透過您的圖書館登入
IP:18.218.127.141
  • 學位論文

多焦距融合方法基於拉普拉斯小波轉換

Multi-Focus Fusion Method Based on LADWT

指導教授 : 顏淑惠

摘要


眼睛是靈魂之窗,人類透過視覺的辨識功能維持主要的生活能力。影像則是必須清晰度足夠才可以足以被識別。所以影像融合(image fusion)常常被應用在提高影像的清晰度以增加眼睛的辨識能力。 在本篇論文中提出了一個多焦距融合方法,利用拉普拉斯運算可以提高影像銳利度與小波轉換的多重尺寸特性以達到增強影像的清晰度和辨識度的目的。實驗的部份,在測試合成影像的品質都得到滿意的結果,也測試了此方法對於位移(shift)具有一定程度上的容忍度。本方法也適用於多來源影像融合與彩色影像融合。

並列摘要


A scene to be photographed usually includes objects at various distances and this causes the out of focus objects appear blurry. This paper presents a multi-focus image fusion method to solve this problem. It utilizes Laplacian pyramid and discrete wavelet transform to extract important information from two sources images and fuse them into a single image with high spatial and high spectral information. The algorithm has been tested on synthetic images and natural images with satisfactory results. Robustness in a small degree of shift is also tested on the proposed algorithm. The algorithm is illustrated to be applicable to color image fusion and multi-sensor image fusion as well.

參考文獻


1. L. Bogoni, and M. Hansen, "Pattern-selective color image fusion," Pattern Recognition, vol. 34, 2001, pp. 1515-1526.
3. F. Sadjadi, "Comparative Image Fusion Analysais," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, pp. 8.
4. S. Dippel, M. Stahl, R. Wiemker, and T. Blaffert, "Multiscale contrast enhancement for radiographies: Laplacian pyramid versus fast wavelet transform," Medical Imaging, IEEE Transactions , vol. 21, Issue 4, 2002, pp 343-353.
5. R.L. Allen, F.A. Kamangar, and E.M. Stokely, "Laplacian and orthogonal wavelet pyramid decompositions in coarse-to-fine registration," Signal Processing, IEEE Transactions on, vol. 41, Issue 12, 1993, pp 3536-3541.
6. C.Y. Wen, and J.K. Chen ,"Multi-resolution image fusion technique and its application to forensic science," Forensic Science International, vol. 140, 2004, pp. 217-232.

延伸閱讀