The detection of Oracle Bone Inscriptions (OBIs) is one of the most fundamental tasks in the study of Oracle Bone, which aims to locate the positions of OBIs on rubbing images. The existing methods are based on the sc...The detection of Oracle Bone Inscriptions (OBIs) is one of the most fundamental tasks in the study of Oracle Bone, which aims to locate the positions of OBIs on rubbing images. The existing methods are based on the scheme of anchor boxes, involving complex network design and a great number of anchor boxes. In order to overcome the problem, this paper proposes a simpler but more effective OBIs detector by using an anchor-free scheme, where shape-adaptive Gaussian kernels are employed to represent the spatial regions of different OBIs. More specifically, to address the problem of misdetection caused by regional overlapping between some tightly distributed OBIs, the character regions are simultaneously represented by multiscale Gaussian kernels to obtain regions with sharp edges. Besides, based on the kernel predictions of different scales, a novel post-processing pipeline is used to obtain accurate predictions of bounding boxes. Experiments show that our OBIs detector has achieved significant results on the OBIs dataset, which greatly outperforms several mainstream object detectors in both speed and efficiency. Dataset is available at http://jgw.aynu.edu.cn.展开更多
Oracle bone inscriptions (OBI) has important historical and cultural values. The traditional OBI research methods are at a choke point, and the research method using computer science and information technology has ope...Oracle bone inscriptions (OBI) has important historical and cultural values. The traditional OBI research methods are at a choke point, and the research method using computer science and information technology has opened up the way of OBI information processing. However, it faces some problems, such as large but not centralized knowledge system, long learning cycle, learning difficulties, being difficult to obtain resources, inconsistent format, low retrieval accuracy, and low knowledge sharing and reuse. To solve these problems, it designs an OBI big data research resource management and intelligent knowledge service platform. Its goal is to make full use of OBI big data characteristics and use the knowledge engineering technology to build an OBI knowledge ecosystem. The experiment results show that the platform proposed provides effective one-stop knowledge management and knowledge service.展开更多
文摘The detection of Oracle Bone Inscriptions (OBIs) is one of the most fundamental tasks in the study of Oracle Bone, which aims to locate the positions of OBIs on rubbing images. The existing methods are based on the scheme of anchor boxes, involving complex network design and a great number of anchor boxes. In order to overcome the problem, this paper proposes a simpler but more effective OBIs detector by using an anchor-free scheme, where shape-adaptive Gaussian kernels are employed to represent the spatial regions of different OBIs. More specifically, to address the problem of misdetection caused by regional overlapping between some tightly distributed OBIs, the character regions are simultaneously represented by multiscale Gaussian kernels to obtain regions with sharp edges. Besides, based on the kernel predictions of different scales, a novel post-processing pipeline is used to obtain accurate predictions of bounding boxes. Experiments show that our OBIs detector has achieved significant results on the OBIs dataset, which greatly outperforms several mainstream object detectors in both speed and efficiency. Dataset is available at http://jgw.aynu.edu.cn.
基金the National Natural Science Foundation of China (No. U1504612, 61806007, U1804153)the National Language Committee scientific research projects of China (No. YWZ-J023, YB135-50)+1 种基金the Development Projects of Henan Province Science and Technology (No. 182102310039)the Science and Technology Key Project of Henan Province Education Department (No. 17A520002).
文摘Oracle bone inscriptions (OBI) has important historical and cultural values. The traditional OBI research methods are at a choke point, and the research method using computer science and information technology has opened up the way of OBI information processing. However, it faces some problems, such as large but not centralized knowledge system, long learning cycle, learning difficulties, being difficult to obtain resources, inconsistent format, low retrieval accuracy, and low knowledge sharing and reuse. To solve these problems, it designs an OBI big data research resource management and intelligent knowledge service platform. Its goal is to make full use of OBI big data characteristics and use the knowledge engineering technology to build an OBI knowledge ecosystem. The experiment results show that the platform proposed provides effective one-stop knowledge management and knowledge service.