基于最大-最小相似度学习方法的文本提取

Text Extraction Based on Maximum-Minimum Similarity Training Method

应用最大-最小相似度(maximum-minimum similarity,简称MMS)学习方法,对基于高斯混合模型的文本区域提取方法中的有关参数进行优化.该学习方法通过最大化正样本相似度和最小化反样本相似度获得最佳分类能力.根据这种判别学习思想,建立了相应的目标函数,并利用最速梯度下降法寻找目标函数最小值,以得到文本区域提取方法的最优参数集合.文本区域提取实验结果表明:在用期望最大化(expectation maximization,简称EM)算法获得参数的极大似然估计值后,使用最大-最小相似度学习方法,使文本提取综合性能明显提高,开放实验的召回率和准确率分别达到98.55%和93.56%.在实验中,最大-最小相似度学习方法的表现还优于常用的判别学习方法——最小分类错误(minimum classification error,简称MCE)学习方法.

This paper proposes a maximum-minimum similarity training algorithm to optimize the parameters in the effective method of text extraction based on Gaussian mixture modeling of neighbor characters. The maximum-minimum similarity training （MMS） methods optimize recognizer performance through maximizing the similarities of positive samples and minimizing the similarities of negative samples. Based on this approach to discriminative training, it defines the objective function for text extraction, and uses the gradient descent method to search the minimum of the objective function and the optimum parameters for the text extraction method. The experimental results of text extraction show the effectiveness of MMS training in text extraction, Compared with the maximum likelihood estimation of parameters from expectation maximization （EM） algorithm, the training results after MMS has the performance of text extraction improved greatly. The recall rate of 98.55% and the precision rate of 93.56% are achieved. The experimental results also show that the maximum-minimum similarity （MMS） training behaves better than the commonly used discriminative training of the minimum classification error （MCE）.