為了要改善Pal和King提出的傳統演算法的缺點,本篇論文提出一個新演算法『基於邊緣檢測之適應性模糊影像增強』。我們運用邊緣檢測找出影像的邊緣,然後計算邊緣的平均值,並設定為閥值,進而找出轉折點來確保邊緣的訊息不會遺失。我們設計了新的隸屬函數和對比度加強運算式來更有效的執行模糊影像增強。由實驗結果可以看出我們提出的演算法對於不同的影像皆可增強對比度並且保留更好的細節度。
To overcome the drawbacks of the traditional Pal and King’s algorithm, a new algorithm of adaptive fuzzy image enhancement based on edge detection is proposed in this thesis. We apply the edge detection to find the edges of images and then set the mean of edges as the threshold to obtain the crossover point for edge preserving. Using the crossover point, we devise a new membership function and construct a new contrast intensification operator to achieve effective fuzzy image enhancement. The experimental results show that the proposed algorithm can enhance the contrast and preserve better details for different types of images.