梯度向量流動態曲線模型應用至共軛焦顯微鏡昆蟲腦影像分割之研究

Abstract

影像分割(Segmentation)在影像分析上扮演重要的角色。一個成功的影像分割對於分析的有效性具有絕對的影響。而動態曲線模型(Active Contour Model)在影像分割中是一個被廣泛使用的方法。在1998年，一種新型態的模型叫做梯度向量流動態曲線模型被提出來，用以改善傳統動態曲線模型中的一些缺點。在這篇論文中，我們將介紹梯度向量流動態曲線模型的實作方式以及其優點，並應用梯度向量流動態曲線模型，作為由共軛焦光學顯微鏡掃描出來的昆蟲腦組織影像的影像分割法。

Segmentation of meaningful structures form images is an essential step in many applications of image analysis. The challenge is to extract boundary elements that belong to the same structure and integrate these elements into a coherent and consistent model of the structure. Active contour model, known as snakes, integrates the image feature extraction and representation phase into a single process and is widely used in many applications. A new class of active contour model called gradient vector flow snake has been introduced in 1998. Gradient vector flow snake attacks some drawbacks in the traditional active contour model. In this paper, we will introduce gradient vector flow snake and its advantages, and use it in the application of segmenting the structures in the confocal microscopic image of insect brain.