共同資訊在生物影像上的應用

Abstract

影像對位是一個很重要的影像處理工具。其主要的應用是在匹配兩張或是多張影像上，在許多大型的影像處理系統都使用著這樣的技術。在本篇論文中，我們藉由 “共同資訊量”的最大化來做影像對位的研究，並將該技術用在生物影像處理。我們的實驗資料來自清華大學江安世老師的實驗室，利用共同資訊的方法來定義出果蠅腦各特徵點的座標系統。另外也對果蠅左右腦的大小做分析，藉此來解決我們對生物的疑問。

Registration is a important tool in image processing that is applied to match regions in two or more pictures. Virtually all large systems which evaluate images require the registration of images. In this thesis, image registration technique by maximization of mutual information was studied. The technique was applied to biological images of fly brains. Our experimental data supplied by Dr. Chiang’s laboratory of Tsing Hua University. By applying the registration technique, we identify the neuropils in the fly brain and the average locations of the neuropils were computed. In addition, we also analyze the size of Drosophila’s left and right brains.