Document Image Processing for Scanning and Printing (Signals and Communication Technology) - Tapa dura

Acerca del autor

Ilia V. Safonov graduated from Moscow Engineering Physics Institute (at present time National Research Nuclear University MEPhI) in 1994 as engineer-physicist. He obtained PhD degree in computer science in 1997. Since 2000, he is associated professor in the department of Computer Science and Control Systems at MEPhI. At last decade, he had senior researcher position in RnD of Samsung, Nokia and Intel. At present time, Dr. Ilia Safonov is principal research-scientist at Schlumberger Moscow Research. His interests include image and signal processing, machine learning, measurement systems, computer graphics and vision.

 Ilya V. Kurilin received his MS degree in radio engineering from Novosibirsk State Technical University (NSTU), Russia in 1999 and his PhD degree in theoretical bases of informatics from NSTU in 2006. In 2007, Dr. Ilya Kurilin joined Samsung RnD Institute in Moscow, Russia, where he engaged in image processing projects for multi-function printers and mobile devices. Recently, he leads Media Processing Team specialized in real-time computational imaging for mobile devices, machine learning methods for image analysis and reconstruction, dedicated sensors for visual data processing.

 Michael N. Rychagov received MS degree in acoustical imaging and PhD degree from the Moscow State University (MSU) in 1986 and 1989, respectively. In 2000, he received a Dr.Sc. degree (Habilitation) from the same University. From 1991, he is involved in teaching and research at the National Research University of Electronic Technology (MIET) as an associate professor in the Department of Theoretical and Experimental Physics (1998), professor in the Department of Biomedical Systems (2008), professor in the Department of Informatics and SW for Computer Systems (2014). Since 2004, he joined Samsung R&D Institute in Moscow, Russia (SRR) working on imaging algorithms for printing, scanning and copying, TV and display technologies, multimedia and tomographic areas during almost 14 years, including last 8 years as Director of Division at SRR. Currently, he is Senior Manager of SW Development at Align Technology. His technical and scientific interests are image and video signal processing, biomedical modeling, engineering applications of machine learning and artificial intelligence. He is a Member of the Society for Imaging Science and Technology and Senior Member of IEEE.

 Ekaterina V. Tolstaya received her MS degree in applied mathematics from Moscow State University, in 2000. In 2004, she completed her MS degree in geophysics from University of Utah, USA, where she worked on inverse scattering in electromagnetics. Since 2004, she worked on problems of image processing and reconstruction in Samsung R&D Institute in Moscow, Russia. Based on these investigations she obtained in 2011 her PhD degree with research on image processing algorithms for printing. In 2014, she continued hercareer with Align Technology on problems involving computer vision, 3D geometry and machine learning.

De la contraportada

This book continues first one of the same authors Adaptive Image Processing Algorithms for Printing and presents methods and software solutions for copying and scanning various types of documents by conventional office equipment, offering techniques for correction of distortions and enhancement of scanned documents; techniques for automatic cropping and de-skew; approaches for segmentation of text and picture regions; documents classifiers; approach for vectorization of symbols by approximation of their contour by curves; methods for optimal compression of scanned documents, algorithm for stitching parts of large originals; copy-protection methods by microprinting and embedding of hidden information to hardcopy; algorithmic approach for toner saving. In addition, method for integral printing is considered. Described techniques operate in automatic mode thanks to machine learning or ingenious heuristics. Most the techniques presented have a low computational complexity and memory consumption due to they were designed for firmware of embedded systems or software drivers. The book reflects the authors practical experience in algorithm development for industrial R&D.