: In this paper we present a novel methodology to recognize the layout structure of handwritten filled table-forms. Recognition methodology includes locating line intersections, co...
We have developed a biologically-motivated, unsupervised way of grouping together images whose salient regions of interest (ROIs) are perceptually similar regardless of the visual...
Gustavo B. Borba, Humberto R. Gamba, Oge Marques, ...
An unsupervised probabilistic learning framework for normalizing product records across different retailer Web sites is presented. Our framework decomposes the problem into two ta...
Documentimageunderstandingdenotesthe recognition of semanticallyrelevant componentsin the layout extracted froma documentimage.This recognitionprocessis based on somevisual models...
Floriana Esposito, Donato Malerba, Francesca A. Li...
We propose a novel approach to unsupervised facial image
alignment. Differently from previous approaches, that
are confined to affine transformations on either the entire
face o...