以顏色區塊為基礎之影像放大

Image Upsampling with Color-based Segmentation

蘇俊睿(Ezra Su)

指導教授 ： 徐郁輝

共同指導教授 ： 黃連進

淡江大學/工學院/資訊工程學系碩士班/碩士(2005年)

https://doi.org/10.6846/TKU.2005.00273

摘要

時下越來越多的電子消費產品內建了數位相機，一般人也有越來越多的機會接觸到數位影像，所以數位影像的處理就成為了重要的一環，影像縮放廣泛的應用在各個領域之中，也使得它在影像處理中始終佔有一定的份量，屹立不搖，其中影像放大更是佔了相當大的應用比例。本文提出以顏色資訊將影像分割，在放大影像時，針對邊界的部分單獨處理，以得到較清晰平滑的邊緣。

本文在分割圖片的顏色區塊時，利用將RGB 轉換至HIS 色彩空間，來得到顏色的資訊，利用先在圖片邊緣灑下的生長點，尋找相同顏色的點合併為區塊，再以區塊融合的方式來達到顏色區塊分割，當進行影像放大時，本文以Bilinear 作為基礎，當區塊沒有明顯的顏色交界時，我們使用一般的Bilinear進行放大，在面對顏色的交界處時，便改用自定義的演算法，捨棄非同顏色的點，以達到較平滑的邊緣。

最後，本文結合顏色分塊和Bilinear 以及顏色交界處的自定義插值法，只需要增加少量的處理時間，便能得到比Bilinear 較佳的視覺效果。

關鍵字

影像放大 ； 型態影像學 ； 影像分割

並列摘要

In present time, many consumer electronic devices have build-in digital camera that makes peoples have more chances to use digital camera related devices. Therefore, digital image processing has become an important research topic in present days. The technique of image scaling is always a major topic of the digital image processing, especially the image upsampling technique. In this thesis, by using the color information of the image, a bilinear interpolation based method is proposed for smoothing the edge of the objects in the image.

In this thesis, a novel method is proposed to segment the image according to the color information at first. The segmentation process starts from the border of the image, and assemble the pixels that have similar color. In this work, the image is cut into several blocks. When the small block contains features of the color edges, the upsampling process will be performed on the corresponding block by the proposed method based on the bilinear interpolation technique. Otherwise, the upsampling process is performed using the pure bilinear interpolation technique.

The proposed method combines the color information and modified bilinear interpolation technique to achieve better visual quality. Moreover, comparing to the traditional methods, the proposed method only requires a few extra computational time to accomplish the goal.

並列關鍵字

Image scaling ； mathematical morphology ； image segmentation

參考文獻

[1] E. Maeland, “On the comparison of interpolation methods,” IEEE Trans. Medical Imaging, vol. 7, pp. 213–217, 1988.

[2] T. M. Lehmann, C. G¨onner, and K. Spitzer, “Survey: Interpolation methods in medical image processing,” IEEE Trans. Medical Imaging, vol. 18, pp. 1049–1075, 1999.

[3] JK Han and SU Baek, “Parametric cubic convolution scaler for enlargement and reduction of image,” IEEE Trans. Consumer Electronics, vol.46, no.2, pp.247-256, May 2000.

[4] C. Lee, M. Eden, and M. Unser, “High-quality image resizing using. oblique projection operators,” IEEE Trans. Image Processing, vol. 7,. no. 5, pp. 679–692, May, 1998.

[5] M. Unser, A. Aldroubi, and M. Eden, “Enlargement or reduction of digital images with minimum loss of information, ” IEEE Trans. Image Processing, vol. 4, pp.247-258, 1995.