跳到主要內容

臺灣博碩士論文加值系統

(44.210.99.209) 您好!臺灣時間:2024/04/15 14:11
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:陳冠樺
研究生(外文):Kuan-Wha Chen
論文名稱:應用WHT於物體偵測之研究
論文名稱(外文):Study on Application of Object Detection with WHT
指導教授:張嘉銘張嘉銘引用關係
指導教授(外文):Chia-Ming Chang
口試委員:張嘉銘
口試委員(外文):Chia-Ming Chang
口試日期:2015-01-29
學位類別:碩士
校院名稱:大同大學
系所名稱:資訊工程學系(所)
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:中文
論文頁數:35
中文關鍵詞:Hadamard轉換Haar-like特徵物體偵測
外文關鍵詞:object detectionHadamard TransformHaar-like feature
相關次數:
  • 被引用被引用:0
  • 點閱點閱:113
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
Haar-like特徵擷取和Adaboost演算法最初被應用在人臉偵測上,隨後並被廣泛應用在其它物體的偵測上。在先前的研究中利用Walsh-Hadamard轉換取代積分影像及Haar-like特徵擷取,再經由Adaboost學習來偵測人臉。
  本研究將進一步探討Walsh-Hadamard轉換在其他類型之物體偵測的偵測效果,以建築物的窗戶、汽車的車牌以及機車的車輪進行實驗。此外,除原先的Haar-like特徵外,另外加入利用Sobel運算取得梯度大小及方向,並以梯度方向累計直方圖來計算Haar-like特徵之方法作為實驗對照,以三種特徵擷取技術實驗並探討學習樣本數與偵測結果,以及物體角度變化下的影響。
  在實驗中可發現Walsh-Hadamard轉換方法使用較少的學習樣本數,就能得到良好的偵測效果。在物體角度變化下,影響也較使用Haar-like特徵方法來的小。因此可以獲得一個結論,在各類型的物體偵測上,Walsh-Hadamard轉換可以取代Haar-like特徵作為偵測。
Haar-like feature extraction and Adaboost algorithm were applied to the human face detection in the beginning. Then they were widely used in the detection to other objects. In previous study, the Walsh-Hadamard transform is applied to replace the integral image and Haar-like feqtures to obtain the features of images. Through the Adaboost learning the process is used to detect human face.
In this these, the other object detection of Walsh-Hadamard transform and Adaboost algorithm is studied, including the windows of building, the license plate of cars and wheels of motorcycles. Furthermore, in addition to the original Haar-like features, the Sobel operator is used to find the gradient. The direction of the gradient is calculated to obtain the cumulative histogram. And the Haar-like features are extracted from the histogram. These three experiments are studied to evaluate the effects of the learning samples with detection results and the influence in the angle of the object.
From the experiment can be found that: less learning samples are needed with application of the Walsh-Hadamard transformation to get a good detection results. The changes in the angle of the object is less than original Haar-like features methods. Therefore, the conclusion that the object detection with Walsh-Hadamard transformation can replace the Haar-like features in the applications of objects detection.
第1章 前言1
1.1動機1
1.2目的1
1.3論文架構1
第2章 相關研究2
2.1介紹2
2.1.1灰階影像2
2.2對比度及對比度擴張2
2.2.1直方圖3
2.4AdaBoost演算法5
2.4.1Haar-like特徵擷取6
2.4.2積分影像7
2.4.3AdaBoost學習演算法9
2.5Walsh-Hadamard 轉換10
2.5.1Hadamard 矩陣11
2.5.2Hadamard 轉換11
第3章 系統說明13
3.1介紹13
3.2 系統架構13
3.3圖片學習階段14
3.3.1 Haar-like特徵擷取18
3.3.2 AdaBoost學習訓練18
3.3.3自動閥值20
3.4 圖片比對階段21
3.4.1 特徵比對21
第4章 實驗結果23
4.1實驗平台與開發工具23
4.1.1 Fedora23
4.1.2 Opencv23
4.1.3圖片資料庫24
4.2 結果與分析24
4.2.1加權和使用角度分析24
4.2.2 分類器特徵位置數量分析25
4.2.3 窗戶樣本數量分析26
4.2.4 Haar-like(histogram)、Haar-like與Hadamard特徵效能分析29
4.2.5 窗戶角度分析30
4.2.6車輪樣本數量分析32
4.2.7車牌樣本數量分析33
第5章 結論34
5.1 結論34
5.2未來展望34
[1] 吳柏諺, “應用WHT於AdaBoost 演算法之人臉辨識 ,” Tatung University, Taipei, Taiwan, Jul. 2014.
[2] Haider Ali , Christin Seifert, Nitin Jindal, Lucas Paletta and Gerhard Paar , “Window Detection in Facades ,” 14th International Conference on Image Analysis and Processing, 2007.
[3] Yuanxing Zhao, Jing Gu, Chui Liu, Shumin Han, Yong Gao and Qingmao Hu, “License Plate Location Based on Haar-like Cascade Classifiers and Edges,” Second WRI Global Congress on Intelligent System, June 2010.
[4] Wei Zheng and Luhong Liang, “Fast Car Detection Using Image Strip Features,” Computer Vision and Pattern Recognition, 2009.
[5] Huang, J. and Zabih, R., “Combining color and spatial information for content-based image retrieval,” European Conference on Digital Libraries, September 1998.
[6] Kearns, M.J. and Vazirani, U.V., “An Introduction to Computational Learning Theory,” The MIT Press, August 1994.
[7] T.C., Yang. and M.S., Wang,“Implementation of a Road Sign Recognition System Based on Integration of Adaboost Classifier and Support Vector Machine,”Thesis for Master of Science, National Cheng Kung University, 2009.
[8] Viola, P. and Jones, M.J., “Robust Real-Time Face Detetion,” International Journal of Computer Vision, pp.137-154, 2004.
[9] Georgiou, S. Koukouvinos, C. Seberry, J., "Hadamard matrices, orthogonal designs and construction algorithms,". Designs 2002: Further computational and constructive design theory. Boston: Kluwer. pp. 133–205.
[10] Townsend, W. J. and Thornton, M. A., “Walsh spectrum computations using Cayley graphs,” IEEE Midwest Symposium on Circuits and Systems,pp. 110-113,MWSCAS 2001.
[11] TSG-20: Tourist Sights Graz Image Database. http://dib.joanneum.at/cape/TSG-20/.
[12] TSG-60: Tourist Sights Graz Image Database. http://dib.joanneum.at/cape/TSG-60/.
[13] ZuBuD: Zurich Building Image Database.
http://www.vision.ee.ethz.ch/showroom/zubud/index.en.html
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top