(3.215.180.226) 您好!臺灣時間:2021/03/06 13:42
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:郭宇航
研究生(外文):Yu-Hang Kuo
論文名稱:基於樣本自動化修補與形變之組合式卡通圖像創作系統
論文名稱(外文):Automatic Cartoon Image Creation With Inpainting And Deformation
指導教授:鄭旭詠
指導教授(外文):Hsu-Yung Cheng
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:2018
畢業學年度:106
語文別:中文
論文頁數:69
中文關鍵詞:圖像創作形變影像組合影像修補影像處理
相關次數:
  • 被引用被引用:0
  • 點閱點閱:59
  • 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
人工智慧是電腦科學領域近年廣泛討論的議題之一,透過的對訓練資料擷取特徵學習,使用機器學習自主創作的技術也蓬勃發展,其中發展最佳的領域莫過於圖像生成。
本篇論文著重於自動創作生成卡通圖像,已將同種類的訓練資料透過分割、分群並取得區域部位之間的鄰近相連關係(Region Relationship Graph)為前提,後續將各個區域部位(Region)實作修補、形變、組合等等,創作出全新的圖像,相較於生成對抗網路(Generative Adversarial Network,GAN)使用深度學習的神經網路,本篇採用影像處理的方法實作,較能在運算時間、資料集數量與硬體資源上取得優勢。
本篇論文所提出的系統分為三個階段,考慮到原始輸入圖像之中Region與Region有遮蔽的影響,分割出來的Region會有被遮蔽的凹陷處,系統第一階段是將各個Region做修補的動作。為了創作的多樣性,第二階段是將各Region做形變的動作。最後則是隨機選擇一種模板,將形變後的Region組裝並調整。其中使用者也能調整參數,其系統自帶的隨機參數與使用者的參數會交叉出無數種組合,如此創作出全新的圖像。
在實驗中可見,其創作的訓練資料只要數張,就能有全新的創作,越多的訓練資料能有更多樣性的創作。而結果也能辨別出與訓練資料是同種類的物件。
Artificial intelligence is one of the topics that have been widely discussed in the field of computer science in recent years. Through the acquisition of feature learning from training data and using machine learning to create, the technology has also flourished. Among them, the best field for development is image generation.
This paper focuses on the automatic creation of cartoon images. It has premised that the same kind of training data is divided, grouped, and acquired the region relationship graph. Subsequent implementation of each region. Patching, deformation, assembling, and so on, create new images. Compared to the neural network that uses deep learning in Generative Adversarial Network (GAN), this paper adopts image processing method to implement it. Take advantage of computing time, data sets, and hardware resources.
The system proposed in this paper is divided into three stages. Considering that Region and Region in the original input image have covering effects, the segmented region will have shadowed depressions. The first stage of the system is to inpaint each region. For the diversity of creation, the second stage is deforming the regions. Finally, a template is randomly selected, and the modified Region is assembled and adjusted. The user can also adjust the parameters. The random parameters of the system and the user's parameters will cross the countless combinations, creating a new image.
It can be seen in the experiment that if using a few training data, they can have new creations, and more training materials can create more diversity. The results can also identify objects of the same kind as the training data.
摘要 i
ABSTRACT ii
致謝 iii
目錄 1
圖目錄 3
表目錄 5
第一章 緒論 1
1.1 研究動機 1
1.2 相關文獻 2
1.3 系統流程論文架構 3
第二章 部位區域修補 5
2.1 尋找被遮蔽輪廓 5
2.1.1 分割分群連結資訊 5
2.1.2 遮蔽特徵判斷 7
2.2輪廓修補 9
2.2.1 對稱性修補 9
2.2.2 直線修補 13
第三章 部位區域形變 16
3.1 Moving Least Squares Deformation 16
3.2 MLS Deformation Application 19
3.2.1 曲率 19
3.2.2 控制點選取 21
3.2.3 形變實作 23
3.2.4 Morphology 26
第四章 組合創作 28
4.1 Region填色 28
4.2 Particle Swarm Optimization 30
4.3 組合關係 33
4.4 組合連結 36
4.5 組合角度 41
第五章 實驗結果與討論 42
5.1 實驗環境 42
5.2 實驗資料集 42
5.3 卡通圖像創作結果 47
第六章 結論與未來工作 55
參考文獻 56
[1] L. A. Gatys, A. S. Ecker, and M. Bethge. Image Style Transfer Using Convolutional Neural Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2414–2423, 2016.
[2] H. Fang and M. Zhang. Creatism. A deep-learning photographer capable of creating professional work. ArXiv:1707.03491
[3] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. C. Courville, and Y. Bengio. Generative adversarial nets. In Proceedings of NIPS, pages 2672– 2680, 2014.
[4] Kingma, Durk P. and Welling, Max. Auto-encoding variational bayes. In Proceedings of the International Conference on Learning Representations (ICLR), 2014.
[5] A. v. d. Oord, N. Kalchbrenner, and K. Kavukcuoglu. Pixel recurrent neural networks. In International Conference on Machine Learning (ICML), 2016.
[6] R. Nock and F. Nielsen. Statistical region merging. IEEE Trans. Pattern Anal. Machine Intell., vol. 26, no. 11, pp. 1452–1458, Nov. 2004.
[7] 游孟航, “基於樣本學習自動合成創作卡通圖像”, 國立中央大學 資訊工程學系碩士論文, 2017
[8] Hayashi T, Ooi T. A Scoring Model of Figural Goodness and Its Application to Contour Completion.
[9] SCHAEFER, S., MCPHAIL, T., AND WARREN, J. 2006. Image deformation using moving least squares. ACM Trans. Graph. 25, 3, 533–540.
[10] D. Levin. The Approximation Power of Moving Least-Squares. Math. Computation, vol. 67, no. 224, 1998
[11] S. Tulsiani, H. Su, L. J. Guibas, A. A. Efros, and J. Malik. Learning shape abstractions by assembling volumetric primitives. CoRR, abs/1612.00404, 2016
[12] S. Gurumurthy, R. Kiran Sarvadevabhatla, and V. Babu Radhakrishnan. DeLiGAN. Generative Adversarial Networks for Diverse and Limited Data. ArXiv e-prints, June 2017
電子全文 電子全文(網際網路公開日期:20210720)
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