Abstract: This paper presents a new approach to addresses the problems associated with text documents protection, such as copyright protection and content verification. This problem has not been investigated much for text media and most of the work available in literature is based on multimedia forms. Therefore, due to the large amount of text documents available and with the extensive use of the Internet to distribute such documents it becomes essential to protect and secure information delivered through the Internet. Few techniques have been proposed to attain this goal; however, they are not sufficient to protect sensitive documents such as the Holy Quran. This paper presents a new adaptive approach based on zero-watermarking for highly-sensitive documents in order to achieve content verification and authentication without physically modifying the cover-text in anyway. Finally, this work is anticipated to open new research directions in text and multimedia watermarking.

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-43
• Views: 0
• Downloads: 0

Abstract: Graphical text representation method attempts to capture the syntactical structure and semantics of documents. As such, they are the preferred text representation approach for a wide range of problems namely in natural language processing, information retrieval and text mining. In a number of these applications, it is necessary to measure the similarity between knowledge represented in the graphs. In this paper, we present semantic similarity measure to compare graph based representation of sentences. The proposed method incorporates computational linguistic method to obtain syntactical information prior to representation with graph. Word synonyms are embedded in the graph representation to support semantic matching. In this paper, we present our idea and initial results on the feasibility of the proposed similarity measurement method.

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-42
• Views: 0
• Downloads: 0