Deep Active Shape Model for Robust Object Fitting

Object recognition and localization is still a very challenging problem, despite recent advances in deep learning (DL) approaches, especially for objects with varying shapes and appearances. Statistical models, such as an Active Shape Model (ASM), rely on a parametric model of the object, allowing a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing 2020-01, Vol.29, p.2380-2394
Hauptverfasser:	Medley, Daniela O., Santiago, Carlos, Nascimento, Jacinto C.
Format:	Artikel
Sprache:	eng
Schlagworte:	Active appearance model Active shape model Algorithms convolutional neural networks Feature extraction generalized expectation-maximization HOG Image edge detection Image segmentation Machine learning Magnetic resonance Object recognition Outliers (statistics) Probabilistic logic Robustness Shape Shape recognition SIFT Statistical analysis Statistical models
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!