Text Search from Handwritten Digital Ink Using Directional Features
Bilan Zhu, Masaki Nakagawa · 2010
This paper describes a method of retrieving handwritten text using directional features. Text search from handwritten digital ink employing character recognition technology has been developed. However, the character recognition based approach does not support languages which are not assumed. To address this problem, the proposed method was devised to hypothetically segment text into character string pattern blocks and extracts directional features from all pattern blocks, then makes use of those features to calculate the similarity scores by block-shift matching between object patterns and a query pattern. The experimental result shows that, when the search method with the optimal threshold retrieves for a keyword consisting of four characters, its recall rate is 56.18%, its precision rate is 57.18%, and its F-measure is 0.57.