Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) (2007)
Curitiba, Parana, Brazil
Sept. 23, 2007 to Sept. 26, 2007
E. Sriraghavendra , Indian Institute of Science, Bangalore
Karthik K. , Indian Institute of Science, Bangalore
C. Bhattacharyya , Indian Institute of Science, Bangalore
We propose a novel, language-neutral approach for searching online handwritten text using Fr?echet distance. Online handwritten data, which is available as a time series (x,y,t), is treated as representing a parameterized curve in two-dimensions and the problem of searching online hand- written text is posed as a problem of matching two curves in a two-dimensional Euclidean space. Fr?echet distance is a natural measure for matching curves. The main contribu- tion of this paper is the formulation of a variant of Fr?echet distance that can be used for retrieving words even when only a prefix of the word is given as query. Extensive ex- periments on UNIPEN dataset1 consisting of over 16,000 words written by 7 users show that our method outperforms the state-of-the-art DTW method. Experiments were also conducted on a multilingual dataset, generated on a PDA, with encouraging results. Our approach can be used to implement useful, exciting features like auto-completion of handwriting in PDAs.
K. K., E. Sriraghavendra and C. Bhattacharyya, "Fr?chet Distance Based Approach for Searching Online Handwritten Documents," Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)(ICDAR), Curitiba, Parana, Brazil, 2007, pp. 461-465.