研究生: |
葉騰遠 TENG- YUAN YEH |
---|---|
論文名稱: |
機械學習與深度學習於人臉識別之應用 Applications of machine learning and deep learning in face recognition |
指導教授: |
施慶隆
Ching-Long Shih |
口試委員: |
黃志良
Chih-Lyang Hwang 李文猶 Wen-Yo Lee 吳修明 Hsiu-Ming Wu |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2020 |
畢業學年度: | 108 |
語文別: | 中文 |
論文頁數: | 90 |
中文關鍵詞: | 人臉識別 、機器學習 、深度學習 |
外文關鍵詞: | FaceNet, Deep learing |
相關次數: | 點閱:625 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本論文以三種各有具有代表性的人臉辨識系統進行測試比較,第一種方法是使用PCA與KNN的人臉辨識技術;利用PCA提取人臉的出主要特徵,然後再採用KNN進行分類。第二種方法是使用SIFT、K-means與SVM的人臉辨識技術;使用SIFT提取出特徵點,接著利用K-means進行詞袋理論分析,最後再進行SVM分類。第三種方法是使用MTCNN與FaceNet的深度學習人臉辨識技術,首先由MTCNN選取出影像中的人臉,然後再利用FaceNet比較人臉照片之間的歐式距離進行分類。經由實驗結果相互比較第三種方法得到最高的準確率99.44 %和綜合表現F1 99.73%,在執行時間上第二種方法的平均執行時間為最短約0.56秒。
This paper compares three types of representative face recognition systems. The first face recognition method utilizes PCA and KNN machine learning methods; PCA is applied to extract the main features and then KNN is used for classification. The second method utilizes SIFT, K-means and SVM machine learning methods; SIFT is used for image feature extraction, K-means for bag-of-word theory and finally SVM for classification. The third method applies MTCNN and FaceNet deep learning CNN networks; face are selected by MTCNN and classified by FaceNet to compare the Euclidean distance between face photos. After the experimental comparison, the third method obtains the best results with an highest accuracy rate of 99.44% and a comprehensive performance F1 of 99.73%. The second method is fastest in execution time with an average execution time of 0.56 seconds.
參考文獻
[1] Schroff, Florian, Dmitry Kalenichenko, and James Philbin. "Facenet: A unified embedding for face recognition and clustering." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
[2] Zhang, Kaipeng, Zhang Zhanpeng, Li Zhifeng and Qiao Yu. "Joint face detection and alignment using multitask cascaded convolutional networks." IEEE Signal Processing Letters 23.10 (2016): 1499-1503.
[3] Taleb, Imene, and Madani Ould Mammar. "Parking access system based on face recognition." 2015 12th International Symposium on Programming and Systems (ISPS). IEEE, 2015.
[4]Li, Qian, Usman Niaz, and Bernard Merialdo. "An improved algorithm on Viola-Jones object detector." 2012 10th International Workshop on Content-Based Multimedia Indexing (CBMI). IEEE, 2012.
[5] Khan, Zohaib, Faisal Shafait, and Ajmal Mian. "Joint group sparse PCA for compressed hyperspectral imaging." IEEE Transactions on Image Processing 24.12 (2015): 4934-4942.
[6] Turhan, Ceren Guzel, and Hasan Sakir Bilge. "Class-wise two-dimensional PCA method for face recognition." IET Computer Vision 11.4 (2016): 286-300.
[7] https://en.wikipedia.org/wiki/Karhunen%E2%80%93Lo%C3%A8ve_ theorem
[8] Taneja, Shweta, Gupta Charu, Aggarwal Sakshi and Jindal Veni. "MFZ-KNN—A modified fuzzy based K nearest neighbor algorithm." 2015 International Conference on Cognitive Computing and Information Processing (CCIP). IEEE, 2015.
[9] Huang, Jie, Wei Yongqing, Yi Jing and Liu Mengdi . "An improved kNN based on class contribution and feature weighting." 2018 10th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA). IEEE, 2018.
[10] Revina, I. Michael, and WR Sam Emmanuel. "Facial expression recognition via modified GAD features with PSO-KNN." 2018 International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE, 2018.
[11] Abuzneid, Mohannad A., and Ausif Mahmood. "Enhanced human face recognition using LBPH descriptor, multi-KNN, and back-propagation neural network." IEEE Access 6 (2018): 20641-20651.
[12] Lei, Xiujuan, and Chen Bian. "Integrating random walk with restart and k-Nearest Neighbor to identify novel circRNA-disease association." Scientific Reports 10.1 (2020): 1-9.
[13] Kalpana, J., and R. Krishnamoorthi. "Color image retrieval technique with local features based on orthogonal polynomials model and SIFT." Multimedia Tools and Applications 75.1 (2016): 49-69.
[14] Walch Florian, Hazırbaş Caner, Leal-Taixé Laura, Sattler Torsten, Sattler Torsten, Hilsenbeck Sebastian and Cremers Daniel "Image-based localization using lstms for structured feature correlation." Proceedings of the IEEE International Conference on Computer Vision. 2017.
[15] DeTone, Daniel, Tomasz Malisiewicz, and Andrew Rabinovich. "Superpoint: Self-supervised interest point detection and description." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2018.
[16] Tang, Jinjun, et al. "An improved fuzzy neural network for traffic speed prediction considering periodic characteristic." IEEE Transactions on Intelligent Transportation Systems 18.9 (2017): 2340-2350.
[17] Wu, Zhibin, and Jiuping Xu. "A consensus model for large-scale group decision making with hesitant fuzzy information and changeable clusters." Information Fusion 41 (2018): 217-231.
[18] Wan, Shaohua, et al. "Multi-dimensional data indexing and range query processing via Voronoi diagram for internet of things." Future Generation Computer Systems 91 (2019): 382-391.
[19] Erfani, Sarah M., et al. "High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning." Pattern Recognition 58 (2016): 121-134.
[20] Chang, Xiaojun, et al. "Semantic pooling for complex event analysis in untrimmed videos." IEEE transactions on pattern analysis and machine intelligence 39.8 (2016): 1617-1632.
[21] Hassan, Mohammed Mehedi, et al. "A robust human activity recognition system using smartphone sensors and deep learning." Future Generation Computer Systems 81 (2018): 307-313.
[22] Deng, Wu, et al. "A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm." Soft Computing 23.7 (2019): 2445-2462.
[23] Fu, Rong, et al. "University classroom attendance based on deep learning." 2017 10th International Conference on Intelligent Computation Technology and Automation (ICICTA). IEEE, 2017.
[24] Ke, Qiuhong, et al. "Learning clip representations for skeleton-based 3d action recognition." IEEE Transactions on Image Processing 27.6 (2018): 2842-2855.
[25] Ma, Mei, and Jianji Wang. "Multi-view face detection and landmark localization based on MTCNN." 2018 Chinese Automation Congress (CAC). IEEE, 2018.
[26] Lin, Shilun, Zhicheng Zhao, and Fei Su. "Homemade ts-net for automatic face recognition." Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval. 2016.
[27] Zhuge, Chuanhao, et al. "Face recognition with hybrid efficient convolution algorithms on FPGAs." Proceedings of the 2018 on Great Lakes Symposium on VLSI. 2018.
[28] Chinapas, Adulwit, et al. "Personal verification system using ID card and face Photo." Int. J. Mach. Learn. Comput. 9 (2019): 407-412.
[29] Liu, Yuchen, et al. "Strategic way to count the number of people in aroom using multiple kinect cameras." International Ethical Hacking Conference. Springer, Singapore, 2019.