Knowledge Commons of Institute of Automation,CAS
Oracle Character Recognition by Nearest Neighbor Classification with Deep Metric Learning | |
Zhang, Yikang1,2; Zhang, Heng1; Liu, Yongge4,5; Yang, Qing1; Liu, Chenglin1,2,3 | |
2019-09-20 | |
会议名称 | The 15th IAPR International Conference on Document Analysis and Recognition (ICDAR 2019) |
会议日期 | 20-25 Sep. 2019 |
会议地点 | International Convention Centre (ICC) Sydney |
摘要 | Oracle character is one kind of the earliest hieroglyphics, which can be dated back to Shang Dynasty in China. Oracle character recognition is important for modern archaeology, ancient text understanding, and historical chronology, etc. To overcome the limitation and class imbalance of training data in oracle character recognition, we propose a classification method based on deep metric learning. We use a convolutional neural network (CNN) to map character images to an Euclidean space where the distance between different samples can measure their similarities such that classification can be performed by the Nearest Neighbor (NN) rule. Because new categories are still being discovered in reality, our model enables the rejection of unseen categories and the configuration of new categories. To accelerate NN classification, we also propose a prototype pruning method with little loss of accuracy. The proposed method exceeds the state of the art on the public dataset Oracle-20K and outperforms CNN with softmax layer on a new dataset Oracle-AYNU. |
关键词 | Oracle Character Recognition Dense Convolutional Network Deep Metric Learning Nearest-neighbor Classifier |
学科门类 | 工学 |
收录类别 | EI |
资助项目 | Beijing Science and Technology Project[Z181100008918010] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61721004] ; Beijing Science and Technology Project[Z181100008918010] |
语种 | 英语 |
七大方向——子方向分类 | 文字识别与文档分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/28356 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
通讯作者 | Zhang, Yikang |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence of Brain Science and Intelligence Technology 4.School of Computer & Information Engineering, Anyang Normal University 5.Key Laboratory of Oracle Bone Inscriptions Information Processing, Ministry of Education |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhang, Yikang,Zhang, Heng,Liu, Yongge,et al. Oracle Character Recognition by Nearest Neighbor Classification with Deep Metric Learning[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ICDAR_YKZhang.pdf(410KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论