English  |  正體中文  |  简体中文  |  Items with full text/Total items : 70585/70585 (100%)
Visitors : 23119010      Online Users : 704
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/987654321/84091


    Title: 人臉圖片生成與增益之可用性與效率探討分析
    Authors: 江翰霖;Chiang, Han-Lin
    Contributors: 資訊管理學系在職專班
    Keywords: 人臉辨識;資料生成;資料增益;Face detection;Data generation;Data augmentation
    Date: 2020-07-28
    Issue Date: 2020-09-02 18:03:27 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 人臉辨識一直是相當熱門的話題,而在近年機器學習技術的興起,更將人臉辨識推往更上一層樓。經由大量的數據做訓練,能夠有效的提升辨識準確度,因此如何更大量的收集人臉辨識訓練圖片,便是一門重要的課題。

    本研究個案公司因應研發計畫,在人臉辨識專案,採用監督式學習方式,對人臉圖片進行訓練,以產生人臉偵測模組,因此常有大量人臉圖片的需求。在長期的需求之下,利用資料生成與資料增益,是相當適合的方式。

    本研究針對人臉資料生成與人臉資料增益,探討兩種方式何者在產出人臉圖片較有效率,包含了產生圖片花費的時間以及產生的圖片可用性。

    經過實驗後,可得知在兩者相較之下,兩者的可用性相似,並無太大差異,但在時間效率上,使用人臉資料增益的方式,遠比使用人臉生成的方式快上許多。因此,對本研究個案公司而言,使用人臉資料增益的方式產生人臉圖片,是較符合個案需求的方式。
    ;Face detection has always been a very popular topic, and in recent years, the rise of machine learning technology has pushed face detection to a higher level.
    Training through a large amount of data can effectively improve the detection accuracy, so how to collect a larger number of face detection training pictures is an important topic.
    In response to the research and development plan, the case of A Company in this study adopted a supervised learning method in the face detection project to train the face pictures to generate face detection modules, so there is often a demand for a large number of face pictures. Under long-term demand, the use of data generation and data augmentation is a very suitable way.
    This study focuses on face data generation and face data augmentation, and explores which of the two methods is more efficient in producing face images, including the time it takes to generate the images and the availability of the generated images.
    Comparing the two, we can find that the two are similar in terms of usability, but in terms of time efficiency, the way of using face data augmentation is much faster than the way of using face generation.
    After confirming the efficiency and availability, it will be of great help to the future development of A company in this research case.
    Appears in Collections:[資訊管理學系碩士在職專班 ] 博碩士論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML60View/Open


    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 ©   - Feedback  - 隱私權政策聲明