Clustering Low Quality Farsi Sub-words For Word Recognition

OCR of low resolution documents is not so common, because it has a lot of problems. However, today there are several archives of digital documents which are scanned at lowresolution, to consume less storage. These documents which usually have a resolution of 100 to 150 dpi, require to beconverted to searchable documents. In this paper presents a new method for clustering of low quality printed Persian sub-words.This is necessary to reduce the number of classes of sub-words inorder to improve the overall recognition rate. Two popular clustering methods, hierarchical and k-means implemented andcompared. Local binary patterns (LBP) and zoning algorithms used for feature extraction. Both features are fast and representthe global shape information very well. Moreover, we used different distance measures to find the similarity of featurevectors. We applied our algorithms on a dataset of 10,700 imagesof distinct Persian sub-words with 96 dpi resolution. Experimental results show that the hierarchical clustering withthe correlation distance measure has the best performance over other clustering methods and distance measures

Keywords:

Clustering , Persian Typing Sub-Words , Low Resolution , Hierarchical , K-meams , Local Binary Patterns , Zoning