Abstract

Document image structure analysis is to achieve computerized document management and storage and retrieval. The main objective is to identify different pages of books, journals and reports and segregate it from other document images. This process helps to create a database of digital documents. It provides an immediate solution to enable the archived valuable materials so that it can be searchable and usable by users in order to achieve its objective. It also provides way of representing and managing the paper document in electronic form. For, the purpose of viewing, indexing and extracting the intended portions. The proposed technique work on every aspect of image including its size, shape and orientation of image.