影像分割技術在影像處理以及電腦視覺中都是一個重要且具挑戰性的問題,前景分割是影像分割技術中的一種。前景物件分割的目標是將一張圖片分成前景及背景兩個部份,這種技術可以運用到物件偵測或其他電腦視覺的應用當中。近來,已經有不少關於前景分割的研究,但是,這些研究通常是屬於監督式的方法,亦即需要使用者的一些互動才能得出結果,使得便利性不盡理想,而傳統的非監督式影像前景分割方法通常存在一些缺點。 不同於傳統圖形切割的方法,在這篇論文中我們提出了一個非監督式的影像前景分割方法,以改善圖形切割的便利性。此方法利用了顯著區域標出前景可能所在的位置,以及利用邊界偵測來與顯著區域獲得圖形切割所需的閾值,將影像分割成前景和背景。我們所提出的方法不僅不需要使用者的介入,根據我們的實驗結果,相較於其他基於顯著區域的圖形切割,結果也相當不錯。
Image segmentation is an essential and challenging problem in computer vision and image processing. Figure-ground segmentation is one of image segmentation that separate image into two labels, which are foreground and background. It can be used in object detection or many other applications. Recently, a lot of methods have been proposed for solving figure-ground segmentation problems. However, most of them are supervised approaches. In other words, the procedures of those methods need some interactions of users. It makes those methods unfavorable. Also, there are some disadvantage in traditional unsupervised image segmentation methods. We proposed an unsupervised figure-ground approach. It uses the saliency detection method to indicate the position of the foreground, and use the boundary detection method to obtain a suitable threshold for image segmentation automatically. According to our experiment results, our method does not need user interaction and performs well compared with the previous saliency-based segmentation method for segmentation of iCoseg dataset and MSRA-1000 dataset.