计算机与现代化

• 算法设计与分析 • 上一篇    下一篇

一种手写体识别误差与用户花费平衡算法

  

  1. 新疆工程学院计算机工程系,新疆维吾尔自治区乌鲁木齐830011
  • 收稿日期:2015-05-11 出版日期:2015-09-21 发布日期:2015-09-24
  • 作者简介:尚雪莲(1977-),女,甘肃武威人,新疆工程学院计算机工程系讲师,硕士,研究方向:模式识别,图像处理; 梁传君(1980-),女,讲师,硕士,研究方向:模式识别,图形图像处理。
  • 基金资助:
     新疆维吾尔自治区自然科学基金资助项目(2013211A031); 新疆工程学院基金资助项目(2014030415)

 A Balance Algorithm Between Handwriting Error and User Effort

  1. Department of Computer Engineering, Xinjiang Institute of Engineering, Urumqi 830011, China
  • Received:2015-05-11 Online:2015-09-21 Published:2015-09-24

摘要:

针对当前计算机辅助注释手写文本文件转录算法存在效率不高的问题,提出一种能预测自动识别单词块中的错误率,并估计校正转录到某个用户定义的错误率所需花费精力的手写文本文件
转录算法。首先,分析传统的错误估计方法及其存在的主要问题;然后,提出对整个单词块执行错误估计以提高准确率的思想;最后,将当前执行最好技术进行合并,提出手写文本转录方法。本算法包
含在转录手写文本文件的交互式方法中,以主动学习和半监督学习技术有效利用用户交互。在2个真实手写文件上进行转率实验,实验考虑了用户所花精力和转录准确性之间的平衡,实验结果表明了本算
法的有效性。

关键词:  , 计算机辅助标注, 手写体识别, 用户花费, 平衡, 文本转录, 误差评估

Abstract:

To solve the problem of poor performance in present computer-assisted annotation transcription of handwritten text documents, a new algorithm for predicting the
error rate in a block of automatically recognized words is proposed, and estimates how much effort is required to correct a transcription to a certain user-defined error rate.
Firstly, the main problem in traditional error estimating methods is analyzed. Then, the estimation of the error is performed for a whole block of words to raise the accuracy
rate. Finally, the best-performing techniques presented in previous works are combined to form our method. The proposed method is included in an interactive approach to
transcribe handwritten text documents, which efficiently employs user interactions by means of active and semi-supervised learning techniques. Transcription results, in terms of
trade-off between user effort and transcription accuracy, are reported for two real handwritten documents, and prove the effectiveness of the proposed algorithm.

Key words:  computer-assisted annotation, handwriting recognition, user effort, balance, text transcription, error estimation