Shape Based Feature Extraction in Detection of Image Email
R Mallikka, Merlin Balamurugan - · Journal of Physics Conference Series · 2018
Electronic mail is one of the important communication channels of information technology which serves as a systematic and universal communication mechanism across the globe. Though the functionalities of e-mail have been very helpful in serving both individuals and institutions, it encounters a major issue called 'Spamming'. Spam mails are unwanted text or image-based messages, often sent without the consent of users so as to fill their mailboxes. In this paper, proposes Shape based feature extraction is used which tends to recognize the characters in the images and identify whether an image is Ham or Spam. In this paper at first elaborates on the methods of visual feature extraction (Text layout analysis) and the details of the algorithms used for Image Ham / Spam detection. Furthermore, the score and performance metrics of the identified images are provided which is the result of the experiments. The overall efficiency of the proposed system reached above 90 per cent which discerns the proposed work as a significant contribution to the research community.