類神經網路用於變形影像移動估計與補償

Abstract

本文提出一個變形影像的移動估計的類神經網路系統。傳統的方格比對式 物體移動的估計與補償技術，已經成功的應用於連續影像的壓縮系統之中 。在許多的相關研究中，推廣型的方格比對式移動影像估計，以及可變大 小的方格切割，能有效的改進傳統的方法。然而，這兩種方法各有其優缺 點。在本論文所提出的系統架構中，我們將這兩種技術，有效的融合於一 個類神經的變形影像的移動估計系統之中。在這個類神經的系統中，分為 兩個部份：輸出函數的學習，以及輸入空間的分割；兩者正分別對應於推 廣型的方格比對式移動影像估計，以及可變大小的方格切割兩種技術。而 且我們發現這兩個部份，可視為類神經網路之中的參數學習與架構學習。 因此，本文針對連續影像壓縮的特性，對類神經系統中的各個部份，提出 了適當的學習法則，並加以探討。實驗的結果，驗證了本文所提出的系統 架構，能有效的結合這兩種技術，使得它們得以相輔相成，而進一步的改 善影像壓縮的效率。 In this thesis, a neural system for deformed image motion estimation and compensation with variable-size blocks is proposed, which can be applied to an image sequence compression system. The motion estimation and compensation techniques have been successfully applied in the area of image sequence coding. Many researches on improving the performance of these techniques have been published; many directions are proposed, which can all lead to a better performance than the conventional technique. Among them, the generalized block-matching and variable-size block matching are successfully applied in reducing the data rate of compensation error and motion information, respectively. These two algorithms have their merits, but suffer from their drawbacks. Moreover, reducing the data rate in compensation error is sometimes increasing the data rate in motion information, or vice versa. Based on these two algorithms, we propose and examine several algorithms which are effective in reducing the data rate. We then incorporate these algorithms into a neural system, in which they work together to overcome the disadvantages of individual and keep their merits at the same time. The proposed system can optimally balance the amount of data rate in two aspects (i.e., compensation error and motion information). As experiment result shows, the proposed system outweighs the conventional techniques.