English  |  正體中文  |  简体中文  |  Items with full text/Total items : 67783/67783 (100%)
Visitors : 23096646      Online Users : 178
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/987654321/81107

    Title: 使用紋理能量圖和卷積神經網路在二維條碼偵測
    Authors: 柯羽航;Ke, Halin
    Contributors: 資訊工程學系在職專班
    Keywords: Data-Matrix二維條碼;紋理能量圖;卷積神經網路;Data-Matrix barcode;Texture Energy Map;Convolutional Neural Network
    Date: 2019-07-04
    Issue Date: 2019-09-03 15:34:48 (UTC+8)
    Publisher: 國立中央大學
    Abstract: Data-Matrix二維條碼因其抗損毀能力強、所佔空間小等特性,已被廣泛應用於航太工業、汽車製造業、半導體與印刷電路板零件的識別。條碼偵測是條碼辨識的關鍵。針對低品質的條碼影像,例如扭曲、模糊、光照不均等,典型的條碼偵測方法會有偵測率過低和辨識困難的問題。本研究提出一個創新的條碼偵測方法,基於Data-Matrix二維條碼其邊緣取向具有相互垂直的特性,將條碼影像轉換成紋理能量圖,再結合卷積神經網路進行條碼偵測模型的深度學習。我們使用一個低品質Data-Matrix條碼影像資料庫來驗證所提出的方法,其條碼偵測正確率可以提升22%,可有效改善條碼辨識性能不足的問題。;Data-Matrix 2D barcodes have been widely used in the identification of aerospace industry, automotive industry, semiconductor and printed circuit board parts due to their strong resistance to damage and small space. Barcode detection is the key to barcode recognition. For low-quality barcode images, such as distortion, blur, uneven illumination, etc. The typical barcode detection methods have problems of low detection rate and difficulty in identification. This study proposes an innovative barcode detection method based on Data-Matrix two-dimensional barcode whose edge orientation has mutually perpendicular characteristics, converts the barcode image into a Texture Energy Map, and combines the depth learning of the barcode detection model with the Convolutional Neural Network. We use a low-quality Data-Matrix barcode image database to verify the proposed method. The barcode detection accuracy can be improved by 22%, which can effectively improve the problem of insufficient barcode recognition performance.
    Appears in Collections:[資訊工程學系碩士在職專班 ] 博碩士論文

    Files in This Item:

    File Description 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 ©   - Feedback  - 隱私權政策聲明