Separation and recognition of handwritten superimposed characters

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K00455
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Library and information science/Humanistic social informatics
• Research Institution: Nara National College of Technology
• Principal Investigator: Matsuo Ken'ichi 奈良工業高等専門学校, 情報工学科, 教授 (10259913)
• Research Collaborator: NISHIKAWA Masakiyo ; MIKAMI Tetsuro
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 答案画像 / 支援システム / 採点記号パターン / 採点数字パターン / 文字認識 / 文字切り出し / 分離文字

Outline of Final Research Achievements

The purpose of this research is separation of handwritten superimposed characteors and realization of recognition processing. The research results are as follows：Construction of simulated answer data set and creation of　recognition dictionary pattern．Proposal of separation extraction method of grading symbols and performance evaluation for proposed method．Verification of handwritten scoring symbol and number patterns recognition accuracy. Prototype of scoring error detection support system. Future work is improvement of separation accuracy of superimposed characters.

Free Research Field

画像処理