Skin Detection of Animation Characters

TL;DR

This paper proposes three novel RGB-based methods for detecting skin in anime characters, addressing the limitations of existing human skin detection techniques due to the unique color and texture variations in anime.

Contribution

The paper introduces three new skin detection methods tailored for anime characters, outperforming existing human skin detection algorithms in this domain.

Findings

Improved accuracy in anime skin detection over existing methods

Effective differentiation between skin and similar-colored non-skin objects

Robustness across various lighting and character styles

Abstract

The increasing popularity of animes makes it vulnerable to unwanted usages like copyright violations and pornography. That is why, we need to develop a method to detect and recognize animation characters. Skin detection is one of the most important steps in this way. Though there are some methods to detect human skin color, but those methods do not work properly for anime characters. Anime skin varies greatly from human skin in color, texture, tone and in different kinds of lighting. They also vary greatly among themselves. Moreover, many other things (for example leather, shirt, hair etc.), which are not skin, can have color similar to skin. In this paper, we have proposed three methods that can identify an anime character skin more successfully as compared with Kovac, Swift, Saleh and Osman methods, which are primarily designed for human skin detection. Our methods are based on RGB values and their comparative relations.