中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/8756
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 80990/80990 (100%)
Visitors : 42708865      Online Users : 1462
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/8756


    Title: 不當網頁中之色情圖片偵測;Nude Image Detection on Pornographic Webpage
    Authors: 陳俊宏;Chun-Hung Chen
    Contributors: 資訊工程學系碩士在職專班
    Keywords: 支援向量機;膚色偵測;不當網頁偵測;裸體影像過濾;support vector machine;skin color detection;Pornographic webpage detection;nude image filter
    Date: 2006-06-11
    Issue Date: 2009-09-22 11:34:15 (UTC+8)
    Publisher: 國立中央大學圖書館
    Abstract: 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.
    Appears in Collections:[Executive Master of Computer Science and Information Engineering] Electronic Thesis & Dissertation

    Files in This Item:

    File SizeFormat


    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明