Scalespace Theory in Computer Vision

Python Programming; Deep Learning; Computer Vision; CNNs; Caltech-101; MNIST Digits;

This book was conceived during the Workshop "Calibration and Orientation of Cameras in Computer Vision" at the XVIIth Congress of the ISPRS (In­ ternational Society of Photogrammetry and Remote Sensing), in July 1992 in Washington, D. C. The goal of this workshop was to bring photogrammetry and computer vision experts together in order to exchange ideas, concepts and approaches in camera calibration and orientation. These topics have been addressed in photogrammetry research for a long time, starting in the sec­ ond half of the 19th century. Over the years standard procedures have been developed and implemented, in particular for metric cameras, such that in the photogrammetric community such issues were considered as solved prob­ lems. With the increased use of non-metric cameras (in photogrammetry they are revealingly called "amateur" cameras), especially CCD cameras, and the exciting possibilities of acquiring long image sequences quite effortlessly and processing image data automatically, online and even in real-time, the need to take a new and fresh look at various calibration and orientation issues became obvious.

The goal of this book is to address the use of several important machine learning techniques into computer vision applications. An innovative combination of computer vision and machine learning techniques has the promise of advancing the field of computer vision, which contributes to better understanding of complex real-world applications.