Oracle bone inscriptions (OBIs) are invaluable materials for recovering the economic and social forms for ShangDynasty, one of the most ancient dynasties in China. It is very important to get the original OBIs from scanned images oforacle bone rubbings. To this end, researchers have to employ a very time-consuming method that they follow theinscriptions by handwritten tools, pixel by pixel and image by image. In this paper, an image segmentation method wasproposed to overcome this limitation based on fully convolutional networks (FCN). In order to speed up training as wellas boost the segmentation performance, a simple FCN with only convolutional layers was designed, where batchnormalization was incorporated. The proposed method was tested on a real OBI image set (320 samples). Experimentalresults show that the proposed method is effective enough to get the OBIs from scanned images of oracle bone rubbings.
展开▼