1. NCCU Academic Hub
  2. Publications
  3. College of Commerce
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 貓狗影像辨識之特徵萃取
Feature extraction in dogs and cats image recognition
作者 鍾立強
Chung, Li Chiang
貢獻者 薛慧敏
鍾立強
Chung, Li Chiang
關鍵詞 Asirra
機器學習
影像辨識
方向梯度直方圖
主成分分析
日期 2016
上傳時間 2-Aug-2016 15:53:42 (UTC+8)
摘要 近年來，很多要求高安全性的網站都使用扭曲變形的英文或數字字串作為辨識碼，以避免網站或系統受到大量暴力的攻擊。微軟公司則於2007年提出以貓狗影像的新辨識碼系統—Asirra。對於電腦而言，貓狗影像辨識較字串更為困難。本研究主要針對Asirra的影像資料試圖建構出貓狗影像自動辨識法，藉此來了解此辨識碼系統的有效性。已知影像包含大量雜訊，若使用原始資料則計算困難而且辨識效果差，所以萃取關鍵特徵為重要的研究課題。本文考慮方向梯度直方圖法 (Histograms of Oriented Gradients, HOG) 以及主成分分析 (Principal Components Analysis, PCA) 來篩選重要變數。我們將運用挑選出的特徵建立支持向量機 (Support Vector Machine, SVM) 分類器。在實證分析中，我們發現結合此兩種特徵萃取法，除了能夠大幅降低運算時間，也能得到良好的預測正確率。
In recent years, many websites, which requires a high standard of security, use CAPTCHA to avoid mass and brutal attacks from hackers. The CAPTCHA considers the use of strings of twisted and deformed English letters or numbers as an identification code. In 2007, the company Microsoft proposed a new image-based recognition system-Assira, which uses dogs and cats images as an identification code. Dogs and cats image recognition is not more difficult than strings of letters or numbers recognition for human, but is more challenging for computers. In this paper, we aim to develop a classification method for images from Asirra. An image is represented by an enormous number of pixels. Only few pixels carry important feature information, most pixels are noise. The abundance of noise leads to computational inefficiency, and even worse, may results in inaccurate recognition. Therefore, in this problem feature extraction is an essential step before a classifier construction. We consider HOG (Histograms of Oriented Gradients) and PCA (Principal Components Analysis) to select important features, and use the features to construct a SVM (Support Vector Machine) classifier. In the real example, we find that combining the two feature detection methods can dramatically reduce computational time and have satisfactory predictive accuracy.
參考文獻  A. Rencher, (1995), “Methods of multivariate analysis,” New York : John Wiley.
 C.-C. Chang and C.-J. Lin, (2001), “LIBSVM: a library for support vector machines,” Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
 C. Cortes and V. Vapnik, (1995), “Support vector networks,” Machine Learning, 20, 273–297.
 D. L. Schwartz, (1995), “Reasoning about the referent of a picture versus reasoning about the picture as the referent: An effect of visual realism,” Memory and Cognition, 23, 709–722.
 D. G. Lowe., (2004), “Distinctive image features from scale-invariant keypoints,” IJCV, 60, 91-110.
 H. Bay, T. Tuytelaars, and L. Van Gool, (2006), “Surf: Speeded up robust features,” In European Conference on Computer Vision.
 I. Kim, J. H. Shim, and J. Yang, (2003), “Face detection,” Stanford University, Tech. Rep. , eE368 Final Project Report.
 I. T. Jolliffe, (1986), “Principal Component Analysis,” Springer-Verlag, New York.
 J. Elson, J. R. Douceur, J. Howell and J. Saul, (2007), “Asirra: a CAPTCHA that exploits interest-aligned manual image categorization,” Proceedings of the 14th ACM conference on Computer and communications security, Alexandria, Virginia, USA .
 L. von Ahn, M. Blum, N. J. Hopper and J. Langford, (2003), “CAPTCHA: using hard AI problems for security,” In Lecture notes in computer science, Berlin: Springer, 294–311.
 L.I. Smith, (2002), “A tutorial on Principal Components Analysis,” Cornell University, USA.
 N. Dalal, B. Triggs, (2005), “Histograms of Oriented Gradients for Human Detection,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2, 886-893.
 P. Domingos, (2012), “A few useful things to know about machine learning,” Commun. ACM. 55, 78–87.
 S.-Y. Huang, Y.-K. Lee, G. Bell, Z.-H. Ou, (2010), “An efficient segmentation algorithm for CAPTCHAs with line cluttering and character warping,” Multimedia Tools and Applications, 48, 267-289.
 S. Süsstrunk, R. Buckley and S. Swen, (1999), “Standard RGB color spaces,” Proc. IS T/SID 7th Color Imaging Conf., 127-134.
 T. Burghardt and J. Calic. , (2006), “Analysing animal behaviour in wildlife videos using face detection and tracking,” IEEE Proceedings - Vision, Image, and Signal Processing, 153, 305-312.
描述 碩士
國立政治大學
統計學系
103354018
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0103354018
資料類型 thesis
dc.contributor.advisor 薛慧敏zh_TW
dc.contributor.author (Authors) 鍾立強zh_TW
dc.contributor.author (Authors) Chung, Li Chiangen_US
dc.creator (作者) 鍾立強zh_TW
dc.creator (作者) Chung, Li Chiangen_US
dc.date (日期) 2016en_US
dc.date.accessioned 2-Aug-2016 15:53:42 (UTC+8)-
dc.date.available 2-Aug-2016 15:53:42 (UTC+8)-
dc.date.issued (上傳時間) 2-Aug-2016 15:53:42 (UTC+8)-
dc.identifier (Other Identifiers) G0103354018en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/99532-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 統計學系zh_TW
dc.description (描述) 103354018zh_TW
dc.description.abstract (摘要) 近年來，很多要求高安全性的網站都使用扭曲變形的英文或數字字串作為辨識碼，以避免網站或系統受到大量暴力的攻擊。微軟公司則於2007年提出以貓狗影像的新辨識碼系統—Asirra。對於電腦而言，貓狗影像辨識較字串更為困難。本研究主要針對Asirra的影像資料試圖建構出貓狗影像自動辨識法，藉此來了解此辨識碼系統的有效性。已知影像包含大量雜訊，若使用原始資料則計算困難而且辨識效果差，所以萃取關鍵特徵為重要的研究課題。本文考慮方向梯度直方圖法 (Histograms of Oriented Gradients, HOG) 以及主成分分析 (Principal Components Analysis, PCA) 來篩選重要變數。我們將運用挑選出的特徵建立支持向量機 (Support Vector Machine, SVM) 分類器。在實證分析中，我們發現結合此兩種特徵萃取法，除了能夠大幅降低運算時間，也能得到良好的預測正確率。zh_TW
dc.description.abstract (摘要) In recent years, many websites, which requires a high standard of security, use CAPTCHA to avoid mass and brutal attacks from hackers. The CAPTCHA considers the use of strings of twisted and deformed English letters or numbers as an identification code. In 2007, the company Microsoft proposed a new image-based recognition system-Assira, which uses dogs and cats images as an identification code. Dogs and cats image recognition is not more difficult than strings of letters or numbers recognition for human, but is more challenging for computers. In this paper, we aim to develop a classification method for images from Asirra. An image is represented by an enormous number of pixels. Only few pixels carry important feature information, most pixels are noise. The abundance of noise leads to computational inefficiency, and even worse, may results in inaccurate recognition. Therefore, in this problem feature extraction is an essential step before a classifier construction. We consider HOG (Histograms of Oriented Gradients) and PCA (Principal Components Analysis) to select important features, and use the features to construct a SVM (Support Vector Machine) classifier. In the real example, we find that combining the two feature detection methods can dramatically reduce computational time and have satisfactory predictive accuracy.en_US
dc.description.tableofcontents 第一章 緒論 1
第二章 貓狗特徵萃取與辨識 4
一、數位影像 4
二、方向梯度直方圖 6
1. 影像灰階化 6
2. 統一圖像大小 7
3. 計算梯度 8
4. 繪製方向梯度直方圖 11
5. 區塊正規化及HOG特徵值 13
三、主成分分析 16
四、支持向量機分類器 19
第三章 實證分析 20
一、 貓狗特徵萃取的辨識結果 22
二、 針對貓狗正臉特徵萃取的辨識結果 30
第四章 結論與建議 38


參考文獻 39		zh_TW
dc.format.extent 2198263 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0103354018en_US
dc.subject (關鍵詞) Asirrazh_TW
dc.subject (關鍵詞) 機器學習zh_TW
dc.subject (關鍵詞) 影像辨識zh_TW
dc.subject (關鍵詞) 方向梯度直方圖zh_TW
dc.subject (關鍵詞) 主成分分析zh_TW
dc.title (題名) 貓狗影像辨識之特徵萃取zh_TW
dc.title (題名) Feature extraction in dogs and cats image recognitionen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻)  A. Rencher, (1995), “Methods of multivariate analysis,” New York : John Wiley.
 C.-C. Chang and C.-J. Lin, (2001), “LIBSVM: a library for support vector machines,” Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
 C. Cortes and V. Vapnik, (1995), “Support vector networks,” Machine Learning, 20, 273–297.
 D. L. Schwartz, (1995), “Reasoning about the referent of a picture versus reasoning about the picture as the referent: An effect of visual realism,” Memory and Cognition, 23, 709–722.
 D. G. Lowe., (2004), “Distinctive image features from scale-invariant keypoints,” IJCV, 60, 91-110.
 H. Bay, T. Tuytelaars, and L. Van Gool, (2006), “Surf: Speeded up robust features,” In European Conference on Computer Vision.
 I. Kim, J. H. Shim, and J. Yang, (2003), “Face detection,” Stanford University, Tech. Rep. , eE368 Final Project Report.
 I. T. Jolliffe, (1986), “Principal Component Analysis,” Springer-Verlag, New York.
 J. Elson, J. R. Douceur, J. Howell and J. Saul, (2007), “Asirra: a CAPTCHA that exploits interest-aligned manual image categorization,” Proceedings of the 14th ACM conference on Computer and communications security, Alexandria, Virginia, USA .
 L. von Ahn, M. Blum, N. J. Hopper and J. Langford, (2003), “CAPTCHA: using hard AI problems for security,” In Lecture notes in computer science, Berlin: Springer, 294–311.
 L.I. Smith, (2002), “A tutorial on Principal Components Analysis,” Cornell University, USA.
 N. Dalal, B. Triggs, (2005), “Histograms of Oriented Gradients for Human Detection,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2, 886-893.
 P. Domingos, (2012), “A few useful things to know about machine learning,” Commun. ACM. 55, 78–87.
 S.-Y. Huang, Y.-K. Lee, G. Bell, Z.-H. Ou, (2010), “An efficient segmentation algorithm for CAPTCHAs with line cluttering and character warping,” Multimedia Tools and Applications, 48, 267-289.
 S. Süsstrunk, R. Buckley and S. Swen, (1999), “Standard RGB color spaces,” Proc. IS T/SID 7th Color Imaging Conf., 127-134.
 T. Burghardt and J. Calic. , (2006), “Analysing animal behaviour in wildlife videos using face detection and tracking,” IEEE Proceedings - Vision, Image, and Signal Processing, 153, 305-312.		zh_TW