PT Unknown
AU Jon Almazan
   Albert Gordo
   Alicia Fornes
   Ernest Valveny
TI Handwritten Word Spotting with Corrected Attributes
BT 15th IEEE International Conference on Computer Vision
PY 2013
BP 1017
EP 1024
DI 10.1109/ICCV.2013.130
AB We propose an approach to multi-writer word spotting, where the goal is to find a query word in a dataset comprised of document images. We propose an attributes-based approach that leads to a low-dimensional, fixed-length representation of the word images that is fast to compute and, especially, fast to compare. This approach naturally leads to an unified representation of word images and strings, which seamlessly allows one to indistinctly perform query-by-example, where the query is an image, and query-by-string, where the query is a string. We also propose a calibration scheme to correct the attributes scores based on Canonical Correlation Analysis that greatly improves the results on a challenging dataset. We test our approach on two public datasets showing state-of-the-art results.
ER