This title is reprinted to order which may result in extended delivery times
For upper level courses in Computer Vision and Image Analysis.
Provides necessary theory and examples for students and practitioners who will work in fields where significant information must be extracted automatically from images. Appropriate for those interested in multimedia, art and design, geographic information systems, and image databases, in addition to the traditional areas of automation, image science, medical imaging, remote sensing and computer cartography. The text provides a basic set of fundamental concepts and algorithms for analyzing images, and discusses some of the exciting evolving application areas of computer vision.
2. Imaging and Image Representation.
3. Binary Image Analysis.
4. Pattern Recognition Concepts.
5. Filtering and Enhancing Images.
6. Color and Shading.
8. Content-Based Image Retrieval.
9. Motion from 2D Image Sequences.
10. Image Segmentation.
11. Matching in 2D.
12. Perceiving 3D from 2D Images.
13. 3D Sensing and Object Pose Computation.
14. 3D Models and Matching.
15. Virtual Reality.
16. Case Studies.
- Broad range of topics—Topics include image databases and virtual and augmented reality in addition to classical topics.
Familiarizes students with the traditional topics as well as exciting evolving application areas. Ex.___
- Two significant case studies—(Ch. 16) 1) Veggie Vision: A System for Checking Out Vegetables; 2) Identifying Humans via the Iris of an Eye.
Gives students a complete view of real-world systems that use computer vision. Ex.___
- Progressive intuitive/mathematical approach—The early chapters begin at an intuitive level and progress towards mathematical models. (Optional more mathematical/advanced sections are marked with an asterisk.) The processing of iconic imagery is emphasized in the first eleven chapters, and 3D computer vision is covered in later chapters. Instructors could easily re-sequence chapters to fit a particular course or teaching style.
Helps students achieve an intuitive understanding before tackling formal characterization. Ex.___
- Language independent—The text does not rely on any programming language, but uses a generic algorithmic notation.
Allows students to do projects using their choice of languages and tools. Ex.___
- Specific Software independent.
Enables students to study and learn principles in an environment with few variables. Gives students a firm foundation for successfully choosing and using an industrial system. Ex.___
- Course flexibility and short-course option.
Enables instructors to select, and sometimes sequence, content in different ways according to the goal of the course and their own and students' interests. The first four chapters provide sufficient depth for a complete short course. Ex.___
- 360 figures; 270 exercises; 48 separately defined algorithms; 118 highlighted definitions; 300 numbered equations.
LINDA G. SHAPIRO is Professor of Computer Science and Engineering and Professor of Electrical Engineering at the University of Washington. She earned a bachelor's degree in mathematics from the University of Illinois in 1970 and master's and Ph.D. degrees in computer science from the University of Iowa in 1972 and 1974, respectively. She taught at Kansas State University and at Virginia Polytechnic Institute and State University and served as Director of Intelligent Systems at Machine Vision International before joining the University of Washington in 1986. Professor Shapiro is past editor-in-chief of the journal Image Understanding and is a member of the editorial boards of Computer Vision and Image Understanding and of Pattern Recognition. She has served on the program committees of many computer vision workshops and conference and is co-author of the text, Computer and Robot Vision with Robert M. Haralick. She was elected a Fellow of the IEEE in 1995, and a Fellow of the International Association for Pattern Recognition in 2000.
GEORGE C. STOCKMAN received the B.S. degree in Mathematics-Education from East Stroudsburg State University in 1966, the MAT degree from Harvard in 1967, the M.S. degree in computer science from Penn State in 1971, and the Ph.D. degree in computer science from The University of Maryland in 1977. Currently he is a Professor of Computer Science and Engineering at Michigan State University, where he joined the faculty in 1982. From 1974 to 1982, he worked as a Research Scientist for LNK Corporation on problems in image analysis and computer cartography. At MSU he teaches programming and data structures as well as computer vision and computer graphics. Professor Stockman has been active in many activities of the IEEE, including workshops on the teaching of computing with images.