Design and Implementation of a Cognitive Tool to Detect Malicious Images Using the Smart Phone

Design and Implementation of a Cognitive Tool to Detect Malicious Images Using the Smart Phone

Hiroyuki Nishiyama (Faculty of Science and Technology, Tokyo University of Science, Noda, Japan) and Fumio Mizoguchi (Faculty of Science and Technology, Tokyo University of Science, Noda, Japan & WisdomTex Co. Ltd., Tokyo, Japan)
DOI: 10.4018/ijssci.2014040102
OnDemand PDF Download:
List Price: $37.50
10% Discount:-$3.75


In this study, the authors design a cognitive tool to detect malicious images using a smart phone. This tool can learn shot images taken with the camera of a smart phone and automatically classify the new image as a malicious image in the smart phone. To develop the learning and classifier tool, the authors implement an image analysis function and a learning and classifier function using a support vector machine (SVM) with the smart phone. With this tool, the user can collect image data with the camera of a smart phone, create learning data, and classify the new image data according to the learning data in the smart phone. In this study, the authors apply this tool to a user interface of a cosmetics recommendation service system and demonstrate its effectiveness by in reducing the load of the diagnosis server in this service and improving the user service.
Article Preview

1. Introduction

Recently, many multifunctional cellular phone terminals, such as smart phones (e.g., Android and iPhone), have been developed as a result of the evolution of the computer, network infrastructure, and lightweight battery technology. Thus, the number of users is rapidly increasing (Mobile Content Forum, 2009). The smart phone is equipped with various sensor systems (e.g., an acceleration sensor, an infrared sensor, and a luminosity sensor), besides the camera function. Furthermore, an easily programmed application acquires input from each function. Various research and services are performed with a smart phone using such features. Examples are the study of a service that recommends cosmetics that are appropriate for the skin condition by transmitting the skin image from the camera function to an analysis server using a data mining (Hiraishi & Mizoguchi, 2012)(Nishiyama & Mizoguchi, 2011)(Nishiyama & Mizoguchi, 2013), and a navigation service using location information. Studies of skin diagnosis using data mining have been performed in the past (Gagliardi, 2012). With these services (Hiraishi & Mizoguchi, 2012)(Nishiyama & Mizoguchi, 2011)(Nishiyama & Mizoguchi, 2013), information obtained from various sensors of the smart phone is transmitted to a server via the network; next, the server performs analysis and calculation are executed on the server side; and finally, the result is displayed on the smart phone. Thus, the server should have the computational performance and the communication performance to enable correspondence even if many requests are received at the same time (Hiraishi & Mizoguchi, 2012), and to strengthen the server environment as the number of users increases. However, some users may send to the server the image is not a skin caused by shooting mistakes (or intentionally). In particular, in the evaluation stage of this experiment skin diagnostic services start early, users who submit images “Malicious” with variety, such as egg yolk and refrigerator were present. If such “Malicious” images have had more, because the adverse effect on the performance analysis of server side, some measures were also necessary. Moreover, the calculation ability of the smart phone and the portable terminal PDA has advanced more rapidly than that of the past cellular phone terminal such that these devices now have the same processing performance as a small notebook computer. Therefore, interest in research into data mining with a portable terminal has also increased.

Complete Article List

Search this Journal:
Volume 15: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing