Logo

Computer Vision: Models, Learning, and Inference

Large book cover: Computer Vision: Models, Learning, and Inference

Computer Vision: Models, Learning, and Inference
by

Publisher: Cambridge University Press
ISBN/ASIN: 1107011795
ISBN-13: 9781107011793
Number of pages: 665

Description:
This modern treatment of computer vision focuses on learning and inference in probabilistic models as a unifying theme. It shows how to use training data to learn the relationships between the observed image data and the aspects of the world that we wish to estimate, such as the 3D structure or the object class, and how to exploit these relationships to make new inferences about the world from new image data.

Home page url

Download or read it online for free here:
Download link
(105MB, PDF)

Similar books

Book cover: Computer VisionComputer Vision
by - InTech
This book presents research trends on computer vision, especially on application of robotics, and on advanced approaches for computer vision. Research on RFID technology integrating stereo vision to localize an indoor mobile robot is included.
(12734 views)
Book cover: Notes on Elementary Spectral Graph TheoryNotes on Elementary Spectral Graph Theory
by - arXiv
These are notes on the method of normalized graph cuts and its applications to graph clustering. I provide a thorough treatment of this deeply original method, including complete proofs. The main thrust of this paper is the method of normalized cuts.
(8839 views)
Book cover: Introduction to Programming for Image Analysis with VTKIntroduction to Programming for Image Analysis with VTK
by - Image Processing and Analysis Group
The author's goal was to provide sufficient introductory material for a typical 1st year engineering graduate student with some background in programming in C and C++ to leverage modern open source toolkits in medical image analysis.
(16715 views)
Book cover: Object Detection in Real ImagesObject Detection in Real Images
by - arXiv
We propose a new object detection/recognition method, which improves over the existing methods in every stage of the object detection/recognition process. In addition to the usual features, we propose to use geometric shapes as additional features.
(8306 views)