Abstract
In Document processing typed and handwritten text on paper-based & electronic documents converted into electronic information. To electronically process the contents of printed documents, information must be extracted from digitally scanned images. The manipulation of printed documents is largely in use like printed forms are delivered to end users for completion, storage and verification etc. In such situations these printed documents must return to digital form in order to participate in digitalized workflows. In printed documents, the contents of different regions and fields are highly heterogeneous. They have different layout, different printing quality and typing standards. The text line, keywords and image extraction from such complex printed document can be a difficult problem.