圖地認知一詞指的是一種視覺認知經驗，透過一個指定的輪廓，可以將影像分為兩個區域，而此兩個相鄰的區域分別代表圖與地。圖具有清晰的形狀；而另一個連續且不具清楚形狀的區域，也就是地，則具有襯托圖的作用。視覺在感知形狀的提示上和圖的指定過程有所關聯，其中包含了低階的幾何形狀和高階的語意特性，此部分在電腦視覺和心理學領域上皆有廣泛地研究。而圖地反轉是一種具有多重意義的特殊影像，在影像中相鄰的兩個區域圖與地，在視覺感知上被視為主體的力量為一種均衡的程度時，觀察者可以透過視覺感知，隨時在兩個區域間將圖與地分別視為主體來的切換，而看到雙重意義的影像。在本論文中，我們提出了一個技術用來產生此種具有多重意義的圖地反轉影像。在我們的演算法設計中由使用者手動地輸入兩張影像並分別標注為共享相同邊緣的圖和地，再根據幾何特性，也就是凸的輪廓形狀以及圖與地各別的面積，用來調整圖與地的區域來平衡在視覺上視為主體的競爭性。最後我們透過產生大量在視覺上具多重意義的圖地反轉影像來論證我們方法的有效性。

Figure-ground perception refers to a perceptual experience of assigning a contour to one of the two adjacent regions and that region, the figure, has a definite shape while the other region, the ground, appears shapeless and continue behind the figure. Visual cues that associate with figure assignment process including low-level geometric and high-level semantic properties have been extensively studies in computer vision and psychology. Ambiguous figure-ground perception is a special phenomena by which adjacent regions in a image compete with each other in terms of visual cues such that viewers could switch the perceived figure among regions in any moment. In this thesis, we present a technique to generate images with ambiguous figure-ground perception. Our algorithm is designed so that two input regions manually labeled as figure and ground are registered locally along a shared contour. Then two geometric properties, namely convexity and area, are adjusted to balance the competition in between figure and ground regions. We demonstrate the effectiveness of our technique using a large number of visually promising ambiguous figure-ground images.

[1] Beier, Thaddeus and Neely, Shawn. Feature-based image metamorphosis. ACM SIGGRAPH Comput. Graph. 26, 2, 35-42. (1992)
[2] Chen, L., Feris, R., Turk, M. Efficient partial shape matching using smith waterman algorithm. Proceedings of NORDIA Workshop at CVPR. (2008)
[3] D. Lowe. Distinctive image features from scale-invariant key points. International Journal of Computer Vision 20, pp. 91--110. (2003)
[4] Delaunay, Boris N. Sur la sphère vide. Bulletin of Academy of Sciences of the USSR, 6, 793-800. (1934)
[5] J.-C. Yoon, I.-K. Lee, and H. Kang. A hidden-picture puzzles generator. Computer Graph. Forum, 27(7):1869–1877. (2008)
[6] M. Donoser, H. Riemenschneider, and H. Bischof. Efficient partial shape matching of outer contours. Computer Vision–ACCV 2009, pages 281–292. (2010)
[7] Mary A. Peterson and Emily Skow Grant . Memory and Learning in Figure-Ground Perception. In B. Ross & D. Irwin (Eds.). Cognitive Vision: Psychology of Learning and Motivation, 42, 1-34. (2003)
[8] O. van Kaick, G. Hamarneh, H. Zhang, P. Wighton. Contour Correspondence via Ant Colony Optimization Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2007), Maui, Hawaii, United States, pp. 271-280. (2007)
[9] Qiang Tong, Song-Hai Zhang, Ralph R. Martin and Paul L. Rosin. Nested Images. Asian Conference. (2010)
[10] S. Belongie, J. Malik, and J. Puzicha. Shape matching and object recognition using shape contexts. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 24(4):509–522, (2002)
[11] Sorkine, O., Cohen-Or, D., Lipman, Y., Alexa, M., Rössl, C., and Seidel, H.-P. Laplacian surface editing. In Proceedings of the Eurographics, 175-184. (2004)
[12] Wang, Y.-S., Tai, C.-L., Sorkine, O., and Lee, T.-Y. Optimized scale-and-stretch for image resizing. ACM Trans. Graph. 27, 5, 118:1–118:8. (2008)