A Pornographic Image and Video Filtering Application Using Optimized Nudity Recognition and Detection Algorithm

Abstract

The combination of multimedia technology and Internet provides an amiss channel for pornographic contents accessible by certain sensitive groups of people. Furthermore, the same channel provides the easiest medium to distribute illicit images and videos without an autonomous content supervision process. In this study, an application was developed grounded from a pixel-based approach and a skin tone detection filter to identify images and videos with a large skin color count and considered as pornographic in nature. With nudity detection algorithm as the foundation of the system, all multimedia files were preprocessed, segmented, and filtered to analyze skincolored pixels by processing in YCbCr space and then classifying it as skin or non-skin pixels. Afterwards, the percentage of skin pixels relative to the size of the frames is calculated to be part of the mean baseline for nudity and non-nudity materials. Lastly, the application classifies the files as nude or not, and then filter it. The application was evaluated by supplying a dataset of 1,239 multimedia files (Images = 986; Videos = 253) collected from theWeb. On the final testing set, the application obtained a precision of 90.33% and accuracy of 80.23% using the supplied dataset.

“I thought you were okay”: Participatory Design with Young Adults to Fight Multiparty Privacy Conflicts in Online Social Networks

“…Most of the designed solutions refer to automatic computervision-based algorithms for detecting content that is likely to cause an MPC (e.g., photos with nudity, photos with multiple individuals). Examples of these algorithms have already been proposed in the prior state-of-the-art, e.g., previous literature focused on face detection [1,55], bystander detection [45], and nudity detection [39].…”

A review of human skin detection applications based on image processing

“…At present, many techniques are recommended to recognize the obscene images. One of the functions of skin detection is the identification of obscene images and pornography such as; multimedia files pre-processed, to analyze skin-colored pixels [19], Oriented FAST and Rotated BRIEF (ORB) [20], and combination of global and local features [21]. DATA: (From internet, NPDI).…”

“…With the growing amount of inappropriate content on the Internet like pornography the need to detect and filter such material has arisen. They [35], color-saliency preserved mixture deformable part model [36], deep convolutional neural networks [37], key-frame extraction algorithm [38], local feature with Bagof-Words models (BoW) [39], deep learning [40], deep learning [41], optimized nudity recognition [19]…”

RingFIR: A Large Volume Earring Dataset for Fashion Image Retrieval

“…Sharma et al [4] have proposed a novel face image dataset namely, UCD Colour Face Image Database for face detection. Garcia et al [30] have proposed a dataset by collecting image and video from website and developed an application to filter pornographic content. From real-world traffic surveillance environment, Liu et al [31] have constructed the VeRi dataset, contains over 50k images of 776 vehicles and also proposed a vehicle re-identification framework.…”