联机手写英文识别的解码算法

提出了一些新的方法来解决联机英文手写识别问题。基于手写英文的主笔画属性,提出了快速有效的解码算法——主笔画层次建立Beam Viterbi算法。由于整个识别过程是一个多阶段决策的过程,将多阶段的分类信息融合到决策过程中,较大幅度提高了系统的性能。在Unipen训练集和实验室数据集上测试取得了良好的效果。     

不规则数码脱机识别技术

在人类手写数码识别中，脱机不规则数码的识别是识别算法中比较难解决的问题．本文提出的一种识别方法，将笔道密度识别算法和层次特征识别算法相结合，对不规则数码脱机识别起到了十分有效的作用．在对0一9共10个数码，用多种方法手写，经扫描、二值化、平滑、边缘跟踪、压缩、细化等处理后，它的识别正确率在90％以上，达到了很好的效果．     

一种基于KNN算法的手写数字识别实现

KNN是比较成熟的分类算法,关于KNN手写数字识别的分类应用实战很多都是基于sklearn提供的手写数字识别数据集traningDigits。笔者结合KNN算法原理用Python实现其手写数字识别的算法过程,并支持用户用拍照、绘图软件手写数字,方法就是将图片处理成sklearn提供的数据集格式,然后作为测试样本应用在分类模型中进行预测,经过运行验证算法分类效果良好。     

改进YOLOv4的实验室设备检测算法

针对实验室设备的检测识别问题，提出一种改进YOLOv4算法。针对K-means聚类算法在尺度分布不均匀场景下的局限性，提出一种将数据集标注框按大小划分区间，分别聚类的IK-means++算法；在主干网络中引入通道注意力模块，提出一种阶梯状特征融合网格加强特征融合能力；以计算机实验室为例构建数据集进行训练。实验结果表明，IK-means++算法聚类效果得到有效提升；改进后的YOLOv4算法检测精度更高，模型复杂度更低，速度更快。     

基于PCA初始化卷积核的CNN手写数字识别算法

针对卷积神经网络对手写数字识别训练在卷积核随机初始化情况下收敛速度慢和识别率低的问题，提出一种主成分分析（PCA）初始化卷积核的卷积神经网络（CNN）手写数字识别算法。算法首先选取训练样本集并将其送入CNN，在相应层对Feature Map进行全覆盖取图像块处理，然后进行分层PCA学习，将学习到的特征向量做为对应卷积层的卷积核参数进行初始化，最后再用这些卷积核对原始图像进行卷积操作。实验结果表明，与随机初始化卷积核的CNN手写数字识别算法相比，改进的算法在应用MNIST数据库训练时不仅收敛，而且在产生相同均方误差的情况下迭代次数少，识别率高。     

基于改进遗传算法的神经网络手写体数字识别

BP网络作为人工神经网络的重要分支,已经广泛应用于手写数字识别。然而BP神经网络存在训练时间长、易陷入局部最小的问题。为了克服这些问题,提出了一种改进的遗传算法,并用该算法来优化神经网络的权值和阈值。最后,利用基于该算法的神经网络对大量USPS手写数字样本集进行训练。实验结果表明,该算法比单纯的BP算法具有更快的识别速率。     

基于多维特征和候选项的易混手写英文识别

针对手写英文识别中易混字符的识别问题,提出一种结合多维特征和候选项以区分易混字符的识别方法.利用卷积神经网络(convolutional neural networks,CNN)对手写英文字符进行识别,根据初始字符识别信息确定易混字符的类别;利用多维特征,设计针对不同类别易混字符的识别规则;由易混字符和其相连字符组成候选项单词,结合语料库以及字符间构成关系,最终对易混字符进行识别判断.实验结果表明,该方法在解决了易混字符的识别问题后,识别手写英文字符的平均准确率达到98.67％,具有一定应用价值.     

基于伪PCA的手写数字识别算法

PCA(Principal Component Analysis)是最重要的数据降维算法之一,针对降维过程出现的信息丢失问题,学术界说法不一。基于此,文中提出了一种新的改进算法(Similar Principal Component Analysis,SPCA), 新算法 在处理过程中保留了部分细节信息。以手写数字(MNIST)数据库为例,将原始向量组进行临近特征筛选,得出多维复合非正交特征向量组;将训练库所得的向量组与测试集的向量组进行比对,识别出所测试的手写数字。结果表明,该算法能够以较少量的训练样本实现对测试样本的较为完全的识别。     

基于质心高度增量特征的目标识别算法

针对传统目标识别算法识别准确率低、复杂度高等问题，提出基于质心高度增量特征的目标识别算法。在提取轮廓特征阶段，以轮廓质心为参考点，对于任意采样点，根据其它采样点相对于该点的高度关系构建质心高度增量描述符。描述符不仅计算简单，对旋转、平移和缩放等几何变换具有不变性，而且引入轮廓顺序这一全局特征，提升了描述符的鲁棒性和区分能力。在特征匹配阶段，利用轮廓顺序已知这一优势，采用动态规划算法计算质心高度增量描述符的相似度，最后引入形状复杂度分析，优化识别效果。MPEG-7测试集和Kimia99测试集的实验结果表明，上述算法能够有效的对目标图像进行匹配识别，而且对于噪声的干扰具良好的鲁棒性。     

基于统计和结构特征的手写数字识别研究

针对目前手写数字识别精度不高的问题,通过对手写数字图像的研究,提出了基于手写数字图像的空间、旋转、层次和结构特性的特征提取方法.该方法把手写数字的统计和结构特征结合起来,以特征提取方法为基础,利用LibSVM算法对手写数字特征进行了训练和识别.通过实验给出了各个参数的推荐值,利用推荐参数值,手写数字MNIST字体库的识别率高达99.3333％.实验结果表明了该算法在识别手写数字上的有效性和准确性.     

On-line recognition of Korean characters using ART neural network and hidden Markov model

This paper proposes an efficient method for on-line recognition of cursive Korean characters. The recognition of cursive strokes and the representation of a large character set are important determinants in the recognition rate of Korean characters. To deal with cursive strokes, we classify them automatically by using an ART-2 neural network. This neural network has the advantage of assembling similar patterns together to form classes in a self-organized manner. To deal with the large character set, we construct a character recognition model by using the hidden Markov model (HMM), which has the advantages of providing an explicit representation of time-varying vector sequence and probabilistic interpretation. Probabilistic parameters of the HMM are initialized using the combination rule for Korean characters and a set of primitive strokes that are classified by the ART stroke classifier, and trained with sample data. This is an efficient means of representing all the 11,172 possible Korean characters. We tested the model on 7500 on-line cursive Korean characters and it proved to perform well in recognition rate and speed.     

Binary segmentation algorithm for English cursive handwriting recognition

Segmentation in off-line cursive handwriting recognition is a process for extracting individual characters from handwritten words. It is one of the most difficult processes in handwriting recognition because characters are very often connected, slanted and overlapped. Handwritten characters differ in size and shape as well. Hybrid segmentation techniques, especially over-segmentation and validation, are a mainstream to solve the segmentation problem in cursive off-line handwriting recognition. However, the core weakness of the segmentation techniques in the literature is that they impose high risks of chain failure during an ordered validation process. This paper presents a novel Binary Segmentation Algorithm (BSA) that reduces the risks of the chain failure problems during validation and improves the segmentation accuracy. The binary segmentation algorithm is a hybrid segmentation technique and it consists of over-segmentation and validation modules. The main difference between BSA and other techniques in the literature is that BSA adopts an un-ordered segmentation strategy. The proposed algorithm has been evaluated on CEDAR benchmark database and the results of the experiments are very promising.     

英文手写联机识别的基础模型

为了识别较为工整的英文联机手写文字,定义了适合每个字母的字元,一共有七组不同的基本子元。使用简单的二维图形学,与简单的数学计算,可以确定每个不同字母的字元性质。使用这些字元,对大小写字母与数字实施具体组合定义,因为每个字符的具体定义内容,完全各不相同,依照逻辑可以推断,能够成功迅速的识别不连笔的较为工整的英文手写字符。这种建模方法,如果移植到类似的不同国家或地区的文字,如果笔画工整,每个字符又互相独立,那么在逻辑上就可以判定很有应用价值。     

Recognition-directed recovering of temporal information from handwriting images

This paper analyses a handwriting recognition system for offline cursive words based on HMMs. It compares two approaches for transforming offline handwriting available as two-dimensional images into one-dimensional input signals that can be processed by HMMs. In the first approach, a left–right scan of the word is performed resulting in a sequence of feature vectors. In the second approach, a more subtle process attempts to recover the temporal order of the strokes that form words as they were written. This is accomplished by a graph model that generates a set of paths, each path being a possible temporal order of the handwriting. The recognition process then selects the most likely temporal stroke order based on knowledge that has been acquired from a large set of handwriting samples for which the temporal information was available. We show experimentally that such an offline recognition system using the recovered temporal order can achieve recognition performances that are much better than those obtained with the simple left–right order, and that come close to those of an online recognition system. We have been able to assess the ordering quality of handwriting when comparing true ordering and recovered one, and we also analyze the situations where offline and online information differ and what the consequences are on the recognition performances. For these evaluations, we have used about 30,000 words from the IRONOFF database that features both the online signal and offline signal for each word.     

Fuzzy state machines to recognize totally unconstructed handwritten strokes

An automatic off-line character recognition system for totally unconstrained handwritten strokes is presented. A stroke representation is developed and described using five types of feature. Fuzzy state machines are defined to work as recognizers of strokes. An algorithm to obtain a deterministic fuzzy state machine from a stroke representation, that is capable of recognizing that stroke and its variants is presented. An algorithm is developed to merge two fuzzy state machines into one machine. The use of fuzzy machines to recognize strokes is clarified through a recognition algorithm. The learning algorithm is a complex of the previous algorithms. A set of 20 stroke classes was used in the learning and recognition stages. The system was trained on 5890 unnormalized strokes written by five writers. The learning stage produced a fuzzy state machine of 2705 states and 8640 arcs. A total of 6865 unnormalized strokes, written freely by five writers other than the writers of the learning stage, was used in testing. The recognition, rejection and error rates were 94.8%, 1.2% and 4.0%, respectively. The system can be more developed to deal with cursive handwriting.     

SEGMENTATION OF OFF-LINE CURSIVE HANDWRITING USING LINEAR PROGRAMMING

Segmentation of cursive words into letters has been one of the major problems in handwriting recognition. We introduce a new segmentation algorithm, guided in part by the global characteristics of the handwriting. We find the successive segmentation points by evaluating a cost function at each point along the baseline. The cost of segmenting at a point is a weighted sum of four feature values at that point. The weights of the features are determined using linear programming.In our tests with 750 words written by 10 writers, 97% of the letter boundaries were correctly located.     

Augmenting the Discrimination Power of HMM by NN for On-Line Cursive Script Recognition

For on-line handwriting recognition, a hybrid approach that combines the discrimination power of neural networks with the temporal structure of hidden Markov models is presented. Initially, all plausible letter components of an input pattern are detected by using a letter spotting technique based on hidden Markov models. A word hypothesis lattice is generated as a result of the letter spotting. All letter hypotheses in the lattice are evaluated by a neural network character recognizer in order to reinforce letter discrimination power. Then, as a new technique, an island-driven lattice search algorithm is performed to find the optimal path on the word hypothesis lattice which corresponds to the most probable word among the dictionary words. The results of this experiment suggest that the proposed framework works effectively in recognizing English cursive words. In a word recognition test, on average 88.5% word accuracy was obtained.     

Combining shape and physical modelsfor online cursive handwriting synthesis

This paper proposes a novel learning-based approach to synthesizing cursive handwriting of a user's personal handwriting style by combining shape and physical models. In the training process, some sample paragraphs written by a user are collected and these cursive handwriting samples are segmented into individual characters by using a two-level writer-independent segmentation algorithm. Samples for each letter are then aligned and trained using shape models. In the synthesis process, a delta log-normal model based conditional sampling algorithm is proposed to produce smooth and natural cursive handwriting of the user's style from models. Received: 26 April 2003, Accepted: 27 September 2004, Published online: 29 November 2004 Correspondence to: Jue Wang Jue Wang and Chenyu Wu completed this work while interns at Microsoft Research Asia.