(3.92.96.236) 您好!臺灣時間:2021/05/07 15:53
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:彭宇喧
研究生(外文):Yu-Syuan Peng
論文名稱:基於pix2pix深度學習模型之條件式虹膜影像生成架構
論文名稱(外文):A Deep Learning Framework for Conditional Iris Image Generation Based on Pix2Pix Model
指導教授:栗永徽
指導教授(外文):Yung-Hui Li
學位類別:碩士
校院名稱:國立中央大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:71
中文關鍵詞:深度學習生成對抗式網路虹膜辨識
外文關鍵詞:Deep LearningGenerative Adversarial NetworkIris Recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:44
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在市場上主流的生物辨識技術有指紋辨識、人臉辨識、虹膜辨識,而在安全性需求高的門禁系統,虹膜辨識往往佔有舉足輕重的角色。近年來興起的深度學習技術也漸漸應用到虹膜辨識技術上。眾所皆知,應用深度學習技術需要大量且有良好人工標籤的資料集,越大量的資料越能提升演算法效能。
現今社會大眾重視隱私權及法律的限制下,收集個人虹膜影像資料變得非常困難,更遑論能收集到有人工標籤且品質良好的虹膜影像資料,於是我們提出了一個基於pix2pix的深度學習網路架構,並人工標記了兩個虹膜資料集,CASIA-Iris-Thousoud與ICE,使每張虹膜影像資料有對應的虹膜遮罩與眼周遮罩,只要提供相對應的虹膜遮罩與眼周遮罩,透過生成對抗式模型生成擬真的虹膜影像資料,以增加虹膜影像資料庫。並提出方法產生合理的虹膜遮罩與眼周遮罩,為後續研究基於深度學習的虹膜分割演算法,提供大量的人造資料集,以提升演算法的準確度。
The mainstream biometrics technology in the market include fingerprint recognition, face recognition, and iris recognition. Iris recognition often plays a pivotal role on access control system with high security requirements. The deep learning techonology that rise in recent years has gradually been applied to iris recognition technology. As we all know, applying deep learning techniques requires a large amount of data sets with high quality manual labels. The larger the amount of data, the better the algorithm performs.
Nowadays, the general public pays more attention to privacy and legal restrictions, so it is very difficult to collect personal iris image data. Not to mention the high quality iris image data with decent manual labels. In this work, we proposed a deep learning network architecture based on pix2pix. We have manually produce iris masks for two iris datasets: CASIA-Iris-Thousoud dataset and ICE dataset. Based on the original iris image in Cartesian domain, we create contour information and binary mask for each iris image. The ultimate goal for this study is a conditional iris image and mask generator, which takes inputs of iris and eye mask are provided, and outputs a photo-realistic iris image by applying the proposal conditional Pix2Pix generative models. We also proposed a method to produce a reasonable iris mask and periocular mask for follow-up research based on deep learning iris segmentation algorithm, which enables researchers to generate unlimited number of artificial iris data sets. Such large-scale iris dataset is very hard to be collected in practical situations. The work described in this thesis will enable researchers to have enough training data to train iris segmenter and mask producer based on deep learning technique.
中文摘要 ii
英文摘要 iii
致謝 v
目錄 vi
圖目錄 viii
表目錄 x
1、 緒論 1
1-1 研究背景與動機 1
1-2 研究目的 3
1-3 論文架構 5
2、 文獻探討 6
2-1 生成對抗式網路介紹 6
2-1-1 GAN 6
2-1-2 cGAN 8
2-1-3 Pix2Pix 10
2-2 語意分割技術介紹 12
2-2-1 FCN 12
2-2-2 Unet 14
3、 方法介紹 16
3-1 方法架構 16
3-2 網路架構 17
3-2-1 生成器網路 17
3-2-2 判別器網路 18
3-3 損失函數 19
3-4 遮罩生成與參數定義 21
3-5 參數範圍的選擇 23
3-6 評估指標 33
3-6-1 Pixel Accuracy (PA) 33
3-6-2 Mean Pixel Accuracy (MPA) 33
3-6-3 Mean Intersection over Union (MIoU) 34
3-6-4 Frequency Weighted Intersection over Union (FWIoU) 34
4、 虹膜影像介紹及實驗結果 35
4-1 虹膜影像介紹 35
4-1-1 CASIA-Iris-Thousand虹膜資料庫 35
4-1-2 ICE虹膜資料庫 38
4-2 生成對抗式網路訓練 40
4-2-1 資料增量與前處理 40
4-2-2 訓練細節與生成階段 40
4-3 生成對抗式網路實驗結果 41
4-3-1 使用ICE資料庫中的遮罩生成虹膜影像 42
4-3-2 使用遮罩生成方法的遮罩生成虹膜影像 44
4-4 語意分割網路架構及訓練 46
4-5 語意分割網路實驗結果 49
4-6 評估指標結果 50
5、 結論與未來展望 53
5-1 結論 53
5-2 未來展望 53
6、 參考文獻 55
[1]. LeCun, Y., Haffner, P., Bottou, L., & Bengio, Y.“Object recognition with gradient-based learning,” In D. A. Forsyth, J. L. Mundy, V. di Gesu, & R. Cipolla (Eds.), Shape, Contour and Grouping in Computer Vision, pp. 319-345.
[2]. Krizhevsky, A., Sutskever, I. & Hinton, G. E. “ImageNet Classification with Deep Convolutional Neural Networks,” In F. Pereira, C. J. C. Burges, L. Bottou & K. Q. Weinberger (ed.), Advances in Neural Information Processing Systems 25, 2012, pp. 1097-1105
[3]. Szegedy, C., Wei Liu, Yangqing Jia, Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. & Rabinovich, A. “Going deeper with convolutions,” In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-9, June.
[4]. He, K., Zhang, X., Ren, S., & Sun, J. “Deep Residual Learning for Image Recognition,” In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778.
[5]. Huang, G., Liu, Z., van der Maaten, L. & Weinberger, K. Q. “Densely Connected Convolutional Networks,” (CVPR),pp. 2261-2269, In 2017 IEEE Computer Society. ISBN: 978-1-5386-0457-1
[6]. Redmon, J., Divvala, S.K., Girshick, R.B., & Farhadi, A. “You Only Look Once: Unified, Real-Time Object Detection,” In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788.
[7]. Liu, Wei & Anguelov, Dragomir & Erhan, Dumitru & Szegedy, Christian & Reed, Scott & Fu, Cheng-Yang & Berg, Alexander. “SSD: Single Shot MultiBox Detector,” 9905. 21-37. 10.1007/978-3-319-46448-0_2.
[8]. S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in 2017 IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 1 June 2017, doi: 10.1109/TPAMI.2016.2577031.
[9]. MegaFace Dataset http://megaface.cs.washington.edu.
[10]. Large-scale CelebFaces Attributes (CelebA) Dataset http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html.
[11]. CASIA-IrisV4 Dataset http://www.cbsr.ia.ac.cn/china/Iris%20Databases%20CH.asp.
[12]. J. Daugman, “How Iris Recognition Works,” In IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, no. 1, pp. 21-30, JAN 2004.
[13]. J. Daugman, “High Confidence Visual Recognition of Persons by A Test of Statistical Independence,”In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1148-1161, NOV 1993.
[14]. R. Wildes, “Iris Recognition: An Emerging Biometric Technology,” Proceedings of the IEEE, vol. 85, no. 9, pp. 1348-1363, SEP 1997.
[15]. R. Tang and S. Weng, “Improving Iris Segmentation Performance via Borders Recognition,” 2011 4th International Conference on Intelligent Computation Technology and Automation, pp. 580-583, MAR 2011.
[16]. H. Li, Z. Sun, and T. Tan, “Robust Iris Segmentation based on Learned Boundary Detectors,” 2012 5th IAPR International Conference on Biometrics, pp. 317-322, APR 2012
[17]. J. Friedman, T. Hastie, and R. Tibshirani, “Additive Logistic Regression: A Statistical View of Boosting,” The Annals of Statistics, vol. 28, no. 2, pp. 337-407, APR 2000.
[18]. Y. Li and M. Savvides, “An Automatic Iris Occlusion Estimation Method Based on High-Dimensional Density Estimation,” In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 4, pp. 784-796, April 2013, doi: 10.1109/TPAMI.2012.169.
[19]. Wang, Caiyong & Zhu, Yuhao & Liu, Yunfan & He, Ran & Sun, Zhenjun. “Joint Iris Segmentation and Localization Using Deep Multi-task Learning Framework,” In arXiv:1901.11195 [cs.CV]
[20]. Li, Yunghui & Po-Jen, Huang. “An Accurate and Efficient User Authentication Mechanism on Smart Glasses Based on Iris Recognition,” In Mobile Information Systems. 2017, pp. 1-14.
[21]. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David WardeFarley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. “Generative adversarial nets,” In Advances in Neural Information Processing Systems 27, pages 2672–2680. Curran Associates, Inc., 2014.
[22]. Mirza, Mehdi and Osindero, Simon. “Conditional generative adversarial nets,” In CoRR, abs/1411.1784, 2014.
[23]. Isola, P., Zhu, J., Zhou, T., & Efros, A.A. “Image-to-Image Translation with Conditional Adversarial Networks” In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5967-5976.
[24]. J. Long, E. Shelhamer and T. Darrell, “Fully convolutional networks for semantic segmentation,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 2015, pp. 3431-3440, doi: 10.1109/CVPR.2015.7298965. (FCN)
[25]. Ronneberger, O., Fischer, P., & Brox, T. “U-Net: Convolutional Networks for Biomedical Image Segmentation” In arXiv:1505.04597 [cs.CV].
[26]. Hinton, G.E., & Salakhutdinov, R. “Reducing the dimensionality of data with neural networks,” In Science, 313 5786, 504-7.
[27]. Radford, A., Metz, L., & Chintala, S. “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” In ICLR 2016 : International Conference on Learning Representations 2016.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔