Offline Handwritten Script Identification in Document Images

Automatic handwritten script identification from document images facilitates many important applications such as sorting, transcription of multilingual documents and indexing of large collection of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate a texture as a tool for determining the script of handwritten document image, based on the observation that text has a distinct visual texture. Further, K nearest neighbour algorithm is used to classify 300 text blocks as well as 400 text lines into one of the three major Indian scripts: English, Devnagari and Urdu, based on 13 spatial spread features extracted using morphological filters. The proposed algorithm attains average classification accuracy as high as 99.2% for bi-script and 88.6% for tri-script separation at text line and text block level respectively with five fold cross validation test. General Terms Pattern Recognition, Document Image Analysis