Integration of structural and statistical information for unconstrained handwritten numeral recognition
Integration of structural and statistical information for unconstrained handwritten numeral recognition
复制标题
DOI：
10.1109/34.754622
复制
发表时间：
1999-03-01
影响因子：
23.6
通讯作者：
Liu, ZQ
中科院分区：
文献类型：
--
作者：
Cai, JH;Liu, ZQ
本文提出了一种结合统计信息和结构信息的无约束手写体数字识别方法。该方法利用状态持续时间自适应转移概率改进了传统hmm中状态持续时间的建模，并利用宏观状态克服了hmm建模模式结构的困难。该方法在许多方面都优于传统方法。在统计模型和结构模型中，方向被编码到离散码本中，位置的分布由联合高斯分布函数建模。实验结果表明，该方法在速度和精度方面都取得了较高的性能。
In this paper, we propose an approach that integrates the statistical and structural information for unconstrained handwritten numeral recognition. This approach uses state-duration adapted transition probability to improve the modeling of state-duration in conventional HMMs and uses macro-states to overcome the difficulty in modeling pattern structures by HMMs. The proposed method is superior to conventional approaches in many aspects. in the statistical and structural models, the orientations are encoded into discrete codebooks and the distributions of locations are modeled by joint Gaussian distribution functions. The experimental results show that the proposed approach can achieve high performance in terms of speed and accuracy.