Abstract

An approach to segmentation or clustering of a set of ele ments combines separate procedures and uses training data for those procedures on labeled data. This approach is applied to elements being components of an image of text (eg, printed or handwritten). In some examples, the elements are connected sets of pixels. In images of text, the clusters can correspond to individual lines. The approach provides improved clustering performance as compared to any one of the procedures taken alone.

Date

2015

Authors

SN Vitaladevuni, R Prasad, P Natarajan

Inventors

Shiv N Vitaladevuni, Rohit Prasad, Premkumar Natarajan

Patent_office

US

Patent_number

9224207

Application_number

14028833