本論文提出一基於優先權式信賴度傳遞的方法能夠修補缺失區域位在影像四周的情況。要能夠達到這個目的,本方法重新定義馬可夫隨機場中節點的產生方式,並且使用漸進式方法一層一層的去修補影像。同時為了降低其運算量,我們先限制取得候選區塊的範圍之後再使用亮度和飽和度來對馬可夫隨機場中之每個節點的候選區塊做篩選。最後為了產生一張視覺上美觀的結果圖,因此在修補的階段我們加入了節點的目標區塊和候選區塊間之相似度與信賴度值這兩個條件來判斷每個節點是否可以修補。 實驗結果顯示,不只缺失區域位在影像四周的修補結果,同時缺失區域位在影像中間的情況其修補的結果都令人滿意。
In this paper we propose a priority belief propagation based method to complete the missing region located on the periphery of the input image. To reach this goal, we redefine the nodes of Markov Random Field (MRF) and use onion-based approach to complete the image. Meanwhile, avoiding the heavy computation, we restrict the range to getting candidates for MRF. Then, applying intensity and saturation as criteria to filter the candidate of each node of MRF. Finally, we combine the similarity between MRF node’s target and best candidate patch and confidence value to decide whether the node is suitable to complete or not. From the experiments shows that our method successfully produces the visual plausible results.