Historical Handwritten Text Images Word Spotting Through Sliding Window HOG Features
Lists
Only you see this
Abstract
In this paper we present an innovative technique to semi-automatically index handwritten word images. The proposed method is based on HOG descriptors and exploits Dynamic Time Warping technique to compare feature vectors elaborated from single handwritten words. Our strategy is applied to a new challenging dataset extracted from Italian civil registries of the XIX century. Experimental results, compared with some previously developed word spotting strategies, confirmed that our method outperforms competitors.
BibTeX
@inproceedings{bolelli2017historical,
author = {Federico Bolelli and Guido Borghi and Costantino Grana},
title = {{Historical Handwritten Text Images Word Spotting Through Sliding Window HOG Features}},
booktitle = {ICIAP},
year = {2017},
doi = {10.1007/978-3-319-68560-1\_65},
}