Script Identification from Indian Documents

Abstract

Abstract. Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we present a scheme to identify different Indian scripts from a document image. This scheme employs hierarchical classification which uses features consistent with human perception. Such features are extracted from the responses of a multi-channel log-Gabor filter bank, designed at an optimal scale and multiple orientations. In the first stage, the classifier groups the scripts into five major classes using global features. At the next stage, a sub-classification is performed based on script-specific features. All features are extracted globally from a given text block which does not require any complex and reliable segmentation of the document image into lines and characters. Thus the proposed scheme is efficient and can be used for many practical applications which require processing large volumes of data. The scheme has been tested on 10 Indian scripts and found to be robust to skew generated in the process of scanning and relatively insensitive to change in font size. This proposed system achieves an overall classification accuracy of 97.11% on a large testing data set. These results serve to establish the utility of global approach to classification of scripts.

Scripts and Numerals Identification From Printed Multilingual Document Images

“…Dhanya et al [14], has achieved better performance in the latter method rather than the Pati et al [24]. But this would fail for some English characters which are descender dominant.…”

“…Dhanya et al [9], has performed script classification using Gabor filters for bilingual document images in frequency domain. In the work of Joshi et al [14], different Indian scripts are identified with a Log Gabor filter. Regarding token based approach Judith Hochberg et al [8], [9] exemplars are grouped into clusters based on a similarity measure.…”

“…Tamil and English scripts has been done by a group of people [4], [14], [28], etc.. Among the works reported in this direction, to distinguish between various Indian scripts at word level is addressed only alphabet-based script identification, whereas numeral script identification is ignored.…”

Segmentation of Tri-Lingual Documents

“…The local approaches(Pal and Chaudhury [2], Pal et al [3]) analyze a list of connected components (Line, word, char) in the document images, to identify the script(or class of script). In contrast, global approaches (Joshi [4]) employ an analysis of regions (block of text) comprising atleast two lines (or words)without finer segmentation. In general, global approaches work well based on texture measurement, but this relies heavily on a uniform block of text (Buschet al [5]), and extensive preprocessing (to make the text block uniform) is required to measure the texture.…”

Subspace models for document script and language identification

“…In Europe and in countries like India, where there are multiple official languages with independent scripts, the automation of language recognition is of utmost importance for proper management of digitized documents. Automatic script identification is useful in sorting document images, selecting appropriate script-specific OCRs, and search online archives of document image for those containing a particular script Joshi et al (2006). With the high amount of digitization happening all over which is not just restricted to English documents, a language identification system capable of identifying both Asian and European languages is important.…”