就網路的隱密性來說，使用者瀏覽色情網站多數為了滿足好奇心，以網路的匿名性、易得性、立即性、互動性的一些特質來說，多數原本只停留在瀏覽階段的使用者轉逐漸轉變成為影像的提供者，基於互相分享的回饋心理，加上免費網頁空間的服務，造成網路上到處都可以放置色情影像，貼圖區就是一個很明顯的例子，這是一個集合眾人貢獻的地方，沒有商業色情網站的付費機制做為第一道關卡，也不受網路內容分級的規範，任何人都可以輕易的取得色情影像，因此有必要加以防治。 本研究以膚色偵測、人臉偵測、膚色區域特徵來判斷影像內容是否為裸露之人體影像，透過網路封包擷取技術取出使用者所瀏覽網頁的URL，分析其網頁內容是否包含不適當的影像，最後產生URL黑、白名單。 It is a popular internet behavior that users browse through the pornographic websites for the purpose of satisfying their curiosity. Most users start to be image provider due to the anonymity, availability, immediacy, and interaction of internet. Pornographic images can be posted on almost every website because people tend to share whatever files they have with other users along with the offer of free homepage space service. The chart website is a typical example, which is a space with no payment mechanism and censorship. Almost all kinds of pornographic images are available on the website. It is a must to control and prevent such behavior. In this thesis, we propose a nude image detection mechanism based on the techniques of skin color detection, face detection, and skin region detection. By utilizing internet packet, we can retrieve the user’s URL and then analyze whether the contents contain any inappropriate image. Finally, black and white URL lists will be produced to prevent the act.
