Title :
Stacked Sequential Scale-SpaceTaylor Context
Author :
Gatta, Carlo ; Ciompi, Francesco
Author_Institution :
Centre de Visio per Computador, Bellaterra, Spain
Abstract :
We analyze sequential image labeling methods that sample the posterior label field in order to gather contextual information. We propose an effective method that extracts local Taylor coefficients from the posterior at different scales. Results show that our proposal outperforms state-of-the-art methods on MSRC-21, CAMVID, eTRIMS8 and KAIST2 data sets.
Keywords :
feature extraction; image representation; image segmentation; learning (artificial intelligence); CAMVID data set; KAIST2 data set; MSRC-21 data set; contextual information; eTRIMS8 data set; local Taylor coefficients extraction; posterior label; sequential image labeling methods; stacked sequential scale-space Taylor context; Context; Feature extraction; Image segmentation; Nickel; Semantics; Training; Vectors; Contextual modeling; semantic image labeling; stacked sequential learning;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2013.2297706
