Oracle Bone Script Detection: A Benchmark Dataset and Analysis of Object Detection Frameworks

This research addresses the challenging task of detecting oracle bone script in images. We first constructed a large-scale dataset comprising 9500 images, providing a valuable resource for training and evaluating detection models. Leveraging this dataset, we conducted a comprehensive analysis of representative general object detection frameworks developed in recent years. Our findings offer insights into the capabilities and limitations of these frameworks when applied to the unique challenges of oracle bone script detection.