马杰,张小美,苑焕朝.基于并行分离增广拉格朗日乘子法的字符矫正[J].光电子激光,2015,26(6):1170~1178 |
基于并行分离增广拉格朗日乘子法的字符矫正 |
Character rectification method based on augmented Lagrange multiplier using parallel splitting |
投稿时间:2014-12-31 |
DOI: |
中文关键词: 字符矫正 凸优化 增广拉格朗日乘子法(ALM) 并行分离 |
英文关键词:character rectification convex optimization augmented Lagrangian multiplier (A LM) method parallel splitting |
基金项目:国家自然科学基金(61203245)和河北省自然基金(F2012202027)资助项目 (河北工业大学 电子信息工程学院,天津 300400) |
|
摘要点击次数: 1236 |
全文下载次数: 0 |
中文摘要: |
字符矫正是光学字符识别(OCR)系统预处理过程中 的重要步骤,针对传统的增广拉格朗日乘子法(ALM)求解字符矫正问题时收敛性和计算速度 的不足,本文研究了并行分离的增广拉格朗日乘子法,综合考虑字符矫正模型的建立过程, 提出并行分离方法与ALM相结合的思想解决字符 矫正问题。用并行方式将迭代问题分解成3个子问题,计算时能够同时求解分解后的这3个 子问题,然后进行凸组合,最 后收敛到问题的最优解。实验结果表明,本文算法能够快速准确地对变形的字符图像进 行矫正,并且具有良好的实时性和适 应性,可用于OCR系统的矫正预处理中,提高OCR系统的识别率。 |
英文摘要: |
Character modification is an important step in the preprocessing of optical char acter recognition (OCR) system,which determines the OCR performance.Classic augmented Lagrangian multiplier (ALM) method is still insufficient to solve low rank character image.For the lack of convergence and computation rate of traditional augmented Lagrangian multiplier method,thi s paper proposes a new parallel splitting augmented Lagrangian multiplier method (PSALM),which combine s the parallel separation method with the ALM algorithm.The optimal solution of the original problem can b e attained using three iterated sub problems.Experimental results show that parallel splitting ALM can correct the distorted character image efficiently and accurately and has sufficient adaptability and real-time abilit y,which can be used for the preprocessing of OCR system to improve OCR performan ce. |
查看全文 下载PDF阅读器 |
关闭 |
|
|
|
|
|