Handwritten Gurmukhi Character Recognition Using Statistical and Background Directional Distribution Features
Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 6
Abstract
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), distance profiles (from left, right, top and bottom sides). In addition, we have used background directional distribution (BDD) features. Our database consists of 200 samples of each of basic 35 characters of Gurmukhi script collected from different writers. These samples are pre-processed and normalized to 32*32 sizes. SVM, K-NN and PNN classifiers are used for classification. The performance comparison of features used in different combination with different classifiers is presented and analysed. The highest accuracy obtained is 95.04% as 5-fold cross validation of whole database using zonal density and background distribution features in combination with SVM classifier used with RBF kernel.
Authors and Affiliations
Kartar Singh Siddharth , Mahesh Jangid, , Renu Dhir , Rajneesh Rani
Keywords
Related Articles
- EP ID EP124358
- DOI -
- Views 115
- Downloads 0
Cost Effective Cloud Environment Setup to Secure Corporate Data
In recent years ad-hoc parallel processing has emerged to be one among the killer applications for Infrastructure-as-a-Service (IaaS) clouds. Major Cloud computing firms have began to integrate frameworks for parallel pr...
Differential Evolution and Dynamic Differential Evolution Variants for High Dimensional Function Optimization : An Empirical Scalability Study
This paper empirically compares the performance and scalability of Differential Evolution (DE) and Dynamic Differential Evolution (DDE) variants for solving high dimensional unconstrained global optimization functions. F...
Frequent Itemset mining over transactional data streams using Item-Order-Tree
The association rule mining is one of the important area for research in data mining. In association rule mining online association rule mining is one of the hottest area due to the reason that the knowledge embedded in...
Chairperson and Secretarius Meeting Guides for Electronic Meeting Direction
Facilitation and guidance of computer-supported meetings is a well-known activity that can be supported electronically. Various forms of facilitator support have been developed over the years. This paper presents a uniqu...
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)...