In this paper, we propose a framework for isolating text regions from natural scene images. The main algorithm has two functions: it generates text region candidates, and it veri...
Reconstruction is imperative whenever an image or a volume needs to be resampled as a result of an affine or perspective transformation, texture mapping, or volume rendering. We p...
We present a comprehensive approach to address three challenging problems in face recognition: modelling faces across multi-views, extracting the non-linear discriminating feature...
It is now well established that sparse signal models are well suited for restoration tasks and can be effectively learned from audio, image, and video data. Recent research has be...
Julien Mairal, Francis Bach, Jean Ponce, Guillermo...
We present a scale-space with separate scales in the greyscale and spatial dimensions, using ideas from mathematical morphology. Dynamics are used for greyscale (luminance) filter...