Word retrieval in ottoman documents

In this paper, two image matching methods are adapted to retrieve words in Ottoman documents. The first method is based on Dynamic Time Warping (DTW) method proposed in, while the second method is based on the Shape Context descriptor. Firstly, all sub-words in a given Ottoman document are extracted. In the first method, a 4-variant feature vector (upper and lower word profiles, background to ink transition, vertical projection) is calculated for each sub-word and feature vectors' distance to each other is found by DTW algorithm. In the second method, shape context descriptor is used to calculate the distances of sub-word images. The methods are tested on an Ottoman data set, which consists of 10 pages of Leyla and Mecnun Divan of Fuzuli.