裁縫演算法為影像縮放方法之一，此演算法因其便利性及廣泛性受到注目，然而，裁縫演算法存在邊緣不連續及顯著目標物偵測失衡等問題。本論文以改進裁縫演算法的顯著圖與分散裁縫分佈兩步驟為基礎提出一更佳的影像縮放方法。所提方法以小波轉換取得影像細微資訊解決邊緣不連續的問題，超像素分割技術偵測影像中的顯著目標物，根據取得的區域及全域顯著圖的閥值來混合兩者，接者，記錄每次裁縫的位置，藉由增強這些位置的顯著值來達到分散裁縫的目的。
　　實驗結果顯示所提演算法較能保留顯著目標物，同時在不顯著區域避免嚴重失真，對具有線條/架構的影像類型有較低的幾何失真，而對具有前景的影像類型有較低的影像資訊遺失。

　　Seam carving is one of image resizing methods. The resulting image has the issue of producing distortion in the main content of images. One way to improve seam carving is to fuse local and global saliency information to generate the final saliency map. In our proposed method, the saliency values of local saliency map are acquired by using the wavelet transform and the saliency values of global saliency map are acquired by using superpixel segmentation. In the proposed saliency map fusion, the degree of contribution from local and global saliency is determined by comparing their values. To prevent the seam distribution from being too concentrate, the saliency value at the removed seam locations are increased.
　　Experiments show that our improved seam carving method can protect the main content and carve the background more uniformly. Objective analysis using the distortion value proposed in [5] shows that our improved seam carving method has less information loss than the seam carving method for P/F type images and less geometric distortion for L/G type images.

[1] S. Avidan and A. Shamir, "Seam carving for content-aware image resizing," ACM Transactions on Graphics, vol. 26, no. 3, p. 10, 2007.
[2] M. R. Abkenar and M. O. Ahmad, "Superpixel-based salient region detection using the wavelet transform," in 2016 IEEE International Symposium on Circuits and Systems, pp. 2719-2722, 2016.
[3] D. S. Hwang and S. Y. Chien, "Content-aware image resizing using perceptual seam carving with human attention model," in 2008 IEEE International Conference on Multimedia and Expo, pp. 1029-1032, 2008.
[4] J. W. Han, K. S. Choi, T. S. Wang, S. H. Cheon and S. J. Ko, "Wavelet based seam carving for content-aware image resizing," in 2009 16th IEEE International Conference on Image Processing, pp. 345-348, 2009.
[5] C. C. Hsu, C. W. Lin, Y. Fang, and W. Lin, "Objective quality assessment for image retargeting based on perceptual geometric distortion and information loss," IEEE Journal of Selected Topics in Signal Processing, vol. 8, no. 3, pp. 377-389, 2014.
[6] N. Imamoglu, W. Lin and Y. Fang, "A saliency detection model using low-level features based on wavelet transform," IEEE Transactions on Multimedia, vol. 15, no. 1, pp. 96-105, 2013.
[7] Y. Lin, Y. Niu, J. Lin, and H. Zhang, "Accumulative energy-based seam carving for image resizing," in 2016 17th International Conference on Parallel and Distributed Computing, Applications and Technologies, pp. 366-371, 2016.
[8] N. Mu and X. Xu, "Superpixel-based global contrast driven saliency detection in Low Contrast Images," in Computer Vision: CCF Chinese Conference, CCCV 2015, Xi'an, China, September 18-20, 2015, Proceedings, Part I, Heidelberg: Springer Berlin Heidelberg, Berlin, pp. 407-417, 2015.
[9] M. Rubinstein, A. Shamir, and S. Avidan, "Improved seam carving for video retargeting," ACM Transactions on Graphics, vol. 27, no. 3, pp. 1-9, 2008.
[10] L. Wolf, M. Guttmann and D. Cohen-Or, "Non-homogeneous content-driven video-retargeting," in 2007 IEEE 11th International Conference on Computer Vision, pp. 1-6, 2007.
[11] Y. S. Wang, C. L. Tai, O. Sorkine and T. Y. Lee, "Optimized scale-and-stretch for image resizing," ACM Transactions on Graphics, vol. 27, no. 5, pp. 1-8, 2008.
[12] Z. Yan and H. Chen, "A study of image retargeting based on seam carving," in 2014 Sixth International Conference on Measuring Technology and Mechatronics Automation, pp. 60-63, 2014.
[13] B. Yan, K. Li, X. Yang, and T. Hu, "Seam searching-based pixel fusion for Image retargeting," IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 1, pp. 15-23, 2015.
[14] W. Zeng, M. Yang, Z. Cui, and A. Al. Kabbany, "An improved saliency detection using wavelet transform," in 2015 IEEE International Conference on Communication Software and Networks, pp. 345-351, 2015.