Local Jet Feature Space Framework for Image Processing and Representation

Antoine Manzanera (1)

1 RV - Robotique et Vision

We present a unified framework for processing and representing images using a feature space related to local similarity. The visual data is represented by the versatile multiscale local jet feature space, possibly reduced by vector quantisation and/or represented by data structures enabling efficient nearest neighbours search (e.g. kd-trees). We demonstrate the interest of the local jet feature space processing through three fundamental low level tasks: noise reduction, motion estimation and background modelling/subtraction. We also show the potential of the framework in terms of higher level visual representation (e.g. recognition/retrieval).

Mots clés: non local means; background modelling; optical flow; nearest neighbours; similarity space; multiscale local jets; vision framework

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]

Antoine Manzanera. Local Jet Feature Space Framework for Image Processing and Representation. The 7th International Conference on SIGNAL IMAGE TECHNOLOGY & INTERNET BASED SYSTEMS, Nov 2011, Dijon, France. ⟨10.1109/SITIS.2011.49⟩. ⟨hal-01119682⟩