- 學位論文
以影像失焦之像素強度分佈進行場景深 度估測與影像品質評估
Defocus Blur Identification for Depth Estimation and Image Quality Assessment
摘要
在本論文中，我們提出利用分析真實影像上失焦模糊邊緣的區域之直方圖的特性，得到一個絕對的模糊程度，進一步可以用薄透鏡的成像特性來歸納出模糊程度與物體跟相機間距離的關係。除了薄透鏡的成像特性外，我們還考慮到相機感光元件得到的原始數據會經由相機內部做非線性的亮度轉換，所以另外提出了一個依賴像素強度變化的雜訊模型、一個依賴像素強度變化的模糊濾波器，用來合成模糊邊緣影像，以模擬真實場景中的模糊邊緣影像，當模糊模型中的模糊參數產生出的影像與真實擷取之影像達到一定程度的符合，這時我們就得到了該模糊值。在經過一連串的實驗後，我們得到了在不同對焦位置上，相機與物體的距離與模糊程度間的數學模型。另外，我們亦經由模糊的程度來評估一張照片的影像品質，在評估影像品質方面，除了使用了 LIVE database 之外，我們還挑選了校內 10 處景點，每個景點選擇三個角度，各自拍攝 32 張影像，從對焦到失焦逐漸變化共 960 張的序列影像，來驗證我們演算法的可行性與強健性。
並列摘要
In this thesis, we present a defocus blur identification technique based on histogram analysis of an image. The image defocus process is formulated by incorporating the non-linear camera response and intensity dependent noise model. The histogram matching between the synthesized and real defocused regions is then carried out with intensity dependent filtering. By iteratively changing the point-spread function parameters, the best blur extent is identified from histogram comparison. The presented technique is first applied to depth measurement using the defocus information. It is also used for image quality assessment applications, specifically associated with optical defocus blur. We have performed the experiments on both the real scene images. The results have demonstrated the robustness and feasibility of the proposed technique.