A Model for Document classification using Kernel Discriminant Analysis(KDA) and semantic analysis

Abstract

In recent days, digital communication has become inevitable. The scope of this research is to provide a theoretical framework of automatically classification of question paper. It can be helpful to the library of any University to automate their archival process. A survey has been conducted to understand the existing systems in this research area. After doing the survey we observed that many authors have done significant work in document classification but little work has been done to automatically store the documents in particular folder. Therefore, there is a huge scope to develop working model of the framework suggested in this paper. Keywords: OCR, Kernel Discriminant Analysis (KDA), Semantic Analysis, document classification, binarization