Theme-Based Multi-class Object Recognition and Segmentation

In this paper, we propose a new theme-based CRF model and investigate its performance on class based pixel-wise segmentation of images. By including the theme of an image, we also propose a new texture-environment potential to represent texture environment of a pixel, which alone gives satisfactory...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2010 20th International Conference on Pattern Recognition S. 3013 - 3016
Hauptverfasser: Shilin Wu, Jiajia Geng, Feng Zhu
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.08.2010
Schlagworte:
Accuracy
Conditional random field(CRF)
Image recognition
Image segmentation
Joint-boost
Object recognition
Pixel
Training
Visualization
ISBN:1424475422, 9781424475421
ISSN:1051-4651
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we propose a new theme-based CRF model and investigate its performance on class based pixel-wise segmentation of images. By including the theme of an image, we also propose a new texture-environment potential to represent texture environment of a pixel, which alone gives satisfactory recognition results. The pixel-wise segmentation accuracy is remarkably improved by introducing texture potential. We compare our results to recent published results on the MSRC 21-class database and show that our theme-based CRF model significantly outperforms the current state-of-the-art. Especially, by assigning a theme for each image, our model obtains greatly improved accuracy of structured classes with high visual variability and fewer training examples, the accuracy of which is very low in most related works.
ISBN:1424475422
9781424475421
ISSN:1051-4651
DOI:10.1109/ICPR.2010.738