The increased number of spam images in mobile phones has become a big trouble by annoying users steadily. One big issue in developing an effective phone spam image detection system using machine learning and data mining techniques is unavailability of sufficient phone spam image data. In this study, we demonstrate that the utilization of similar email spam image data obtained by chi-square similarity distance is an effective solution to develop phone spam image classifier. We compared the performance of our approach with the one using randomly selected email spam image data and showed that this approach works better than the one using randomly selected images. Our analysis further illustrates that a more sophisticated clustering algorithm is expected to improve the performance.
CITATION STYLE
Kim, S. Y., Biad, Y., & Sohn, K. A. (2015). Investigating the effectiveness of E-mail spam image data for phone spam image detection using scale invariant feature transform image descriptor. Lecture Notes in Electrical Engineering, 339, 591–598. https://doi.org/10.1007/978-3-662-46578-3_69
Mendeley helps you to discover research relevant for your work.