The objective of Document Analysis and Recognition (DAR) is to recognize the text and graphical components of a document and to extract information. This book is a collection of research papers and state-of-the-art reviews by leading researchers all over the world. It includes pointers to challenges and opportunities for future research directions. The main goal of the book is to identify good practices for the use of learning strategies in DAR.

Non-linear image processing -- Color photo denoising via hue, saturation and intensity diffusion / Lei He and Chenyang Xu -- Examining the role of scale in the context of the non-local-means filter / Mehran Ebrahimi and Edward R. Vrscay -- Geometrical mutliscale noise resistant method of edge detection / Agnieszka Lisowska -- A simple, general model for the affine self-similarity of images / SImon K. Alexander, Edward R. Vrscay, and Satoshi Tsurumi -- Image and video coding and encryption -- Efficient bit-rate estimation for mode decision of H. 264 / AVC / Shuwei Sun and Shuming Chen -- Introducing a two dimensional measure for watermarking capacity in images / Farzin Yaghmaee and Mansour Jamzad -- Estimating the detectability of small lesions in high resolution MR compressed images / Juan Paz, Marlen Pérez, Iroel Miranda, and Peter Schelkens -- JPEG artifact removal using error distributions of linear coefficient estimates / Mika Inki --

The conference topics address different theoretical and practical aspects, and implementing solutions for intelligent systems and informatics disciplines including bioinformatics, computer science, medical informatics, biology, social studies, as well as robotics research. The conference also discuss and present solutions to the cloud computing and big data mining which are considered hot research topics. The conference papers discussed different topics – techniques, models, methods, architectures, as well as multi aspect, domain-specific, and new solutions for the above disciplines. The accepted papers have been grouped into five parts: Part I—Intelligent Systems and Informatics, addressing topics including, but not limited to, medical application, predicting student performance, action classification, and detection of dead stained microscopic cells, optical character recognition, plant identification, rehabilitation of disabled people. Part II—Hybrid Intelligent Systems, addressing topics including, but not limited to, EMG signals, text classification, geomagnetic inverse problem, email filtering. Part III—Multimedia Computing and Social Networks, addressing topics including, but not limited to, augmented reality, telepresence robot, video flash matting, community detection, quality images, face thermal image extraction, MRI tumor segmentation. Part V—Cloud Computing and Big Data Mining, discussing topics including, but not limited to, mining on microblogs, query optimization, big data classification, access control, friendsourcing, and assistive technology. Part VI—Swarm Optimization and Its Applications, addressing topics including, but not limited to, solving set covering problem, adaptive PSO for CT liver segmentation, water quality assessment, attribute reduction, fish detection, solving manufacturing cell design problem.

In recent years, libraries have embraced new technologies that organize and store a variety of digital information, such as multimedia databases, digital medical images, and content-based images. Modern Library Technologies for Data Storage, Retrieval, and Use highlights new features of digital library technology in order to educate the database community. By contributing research from case studies on the emerging technology use in libraries, this book is essential for academics and scientists interested in the efforts to understand the applications of data acquisition, retrieval and storage.

The book constitutes the refereed proceedings of the Summit on Arabic and Chinese Handwriting Recognition, SACH 2006, held in College Park, USA, September 27-28, 2006. The 16 revised full papers presented were carefully reviewed and selected from a total of over 60 submissions. The first six papers deal directly with Arabic handwriting together with a short historic survey of the language and techniques used in recognition. Five papers present the current research in Chinese handwriting and three more papers deal with cross cutting methods applied to other languages. The book closes with two articles on recognition of English and south Indian handwriting.