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

Statistical study of performance metrics of Adaptive Fault Tolerant Replication Routing Protocol for MANET

Ad hoc networks are multi-hop wireless networks having dynamic topology due to node mobility. Routing protocols for such networks should be able to respond rapidly to topological changes. Designing and analyzing routing...

Comparison of Pre-fetched Pages Before and After Path Completion

In this study we uses an approach for increasing web performance by analyzing and predicting the user behavior from user access log , identifying the missing paths in the logs and completing the same using a web structur...

Mathematical modeling And Fuzzy logic control of Inspired Isoflurane to obtain minimal flow of Anesthesia

In this paper, a fuzzy logic controller is designed and developed for control of Mean Arterial Pressure (MAP) of a patient during anesthesia using the anesthetic drug Isoflurane. Isoflurane is an anesthetic drug administ...

Improved and Balanced LEACH for heterogeneous wireless sensor networks

While wireless sensor networks (WSN) is a power constrained system, since nodes run on limited power batteries which shorten its lifespan. Prolonging the network lifetime depends on efficient management of sensing node e...

Electronic Music Synthesis and Audio Effects Processing

Music is a gratifying part of the life of a plethora of people in the world. The application of various signal processing techniques in the field of music has paved way to ‘Music Technology’. Music technology has changed...

Download PDF file
  • EP ID EP108066
  • DOI -
  • Views 112
  • Downloads 0

How To Cite

Tanzila Saba, , Ghazali Sulong, Amjad Rehman (2010). Non-Linear Segmentation of Touched Roman Characters Based on Genetic Algorithm. International Journal on Computer Science and Engineering, 2(6), 2167-2172. https://europub.co.uk/articles/-A-108066