Publications-Theses
Article View/Open
Publication Export
Google ScholarTM
NCCU Library
Citation Infomation
Related Publications in TAIR
| Title | 微弱光源下之人臉辨識 |
| Creator | 李黛雲 Tai-Yun Li |
| Contributor | 廖文宏 Wen-Hung Liao 李黛雲 Tai-Yun Li |
| Key Words | face recognition illuminaiton feature based low illumination |
| Date | 2002 |
| Date Issued | 18-Sep-2009 18:25:57 (UTC+8) |
| Summary | 本論文的主要目的是建立一套人臉辨識系統，即使在光源不足或甚至是完全黑暗的環境下也能夠正確地進行身分辨識。在完全黑暗的情形下，我們可以利用具有夜視功能(近紅外線)的攝影機來擷取影像，然而，近紅外線影像通常呈現亮度非常不均勻的情形，導致我們無法直接利用現有的人臉辨識系統來作辨識。因此，我們首先觀察近紅外線影像的特性，然後依據此特性提出一個影像成像的模型；接著，利用同構增晰的原理來減低因成像過程所造成的不均勻現象；經由實驗的結果，我們得知現有的全域式人臉辨識系統無法有效地處理近紅外線影像，因此，我們提出了一個新的區域式的人臉辨識演算法，針對光線不足的情況作特殊考量，以得到較佳的辨識結果。本論文實作的系統是以最近點分類法來作身份辨識，在現有的32個人臉影像資料集中，正確的辨識率達75%。 The main objective of this thesis is to develop a face recognition system that could recognize human faces even when the surrounding environment is totally dark. The images of objects in total darkness can be captured using a relatively low-cost camcorder with the NightShot® function. By overcoming the illumination factor, a face recognition system would continue to function independent of the surrounding lighting condition. However, images acquired exhibit non-uniformity due to irregular illumination and current face recognition systems may not be put in use directly. In this thesis, we first investigate the characteristics of NIR images and propose an image formation model. A homomorphic processing technique built upon the image model is then developed to reduce the artifact of the captured images. After that, we conduct experiments to show that existing holistic face recognition systems perform poorly with NIR images. Finally, a more robust feature-based method is proposed to achieve better recognition rate under low illumination. A nearest neighbor classifier using Euclidean distance function is employed to recognize familiar faces from a database. The feature-based recognition method we developed achieves a recognition rate of 75% on a database of 32 people, with one sample image for each subject. TABLE OF CONTENTS CHAPTER 1 Introduction 7 CHAPTER 2 Related Work 6 CHAPTER 3 Homomorphic Preprocessing 11 3. 1 Characteristics of NIR images 12 3.1.1 NIR Image Formation 12 3.1.2 NIR Image Characteristics 12 3.1.3 Gaussian Illumination Model 13 3.2 Homomorphic Filtering Techniques 15 3.2.1 Separating the Illumination Component 15 3.2.2 Homomorphic Filtering 17 3.2.3 NIR Image Correction Results 18 3.2.4 Color Image Correction Results (RGB, HSV Comparison) 22 CHAPTER 4 NIR Image Classification 25 CHAPTER 5 Holistic Face Recognition Algorithms and Evaluation Results 33 5.1 Holistic Methods 34 5.2 Feature-Based Methods 35 5.3 Evaluating Holistic Face Recognition Algorithms 35 CHAPTER 6 Facial Feature Detection Algorithm 42 6.1 Feature-Based Facial Feature Detection Algorithm 42 6.2 Facial Feature Detection Results 54 CHAPTER 7 Proposed Face Recognition Algorithm 56 7.1 Geometric Measures 56 7.2 The Feature Set of Geometric Measures 57 7.3 Recognition 61 7.4 Experimental Results and Discussion 63 CHAPTER 8 Conclusions 68 References 70 |
| 參考文獻 | 【1】 W. Zhao, R. Chellappa, A. Rosenfeld, and P. J. Phillips. 2000. Face recognition: A literature survey. Technical Report CAR-TR-948. 【2】 M.-H. Yang, D. Kriegman, and N. Ahuja. 2002. Detecting faces in images: A survey. IEEE Trans. on Pattern Analysis and Machine Intelligence 24:1 34-58. 【3】 C. H. Jones, S. G. Burnay, and T. L. Williams. Applications of Thermal Imaging, Adam Hilger, 1988. 【4】 M. Bichsel. 1998. Analyzing a scene’s picture set under varying lighting. Computer Vision and Image Understanding 71:3 271-280. 【5】 R. C. Gonzalez and R. E. Woods. Digital Image Processing, Prentice Hall, 2002. 【6】 KAYA http://www.kaya-optics.com/products/applications.shtml 【7】 Y. Moses, Y. Adini, and S. Ullman. 1994. Face recognition: The problem of compensating for changes in illumination direction. European of Conference on Computer Vision 286-296. 【8】 P.N. Belhumeur, J.P. Hespanha and D.J. Kriegman. 1997. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Trans. on Pattern Analysis and Machine Intelligence 19:7 711-720. 【9】 Y. Adini, Y. Moses and S. Ullman. 1997. Face recognition: The problem of compensating for changes in illumination direction. IEEE Trans. on Pattern Analysis and Machine Intelligence 19:7 721-732. 【10】 D.W. Jacobs, P.N. Belhumeur, and R. Basri. 1998. Comparing images under variable illumination. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 610-617. 【11】 P. Hallman. 1994. A low-dimensional representation of human faces for arbitrary lighting conditions. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 995-999. 【12】 W. Zhao. 1999. Robust image based 3D face recognition. PhD Thesis, University of Maryland. 【13】 A. Georghiades P. N. Belhumeur and D. Kriegman. 2001. From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. on Pattern Analysis and Machine Intelligence 23:6 643-660. 【14】 W. Zhao and R. Chellappa. 2000. Illumination-insensitive face recognition using symmetric shape-from-shading. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 1286-1293. 【15】 F. J. Prokoski and R. B. Riedel, Infrared identification of faces and body parts, in A. Jain, R. Bolle, and S. Pankanti. (editors), Biometrics - Personal Identification in Networked Society, Kluwer Academic, 1999. 【16】 J. Wilder, P. J. Phillips, C. Jiang, S. Wiener. 1996. Comparison of visible and infra-red imagery for face recognition. Proc. of International Conference on Automatic Face and Gesture Recognition 182-187. 【17】 B. H. Brinkman, A. Manduca, and R. A. Robb. 1998. Optimized homomorphic un-sharp masking for MR grayscale inhomogeneity correction. IEEE Trans. on Medical Imaging 17:2 161-171. 【18】 R. Chellappa, C. Wilson, and S. Sirohey. 1995. Human and machine recognition of faces: A survey. Proc. of the IEEE 83:5 705-740. 【19】 M. A. Turk and A. P. Pentland. 1991. Face recognition using eigenfaces. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 586-591. 【20】 M. D. Levine. Vision in Man and Machine, McGraw-Hill, 1985. 【21】 Mario Livio. The Golden Ratio: The story of phi, the World’s Most Astonishing Number, Broadway Books, 2002. 【22】 G. Rhodes. 1988. Looking at faces: First-order and second-order features as determinants of facial appearance. Perception 17:43-63. 【23】 K.H. Wong, H.M. Law, and P.W.M. Tsang. 1989. A system for recognizing human faces. Proc. of IEEE Conference on Acoustic, Speech, Signal Processing 1638-1642. 【24】 I. Craw, H. Ellis, and J.R. Lishman. 1987. Automatic extraction of face-features. Pattern Recognition Letters 5:183-187. 【25】 T. Sakai, M. Nagao, and T. Kanade. 1972. Computer analysis and classification of photographics of human faces. Proc. of 1st USA–Japan Computer Conference 55-62. 【26】 H. Mannaert and A. Oosterlinck. 1990. Self-organizing system for analysis and identification of human faces. Procs. of Applications of Digital Processing 1349 227-232. 【27】 R. Rao and D. Ballard. 1995. Natural basis functions and topographics memory for face recognition. International Joint Conference on Artificial Intelligence 10-17. 【28】 Y. Tian, T. Kanade and J. Cohn. 2001. Recognizing action units for facial expression analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 23:2 97-115. 【29】 P. Penev, J. Atick. 1996. Local feature analysis: A general statistical theory for object representation. Neural Systems 7:3 477-500. 【30】 Y. Tian, T. Kanade, and J. Cohn. 2000. Dual-state parametric eye tracking. Proc. of IEEE Conference on Automatic Face and Gesture Recognition 110-115. 【31】 I. Craw, D. Tock, and A. Bennett. 1992. Finding face features. Proc. of the First European Conference on Computer Vision 92-96. |
| Description | 碩士 國立政治大學 資訊科學學系 90753001 91 |
| 資料來源 | http://thesis.lib.nccu.edu.tw/record/#G0090753001 |
| Type | thesis |
| dc.contributor.advisor | 廖文宏 | zh_TW |
| dc.contributor.advisor | Wen-Hung Liao | en_US |
| dc.contributor.author (Authors) | 李黛雲 | zh_TW |
| dc.contributor.author (Authors) | Tai-Yun Li | en_US |
| dc.creator (作者) | 李黛雲 | zh_TW |
| dc.creator (作者) | Tai-Yun Li | en_US |
| dc.date (日期) | 2002 | en_US |
| dc.date.accessioned | 18-Sep-2009 18:25:57 (UTC+8) | - |
| dc.date.available | 18-Sep-2009 18:25:57 (UTC+8) | - |
| dc.date.issued (上傳時間) | 18-Sep-2009 18:25:57 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0090753001 | en_US |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/36374 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 資訊科學學系 | zh_TW |
| dc.description (描述) | 90753001 | zh_TW |
| dc.description (描述) | 91 | zh_TW |
| dc.description.abstract (摘要) | 本論文的主要目的是建立一套人臉辨識系統，即使在光源不足或甚至是完全黑暗的環境下也能夠正確地進行身分辨識。在完全黑暗的情形下，我們可以利用具有夜視功能(近紅外線)的攝影機來擷取影像，然而，近紅外線影像通常呈現亮度非常不均勻的情形，導致我們無法直接利用現有的人臉辨識系統來作辨識。因此，我們首先觀察近紅外線影像的特性，然後依據此特性提出一個影像成像的模型；接著，利用同構增晰的原理來減低因成像過程所造成的不均勻現象；經由實驗的結果，我們得知現有的全域式人臉辨識系統無法有效地處理近紅外線影像，因此，我們提出了一個新的區域式的人臉辨識演算法，針對光線不足的情況作特殊考量，以得到較佳的辨識結果。本論文實作的系統是以最近點分類法來作身份辨識，在現有的32個人臉影像資料集中，正確的辨識率達75%。 | zh_TW |
| dc.description.abstract (摘要) | The main objective of this thesis is to develop a face recognition system that could recognize human faces even when the surrounding environment is totally dark. The images of objects in total darkness can be captured using a relatively low-cost camcorder with the NightShot® function. By overcoming the illumination factor, a face recognition system would continue to function independent of the surrounding lighting condition. However, images acquired exhibit non-uniformity due to irregular illumination and current face recognition systems may not be put in use directly. In this thesis, we first investigate the characteristics of NIR images and propose an image formation model. A homomorphic processing technique built upon the image model is then developed to reduce the artifact of the captured images. After that, we conduct experiments to show that existing holistic face recognition systems perform poorly with NIR images. Finally, a more robust feature-based method is proposed to achieve better recognition rate under low illumination. A nearest neighbor classifier using Euclidean distance function is employed to recognize familiar faces from a database. The feature-based recognition method we developed achieves a recognition rate of 75% on a database of 32 people, with one sample image for each subject. | en_US |
| dc.description.abstract (摘要) | TABLE OF CONTENTS CHAPTER 1 Introduction 7 CHAPTER 2 Related Work 6 CHAPTER 3 Homomorphic Preprocessing 11 3. 1 Characteristics of NIR images 12 3.1.1 NIR Image Formation 12 3.1.2 NIR Image Characteristics 12 3.1.3 Gaussian Illumination Model 13 3.2 Homomorphic Filtering Techniques 15 3.2.1 Separating the Illumination Component 15 3.2.2 Homomorphic Filtering 17 3.2.3 NIR Image Correction Results 18 3.2.4 Color Image Correction Results (RGB, HSV Comparison) 22 CHAPTER 4 NIR Image Classification 25 CHAPTER 5 Holistic Face Recognition Algorithms and Evaluation Results 33 5.1 Holistic Methods 34 5.2 Feature-Based Methods 35 5.3 Evaluating Holistic Face Recognition Algorithms 35 CHAPTER 6 Facial Feature Detection Algorithm 42 6.1 Feature-Based Facial Feature Detection Algorithm 42 6.2 Facial Feature Detection Results 54 CHAPTER 7 Proposed Face Recognition Algorithm 56 7.1 Geometric Measures 56 7.2 The Feature Set of Geometric Measures 57 7.3 Recognition 61 7.4 Experimental Results and Discussion 63 CHAPTER 8 Conclusions 68 References 70 | - |
| dc.description.tableofcontents | TABLE OF CONTENTS CHAPTER 1 Introduction 7 CHAPTER 2 Related Work 6 CHAPTER 3 Homomorphic Preprocessing 11 3. 1 Characteristics of NIR images 12 3.1.1 NIR Image Formation 12 3.1.2 NIR Image Characteristics 12 3.1.3 Gaussian Illumination Model 13 3.2 Homomorphic Filtering Techniques 15 3.2.1 Separating the Illumination Component 15 3.2.2 Homomorphic Filtering 17 3.2.3 NIR Image Correction Results 18 3.2.4 Color Image Correction Results (RGB, HSV Comparison) 22 CHAPTER 4 NIR Image Classification 25 CHAPTER 5 Holistic Face Recognition Algorithms and Evaluation Results 33 5.1 Holistic Methods 34 5.2 Feature-Based Methods 35 5.3 Evaluating Holistic Face Recognition Algorithms 35 CHAPTER 6 Facial Feature Detection Algorithm 42 6.1 Feature-Based Facial Feature Detection Algorithm 42 6.2 Facial Feature Detection Results 54 CHAPTER 7 Proposed Face Recognition Algorithm 56 7.1 Geometric Measures 56 7.2 The Feature Set of Geometric Measures 57 7.3 Recognition 61 7.4 Experimental Results and Discussion 63 CHAPTER 8 Conclusions 68 References 70 | zh_TW |
| dc.language.iso | en_US | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0090753001 | en_US |
| dc.subject (關鍵詞) | face recognition | en_US |
| dc.subject (關鍵詞) | illuminaiton | en_US |
| dc.subject (關鍵詞) | feature based | en_US |
| dc.subject (關鍵詞) | low illumination | en_US |
| dc.title (題名) | 微弱光源下之人臉辨識 | zh_TW |
| dc.type (資料類型) | thesis | en |
| dc.relation.reference (參考文獻) | 【1】 W. Zhao, R. Chellappa, A. Rosenfeld, and P. J. Phillips. 2000. Face recognition: A literature survey. Technical Report CAR-TR-948. | zh_TW |
| dc.relation.reference (參考文獻) | 【2】 M.-H. Yang, D. Kriegman, and N. Ahuja. 2002. Detecting faces in images: A survey. IEEE Trans. on Pattern Analysis and Machine Intelligence 24:1 34-58. | zh_TW |
| dc.relation.reference (參考文獻) | 【3】 C. H. Jones, S. G. Burnay, and T. L. Williams. Applications of Thermal Imaging, Adam Hilger, 1988. | zh_TW |
| dc.relation.reference (參考文獻) | 【4】 M. Bichsel. 1998. Analyzing a scene’s picture set under varying lighting. Computer Vision and Image Understanding 71:3 271-280. | zh_TW |
| dc.relation.reference (參考文獻) | 【5】 R. C. Gonzalez and R. E. Woods. Digital Image Processing, Prentice Hall, 2002. | zh_TW |
| dc.relation.reference (參考文獻) | 【6】 KAYA http://www.kaya-optics.com/products/applications.shtml | zh_TW |
| dc.relation.reference (參考文獻) | 【7】 Y. Moses, Y. Adini, and S. Ullman. 1994. Face recognition: The problem of compensating for changes in illumination direction. European of Conference on Computer Vision 286-296. | zh_TW |
| dc.relation.reference (參考文獻) | 【8】 P.N. Belhumeur, J.P. Hespanha and D.J. Kriegman. 1997. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Trans. on Pattern Analysis and Machine Intelligence 19:7 711-720. | zh_TW |
| dc.relation.reference (參考文獻) | 【9】 Y. Adini, Y. Moses and S. Ullman. 1997. Face recognition: The problem of compensating for changes in illumination direction. IEEE Trans. on Pattern Analysis and Machine Intelligence 19:7 721-732. | zh_TW |
| dc.relation.reference (參考文獻) | 【10】 D.W. Jacobs, P.N. Belhumeur, and R. Basri. 1998. Comparing images under variable illumination. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 610-617. | zh_TW |
| dc.relation.reference (參考文獻) | 【11】 P. Hallman. 1994. A low-dimensional representation of human faces for arbitrary lighting conditions. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 995-999. | zh_TW |
| dc.relation.reference (參考文獻) | 【12】 W. Zhao. 1999. Robust image based 3D face recognition. PhD Thesis, University of Maryland. | zh_TW |
| dc.relation.reference (參考文獻) | 【13】 A. Georghiades P. N. Belhumeur and D. Kriegman. 2001. From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. on Pattern Analysis and Machine Intelligence 23:6 643-660. | zh_TW |
| dc.relation.reference (參考文獻) | 【14】 W. Zhao and R. Chellappa. 2000. Illumination-insensitive face recognition using symmetric shape-from-shading. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 1286-1293. | zh_TW |
| dc.relation.reference (參考文獻) | 【15】 F. J. Prokoski and R. B. Riedel, Infrared identification of faces and body parts, in A. Jain, R. Bolle, and S. Pankanti. (editors), Biometrics - Personal Identification in Networked Society, Kluwer Academic, 1999. | zh_TW |
| dc.relation.reference (參考文獻) | 【16】 J. Wilder, P. J. Phillips, C. Jiang, S. Wiener. 1996. Comparison of visible and infra-red imagery for face recognition. Proc. of International Conference on Automatic Face and Gesture Recognition 182-187. | zh_TW |
| dc.relation.reference (參考文獻) | 【17】 B. H. Brinkman, A. Manduca, and R. A. Robb. 1998. Optimized homomorphic un-sharp masking for MR grayscale inhomogeneity correction. IEEE Trans. on Medical Imaging 17:2 161-171. | zh_TW |
| dc.relation.reference (參考文獻) | 【18】 R. Chellappa, C. Wilson, and S. Sirohey. 1995. Human and machine recognition of faces: A survey. Proc. of the IEEE 83:5 705-740. | zh_TW |
| dc.relation.reference (參考文獻) | 【19】 M. A. Turk and A. P. Pentland. 1991. Face recognition using eigenfaces. Proc. of IEEE Conference on Computer Vision and Pattern Recognition 586-591. | zh_TW |
| dc.relation.reference (參考文獻) | 【20】 M. D. Levine. Vision in Man and Machine, McGraw-Hill, 1985. | zh_TW |
| dc.relation.reference (參考文獻) | 【21】 Mario Livio. The Golden Ratio: The story of phi, the World’s Most Astonishing Number, Broadway Books, 2002. | zh_TW |
| dc.relation.reference (參考文獻) | 【22】 G. Rhodes. 1988. Looking at faces: First-order and second-order features as determinants of facial appearance. Perception 17:43-63. | zh_TW |
| dc.relation.reference (參考文獻) | 【23】 K.H. Wong, H.M. Law, and P.W.M. Tsang. 1989. A system for recognizing human faces. Proc. of IEEE Conference on Acoustic, Speech, Signal Processing 1638-1642. | zh_TW |
| dc.relation.reference (參考文獻) | 【24】 I. Craw, H. Ellis, and J.R. Lishman. 1987. Automatic extraction of face-features. Pattern Recognition Letters 5:183-187. | zh_TW |
| dc.relation.reference (參考文獻) | 【25】 T. Sakai, M. Nagao, and T. Kanade. 1972. Computer analysis and classification of photographics of human faces. Proc. of 1st USA–Japan Computer Conference 55-62. | zh_TW |
| dc.relation.reference (參考文獻) | 【26】 H. Mannaert and A. Oosterlinck. 1990. Self-organizing system for analysis and identification of human faces. Procs. of Applications of Digital Processing 1349 227-232. | zh_TW |
| dc.relation.reference (參考文獻) | 【27】 R. Rao and D. Ballard. 1995. Natural basis functions and topographics memory for face recognition. International Joint Conference on Artificial Intelligence 10-17. | zh_TW |
| dc.relation.reference (參考文獻) | 【28】 Y. Tian, T. Kanade and J. Cohn. 2001. Recognizing action units for facial expression analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 23:2 97-115. | zh_TW |
| dc.relation.reference (參考文獻) | 【29】 P. Penev, J. Atick. 1996. Local feature analysis: A general statistical theory for object representation. Neural Systems 7:3 477-500. | zh_TW |
| dc.relation.reference (參考文獻) | 【30】 Y. Tian, T. Kanade, and J. Cohn. 2000. Dual-state parametric eye tracking. Proc. of IEEE Conference on Automatic Face and Gesture Recognition 110-115. | zh_TW |
| dc.relation.reference (參考文獻) | 【31】 I. Craw, D. Tock, and A. Bennett. 1992. Finding face features. Proc. of the First European Conference on Computer Vision 92-96. | zh_TW |