Paper Details

Now a days, there is need for the digitalization of handwritten documents. There is a large scope of researchin this area. Continuous improvement in Handwritten Character Recognition (HWCR) techniques milestones in thisresearch area. HWCR system is the software to accept and process the handwritten input images from sources such asdocuments, photographs. HWCR is the ability to transform them to machine readable and editable format. Devanagariscript is used as base for various Indian languages such as Marathi, Sanskrit, Hindi, etc. and foreign languages such asNepali. The work proposed in our Handwritten Devanagari Characters Recognition System tries to automate recognitionof handwritten Devanagari isolated characters by ensembling different classifiers. Ensemble classifier is constructed byusing Support Vector Machine (SVM) [1], K-Nearest Neighbor (KNN) [1] and Neural Network (NN) [2] which increasesthe performance by ensembling classifiers. The proposed system gives better results than individual classifiers.

Prof. Shalaka Deore, Snehal G. Zaware, Anagha A. Shelke, Amina A. Shaikh, Archana B. Dhakne, “OFFLINE HANDWRITTEN DEVANAGARI CHARACTER RECOGNITION USING FUSION OF CLASSIFIERS”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 5, Issue 1, pp. 922-925, January 2018.