跳到主要內容

臺灣博碩士論文加值系統

(44.200.194.255) 您好!臺灣時間:2024/07/23 03:40
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

: 
twitterline
研究生:林冠宏
研究生(外文):Kuan-Hung Lin
論文名稱:基於多尺度預測和循環對抗網路的招牌檢測與識別方法之研製
論文名稱(外文):Signboard detection and recognition deep learning modeling based on multiscale prediction and CycleGAN
指導教授:施國琛施國琛引用關係
指導教授(外文):Timothy K Shih
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
論文種類:學術論文
論文出版年:2021
畢業學年度:109
語文別:英文
論文頁數:59
中文關鍵詞:深度學習物件檢測招牌辨識
外文關鍵詞:deep learningobject detectionsignboard recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:139
  • 評分評分:
  • 下載下載:4
  • 收藏至我的研究室書目清單書目收藏:0
物件偵測在電腦視覺任務上是一個很熱門的領域,此技術被使用在許多領域上。為了在提高預測精確度的同時也要保證執行速度在物件檢測上是一個很大的挑戰。有許多專家、學者已致力於這項任務上並提出了許多方法,使得物件檢測的方法日益成熟。
在物件檢測中的大多資料集其背景相當複雜,使得模型沒有檢測到目標物件或者發生誤判的情形,為了要解決檢測遺漏有許多方法被提出,例如特徵金字塔網路、多尺度預測和注意力模組等,但極少有方法用以解決將背景誤判為目標物件上。在本文中我們提出了一個兩階段訓練方式的物件檢測模型,用以使用在臺灣街景招牌資料集上,此方法添加了部份語意分割技巧且無須使用到像素間的標記,解決由於大多招牌形狀極為相似而引發的誤判情況。此外我們將此方法進一步的改良使其成為一階段的物件檢測模型,使它的預測結果更加穩定且易於訓練。
Object detection is a popular computer vision task in deep learning and the technique is widely used in many fields. To improve the precision of the models while ensuring the inference time is a big challenge. Many experts and scholars have invested in this works and proposed lots of methods to solve this problem, making object detection become more and more mature.
The scenes in most object detection datasets are very complicated so that the model cannot detect the objects or it might regard background as an object. To conquer miss detection, lots of methods are proposed like Feature Pyramid Network, multi-scales prediction and attention module. However, there are few methods to prevent the models from misjudging non-objects to objects. In this thesis, we propose a two-phase training method used for Taiwan Street View Signboard Dataset. The model is added with some techniques from segmentation without pixel-to-pixel labeling, solving misjudgments caused by the similar shapes of various signboards. We further improve the method into a one-stage detection model, make the model to be more stable and easier for training.
1 Introduction 1
2 Related work 3
2.1 Features Extraction Methods 3
2.1.1 AlexNet 3
2.1.2 VGGNet 4
2.1.3 Residual Neural Network 5
2.2 Object Detection 6
2.2.1 Two-Stage Detector 7
2.2.2 One-Stage Detector 11
2.3 Segmentation 19
2.3.1 Fully Convolutional Networks 19
2.3.2 U-Net 20
3 Proposed Method 21
3.1 Two-Phase Training Methods 21
3.1.1 Bounding Boxes Proposal 21
3.1.2 CycleGAN 23
3.1.3 Region Category Checking 25
3.2 Proposed One-Stage Detector 32
3.2.1 Multi-Scales Prediction 32
3.2.2 Ground Truth for Segmentation 34
3.2.3 Segmentation Approach 35
4 Experimental Results 40
4.1 Datasets 40
4.2 Training 41
4.3 Testing 42
5 Conclusion 45
6 Reference 46
[1] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1 Nov. 1998
[2] A. Krizhevsky, I. Sutskever, and G. Hinton. “Imagenet classification with deep convolutional neural networks.” In NIPS, 2012.
[3] K. Simonyan and A. Zisserman. “Very deep convolutional networks for large-scale image recognition.” In ICLR, 2015.
[4] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016.
[5] FN Iandola, S Han, MW Moskewicz, K Ashraf, WJ Dally, K Keutzer, "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size," arXiv:1602.07360, 2016
[6] Howard, Andrew G., Zhu, Menglong, Chen, Bo, Kalenichenko, Dmitry, Wang, Weijun, Weyand, Tobias, Andreetto, Marco and Adam, Hartwig, "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," arxiv:1704.04861, 2017
[7] T. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan and S. Belongie, "Feature Pyramid Networks for Object Detection," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936-944, 2017.
[8] Wei Liu Dragomir Anguelov Dumitru Erhan Christian Szegedy Scott Reed, Cheng-Yang Fu, Alexander C. Berg, "SSD: Single Shot MultiBox Detector," Proceedings of the European Conference on Computer Vision (ECCV), 2016.
[9] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016.
[10] J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517-6525, 2017.
[11] J. Redmon and A Farhadi, "Yolov3: An incremental improvement," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[12] Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv:2004.10934, 2020.
[13] R. Girshick, J. Donahue, T. Darrell and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, 2014.
[14] R. Girshick, "Fast R-CNN," 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440-1448, 2015.
[15] S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 2017.
[16] C. Hong, C. Lin and T. K. Shih, "Automatic Signboard Detection and Semi-Automatic Ground Truth Generation," 2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media), pp. 256-261, 2019.
[17] C. Wang, H. Mark Liao, Y. Wu, P. Chen, J. Hsieh and I. Yeh, "CSPNet: A New Backbone that can Enhance Learning Capability of CNN," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1571-1580, 2020.
[18] K. He, X. Zhang, S. Ren and J. Sun, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 9, pp. 1904-1916, 2015.
[19] Woo S., Park J., Lee JY., Kweon I.S, "CBAM: Convolutional Block Attention Module," Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, vol 11211, 2018.
[20] S. Liu, L. Qi, H. Qin, J. Shi and J. Jia, "Path Aggregation Network for Instance Segmentation," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8759-8768, 2018.
[21] J. Long, E. Shelhamer and T. Darrell, "Fully convolutional networks for semantic segmentation," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431-3440, 2015.
[22] Ronneberger O., Fischer P., Brox T, "U-Net: Convolutional Networks for Biomedical Image Segmentation," Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015.
[23] J. Zhu, T. Park, P. Isola and A. A. Efros, "Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks," 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2242-2251, 2017.
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
無相關期刊