Review on extraction techniques for images, textlines and keywords from document image

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