An on-line free handwritten Chinese character recognition method based on component cascaded HMMs

This paper presents a cascaded Hidden Markov Model （HMM）, which allows state＇s transition, skip and duration. The cascaded HMM extends the way of HMM pattern description of Handwritten Chinese Character （HCC） and depicts the behavior of handwritten curve more reliably in terms of the statistic probability. Hence character segmentation and labeling are unnecessary. Viterbi algorithm is integrated in the cascaded HMM after the whole sample sequence of a HCC is input. More than 26,000 component samples are used tor training 407 handwritten component HMMs. At the improved training stage 94 models of 94 Chinese characters are gained by 32,000 samples, Compared with the Segment HMMs approach, the recognition rate of this model tier the tirst candidate is 87.89% and the error rate could be reduced by 12.4%.

Structural recognition of ancient Chinese ideographic characters

Ancient Chinese characters, typically the ideographic characters on bones and bronze before Shang Dynasty(16th—11th century B.C.), are valuable culture legacy of history. However the recognition of Ancient Chinese characters has been the task of paleography experts for long. With the help of modern computer technique, everyone can expect to be able to recognize the characters and understand the ancient inscriptions. This research is aimed to help people recognize and understand those ancient Chinese characters by combining Chinese paleography theory and computer information processing technology. Based on the analysis of ancient character features, a method for structural character recognition is proposed. The important characteristics of strokes and basic components or radicals used in recognition are introduced in detail. A system was implemented based on above method to show the effectiveness of the method.

Data Pre－processing and Stroke Segment Extraction for On－line Handwritten Chinese Character Recognition

The stroke segments:' are proposed to be used as the basic features for handwritten Chinese character recognition. In this way, it is possible to overcome the difFiculties of unstable stroke information caused by stroke Joinings. The techniques of data pre-processing and stroke segment extraction have been described. In extracting stroke segment, not only the characteristics of the stroke itself, but also its absolute positions as well as relative positions with other strokes in the character have been taken into account.The primitive features for recognition were extracted under these comprehensive considerations.

Research on Handwritten Chinese Character Recognition Based on BP Neural Network

The application of pattern recognition technology enables us to solve various human-computer interaction problems that were difficult to solve before.Handwritten Chinese character recognition,as a hot research object in image pattern recognition,has many applications in people’s daily life,and more and more scholars are beginning to study off-line handwritten Chinese character recognition.This paper mainly studies the recognition of handwritten Chinese characters by BP(Back Propagation)neural network.Establish a handwritten Chinese character recognition model based on BP neural network,and then verify the accuracy and feasibility of the neural network through GUI(Graphical User Interface)model established by Matlab.This paper mainly includes the following aspects:Firstly,the preprocessing process of handwritten Chinese character recognition in this paper is analyzed.Among them,image preprocessing mainly includes six processes:graying,binarization,smoothing and denoising,character segmentation,histogram equalization and normalization.Secondly,through the comparative selection of feature extraction methods for handwritten Chinese characters,and through the comparative analysis of the results of three different feature extraction methods,the most suitable feature extraction method for this paper is found.Finally,it is the application of BP neural network in handwritten Chinese character recognition.The establishment,training process and parameter selection of BP neural network are described in detail.The simulation software platform chosen in this paper is Matlab,and the sample images are used to train BP neural network to verify the feasibility of Chinese character recognition.Design the GUI interface of human-computer interaction based on Matlab,show the process and results of handwritten Chinese character recognition,and analyze the experimental results.

Information Moment for Chinese Character Recognition

Moment invariants firstly introduced by M. K Hu in 1962, has some shortcomings. After counting a large number of statistical distribution information of Chinese characters,the authors put forward the concept of information moments and demonstrate its invariance to translation,rotation and scaling.Also they perform the experiment in which information moments compared with moment invaiants for the effects of similar Chinese characters and font recognition.At last they show the recognition rate of 88% by information moments,with 70% by moment inariants.

A New Method for Chinese Character Strokes Recognition

In this paper, the problem of stroke recognition has been studied, and the strategies and the algorithms related to the problem are proposed or developed. Based on studying some current methods for Chinese characters strokes recognition, a new method called combining trial is presented. The analysis and results of experiments showed that the method has the advantage of high degree of steadiness.

A Novel 6G Scalable Blockchain Clustering-Based Computer Vision Character Detection for Mobile Images

6G is envisioned as the next generation of wireless communication technology,promising unprecedented data speeds,ultra-low Latency,and ubiquitous Connectivity.In tandem with these advancements,blockchain technology is leveraged to enhance computer vision applications’security,trustworthiness,and transparency.With the widespread use of mobile devices equipped with cameras,the ability to capture and recognize Chinese characters in natural scenes has become increasingly important.Blockchain can facilitate privacy-preserving mechanisms in applications where privacy is paramount,such as facial recognition or personal healthcare monitoring.Users can control their visual data and grant or revoke access as needed.Recognizing Chinese characters from images can provide convenience in various aspects of people’s lives.However,traditional Chinese character text recognition methods often need higher accuracy,leading to recognition failures or incorrect character identification.In contrast,computer vision technologies have significantly improved image recognition accuracy.This paper proposed a Secure end-to-end recognition system(SE2ERS)for Chinese characters in natural scenes based on convolutional neural networks(CNN)using 6G technology.The proposed SE2ERS model uses the Weighted Hyperbolic Curve Cryptograph(WHCC)of the secure data transmission in the 6G network with the blockchain model.The data transmission within the computer vision system,with a 6G gradient directional histogram(GDH),is employed for character estimation.With the deployment of WHCC and GDH in the constructed SE2ERS model,secure communication is achieved for the data transmission with the 6G network.The proposed SE2ERS compares the performance of traditional Chinese text recognition methods and data transmission environment with 6G communication.Experimental results demonstrate that SE2ERS achieves an average recognition accuracy of 88%for simple Chinese characters,compared to 81.2%with traditional methods.For complex Chinese characters,the average recognition accuracy improves to 84.4%with our system,compared to 72.8%with traditional methods.Additionally,deploying the WHCC model improves data security with the increased data encryption rate complexity of∼12&higher than the traditional techniques.

A 4-Corner Codes Classifier Based on Decision Tree Inductive Learning for Handwritten Chinese Characters

The classification for handwritten Chinese character recognition can be viewed as a transformation in discrete vector space. In this paper, from the point of discrete vector space transformation, a new 4-corner codes classifier based on decision tree inductive learning algorithm ID3 for handwritten Chinese characters is presented. With a feature extraction controller, the classifier can reduce the number of extracted features and accelerate classification speed. Experimental results show that the 4-corner codes classifier performs well on both recognition accuracy and speed.

A Review of Research on Handwritten Chinese Character Recognition with Multi-Feature Fusion

This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chinese character recognition is pointed out,including its numerous categories,complex structure,and the problem of similar characters,especially the variability of handwritten Chinese characters.Subsequently,recognition methods based on feature optimization,model optimization,and fusion techniques are highlighted.The fusion studies between feature optimization and model improvement are further explored,and these studies further enhance the recognition effect through complementary advantages.Finally,the article summarizes the current challenges of Chinese character recognition technology,including accuracy improvement,model complexity,and real-time problems,and looks forward to future research directions.

An integration approach to handwritten Chinese character recognition system

A network integration method suitable for Chinese character recognition which combines traditional statistical method and artificial neural network is proposed to deal with the problems in machine recognition of handwritten Chinese characters which have the properties of large vocabulary, complex structure, lots of similar characters and variations of character shape due to handwriting. Four different classifiers for handwritten Chinese character recognition are integrated by the proposed method. The experimental results show that the method has a fast learning speed as well as high accuracy and can greatly improve the system performance.

Parallel compact integration in handwritten Chinese character recognition

In this paper, a new parallel compact integration scheme based on multi-layer perceptron (MLP) networks is proposed to solve handwritten Chinese character recognition (HCCR) problems. The idea of metasynthesis is applied to HCCR, and compact MLP network classifier is defined. Human intelligence and computer capabilities are combined together effectively through a procedure of two-step supervised learning. Compared with previous integration schemes, this scheme is characterized with parallel compact structure and better performance. It provides a promising way for applying MLP to large vocabulary classification.

AN AUTOMATIC PRINTED CHINESE CHARACTER RECOGNITION SYSTEM ON MICROCOMPUTER

Based on the feature-point method of recognizing printed Chinses characters, anautomatic printed Chinese character recognition system on microcomputers is proposed. It isan entire system including layout decision, text recognition and post-editing processing.Experiments on 2 million Chinese characters indicate that this system is able to recognizeprinted Chinese characters on books, magazines and documents at a speed of 20 charachersper second on 20 MHz COMPAQ 386 and with a correct recognition rate above 95%.

PRINTED CHINESE CHARACTER RECOGNITION USING POINT TRACKING INCLUSIVE MATCHING METHOD WITH BACKTRACKING STRATEGY

On the basis of the inclusive matching method, double inclusive matching method and point tracking inclusive matching method, a new method of Chinese character recognition has been presented: point tracking inclusive matching method with backtracking control strategies. In the inclusive matching method, the attribute of character depends on the inclusive rate which describes whether the standard lexigraphy is included in an input character; the point tracking inclusive matching method can speed up the procedure of recognition and reduce the memory room occupied by the standard lexigraphy. In order to suit the large number and the complex forms of Chinese characters, and in order to avoid random noise and interference of input, the backtracking control strategy is introduced into the point tracking inclusive matching method. Using this strategy, the simple branch relative tree can be expanded to the multi-branch relative tree, and several paths for matching characters are opened up. Once matching along one path of the multi-branch tree succeeds, the character is recognized. The result of an experiment in recognizing printed multi-typeface Chinese characters shows this method has a rather strong adaptability.

Processing Chinese hand-radicals activates the medial frontal gyrus A functional MRI investigation

Embodied semantics theory asserts that the meaning of action-related words is neurally represented through networks that overlap with or are identical to networks involved in sensory-motor processing. While some studies supporting this theory have focused on Chinese characters, less attention has been paid to their semantic radicals. Indeed, there is still disagreement about whether these radicals are processed independently. The present study investigated whether radicals are processed separately and, if so, whether this processing occurs in sensory-motor regions. Materials consisted of 72 high-frequency Chinese characters, with 18 in each of four categories： hand-action verbs with and without hand-radicals, and verbs not related to hand actions, with and without hand-radicals. Twenty-eight participants underwent functional MRI scans while reading the characters. Compared to characters without hand-radicals, reading characters with hand-radicals activated the right medial frontal gyrus. Verbs involving hand-action activated the left inferior parietal lobule, possibly reflecting integration of information in the radical with the semantic meaning of the verb. The findings may be consistent with embodied semantics theory and suggest that neural representation of radicals is indispensable in processing Chinese characters.

A New Linguistic Decoding Method for Online Handwritten Chinese Character Recognition

This paper presents a new linguistic decoding method for online handwritten Chinese character recognition. The method employs a hybrid language model which combines N-gram and linguistic rules by rule quantification technique. The linguistic decoding algorithm consists of three stages: word lattice construction, the optimal sentence hypothesis search and self-adaptive learning mechanism. The technique has been applied to palmtop computer's online handwritten Chinese character recognition. Samples containing millions of characters were used to test the linguistic decoder. In the open experiment, accuracy rate up to 92% is achieved, and the error rate is reduced by 68%.

2-D EAG Method for the Recognition of Hand-Printed Chinese Characters

A method, called Two-Dimensional Extended Attribute Grammars (2-DEAGs). for the recognition of hand-printed Chinese characters is presented. This method uses directly two dimensional information, and pro- vides a scheme for dealing with various kinds of specific cases in a uniform way. In this method, components are drawn in guided and redundant way and reductions are made level by level just in accordance with the com- ponent combination relations of Chinese characters. The method provides also polysemous grammars, coexisting grammars and structure inferrings which constrain redundant recognition by comparison among similar characters or components and greatly increase the tolerance ability to distortion.

基于Swin Transformer和CNN的汉字书法教学系统

针对日益增长的汉字书法学习需求,将滑动窗口自注意力(Swin Transformer,ST)模型和卷积神经网络(Convolutional Neural Network,CNN)模型相结合,提出手写体汉字识别ST-CNN模型,进而开发了汉字书法教学系统。实测结果表明,ST-CNN模型识别准确率约为91.6%,较传统的ST模型提升了约0.5个百分点,较传统的CNN模型与ST模型,在收敛速度上分别提升了约10和30个百分点,开发的汉字书法教学系统性能良好。

基于多头注意力机制字词联合的中文命名实体识别

针对现有基于字词联合的中文命名实体识别方法会引入冗余词汇干扰、模型网络结构复杂、难以迁移的问题,提出一种基于多头注意力机制字词联合的中文命名实体识别算法.算法采用多头注意力机制融合词汇边界信息,并通过分类融合BIE词集降低冗余词汇干扰.建立了多头注意力字词联合模型,包含字词匹配、多头注意力、融合等模块.与现有中文命名实体识别方法相比,本算法避免了设计复杂的序列模型,方便与现有基于字的中文命名实体识别模型结合.采用召回率、精确率以及F 1值作为评价指标,通过消融试验验证模型各个部分的效果.结果表明,本算法在MSRA和Weibo数据集上F 1值分别提升0.28、0.69,在Resume数据集上精确率提升0.07.

汉字识别中图特征提取方法

为解决图像像素表示汉字特征方法不能有效表示汉字本质特征、空间复杂度较高的问题,提出了一种汉字图特征提取方法。方法主要包含汉字图像二值化,汉字图像骨架提取,汉字图特征提取3个部分;二值化消除图像中的噪声,提高图特征提取的准确度;骨架提取保留图像中重要的像素点,剔除无关的像素点;图特征提取将汉字关键点与图数据结构结合来表示汉字形状特征。在3 908个常用汉字的5种字体上进行实验。结果表明,该方法能够正确提取笔画复杂汉字的图特征,有效表示汉字本质特征;不同字体汉字图特征相同的汉字数量最高为3 195个,方法表现较稳定;平均每个汉字可以用22.6个图节点、19.1个边表示,相较于用单通道图像表示汉字特征,可大幅降低空间复杂度。

听到“牛黄”能想到“黄牛”吗?——口语识别中的语音位置编码机制

在众多语言中,都存在一系列词汇,经过语音位置转置后仍能有效成词,典型如中文中的“牛黄”与“黄牛”。阐明这类可转置词汇在语言理解过程中的编码方式,是一项至关重要的研究课题。在阅读领域,学者们已就词汇的位置编码机制展开了讨论,然而针对口语加工中语音位置编码的认知机制,至今仍存在序列−灵活编码之争:早期口语识别理论认为语音位置编码主要以序列编码方式为主,而近年来的研究则发现,音位、音节和句子等层面上存在以灵活编码为主的语音位置编码方式。未来研究应深入探索与口语识别中语音编码相关的认知机理、神经机制、语言获得以及人工智能等重要问题,由于汉字词在形音对应关系和语音加工单元等方面独具特殊性,后续研究应对汉字词的语音位置编码予以特别关注。