English  |  正體中文  |  简体中文  |  Items with full text/Total items : 69561/69561 (100%)
Visitors : 23206509      Online Users : 263
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/987654321/81564

    Title: 基於深度學習與影像處理之儀表偵測與讀數識別
    Authors: 馬政;Ma, Zheng
    Contributors: 電機工程學系
    Keywords: 深度學習;影像處理;儀表分類;指針提取;讀數識別
    Date: 2019-08-22
    Issue Date: 2019-09-03 16:03:05 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 當前時代人工智慧發展迅速,許多傳統行業都逐漸從人工密集型尋求向人工智慧的轉型。在科技研究領域,深度學習的演算法不斷改進並在多個領域都得到應用。在目前關於儀表自動識別的研究中,使用傳統影像處理方法都會有很大的局限性,往往只能針對單一儀表,而且無法適應不同環境。本文結合深度學習與影像處理,嘗試用新方法辨識多種儀表並讀出儀表指數。
    ;With the rapid development of artificial intelligence, nowadays many traditional industries gradually from labor-intensive industry into artificial intelligence. In the field of scientific technology, deep learning algorithm has been improved and applied in many fields, especially in image processing and pattern recognition. Currently, traditional image processing methods have many limitations in the automatic instrument recognition and most of the proposed methods were designed for recognizing only one type of specific instrument meter. Therefore, this study proposes a novel method to recognize different instrument meters and read the scales pointed in the meters.
    In this study, the main purpose is that a kind of intelligent system based on deep learning and image processing is designed to recognize common instruments such as circular meters, square meters and digital scale meters in the factory. First of all, we use object detection network YOLOv3 to locate instruments of images which are captured from mobile phone and camera. Then we use image processing technology to remove interference information of the images. Secondly, according to the type of instrument, HoughCircles and findContours functions are used to confirm the central position of the instrument, and hough line transform and polar coordinate method are used to realize the pointer position. In addition, YOLOv3 is applied again to recognize the number in order to find the closest number and the second closest number to the pointer, finally, we can calculate the value of the instrument.
    This thesis uses object detection network to locate the instrument position. In comparison with the traditional methods, the proposed method can rapidly locate various types and sizes of the instrument in different images and has strong anti-interference. The system can be adapted to the different range and uneven scale of the instrument, which greatly improves the application range, and really realize the intelligent instrument recognition.
    Appears in Collections:[電機工程研究所] 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