Word Spotting based Retrieval of Urdu Handwritten Documents

Urdu being one of the most popular languages adopted during different swatches of history has a valuable collection of handwritten scripts in different state libraries of South Asia. Digitizing these collections can serve not only to preserve them but also to make them available to general public. Non existence of an Urdu OCR, however, limits the concept of a digital Urdu library to scanning and manual search of documents only. We present a word spotting based search method for Urdu handwritten text. The text is first segmented into partial words and a set of features is computed from each partial word. The user queries the system using word image. The partial words in the query image are then matched with those in the database and the matched partial words are merged into complete words. The proposed method evaluated on 90 handwritten documents reported encouraging precision and recall rates.