Segmentation of Telugu Touching Conjunct Consonants Using Overlapping Bounding Boxes
Journal Title: International Journal on Computer Science and Engineering - Year 2013, Vol 5, Issue 6
Abstract
Telugu is an ancient historic language. It is spoken by about 84.6 million people of Andhra Pradesh. The script has circular orthography with few horizontal and slant strokes. Huge literature exists for this language in printed form which needs to be preserved by scanning and converting it into editable form. Segmentation of touching characters is a major issue in any OCR system. Segmenting the words into individual glyphs by Connected Component Analysis yields poor results due to touching characters. Touching conjunct consonants is the major component which needs to be properly addressed for improving the accuracy of an OCR system. In this paper an overlapping bounding box approach is presented for segmenting the conjunct consonants along with an algorithm for identifying the correct touching location. An accuracy rate of 91.27% is achieved.
Authors and Affiliations
J. Bharathi , Dr. P. Chandrasekar Reddy
Keywords
Related Articles
- EP ID EP156687
- DOI -
- Views 152
- Downloads 0
Implementation Of ROCK Clustering Algorithm For The Optimization Of Query Searching Time
Clustering is a data mining technique of grouping similar type of data or queries together which helps in identifying similar subject areas. The major problem is to identify heterogeneous subject areas where frequent que...
Public key cryptosystem and a key exchange protocol using tools of non-abelian group
Public Key Cryptosystems assure privacy as well as integrity of the transactions between two parties. The sizes of the keys play an important role. The larger the key the harder is to crack a lock of encrypted data. We...
Resilience Against Node Capture Attack using Asymmetric Matrices in Key Predistribution Scheme in Wireless Sensor Networks
Wireless Sensor Networks (WSN) usually consists of a large number of tiny sensors with limited computation capability, memory space and power resource. WSN’s are extremely vulnerable against any kind of internal or exter...
Dynamic Signature Verification System Using Statistics Analysis
In this paper, a new technique for dynamic signature modeling and classification framework is proposed. Raw dynamic data obtained from a digitizer are analyzed using statistic tools. The variation within the same person...
Handwritten Gurmukhi Character Recognition Using Statistical and Background Directional Distribution Features
In this manuscript handwritten Gurmukhi character recognition for isolated characters is proposed. We have used some statistical features like zonal density, projection histograms (horizontal, vertical and both diagonal)...