Smart Algorithms for Multimedia and Imaging
暫譯: 多媒體與影像的智慧演算法

Rychagov, Michael N., Tolstaya, Ekaterina V., Sirotenko, Mikhail Y.

Smart Algorithms for Multimedia and Imaging
  • 出版商: Springer
  • 出版日期: 2021-05-06
  • 售價: $5,210
  • 貴賓價: 9.5 折 $4,950
  • 語言: 英文
  • 頁數: 433
  • 裝訂: Hardcover - also called cloth, retail trade, or trade
  • ISBN: 3030667405
  • ISBN-13: 9783030667405
  • 相關分類: Algorithms-data-structures

    • 海外代購書籍(需單獨結帳)

相關主題

商品描述

This book presents prospective, industrially proven methods and software solutions for storing, processing, and viewing multimedia content on digital cameras, camcorders, TV, and mobile devices. Most of the algorithms described here are implemented as systems on chip firmware or as software products and have low computational complexity and memory consumption. In the four parts of the book, which contains a total of 16 chapters, the authors address solutions for the conversion of images and videos by super-resolution, depth estimation and control and mono-to-stereo (2D to 3D) conversion; display applications by video editing; the real-time detection of sport episodes; and the generation and reproduction of natural effects. The practical principles of machine learning are illustrated using technologies such as image classification as a service, mobile user profiling, and automatic view planning with dictionary-based compressed sensing in magnetic resonance imaging. The implementation of these technologies in mobile devices is discussed in relation to algorithms using a depth camera based on a colour-coded aperture, the animated graphical abstract of an image, a motion photo, and approaches and methods for iris recognition on mobile platforms. The book reflects the authors' practical experience in the development of algorithms for industrial R&D and the commercialization of technologies.

  • Explains digital techniques for digital cameras, camcorders, TV, mobile devices;
  • Offers essential algorithms for the processing pipeline in multimedia devices and accompanying software tools;
  • Features advanced topics on data processing, addressing current technology challenges.

商品描述(中文翻譯)

本書介紹了前瞻性、經過工業驗證的方法和軟體解決方案，用於在數位相機、攝影機、電視和行動裝置上儲存、處理和查看多媒體內容。這裡描述的大多數演算法都是作為系統單晶片（SoC）韌體或軟體產品實現的，並且具有低計算複雜度和記憶體消耗。在本書的四個部分中，共包含16章，作者針對影像和視頻的超解析度轉換、深度估計與控制以及單聲道到立體聲（2D到3D）轉換的解決方案進行了探討；視頻編輯的顯示應用；運動片段的即時檢測；以及自然效果的生成和重現。機器學習的實用原則通過使用影像分類即服務、行動用戶分析和基於字典的壓縮感知在磁共振成像中的自動視圖規劃等技術進行說明。這些技術在行動裝置中的實現與基於顏色編碼光圈的深度相機演算法、影像的動畫圖形摘要、動態照片，以及在行動平台上進行虹膜識別的方法和途徑進行了討論。本書反映了作者在工業研發和技術商業化方面的實踐經驗。

- 解釋數位相機、攝影機、電視和行動裝置的數位技術；
- 提供多媒體裝置處理管道中的基本演算法及其配套的軟體工具；
- 涉及數據處理的進階主題，針對當前技術挑戰。

作者簡介

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, Inc. (USA) in Moscow branch (Russia). His technical and scientific interests are image and video signal processing, biomedical modelling, 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 her career with Align Technology, Inc. (USA) in Moscow branch (Russia) on problems involving computer vision, 3D geometry and machine learning. Since 2020, she works at Aramco Innovations LLC in Moscow, Russia, on geophysical modelling and inversion.

Mikhail Y. Sirotenko received his engineer degree in control systems from Taganrog State University of Radio Engineering (2005) and PhD from Don State Technical University in Robotics and AI (2009). In 2009, he co-founded computer vision startup CVisionLab, shortly after he joined Samsung R&D Institute in Moscow, Russia (SRR) where he led a team working on applied machine learning and computer vision research. In 2015, he joined Amazon to work as a research scientist on Amazon Go project. In 2016, he joined computer vision startup Dresr which was acquired by Google at 2018, where he leads a team working on object recognition.

作者簡介(中文翻譯)

米哈伊爾·N·瑞查戈夫於1986年和1989年分別在莫斯科國立大學（MSU）獲得聲學成像碩士學位和博士學位。2000年，他在同一所大學獲得博士後學位（Habilitation）。自1991年以來，他在國立電子技術研究大學（MIET）從事教學和研究，擔任理論與實驗物理系的副教授（1998年）、生物醫學系的教授（2008年）、計算機系統資訊與軟體系的教授（2014年）。自2004年起，他加入位於俄羅斯莫斯科的三星研發院（SRR），在印刷、掃描和複製、電視和顯示技術、多媒體和斷層成像領域工作了近14年，其中最後8年擔任SRR的部門主管。目前，他是美國Align Technology, Inc.（美國）莫斯科分公司的軟體開發高級經理。他的技術和科學興趣包括影像和視頻信號處理、生物醫學建模、機器學習和人工智慧的工程應用。他是影像科學與技術學會的成員及IEEE的高級會員。

葉卡捷琳娜·V·托爾斯塔亞於2000年在莫斯科國立大學獲得應用數學碩士學位。2004年，她在美國猶他大學獲得地球物理學碩士學位，並在該校從事電磁學中的逆散射研究。自2004年以來，她在俄羅斯莫斯科的三星研發院工作，專注於影像處理和重建問題。基於這些研究，她於2011年獲得博士學位，研究主題為印刷的影像處理演算法。2014年，她在美國Align Technology, Inc.（美國）莫斯科分公司繼續她的職業生涯，專注於計算機視覺、3D幾何和機器學習相關問題。自2020年以來，她在俄羅斯莫斯科的阿美科創新有限責任公司（Aramco Innovations LLC）從事地球物理建模和反演工作。

米哈伊爾·Y·西羅滕科於2005年在塔甘羅格國立無線電工程大學獲得控制系統工程學位，並於2009年在頓河州立技術大學獲得機器人和人工智慧的博士學位。2009年，他共同創立了計算機視覺初創公司CVisionLab，隨後不久加入位於俄羅斯莫斯科的三星研發院（SRR），領導一個專注於應用機器學習和計算機視覺研究的團隊。2015年，他加入亞馬遜，擔任亞馬遜Go項目的研究科學家。2016年，他加入計算機視覺初創公司Dresr，該公司於2018年被谷歌收購，他在那裡領導一個專注於物體識別的團隊。

類似商品