Non-Linear Segmentation of Touched Roman Characters Based on Genetic Algorithm
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 6
Abstract
The segmentation accuracy of Roman cursive characters, especially touched characters, is essential for the high performance of Optical Character Recognition Systems. This paper presents a new approach for non-linear segmentation of multiple touched Roman cursive characters based on genetic algorithm. Initially, a possible segmentation zone is detected and then best segmentation path is evolved by genetic gorithm. The initial population is composed of each point column in possible segmentation zone. The individual coding, fitness function, crossover operator and mutation operator are also defined for this task. Experimental results on a test set extracted on the IAM benchmark database exhibit high segmentation accuracy up to 89.76%. Proposed approach can handle some complex types of touched cursive characters without special heuristic rules and recognition.
Authors and Affiliations
Tanzila Saba, , Ghazali Sulong , Amjad Rehman
Keywords
Related Articles
- EP ID EP108066
- DOI -
- Views 71
- Downloads 0
Analysis of AOMDV and OLSR Routing Protocols Under Levy-Walk Mobility Model and Gauss-Markov Mobility Model for Ad Hoc Networks
In this paper we have compared AOMDV and OLSR routing protocol using Levy-Walk Mobility Model and Gauss-Markov Mobility Model. OLSR is a proactive, table-driven, link state routing protocol while AOMDV is a reactive rout...
Conditional Random Fields based Pronominal Resolution in Tamil
This paper deals with Tamil pronominal resolution using Conditional Random Fields a machine learning approach. A detailed linguistic analysis of Tamil pronominals and its antecedence occurring in various syntactic constr...
Optimizing Live Digital Evidence Mining Using Structural Subroutines of Apriori Algorithm
The Scope and Complexity of the Internet has grown exponentially. This growth has made digital forensic investigation a very challenging task. Even the modest intra-organizational networks have sufficient network traffic...
Investigations and Performance Evaluation of Dynamic Routing Protocol with New Proposed Protocol for WAN
Routing is a relevant issue for maintaining good performance and successfully operating in a network. Routing Protocols allow routers to dynamically advertise and learn routes, determine which routes are available and wh...
Investigation of data clustering preprocessing algorithm on independent attributes to improve the performance of CLONALG
It is a popularly held belief that preprocessing of data generally improves the classification efficiency of data mining algorithms. We study the effects of preprocess by utilizing an algorithm to cluster points in a dat...