臺灣博碩士論文加值系統

近年來，圖像辨識技術在成果上有許多令人突破性的發展。本論文之目的在於解析最近對於物件偵測技術的性能分類非常良好的 YOLO (You Only Look Once) 。對於解析深度學習已經有許多相關的論文，但對於在視覺化網路架構的相關論文卻較少，本論文是用簡易的流程圖表運作方式，並且將過程呈現，可以讓一般大眾更加認識機器學習的運作方式，同時也讓專家方便於解析其架構，並且能夠迅速改善原本的架構，使其加速。

In recent years, convolutional neural networks have had many groundbreaking developments. This paper's goal is to analyze the recent YOLO (You Only Look Once) that has a very good performance classification for object detection technology. This paper is a simple way to explain the operation of the convolutional neural network. Present the process which can make the general public more aware of the way machine learning works, and also make it convenient for experts to analyze the structure of it. The ability to quickly improve the original architecture and accelerate it.

中文摘要 i
英文摘要 ii
致謝 iii
目錄 iv
圖目錄 v
表目錄 vii
1 導論 1
1.1 導論 1
2 相關文件討論 5
3 方法
3.1 YOLO 程式解析 9
3.2 處理方法 9
3.3 D3.js 繪製 2.5D 圖形與流程架構 10
3.4 系統操作 10
3.5 產生特徵圖 11
3.6 產生權重圖 14
3.7 系統限制 14
4 結果與討論 23
5 結論 26
5.1 結論 26
5.2 未來展望 26
參考文獻 27

[1] Yann Lecun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning
applied to document recognition. In Proceedings of the IEEE, 1998.
[2] Dumitru Erhan, Yoshua Bengio, and Aaron Courville Pascal Vincent Dept. IRO. Visualizing higher-layer features of a deep network. June 2009.
[3] Matthew D. Zeiler and Rob Fergus. Visualizing and understanding convolutional networks.
2013.
[4] Hyeonwoo Noh, Seunghoon Hong, and Bohyung Han. Learning deconvolution network
for semantic segmentation. volume abs/1505.04366, 2015.
[5] Joseph Redmon, Santosh Kumar Divvala, Ross B. Girshick, and Ali Farhadi. You only
look once: Unified, real-time object detection. 2015.
[6] Joseph Redmon and Ali Farhadi. YOLO9000: better, faster, stronger. volume abs/
1612.08242, 2016.
[7] Pushparaja Murugan. Feed forward and backward run in deep convolution neural network.
volume abs/1711.03278, 2017.
[8] Ruslan Salakhutdinov, Andriy Mnih, and Geoffrey Hinton. Restricted boltzmann machines
for collaborative filtering. In Proceedings of the 24th International Conference on Machine
Learning, 2007.
[9] Kunihiko Fukushima. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. 1980.
27
[10] J. Weng, N. Ahuja, and T. S. Huang. Cresceptron: a self-organizing neural network which
grows adaptively. In [Proceedings 1992] IJCNN International Joint Conference on Neural
Networks, 1992.
[11] Jake Bouvrie. Notes on convolutional neural networks. November 2006.
[12] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep
convolutional neural networks. In Advances in Neural Information Processing Systems 25.
Curran Associates, Inc., 2012.
[13] Mahendran, Aravindh, and Andrea Vedaldi. Visualizing deep convolutional neural networks using natural pre-images. volume 120, December 2016.
[14] Ross B. Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. volume abs/1311.2524,
2013.
[15] Ross B. Girshick. Fast R-CNN. volume abs/1504.08083, 2015.
[16] Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. Faster R-CNN: towards
real-time object detection with region proposal networks. volume abs/1506.01497, 2015.
[17] Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott E. Reed, ChengYang Fu, and Alexander C. Berg. SSD: single shot multibox detector. 2015.
[18] ᑵדӹ. Ship detection based on deep learning for sar imagery. 2018.