Author : Dipalee Patil 1
Date of Publication :7th February 2018
Abstract: Internet users frequently use e-mail for fast data communication of audio, video and textual data but at the same time, they are facing problem due to unwanted e-m3ail known as spam e-mail. In order to filter this unwanted e-mail, a classifier must be placed in the network or in the computer. Spam e-mail with advertisement text embedded in images presents a great challenge to anti-spam filters. In this paper, we present a fast method to detect image-based spam e-mail. To achieve the objective, Artificial Neural Network is applied for the classification of spam and ham emails. OCR-based modules can be used against image spam, to tolerate the analysis of the semantic content embedded into images
Reference :
-
- Harisinghney A. ; Dixit A. ; Gupta S. ; Arora A. “Text and Image based spam email classification using KNN, naïve Bayes and Reverse DBSCAN algorithm” Optimization, Reliability and Information Technology(ICROIT) , 2014 International Conference on DOI:10.1109/ICROIT.2014.6798302, page(s):153-155, 2014
- N. Nhung and T. Phuong."An Efficient Method for Filtering Image-Based Spam E-mail". Proc. IEEE International Conference on Research, Innovation and Vision for the Future ( RIVF07), IEEE Press, Mar. 2007 , pp. 96- 102. doi: 10.1I 0 9 /RIVF.2007.369I 4 1.
- Ketari, Lamia Mohammed, Munesh Chandra, and MohammadiAkheelaKhanum. "A Study of Image Spam Filtering Techniques."Computational Intelligence and Communication Networks (CICN), 2012 Fourth International Conference on IEEE,2012.
- R. Smith, "An Overview of the Tesseract OCR Engine," in Proc. International Conference on Doc ument Analysis and Recognition, 2007
- Klimt, Bryan, and Yiming Yang. "The Enron corpus: A new dataset for email classification research." Machine learning: ECML 2004. Springer Berlin Heidelberg, 2004. 217-226.
- Breuel, Thomas M. "The OCRopus open source OCR system.“D RR 6815 (2008): 68150.