**Dictionary of Computer Vision and Image Processing**

This dictionary arose out of a continuing interest in the resources needed by beginning students and researchers in the fields of image processing, computer vision and machine vision (however you choose to define these overlapping fields). As instructors and mentors, we often found confusion about what various terms and concepts mean for the beginner. To support these learners, we have tried to define the key concepts that a competent generalist should know about these fields. The results are definitions for more than 2500 terms.

This is a dictionary, not an encyclopedia, so the definitions are necessarily brief and are not intended to replace a proper textbook explanation of the term. We have tried to capture the essentials of the terms, with short examples or mathematical precision where feasible or necessary for clarity. Further information about many of the terms can be found in the references below. These are mostly general textbooks, each providing a broad view of a portion of the field. Some of the concepts are also quite recent and, although commonly used in research publications, have not yet appeared in mainstream textbooks. Thus this book is also a useful source for recent terminology and concepts.

Certainly there are some missing concepts, but we have scanned both textbooks and the research literature to find the central and commonly used terms. Many additional terms also arose as part of the definition process itself.

Although the dictionary was intended for beginning and intermediate students and researchers, as we developed the dictionary it was clear that we also had some confusions and vague understandings of the concepts. It also surprised us that some terms had multiple usages. To improve quality and coverage, each term was reviewed during development by at least two people besides its author. We hope that this has caught any errors and vagueness, as well as reproduced the alternative meanings. Each of the co-authors is quite experienced in the topics covered here, but it was still educational to learn more about our field in the process of compiling the dictionary. We hope that you find using the dictionary equally valuable.

While we have strived for perfection, we recognize that we might have made some errors or been insufficiently precise. Hence, there is a web site where errata and other materials can be found: http://homepages.inf.ed.ac.uk/rbf/CVDICT/. If you spot an error, please email us: .

To help the reader, terms appearing elsewhere in the dictionary are hyperlinked. We have tried to be reasonably thorough about this, but some terms, such as 2D, 3D, light, camera, image, pixel and color were so commonly used that we decided to not cross-reference these.

The current list of terms in numerical and alphabetical order.

We have tried to be consistent with the mathematical notation:

- italics for scalars (
*s*) - arrowed italics for points and vectors () and
- mathbf letters for matrices (
**M**)

These excellent resources can be consulted for further details about the terms defined here:

- BB
- D. Ballard, C. Brown. Computer Vision. Prentice Hall, 1982.

A classic textbook presenting an overview of techniques in the early days of computer vision. Still a source of very useful information. - BT
- R. D. Boyle, R. C. Thomas. Computer Vision: A First Course, Blackwell, 1988.

A good general-purpose introductory textbook. - ERD
- E. R. Davies. Machine Vision, Academic Press, 1990.

A classical text, revised several times, with much detail particularly at the low and middle levels of image analysis. - DH
- R. O. Duda, P. E. Hart. Pattern Classification and Scene Analysis,
James Wiley, 1973.

A classical text, recently updated. - OF
- O. Faugeras, Three-Dimensional Computer Vision - A Geometric Viewpoint, MIT Press, 1999.

An excellent reference book - FP
- D. Forsyth, J. Ponce. Computer Vision - a modern approach. Prentice Hall, 2003.

A recent, comprehensive book covering both 2D (image processing) and 3D material. - LG
- L. J. Galbiati. Machine Vision and Digital Image Processing
Fundamentals, Prentice Hall, 1990.

A short text focusing on machine vision techniques. - HS
- R. M. Haralick, L. G. Shapiro. Computer and Robot Vision. Addison-Wesley Longman Publishing, 1992.

A well-known, extensive collection of algorithms and techniques, with mathematics worked out in detail. Mostly image processing, but some 3D vision as well. - EH
- E. Hecht. Optics. Addison-Wesley, 1987.

A key resource for information on light, geometrical optics, distortion, polarization, Fourier optics, etc. - BKPH
- B. K. P. Horn. Robot Vision. MIT Press, 1986.

A classic textbook in computer vision. Especialy famous the treatment of optic flow. Dated nowadays, but still very interesting and useful. - AJ
- A. Jain. Fundamentals of Digital Image Processing. Prentice Hall Intl, 1989.

A little dated, but still a thorough introduction to the key topics in 2D image processing and analysis. Particularly useful is the information on various whole image transforms, such as the 2D Fourier transform. - JKS
- R. Jain, R. Kasturi, B. Schunck. Machine Vision. McGraw Hill, 1995.

A good balance of image processing and 3D vision, including typically 3D topics like model-based matching. Reader-friendly presentation, also graphically. - AL
- A. Low, Introductory Computer Vision and Image Processing,
McGraw-Hill, 1991.

A good entry-level textbook. - VSN
- V. S. Nalwa. A Guided Tour of Computer Vision. Addison Wesley, 1993.

A discoursive, compact presentation of computer vision at the beginning of the 90s. Good to get an overview of the field as it was, and quickly. - RN
- R. Nevatia. Machine Perception, Prentice-Hall, 1982.

A classic introductory text. - PB
- M. Petrou and P. Bosdogianni. Image Processing: The Fundamentals. Wiley Interscience, 1999.

A student-oriented textbook on image processing, focussing on enhancement, compression, restoration and pre-processing for image understanding. - RJS
- R. J. Schalkoff. Digital Image Processing and Computer Vision,
Wiley, 1989.

A good course textbook. - SS
- L. Shapiro, G. Stockman. Computer Vision. Prentice Hall. 2001.

A thorough and broad 2D and 3D computer vision book, suitable for use as a course textbook and for reference. - SQ
- W. E. Snyder and H. Qi. Machine Vision, Cambridge, 2004.

A more recent textbook on image analysis and pattern recognition. - SHB
- M. Sonka, V. Hlavac, R. Boyle. Image Processing, Analysis, and Machine Vision. Chapman and Hall, 1993.

A well-known, exhaustive textbook covering much image processing and a good amount of 3D vision alike, so that algorithms are sometimes only sketched. A very good reference book. - TV
- E. Trucco, A. Verri. Introductory Techniques for 3-D Computer Vision. Prentice Hall, 1998.

This book gives algorithms and theory for many central 3D algorithms and topics, and includes supporting detail from 2D and image processing where appropriate. - SEU
- S. E. Umbaugh. Computer Vision and Image Processing. Prentice Hall, 1998.

A compact book on image processing, coming with its own development kit and examples on a CD.

We'd like to thank our International Advisory Board who contributed many helpful suggestions on terms and their definitions.

Aaron Bobick | Georgia Institute of Technology |

Chris Brown | Rochester University |

Stefan Carlsson | Swedish Royal Institute of Technology |

Henrik Christensen | Swedish Royal Institute of Technology |

Roberto Cipolla | University of Cambridge |

James L. Crowley | INRIA Rhones Alpes |

Patrick Flynn | University of Notre Dame |

Vaclav Hlavac | Czech Technical University |

Anil Jain | Michigan State University |

Avinash Kak | Purdue University |

Ales Leonardis | University of Ljubljana |

Song-De Ma | Chinese Academy of Sciences |

Gerard Medioni | University of Southern California |

Joe L. Mundy | General Electric Corporation |

Shmuel Peleg | Hebrew University of Jerusalem |

Maria Petrou | Surrey University |

Keith Price | University of Southern California |

Azriel Rosenfeld | University of Maryland |

Amnon Shashua | Hebrew University of Jerusalem |

Yoshiaki Shirai | Osaka University |

Milan Sonka | University of Iowa |

Chris Taylor | University of Manchester |

Demetri Terzopoulos | University of Toronto |

John Tsotsos | York University |

Shimon Ullman | Weizmann Institute |

Andrew Zisserman | University of Oxford |

Steven Zucker | Yale University |

Return to entry.