We tested our image classification methodology in the photo-annotation task of the ImageCLEF competition [Nowak, 2010] using a visual-only approach performing automated labeling. ...
We propose a new method for handwritten word-spotting which does not require prior training or gathering examples for querying. More precisely, a model is trained "on the fly...
: This paper describes a new approach to document classification based on visual features alone. Text-based retrieval systems perform poorly on noisy text. We have conducted serie...
This article proposes a novel similarity measure between
vector sequences. Recently, a model-based approach was
introduced to address this issue. It consists in modeling
each se...
Current face image retrieval methods achieve impressive results, but lack efficient ways to refine the search, particularly for geometric face attributes. Users cannot easily ...