English  |  正體中文  |  简体中文  |  Items with full text/Total items : 55176/89445 (62%)
Visitors : 10659455      Online Users : 24
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU 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://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/111448

    Title: A study for solving livelihood issues based on novel image processing algorithm
    Other Titles: 基於創新影像處理演算法解決民生議題之研究
    Authors: 黃謝璋;Huang, Hsieh-Chang
    Contributors: 淡江大學電機工程學系博士班
    謝景棠;Hsieh, Ching-Tang
    Keywords: 避障;障礙物偵測;Kinect;深度影像;區域生長法;重疊指紋;方向場;蓋柏濾波器;傅利葉轉換;Obstacle Detection;Depth image;Overlapping fingerprint;orientation field;Gabor-filter;Fourier transform
    Date: 2016
    Issue Date: 2017-08-24 23:53:07 (UTC+8)
    Abstract: 民生議題中有大部份十分適合利用數位影像處理來解決,其中像是避障及重疊指紋分離就是十分適切,所以本論文基於創新影像處理演算法解決避障及重疊指紋分離此兩個議題。第一個議題是避障,根據研究資料顯示,目前全台灣約有5萬6 名視障人口,有許多視障人士需要依賴導盲杖觸碰地面或物體, 判斷前方是否有可以行走的區域, 碰觸不到的地方,只能由聽覺去評估周遭環境或用嗅覺判斷所身處的位置。或者是由導盲犬引導視障人士避障,但是不是每一位視障人士都能夠輕易和導盲犬配對成功並取得, 而且導盲犬的訓練需要時間,所以他們往往需要等待很長一段時間,在使用的時間上, 也不會比相關輔助器具長久。為了使視障人士能夠有效的了解周遭環境, 利用電腦視覺與導盲杖相互配合就能解決這方面的問題,因此如何有效地偵測障礙物, 是本研究的重要課題。本研究提出使用深度資訊,協助視障人士避開障礙物,當他們在一個陌生的環境中移動障礙物檢測方法。該系統由三個部分組成:場景偵測,障礙物偵測和聲音警示。本項研究提出了一種新的方法來刪除克服過分割問題的地平面。本系統通過去除邊緣以及用於使用所連接的設備的方法(CCM)的區域生長方法的初始種子位置的問題解決了過分割的問題。本系統可檢測的靜態和動態的障礙,功能強大,高效能,實驗結果證明本系統既強韌又方便。
    Most of the livelihood issues are very suitable for digit image processing to solve. The Livelihood issues are such as obstacle avoidance and overlapping fingerprint separation is very relevant, so this paper based on an innovative image processing algorithms to solve the obstacle avoidance and overlapping fingerprint separation issues. The first issue of this study proposes an obstacle detection method that uses depth information to allow visually impaired to avoid obstacles when they move in an unfamiliar environment. According to new statistics, there are 285 million visually impaired people relying on the guide cane or guide dogs to move around freely in the world. However, not every visually impaired person can easily pair successfully with guide dogs and there is often a long wait for an animal. The system is composed of three parts: scene detection, obstacle detection and a vocal announcement. This study proposes a new method to remove the ground plane that overcomes the over-segmentation problem. This system addresses the over-segmentation problem by removing the edge and the initial seed position problem for the region growth method using the Connected Component Method (CCM). This system can detect static and dynamic obstacles. The system is simple, robust and efficient. The experimental results show that the proposed system is both robust and convenient.
    The second issue of this study presents an improved fingerprint recognition system for overlapping fingerprint of two fingers. The developed system can automatically and precisely separate an overlapping fingerprint into two areas, an overlapping area and a non-overlapping area, by analyzing their orientation fields and complexity. A method being able to remove a misjudging condition from the overlapping area is also proposed in this paper. Moreover, a recursive correction algorithm and a constrained relaxation labeling algorithms are applied to separate two fingerprints from the determined overlapping fingerprint area, and the Gabor filter is applied to enhance figure quality of the two separated fingerprints. After that, the VeriFinger 6.2 SDK is used to identify the fingerprints. In the experiments, the fingerprints in the two databases, Receiver Operating Characteristic (ROC) and Cumulative Match Characteristic (CMC), are used to examine the proposed fingerprint recognition system.
    Appears in Collections:[Graduate Institute & Department of Electrical Engineering] Thesis

    Files in This Item:

    File Description SizeFormat

    All items in 機構典藏 are protected by copyright, with all rights reserved.

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