The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Total Variation Applications in Computer Vision
Abstract
The objectives of this chapter are: (i) to introduce a concise overview of regularization; (ii) to define and to explain the role of a particular type of regularization called total variation norm (TV-norm) in computer vision tasks; (iii) to set up a brief discussion on the mathematical background of TV methods; and (iv) to establish a relationship between models and a few existing methods to solve problems cast as TV-norm. For the most part, image-processing algorithms blur the edges of the estimated images, however TV regularization preserves the edges with no prior information on the observed and the original images. The regularization scalar parameter λ controls the amount of regularization allowed and it is essential to obtain a high-quality regularized output. A wide-ranging review of several ways to put into practice TV regularization as well as its advantages and limitations are discussed.
Related Content
|
Jayashri Dutta, Smitakshi Medhi, Mayurakshi Gogoi, Lisha Borgohain, Nourhan Gamal Abdel Maboud, Hanaa Mustafa Muhameed.
© 2025.
34 pages.
|
|
Abdellah Khouz, Jorge Trindade, Fatima El Bchari, Pedro Pinto Santos, Eusébio Reis, Adil Moumane, Fatima Ezzahra El Ghazali, Mourad Jadoud, Blaid Bougadir.
© 2025.
38 pages.
|
|
Phyo Thandar Hlaing, Muhammad Waqas, Usa Wannasingha Humphries.
© 2025.
32 pages.
|
|
Adil Moumane, Jamal Al Karkouri, Batchi Mouhcine.
© 2025.
28 pages.
|
|
Abdessamad Elmotawakkil, Nourddine Enneya.
© 2025.
20 pages.
|
|
Fatima Ezzahra El Ghazali, Abdellah Khouz.
© 2025.
30 pages.
|
|
Tarik Bahouq, Amina Moumane, Nadia Touhami.
© 2025.
28 pages.
|
|
|