Texture Analysis for Skin Classification in Pornography Content Filtering Based on Support Vector Machine

Journal of Engineering and Technological Sciences

Teguh Bharata Adji¹  Fauziazzuhry Rahadian¹  Ratna Lestari Budiani Buana¹  Hanung Adi Nugroho¹  Widhia K.Z. Oktoeberza¹ 

[1] Department of Electrical Engineering and Information Technology Faculty of Engineering, Universitas Gadjah Mada, Indonesia;

关键词: negative content;    pornography;    skin analysis;    support vector machine;   

DOI  :  10.5614/j.eng.technol.sci.2016.48.5.6

来源: DOAJ

【 摘 要 】

Nowadays, the Internet is one of the most important things in a human’s life. The unlimited access to information has the potential for people to gather any data related to their needs. However, this sophisticated technology also bears a bad side, for instance negative content information. Negative content can come in the form of images that contain pornography. This paper presents the development of a skin classification scheme as part of a negative content filtering system. The data are trained by grey-level co-occurrence matrices (GLCM) texture features and then used to classify skin color by support vector machine (SVM). The tests on skin classification in the skin and non-skin categories achieved an accuracy of 100% and 97.03%, respectively. These results indicate that the proposed scheme has potential to be implemented as part of a negative content filtering system.

【 授权许可】

Unknown