MOMENT AND DENSITY BASED HADWRITTEN MARATHI NUMERAL RECOGNITION
Journal Title: Indian Journal of Computer Science and Engineering - Year 2012, Vol 3, Issue 5
Abstract
In this paper, we present an OCR for handwritten Marathi Numerals recognition using two sets of features, namely, density and central moments. Central moments of order 3 and 4 are computed globally for the numeral image while density features are computed by dividing the numeral image into different zones. The combined features are fed to the classifiers namely, minimum distance, k-nearest neighbor (k- NN) and Support Vector Machines (SVM) to classify the unknown numeral patterns. The proposed method provided encouraging results.
Authors and Affiliations
S. M. Mali
Refined Anchor Free Localisation for Wireless Sensor Monitoring in Wireless Sensor Networks
Localisation is required for many ad-hoc sensor network applications. In this paper we look at the limitations of the existing localisation technique, Anchor Free Localisation (AFL) with regards to coping with non-unifor...
A TRAILBLAZING MODUS OPERANDI TO FACE IDENTIFICATION USING A RECKONING ARCHETYPAL PRINCIPAL COMPONENT ANALYSIS
Face identification is a task of designating human faces with exact names, akin to identifying between similar twins. The work was motivated and is imbibed by physiology and information theory domains. The approach treat...
Computer Profiling Based Model for Investigation
Computer profiling is used for computer forensic analysis, and proposes and elaborates on a novel model for use in computer profiling, the computer profiling object model. The computer profiling object model is an inform...
Impact of Aspect Orientation on Object Oriented Software Metrics
Object Oriented Paradigm has become quite popular over recent years and has completely replaced the Procedural Oriented Paradigm. Object-Oriented Programming (OOP) encourages software reuse by providing design and langua...