一般用於衛星影像的對比增揚方法皆直接使用整張影像的統計資訊對所有灰階值進行增揚處理。但由於原影像中較暗與較亮的區域增揚後常會過度飽和造成對比及細節資訊流失，所以許多不同的地物特徵常難以同時增顯出來。本研究提出一種以模糊理論為基礎的影像對比增揚方法，將單一像元視為數種類別的組合，以混合的程度表示像元內類別間之對應關係，藉以補償上述傳統方法中黑暗區與明亮區損失的對比及資訊。本演算法分為三個階段：第一階段，以Fuzzy c-Means (FCM)群聚分類法對衛星影像作模糊式分類，將原始影像由灰階值空間轉換至歸屬值空間，分類後的各個像元由數個相應於類別比例的歸屬值所組成。第二階段，依照各類別的歸屬值，分別建立各類別的增揚轉換模型。第三階段，將歸屬值依照前一階段中建立的轉換模型轉換回灰階值空間。由於每個像元皆由數個類別的歸屬值組成，原始灰階值會依照各類別的轉換模型被增揚成數個不同的值。因歸屬值代表類別混合的比例，故以各類別歸屬值作為權重，重新組合此些不同的灰階值，得到最後的增揚成果。影像經增揚後，評估採用定性及定量方式，分別以人眼及量化指標判定增揚影像含有的資訊量及對比度，並將模糊分類式增揚法的成果與傳統常用的非線性直方圖等化及線性對比擴展法的成果比較。成果顯示本研究提出的模糊分類式對比增揚演算法可以提供對人眼而言較佳的影像品質，且表現比傳統方法更佳。 Many image enhancement algorithms have been developed to improve the appearance of images. However, it is usually difficult to enhance all land cover classes appearing in the satellite images, because local contrast information and details may be lost in the dark and bright areas. In this study, a fuzzy-based image enhancement method is developed to partition the image pixel values into various degrees of associates in order to compensate the local brightness lost in the dark and bright areas. The algorithm contains three stages: First, the satellite image is transformed from gray-level space to membership space by Fuzzy c-Means clustering. Second, appropriate stretch model of each cluster is constructed based on corresponding memberships. Third, the image is transformed back to the gray-level space by merging stretched gray values of each cluster. Various remotely sensed images are used to test the proposed algorithm. There are various land cover classes appearing on the images, including forests, urban areas, river, farm, and so on. Since the gray values of some classes are extremely dark or bright, apparently the global enhancement will result in poor contrast quality. After using the proposed enhancement method, the results are evaluated and compared with other conventional methods. The test results indicate that the proposed method could provide a superior appearance and visualization than conventional enhancement methods.
