Adult image content filtering: A statistical method based on Multi-Color Skin Modeling

Abstract

Automatic skin detection is a key enabler of various imaging applications, such as face detection, human tracking, and adult content filtering. In 1996, the first paper on identifying nude pictures was published. Since then, different researchers argue different color models to be the best choice for skin detection. But, to the best our knowledge, no siguificant work has been reported previously that attempted to use more than one color model and evaluate the performance for recoguizing adult contents. In this paper, a simple statistical framework for recoguizing adult images based on an MCSM (Multi-Color Skin Model) is described. From a high level, our approach works in two steps. First, skin regions in an input image are detected using the MCSM. Then these suspected regions are fed into a specialized geometrical analyzer that attempts to assemble a human figure using simple geometric shapes derived from human body structure. Quantitative evaluation shows that our method compares favorably with the state-of-the-art methods in terms of detection rate and false alarm, while reducing the computational complexity by a factor of 1/6 with respect to the Forsyth's method.

Reducing Affective Responses to Surgical Images and Videos Through Stylization

“…In particular, pornography is often found inadvertently by users and especially young audiences [Hal14, LSG*18, MMA*16, SP14, WTSHS15] while browsing for information. In addition to society's willingness to protect young users against this content [Mad10] that could lead to behavioural modifications [OBMR12, PV09, PV16, WTK15] through content blocking [CAS*16, MB10, PAM*17, PE10], children also report to be worried about these inappropriate media [Hal14, LKPS14, TBO*17]. While we cannot predict how FlowAbs and Arkangel could help with the issue of nudity and pornography, it is interesting to notice that violent or accident media contain features that are common to the surgery images and videos we have studied here: they include injuries, blood and visible internal organs.…”

A review: Study of various techniques of Hand Gestures Recognition

“…In this step, the hand (which is the region of interest) is separated from its background. This can be done using color-based extraction [3], background subtraction [4], histogram of orientation gradient based approach [5]. The fourth step in gesture recognition process is features extraction.…”

A Beach Image Detection Method Based on Erotic Image Detection

“…With the rapid development of the Internet, erotic images spread widely on the network, which take serious damage to teenagers. Based on this condition, a lot of erotic image detection methods are put forward, in which skin color detection is the most widely used means [1], also some combined with face, body contour information and so on [2]. To improve the recognition rate of erotic image, researches focus on the characteristics of the human body, such as taking model's breast as recognizing object [3].…”