SVM with Gaussian kernel-based image spam detection on textual features
- 1 February 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
With the growth of the internet and the increasing importance of emails in our daily lives, spams have become a common phenomenon posing serious threats, as it gives rise to undesired emails. Image spam is a type of email spam in which the textual message is embedded within an image presenting it as a picture. This paper proposes a Support Vector Machine (SVM) with Gaussian kernel based classifier for detection of spam. In our experiment, we have used publicly available datasets with SVM with Gaussian kernel based classifier showing that our approach gives good performance over considered classifiers for measurement of F-measure, recall, accuracy and precision.Keywords
This publication has 10 references indexed in Scilit:
- On robust image spam filtering via comprehensive visual modelingPattern Recognition, 2015
- Learning Object-to-Class Kernels for Scene ClassificationIEEE Transactions on Image Processing, 2014
- A survey of image spamming and filtering techniquesArtificial Intelligence Review, 2011
- A survey and experimental evaluation of image spam filtering techniquesPattern Recognition Letters, 2011
- PIMSI: A Partial Image Spam Inspector2010
- Combining visual and textual features for filtering spam emails2008
- Detecting image spam using visual features and near duplicate detection2008
- Design and Evaluation of a Bayesian-filter-based Image Spam Filtering Method2008
- Identifying Image Spam based on Header and File Properties using C4.5 Decision Trees and Support Vector Machine Learning2007
- Spam warsCommunications of the ACM, 2003