Learning OpenCV: Computer Vision with the OpenCV Library  (English, Paperback, Bradski Gary Rost)

Adrian Kaehler and Gary Rost Bradski are the ones responsible behind the creation of OpenCV, the open source library which is aimed at computer vision in real time. This book, written by the creators of the platform themselves, discusses computer vision basics, and ways of developing applications using OpenCV.

Summary Of The Book

Learning OpenCV: Computer Vision With The OpenCV Library consists of 14 chapters, each of which deal with a specific aspect of OpenCV and computer vision. The first chapter, entitled ‘Overview’ introduces readers to the world of OpenCV and talks about its origins, content and structure. Instructions on the download and installation functions have also been provided by the authors. The second chapter goes deep into the world of OpenCV, highlighting various key topics like AVI Video, camera inputs and writing to AVI files.

Topics like data persistence, image operators are explained in chapter three. The fourth and fifth chapters deal with HighGUI and image processing respectively. Various image processing concepts like morphology, smoothing and threshold have been highlighted and explained in the fifth chapter.

Image Transforms, Histograms and Contours are dealt with in the sixth, seventh and eighth chapters respectively. Image Parts and relevant topics like watershed algorithm and background subtraction are elucidated in chapter nine. The tenth chapter deals with the various facets involved in tracking and motion.

Calibration and camera models, and 3D Vision and Projection find their places in the eleventh and twelfth chapters respectively. The thirteenth chapter explains the meaning of machine learning and associated concepts like Mahalanobis Distance and Binary Decision Trees. The last chapter focuses on the future of the OpenCV platform and how OpenCV can aid artists.

About The Authors

Adrian Kaehler is currently working for Applied Minds Corporation as a senior scientist.

In 1998, he received his Ph.D. from Columbia University in Theoretical Physics. After completing his education, he worked at organisations like Intel Corporation. He also was a part of the Stanford University AI Lab.

Gary Rost Bradski is currently a consulting professor at Stanford University AI Lab in the computer science department.

He received a BS degree from U. C. Berkeley and then did his Ph.D. from the Boston University. He is the co-founder of Industrial Perception Inc., a company which is working on creating perception systems for aimed at implementation in industrial robots.