研究生: |
Puteri Noraisya Primandari Puteri - Noraisya Primandari |
---|---|
論文名稱: |
An Image Processing Approach toward Seasonal Change of Trees An Image Processing Approach toward Seasonal Change of Trees |
指導教授: |
楊傳凱
Chuan-Kai Yang |
口試委員: |
賴祐吉
Yu-Chi Lai 姚智原 Chih-Yuan Yao |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 資訊管理系 Department of Information Management |
論文出版年: | 2016 |
畢業學年度: | 104 |
語文別: | 英文 |
論文頁數: | 50 |
中文關鍵詞: | HSVcolortransfer 、Foregroundandbackgroundseparation 、Edgedetection 、K-Meansclustering 、Userinteraction |
外文關鍵詞: | HSV color transfer, Foreground and background separation, Edge detection, K-Means clustering, User interaction |
相關次數: | 點閱:271 下載:5 |
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 |
In spite of the fact that a collection of various trees of four different seasons can be found from the internet. Nevertheless, it is definitely not an easy task for a photographer or a professional to take a picture of the same tree for different seasons. In this paper, we provide a comprehensive system to generate a new image of a different season from a given image by reflecting the seasonal characteristics. We construct a new color transfer approach through the HSV color space. We also create the generated season change more properly by identifying the foreground and background of the image. By knowing the foreground of a scene, the system ensures the color modification only apply to the main object which is detected. Once we make in-depth observations of a tree, we extract a tree characteristic from the particular flowers on these trees with different magnitudes and directions. Currently, we create a system that can deploy the flowers along particular paths by generating random scales and rotations. Edge detection and K-Means Clustering are used to find a reasonable place to grow the flowers. Additionally, this system can also be assisted with user interaction to mark the reasonable result. The collaboration between the system and the user would be essential to hint the foreground and background of the image and also to control the final result for an acceptable output.
In spite of the fact that a collection of various trees of four different seasons can be found from the internet. Nevertheless, it is definitely not an easy task for a photographer or a professional to take a picture of the same tree for different seasons. In this paper, we provide a comprehensive system to generate a new image of a different season from a given image by reflecting the seasonal characteristics. We construct a new color transfer approach through the HSV color space. We also create the generated season change more properly by identifying the foreground and background of the image. By knowing the foreground of a scene, the system ensures the color modification only apply to the main object which is detected. Once we make in-depth observations of a tree, we extract a tree characteristic from the particular flowers on these trees with different magnitudes and directions. Currently, we create a system that can deploy the flowers along particular paths by generating random scales and rotations. Edge detection and K-Means Clustering are used to find a reasonable place to grow the flowers. Additionally, this system can also be assisted with user interaction to mark the reasonable result. The collaboration between the system and the user would be essential to hint the foreground and background of the image and also to control the final result for an acceptable output.
[1] F. Chevalier, P. Dragicevic and C. Hurter, "Histomages: fully synchronized views for image editing," in Proceedings of the 25th annual ACM symposium on User interface software and technology, New York, 2012.
[2] D. Lischinski, Z. Farbman, M. Uyttendaele and R. Szeliski, "Interactive local adjustment of tonal values," in ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH 2006, New York, 2006.
[3] F. Ding, J. Li, D. Zou and X. Chen, "Data-Driven Season Characteristic Enhancement of Natural Image," in Seventh International Conference on Image and Graphics , 2013.
[4] Z. L. J. L. X. T. Shifeng Chen, "Image Matting Using Linear Optimization," in MM '07: Proceedings of the 15th ACM international conference on Multimedia, 2007.
[5] Y.-Y. Chuang, B. Curless, D. H. Salesin and R. Szeliski, "A Bayesian approach to digital matting," in Proceedings of the 2001 IEEE Conference on Computer Vision and Pattern Recognition, 2001.
[6] A. Levin, D. Lischinski and Y. Weiss, "A Closed Form Solution to Natural Image Matting," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 228-242, 2008.
[7] J. Wang and M. F. Cohen, "Optimized Color Sampling for Robust Matting," in 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007.
[8] C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli and P. Rott, "A Perceptually Motivated Online Benchmark for Image Matting," in IEEE Conference on Computer Vision and Pattern Recognition, 2009. , 2009.
[9] C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli and P. Rott, "http://www.alphamatting.com/," [Online]. Available: http://www.alphamatting.com/datasets.php. [Accessed 11 june 2016].
[10] E. Reinhard, M. Adhikhmin, B. Gooch and P. Shirley, "Color transfer between images," IEEE Computer Graphics and Applications, pp. 34-41, 2001.
[11] Y. Hwang, J.-Y. Lee, I. S. Kweon and S. J. Kim, "Color Transfer Using Probabilistic Moving Least Squares," 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3342 - 3349, 2014.
[12] C. Yao, X. Yang, L. Chen and J. Wang, "Color transfer via local binary patterns mapping," in 2010 IEEE International Conference on Image Processing, 2010.
[13] X. Qian, B. Wang and L. Han, "An efficient fuzzy clustering-based color transfer method," in 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), 2010.
[14] Y. Pu, X. Wei, Y. Su, Z. Zhao, W. Qian and D. Xu, "Implementation and Research of Multi-Method Color Transfer Algorithms in," in 2010 International Conference on Machine Vision and Human-Machine Interface (MVHI), 2010.
[15] J. Canny, "A Computational Approach to Edge Detection," IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vols. PAMI-8, NO. 6., pp. 679-698, 1986.
[16] "Canny Edge Detection," [Online]. Available: http://www.cse.iitd.ernet.in/~pkalra/csl783/canny.pdf. [Accessed 12 7 2016].
[17] D. Weinbach, "http://trees4seasons.com/," [Online]. Available: http://trees4seasons.com/deciduous-trees/. [Accessed 12 June 2016].
[18] "OnlinePlantGuide.com," [Online]. Available: http://www.onlineplantguide.com/Plant-Details/512/. [Accessed 12 June 2016].
[19] "Wikipedia," [Online]. Available: https://en.wikipedia.org/wiki/K-means_clustering. [Accessed 12 7 2016].
[20] "Cercis canadensis 'Hearts of Gold' Redbud," [Online]. Available: https://kellynurseryllc.com/products/cercishg15. [Accessed 12 june 2016].
[21] "Waitrose Garden," [Online]. Available: http://www.waitrosegarden.com/plants/_/cercis-canadensis-ruby-falls-pbr/classid.2000021233/. [Accessed 12 June 2016].
[22] "Ajenkins Arboretum and Gardens," [Online]. Available: http://www.jenkinsarboretum.org/greenribbon_trees.html. [Accessed 12 June 2016].
[23] "Cercis Canadensis," [Online]. Available: http://wildflowerlense.com/cpages/ce_ca/ce_ca.html. [Accessed 12 June 2016].