{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/high-performance-offline-handwritten-chinese","title":"High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps","arxiv_id":"1505.04925","date":"2015-05-19","proceeding":null,"authors":["Zhuoyao Zhong","Lianwen Jin","Zecheng Xie"],"abstract":"Just like its great success in solving many computer vision problems, the\nconvolutional neural networks (CNN) provided new end-to-end approach to\nhandwritten Chinese character recognition (HCCR) with very promising results in\nrecent years. However, previous CNNs so far proposed for HCCR were neither deep\nenough nor slim enough. We show in this paper that, a deeper architecture can\nbenefit HCCR a lot to achieve higher performance, meanwhile can be designed\nwith less parameters. We also show that the traditional feature extraction\nmethods, such as Gabor or gradient feature maps, are still useful for enhancing\nthe performance of CNN. We design a streamlined version of GoogLeNet [13],\nwhich was original proposed for image classification in recent years with very\ndeep architecture, for HCCR (denoted as HCCR-GoogLeNet). The HCCR-GoogLeNet we\nused is 19 layers deep but involves with only 7.26 million parameters.\nExperiments were conducted using the ICDAR 2013 offline HCCR competition\ndataset. It has been shown that with the proper incorporation with traditional\ndirectional feature maps, the proposed single and ensemble HCCR-GoogLeNet\nmodels achieve new state of the art recognition accuracy of 96.35% and 96.74%,\nrespectively, outperforming previous best result with significant gap.","url_abs":"http://arxiv.org/abs/1505.04925v1","url_pdf":"http://arxiv.org/pdf/1505.04925v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"high-performance-offline-handwritten-chinese","repo_url":"https://github.com/zhongzhuoyao/HCCR-GoogLeNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"offline-handwritten-chinese-character","task_name":"Offline Handwritten Chinese Character Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"googlenet","method_name":"GoogLeNet"},{"method_slug":"inception-module","method_name":"Inception Module"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1505.04925","atlas_url":"https://app.syntology.ai/?focus=1505.04925","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}