and algorithms stemming from these disciplines has been proposed. To address the issues of ill-posed problems and uncertainties in visual pattern modeling and computing, researchers have developed rich toolkits based on pattern analysis theory, harmonic analysis and partial differential eq- tions, geometry and group theory, graph matching, and graph grammars. Among these technologies involved in intelligent visual information processing, statistical learning and pattern analysis is undoubtedly the most popular and imp- tant approach, and it is also one of the most rapidly developing ?elds, with many achievements in recent years. Above all, it provides a unifying theoretical fra- work for intelligent visual information processing applications.

Theoriginalmotivationsfordevelopingopticalcharacterrecognitiontechnologies weremodesttoconvertprintedtexton?atphysicalmediatodigitalform,prod- ingmachine-readabledigitalcontent. Bydoingthis,wordsthathadbeeninertand bound to physical material would be brought into the digital realm and thus gain newandpowerfulfunctionalitiesandanalyticalpossibilities. First-generation digital OCR researchers in the 1970s quickly realized that by limiting their ambitions primarily to contemporary documents printed in st- dard font type from the modern Roman alphabet (and of these, mostly English language materials), they were constraining the possibilities for future research andtechnologiesconsiderably. Domainresearchersalsosawthatthetrajectoryof OCR technologies if left unchanged would exclude a large portion of the human record. Digitalconversionofdocumentsandmanuscriptsinotheralphabets,scripts, and cursive styles was of critical importance. Embedded in non-Roman alp- bet source documents, including ancient manuscripts, papyri scrolls, clay tablets, and other inscribed artifacts was not only a wealth of scholarly information but alsonewopportunitiesandchallengesforadvancingOCR,imagingsciences,and othercomputationalresearchareas. Thelimitingcircumstancesatthetimeincluded the rudimentary capability (and high cost) of computational resources and lack of network-accessible digital content. Since then computational technology has advancedataveryrapidpaceandnetworkinginfrastructurehasproliferated. Over time, thisexponential decrease inthecost of computation, memory, and com- nicationsbandwidthcombinedwiththeexponentialincreaseinInternet-accessible digitalcontenthastransformededucation,scholarship,andresearch. Largenumbers ofresearchers,scholars,andstudentsuseanddependuponInternet-basedcontent andcomputationalresources. Thechaptersinthisbookdescribeacriticallyimportantareaofinvestigation- addressingconversionofIndicscriptintomachine-readableform. Roughestimates haveitthatcurrentlymorethanabillionpeopleuseIndicscripts. Collectively,Indic historic and cultural documents contain a vast richness of human knowledge and experience. The state-of-the-art research described in this book demonstrates the multiple values associated with these activities. Technically, the problems associated with Indicscriptrecognitionareverydif?cultandwillcontributetoandinformrelated v vi Foreword scriptrecognitionefforts. Theworkalsohasenormousconsequenceforenriching andenablingthestudyofIndicculturalheritagematerialsandthehistoricrecord of its people. This in turn broadens the intellectual context for domain scholars focusingonothersocieties,ancientandmodern. Digital character recognition has brought about another milestone in coll- tivecommunicationbybringinginert,?xed-in-place,textintoaninteractivedi- talrealm. Indoingso,theinformationhasgainedadditionalfunctionalitieswhich expandourabilitiestoconnect,combine,contextualize,share,andcollaboratively pursue knowledge making. High-quality Internet content continues to grow in an explosivefashion. Inthenewglobalcyberenvironment,thefunctionalitiesandapp- cationsofdigitalinformationcontinuetotransformknowledgeintonewundersta- ingsofhumanexperienceandtheworldinwhichwelive. Thepossibilitiesforthe futurearelimitedonlybyavailableresearchresourcesandcapabilitiesandtheim- inationandcreativityofthosewhousethem. Arlington,Virginia StephenM.

This revised and updated second edition - now with two new chapters - is the only book to give a comprehensive overview of computer algorithms for image reconstruction. It covers the fundamentals of computerized tomography, including all the computational and mathematical procedures underlying data collection, image reconstruction and image display. Among the new topics covered are: spiral CT, fully 3D positron emission tomography, the linogram mode of backprojection, and state of the art 3D imaging results. It also includes two new chapters on comparative statistical evaluation of the 2D reconstruction algorithms and alternative approaches to image reconstruction.

The two-volume set LNCS 7732 and 7733 constitutes the thoroughly refereed proceedings of the 19th International Conference on Multimedia Modeling, MMM 2012, held in Huangshan, China, in January 2013. The 30 revised regular papers, 46 special session papers, 20 poster session papers, and 15 demo session papers, and 6 video browser showdown were carefully reviewed and selected from numeroues submissions. The two volumes contain papers presented in the topical sections on multimedia annotation I and II, interactive and mobile multimedia, classification, recognition and tracking I and II, ranking in search, multimedia representation, multimedia systems, poster papers, special session papers, demo session papers, and video browser showdown.

EVALITA (http://www.evalita.it/) is the reference evaluation campaign of both Natural Language Processing and Speech Technologies for the Italian language. The objective of the shared tasks proposed at EVALITA is to promote the development of language technologies for Italian, providing a common framework where different systems and approaches can be evaluated and compared in a consistent manner. This volume collects the final and extended contributions presented at EVALITA 2011, the third edition of the evaluation campaign. The 36 revised full papers were carefully reviewed and selected from a total of 87 submissions. The papers are organized in topical sections roughly corresponding to evaluation tasks: parsing - dependency parsing track, parsing - constituency parsing track, domain adaptation for dependency parsing, named entity recognition on transcribed broadcast news, cross-document coreference resolution of named person entities, anaphora resolution, supersense tagging, frame labeling over italian texts, lemmatisation, automatic speech recognition - large vocabulary transcription, forced alignment on spontaneous speech.

This book constitutes the thoroughly refereed post-conference proceedings of five international workshops held in conjunction with PAKDD 2011 in Shenzhen, China, in May 2011: the International Workshop on Behavior Informatics (BI 2011), the Workshop on Quality Issues, Measures of Interestingness and Evaluation of Data Mining Models (QIMIE 2011), the Workshop on Biologically Inspired Techniques for Data Mining (BDM 2011), the Workshop on Advances and Issues in Traditional Chinese Medicine Clinical Data Mining (AI-TCM 2011), and the Second Workshop on Data Mining for Healthcare Management (DMGHM 2011). The book also includes papers from the First PAKDD Doctoral Symposium on Data Mining (DSDM 2011). The 42 papers were carefully reviewed and selected from numerous submissions. The papers cover a wide range of topics discussing emerging techniques in the field of knowledge discovery in databases and their application domains extending to previously unexplored areas such as data mining based on optimization techniques from biological behavior of animals and applications in Traditional Chinese Medicine clinical research and health care management.

An attempt is made in this book to give scientists a detailed working knowledge of the powerful mathematical tools available to aid in data interpretation, especially when con fronted with large data sets incorporating many parameters. A minimal amount of com puter knowledge is necessary for successful applications, and we have tried conscien tiously to provide this in the appropriate sections and references. Scientific data are now being produced at rates not believed possible ten years ago. A major goal in any sci entific investigation should be to obtain a critical evaluation of the data generated in a set of experiments in order to extract whatever useful scientific information may be present. Very often, the large number of measurements present in the data set does not make this an easy task. The goals of this book are thus fourfold. The first is to create a useful reference on the applications of these statistical pattern recognition methods to the sciences. The majority of our discussions center around the fields of chemistry, geology, environmen tal sciences, physics, and the biological and medical sciences. In Chapter IV a section is devoted to each of these fields. Since the applications of pattern recognition tech niques are essentially unlimited, restricted only by the outer limitations of."

This book constitutes thoroughly refereed revised selected papers from the First IAPR TC3 Workshop on Partially Supervised Learning, PSL 2011, held in Ulm, Germany, in September 2011. The 14 papers presented in this volume were carefully reviewed and selected for inclusion in the book, which also includes 3 invited talks. PSL 2011 dealt with methodological issues as well as real-world applications of PSL. The main methodological issues were: combination of supervised and unsupervised learning; diffusion learning; semi-supervised classification, regression, and clustering; learning with deep architectures; active learning; PSL with vague, fuzzy, or uncertain teaching signals; learning, or statistical pattern recognition; and PSL in cognitive systems. Applications of PSL included: image and signal processing; multi-modal information processing; sensor/information fusion; human computer interaction; data mining and Web mining; forensic anthropology; and bioinformatics.