Omnifont Persian OCR System Using Primitives

by   Azarakhsh Keipour, et al.

In this paper, we introduce a model-based omnifont Persian OCR system. The system uses a set of 8 primitive elements as structural features for recognition. First, the scanned document is preprocessed. After normalizing the preprocessed image, text rows and sub-words are separated and then thinned. After recognition of dots in sub-words, strokes are extracted and primitive elements of each sub-word are recognized using the strokes. Finally, the primitives are compared with a predefined set of character identification vectors in order to identify sub-word characters. The separation and recognition steps of the system are concurrent, eliminating unavoidable errors of independent separation of letters. The system has been tested on documents with 14 standard Persian fonts in 6 sizes. The achieved precision is 97.06


page 1

page 2

page 3

page 4


A Trainless Recognition of Handwritten Persian/Arabic Letters using Primitive Elements

This paper aim at applying primitive elements composing Persian/Arabic l...

Primitive Sets of Words

Given a (finite or infinite) subset X of the free monoid A^* over a fini...

Bounding the Probability of Error for High Precision Recognition

We consider models for which it is important, early in processing, to es...

Morphological Reconstruction for Word Level Script Identification

A line of a bilingual document page may contain text words in regional l...

Categorizing ancient documents

The analysis of historical documents is still a topical issue given the ...

Unsupervised Separation of Transliterable and Native Words for Malayalam

Differentiating intrinsic language words from transliterable words is a ...

Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification

Graph structures are powerful tools for modeling the relationships betwe...