CASIA OpenIR  > 模式识别国家重点实验室  > 模式分析与学习
Oracle Character Recognition by Nearest Neighbor Classification with Deep Metric Learning
Zhang YK(张颐康)1,2; Zhang H(张恒)1; Liu YG(刘永革)4,5; Yang Q(杨青)1; Liu CL(刘成林)1,2,3
2019-09-20
Conference NameThe 15th IAPR International Conference on Document Analysis and Recognition (ICDAR 2019)
Conference Date20-25 Sep. 2019
Conference PlaceInternational Convention Centre (ICC) Sydney
Abstract

    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.

KeywordOracle Character Recognition Dense Convolutional Network Deep Metric Learning Nearest-neighbor Classifier
MOST Discipline Catalogue工学
Indexed ByEI
Funding ProjectNational Natural Science Foundation of China[61721004] ; Beijing Science and Technology Project[Z181100008918010]
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/28356
Collection模式识别国家重点实验室_模式分析与学习
Corresponding AuthorZhang YK(张颐康)
Affiliation1.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
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang YK,Zhang H,Liu YG,et al. Oracle Character Recognition by Nearest Neighbor Classification with Deep Metric Learning[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
ICDAR_YKZhang.pdf(410KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang YK(张颐康)]'s Articles
[Zhang H(张恒)]'s Articles
[Liu YG(刘永革)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang YK(张颐康)]'s Articles
[Zhang H(张恒)]'s Articles
[Liu YG(刘永革)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang YK(张颐康)]'s Articles
[Zhang H(张恒)]'s Articles
[Liu YG(刘永革)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ICDAR_YKZhang.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.