Character confidence based on N-best list for keyword spotting in online Chinese handwritten documents

In keyword spotting from handwritten documents by text query, the word similarity is usually computed by combining character similarities, which are desired to approximate the logarithm of the character probabilities. In this paper, we propose to directly estimate the posterior probability (also called confidence) of candidate characters based on the N-best paths from the candidate segmentation-recognition lattice. On evaluating the candidate segmentation-recognition paths by combining multiple contexts, the scores of the N-best paths are transformed to posterior probabilities using soft-max. The parameter of soft-max (confidence parameter) is estimated from the character confusion network, which is constructed by aligning different paths using a string matching algorithm. The posterior probability of a candidate character is the summation of the probabilities of the paths that pass through the candidate character. We compare the proposed posterior probability estimation method with some reference methods including the word confidence measure and the text line recognition method. Experimental results of keyword spotting on a large database CASIA-OLHWDB of unconstrained online Chinese handwriting demonstrate the effectiveness of the proposed method.     

基于CNN图像识别与语义可靠性的路径搜索方法

光学字符识别技术可有效提高票据应用中票据信息录入的工作效率。针对票据的复杂背景与不规范手写字符降低票据识别准确率的问题,结合卷积神经网络图像识别与语义可靠性,提出一种可靠性优先的路径搜索方法,以降低模糊字符对搜索路径的干扰。利用基于公司名结构特点的前后缀推断策略,有效解决公司名前后缀识别错误问题。采用结巴中文分词与字符位置信息检查识别结果中的错误,并将长短期记忆语言模型与在传统字形相似度基础上引入的汉字部件相似度相结合进行纠错。实验结果表明,通过将纠错策略与该方法相结合可有效提高公司名识别准确率至93.08%。     

Writer adaptation via deeply learned features for online Chinese handwriting recognition

This paper proposes a novel framework of writer adaptation based on deeply learned features for online handwritten Chinese character recognition. Our motivation is to further boost the state-of-the-art deep learning-based recognizer by using writer adaptation techniques. First, to perform an effective and flexible writer adaptation, we propose a tandem architecture design for the feature extraction and classification. Specifically, a deep neural network (DNN) or convolutional neural network (CNN) is adopted to extract the deeply learned features which are used to build a discriminatively trained prototype-based classifier initialized by Linde–Buzo–Gray clustering techniques. In this way, the feature extractor can fully utilize the useful information of a DNN or CNN. Meanwhile, the prototype-based classifier could be designed more compact and efficient as a practical solution. Second, the writer adaption is performed via a linear transformation of the deeply learned features which is optimized with a sample separation margin-based minimum classification error criterion. Furthermore, we improve the generalization capability of the previously proposed discriminative linear regression approach for writer adaptation by using the linear interpolation of two transformations and adaptation data perturbation. The experiments on the tasks of both the CASIA-OLHWDB benchmark and an in-house corpus with a vocabulary of 20,936 characters demonstrate the effectiveness of our proposed approach.     

Building efficient CNN architecture for offline handwritten Chinese character recognition

Deep convolutional neural networks-based methods have brought great breakthrough in image classification, which provides an end-to-end solution for handwritten Chinese character recognition (HCCR) problem through learning discriminative features automatically. Nevertheless, state-of-the-art CNNs appear to incur huge computational cost and require the storage of a large number of parameters especially in fully connected layers, which is difficult to deploy such networks into alternative hardware devices with limited computation capacity. To solve the storage problem, we propose a novel technique called weighted average pooling for reducing the parameters in fully connected layer without loss in accuracy. Besides, we implement a cascaded model in single CNN by adding mid output to complete recognition as early as possible, which reduces average inference time significantly. Experiments are performed on the ICDAR-2013 offline HCCR dataset. It is found that our proposed approach only needs 6.9 ms for classifying a character image on average and achieves the state-of-the-art accuracy of 97.1% while requires only 3.3 MB for storage.     

Learning confidence transformation for handwritten Chinese text recognition

Handwritten text recognition systems commonly combine character classification confidence scores and context models for evaluating candidate segmentation-recognition paths, and the classification confidence is usually optimized at character level. In this paper, we investigate into different confidence-learning methods for handwritten Chinese text recognition and propose a string-level confidence-learning method, which estimates confidence parameters by directly optimizing the performance of character string recognition. We first compare the performances of parametric (class-dependent and class-independent parameters) and nonparametric (isotonic regression) confidence-learning methods. Then, we propose two regularized confidence estimation methods and particularly, a string-level confidence-learning method under the minimum classification error criterion. In experiments of online handwritten Chinese text recognition, the string-level confidence-learning method is shown to effectively improve the string recognition performance. Using three character classifiers, the character correct rates are improved from 92.39, 90.24 and 88.69 % to 92.76, 90.91 and 89.93 %, respectively.     

Improving discrimination ability of convolutional neural networks by hybrid learning

The discrimination of similar patterns is important because they are the major sources of the classification error. This paper proposes a novel method to improve the discrimination ability of convolutional neural networks (CNNs) by hybrid learning. The proposed method embeds a collection of discriminators as well as a recognizer in a shared CNN. By visualizing contrastive class saliency, we show that learning with embedded discriminators leads the shared CNN to detect and catch the differences among similar classes. Also proposed is a hybrid learning algorithm that learns recognition and discrimination together. The proposed method learns recognition focusing on the differences among similar classes, and thereby improves the discrimination ability of the CNN. Unlike conventional discrimination methods, the proposed method does not require predefined sets of similar classes or additional step to integrate its result with that of the recognizer. In experiments on two handwritten Hangul databases SERI95a and PE92, the proposed method reduced classification error from 2.56 to 2.33, and from 4.04 to 3.66 % respectively. These improvement lead to relative error reduction rates of 8.97 % on SERI95a, and 9.42 % on PE92. Our best results update the state-of-the-art performance which were 4.04 % on SERI95a and 7.08 % on PE92.     

Recognition of handwritten Chinese characters by critical region analysis

The problem of recognizing offline handwritten Chinese characters has been investigated extensively. One difficulty is due to the existence of characters with very similar shapes. In this paper, we propose a “critical region analysis” technique which highlights the critical regions that distinguish one character from another similar character. The critical regions are identified automatically based on the output of the Fisher's discriminant. Additional features are extracted from these regions and contribute to the recognition process. By incorporating this technique into the character recognition system, a record high recognition rate of 99.53% on the ETL-9B database is obtained.     

Scene word recognition from pieces to whole

Convolutional neural networks (CNNs) have had great success with regard to the object classification problem. For character classification, we found that training and testing using accurately segmented character regions with CNNs resulted in higher accuracy than when roughly segmented regions were used. Therefore, we expect to extract complete character regions from scene images. Text in natural scene images has an obvious contrast with its attachments. Many methods attempt to extract characters through different segmentation techniques. However, for blurred, occluded, and complex background cases, those methods may result in adjoined or over segmented characters. In this paper, we propose a scene word recognition model that integrates words from small pieces to entire after-cluster-based segmentation. The segmented connected components are classified as four types: background, individual character proposals, adjoined characters, and stroke proposals. Individual character proposals are directly inputted to a CNN that is trained using accurately segmented character images. The sliding window strategy is applied to adjoined character regions. Stroke proposals are considered as fragments of entire characters whose locations are estimated by a stroke spatial distribution system. Then, the estimated characters from adjoined characters and stroke proposals are classified by a CNN that is trained on roughly segmented character images. Finally, a lexicondriven integration method is performed to obtain the final word recognition results. Compared to other word recognition methods, our method achieves a comparable performance on Street View Text and the ICDAR 2003 and ICDAR 2013 benchmark databases. Moreover, our method can deal with recognizing text images of occlusion and improperly segmented text images.     

复杂背景图像的字符识别算法研究

为了解决字符识别过程中的局部曝光、印刷字符的断裂以及变形和自然环境下的背景污染等问题, 提出了一种分块处理与卷积神经网络(CNN)相结合的字符图像识别算法. 首先利用OpenCV机器视觉库, 结合分块处理、伽马运算、参数调整等方法对产品零件表面印刷字符进行预处理, 初步解决图像局部曝光和字符断裂问题; 其次为了获得单个字符图像, 利用数学形态学算法对局部曝光处理后的二值化图像进行分步分割, 进而去掉字符间的无用信息; 最后利用Keras模块为字符识别提供的API搭建CNN模型, 经过对100多张字符的识别训练, 准确率高达96.9%, 为某汽车零部件自动化生产中的字符识别提供了可靠的依据.     

Discrimination of similar characters using nonlinear normalization based on regional importance measure

Discrimination of confusing characters is very important in recognition of character sets containing a multitude of similar characters. Confusing characters have very similar shapes and are separated by only a small difference. For a successful discrimination, we need to focus on that difference. However, the small difference can be reduced or even lost during the feature extraction process. In such a case, further analysis after the feature extraction rarely succeeds. This paper proposes a discriminative nonlinear normalization algorithm to improve discrimination ability. The proposed method emphasizes the difference between confusing characters. It measures the importance of each region in the discrimination of confusing characters. Then, it resamples the image according to the regional importance measure. As a result, it expands important regions but shrinks less important regions. Since it emphasizes important regions in the preprocessing step, it does not suffer from the information loss during the feature extraction. In experiments, the proposed method successfully detected and expanded important regions. In handwritten Hangul recognition, the proposed method outperformed other two recently developed pair-wise discrimination methods. On SERI95a data set, it improved the recognition rate from 87.69 to 90.11 %, achieving a 19.66 % error reduction rate.     

结合余弦相关性的卷积网络识别汉字的方法

为了提高卷积神经网络（Convolution Neural Network,CNN）的识别率,增强卷积网络的特征提取能力,使其在模糊、光照不均等恶劣条件下能够有更好的识别效果,因此提出将余弦相关性加入神经卷积网络作为相似度度量的方法。较传统神经卷积网络相比较,有着更强的模式检测能力、更快的收敛速度以及更高的准确率的优点。在卷积神经网络的卷积层加入余弦相似性度量,最后通过对比传统神经卷积网络方法和余弦相关性神经卷积网络在脱机手写汉字的识别实验,在进行20次实验后,得出了在相同训练参数以及相同层数的卷积神经网络上,基于余弦相关性的神经卷积网络在手写汉字数据集上的准确率比传统的神经卷积网络的识别率平均提高了2.01%,并且有着更快的收敛速度。最后通过与现今流行的算法在MNIST数据集上的实验进行准确度、损失函数、时间复杂度的比较,得出结合余弦的卷积神经网络在准确度和损失函数上有一定的优势性,在时间复杂度上还需进一步提高。     

混合神经网络模型与注意力机制的地址匹配算法

中文地名地址的标准化在当前智慧城市的建设中起到至关重要的作用。传统的地名地址标准化技术通常使用基于文本字符层面的相似度计算或规则库匹配的方法,对复杂、特殊或冗余地址的处理效果较差。通过将地址标准化任务转换为针对地址相似的匹配度计算任务,提出了一种融合注意力机制与多层次语义表征的地址匹配算法。首先依据地址文本特殊的语法结构,利用Trie语法树构建标准地址树;而后基于注意力机制,利用Bi-LSTM网络与CNN网络生成地址对的多层次语义表示;最后通过曼哈顿距离计算相似度。在自主构建的数据集上,提出的SGAM模型的匹配准确度（91.22%）相比TextRCNN、FastText、基于注意力的卷积神经网络（ABCNN）等模型提升了4%~10%,表明SGAM模型在地址匹配任务上有着更好的性能表现。     

基于卷积神经网络的车牌字符识别

车牌字符识别是智能车牌识别系统中的重要组成部分。针对车牌字符类别多、背景复杂影响正确识别率的问题,提出了一种基于卷积神经网络（CNN）的车牌字符识别方法。首先对车牌字符图像进行大小归一化、去噪、二值化、细化、字符区域居中等预处理,去除复杂背景,得到简单的字符形状结构;然后,利用所提出的CNN模型对预处理后的车牌字符集进行训练、识别。实验结果表明,所提方法能够达到99.96%的正确识别率,优于其他三种对比方法。说明所提出的CNN方法对车牌字符具有很好的识别性能,能满足实际应用需求。     

基于多重规则和路径评价的在线中英文手写识别方法

手写文本识别方法主要应用于文本输入技术,对人机交互领域的发展起关键作用。针对多数在线输入法无法识别中英文混合手写识别的问题,提出一种在线中英文混合手写文本识别方法。通过对文本笔画进行基于水平相对位置、垂直重叠率、面积重叠率规则的整合以及连笔切分,得到一系列字符片段,同时利用笔画个数、宽高比、中心偏离、平滑度等几何特征和识别置信度,对字符片段进行中英文分类。在此基础上,根据分类结果并结合自然语言模型的路径评价及动态规划搜索算法,分别对候选的中、英文字符片段进行合并处理,得到待识别的中、英文字符序列,并将其分别送入卷积神经网络的中、英文识别模型中,得到手写文本识别结果。实验结果表明,在线手写中英文混合文本识别正确率达93.67%,不仅能切分在线手写中文文本行,而且对包含字符连笔的在线手写中英文文本行也有较好的切分效果。     

基于二维主成分分析与卷积神经网络的手写体汉字识别

随着计算能力的飞速增长、训练数据的不断积累以及非线性激活函数的不断完善,卷积神经网络（CNN）在手写体汉字识别中表现出较好的识别性能。针对CNN识别手写体汉字识别速度慢的问题,将二维主成分分析（2DPCA）与CNN相结合识别手写体汉字。首先,利用2DPCA提取手写体汉字的投影特征向量;然后,将得到的投影特征向量组成特征矩阵;其次,用组成的特征矩阵作为CNN的输入;最后,用Softmax函数进行分类。与基于AlexNet的CNN模型相比,所提方法的运行时间降低了78%,与基于ACNN与DCNN的模型相比,所提方法的运行时间分别降低了80%与73%。实验结果表明,该方法在不降低识别精度的同时,可以减少识别手写体汉字的运行时间。     

基于模板匹配和局部HOG特征的车牌识别算法

针对车牌字符识别中模板匹配法识别率低,尤其是无法准确识别相似字符的不足,本文提出了一种模板匹配法结合局部HOG特征的车牌识别算法.首先利用模板匹配法对车牌所有字符进行初步识别,然后分别提取车牌和模板相似字符中最具区分度的一小块HOG特征进而构建特征向量,最后根据特征向量之间的欧氏距离来度量车牌字符和模板字符的相似性,进而完成二次识别.实验结果表明,本文方法有效地解决了相似字符误识别的问题,在保证识别速率的同时识别率显著提高.     

一种相似汉字的识别算法

本文提出了一种通用的基于部分空间方法的相似汉字识别算法, 该算法无须事先确定相似字组, 也不必人工选择各个相似字组的部分空间, 能够自动决定待识别字是否需要进入相似字识别过程, 以及怎样选择部分空间。实验结果证明了本算法的有效性。     

Recognition of Bangla compound characters using structural decomposition

In this paper we propose a novel character recognition method for Bangla compound characters. Accurate recognition of compound characters is a difficult problem due to their complex shapes. Our strategy is to decompose a compound character into skeletal segments. The compound character is then recognized by extracting the convex shape primitives and using a template matching scheme. The novelty of our approach lies in the formulation of appropriate rules of character decomposition for segmenting the character skeleton into stroke segments and then grouping them for extraction of meaningful shape components. Our technique is applicable to both printed and handwritten characters. The proposed method performs well for complex-shaped compound characters, which were confusing to the existing methods.     

A hybrid method for robust car plate character recognition

Image-based car plate recognition is an indispensable part of an intelligent traffic system. The quality of the images taken for car plates, especially for Chinese car plates, however, may sometimes be very poor, due to the operating conditions and distortion because of poor photographical environments. Furthermore, there exist some “similar” characters, such as “8” and “B”, “7” and “T” and so on. They are less distinguishable because of noises and/or distortions. To achieve robust and high recognition performance, in this paper, a two-stage hybrid recognition system combining statistical and structural recognition methods is proposed. Car plate images are skew corrected and normalized before recognition. In the first stage, four statistical sub-classifiers recognize the input character independently, and the recognition results are combined using the Bayes method. If the output of the first stage contains characters that belong to prescribed sets of similarity characters, structure recognition method is used to further classify these character images: they are preprocessed once more, structure features are obtained from them and these structure features are fed into a decision tree classifier. Finally, genetic algorithm is employed to achieve optimum system parameters. Experiments show that our recognition system is very efficient and robust. As part of an intelligent traffic system, the system has been in successful commercial use.     

基于不对称性的相似汉字识别方法

相似字识别的正确与否对整个识别系统的准确性和可用性都有着极大的影响。在实际应用中,我们发现相似汉字之间的误识存在不对称性,并对这种不对称现象的成因进行了细致的探讨和分析。基于这种不对称性,本文提出了一种分类的部分空间方法来解决相似字的识别问题。相似字按其结构特点被分成若干基本类别,不同类别在相应的部分空间提取不同的特征进行比较,以达到正确识别相似字的目的。实验结果表明了本方法的有效性,相似字识别的准确性得到了很大的提高,其中易错相似字的识别正确率平均提高了4.55个百分点,不易错相似字的识别正确率平均提高了0.38个百分点。