淡江大學機構典藏:Item 987654321/74573
English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 62805/95882 (66%)
造訪人次 : 3926640      線上人數 : 736
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/74573


    題名: 在雲端計算中使用支援向量機來做性別分類
    其他題名: Using support vector machines for gender classification on cloud computing
    作者: 周俊昌;Chou, Chun-Chang
    貢獻者: 淡江大學資訊工程學系碩士在職專班
    洪文斌;Horng, Wen-Bing
    關鍵詞: 支援向量機;區域二元模式;性別辨識;雲端計算;Cloud Computing;Gender classification;LBP;SVM
    日期: 2011
    上傳時間: 2011-12-28 18:55:34 (UTC+8)
    摘要: 在近幾年電腦視覺影像研究中,人臉的辨識上已有相當大的進步,延伸而來的應用也相當多,如人臉的性別、表情、年齡辨識等。在這些影像的辨識研究領域中,系統的辨識率以及系統的效能,一直是相關領域的研究重點。
    在本論文中,輸入影像可經由個人電腦選取,或經由手機端擷取數位相機影像。經由用戶端裝置偵測人臉的位置,並使用區域二元模式演算法作為人臉正面影像的特徵值,以及降低此特徵值維度以減低系統的運算負擔,之後傳送至伺服器端以辨識性別。在性別辨識的問題中,我們利用支援向量機的統計學理論來做為人臉的性別辨識分類器。
    支援向量機演算法對於在計算能力或記憶體容量比較低裝置是相當大的負擔如個人掌上型電腦或手機等。為了解決這類的問題,我們開發了主從式架構的程式,在伺服器端負責訓練性別分類器,及對用戶端所傳送之影像特徵值辨識性別並把辨識的結果回報給用戶端的裝置,以避免用戶者端的裝置運算負荷過大。在本實驗中,我們對FERET人臉資料庫做交叉驗證,可得到93.21%辨識率。
    Face detection has been considerable progress in computer vision recently, and extends from the applications are quite a few, such as gender recognition, expression, age identification. In the field of computer vision, recognition rate and system performance has been attention in the related field.
    In this paper, client device is responsible for detecting the location of face then reduce dimension of the face feature using LBP (local binary patterns) operator, and send to server side. The classification problem is performed by support vector machines.
    The support vector machine algorithm requests amount of computing and memory, which is a considerable burden on handheld computers or mobile phones. To solve the problem, we developed client-server programming. In order to avoid that client device over loading, the server side is responsible for training of gender classifier and predicts results which received the face feature form client device then sends to the client device. In our experiments, 5-fold cross-validation are performed on FERET face database and obtained the accuracy of 93.21%.
    顯示於類別:[資訊工程學系暨研究所] 學位論文

    文件中的檔案:

    檔案 大小格式瀏覽次數
    index.html0KbHTML196檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋