词典驱动的联机手写日文病名识别研究

研究了一种有效的词典驱动的联机手写日文病名识别方法。病名词典以树结构存储,包含21 713个病名短语。在切分中,手写病名字符串通过分析相邻笔划之间的空间信息等特征被切分为原始的片段序列。连续的片段动态地合并为候选字符模式,不同的合并方式产生不同的候选字符序列,这样可构成一个切分候选网格。在识别过程中,结合病名词典匹配来限制候选字符模式的类别扩展,采用集束搜索策略来寻找到一条最优路径作为识别结果。用500个实际的手写病名样本做实验,平均每个病名的识别时间为0.87 s,识别正确率为83.16%。     

Model-based stroke extraction and matching for handwritten Chinese character recognition

This paper proposes a model-based structural matching method for handwritten Chinese character recognition (HCCR). This method is able to obtain reliable stroke correspondence and enable structural interpretation. In the model base, the reference character of each category is described in an attributed relational graph (ARG). The input character is described with feature points and line segments. The strokes and inter-stroke relations of input character are not determined until being matched with a reference character. The structural matching is accomplished in two stages: candidate stroke extraction and consistent matching. All candidate input strokes to match the reference strokes are extracted by line following and then the consistent matching is achieved by heuristic search. Some structural post-processing operations are applied to improve the stroke correspondence. Recognition experiments were implemented on an image database collected in KAIST, and promising results have been achieved.     

Document image binarization based on texture features

Binarization has been difficult for document images with poor contrast, strong noise, complex patterns, and/or variable modalities in gray-scale histograms. We developed a texture feature based thresholding algorithm to address this problem. Our algorithm consists of three steps: 1) candidate thresholds are produced through iterative use of Otsu's algorithm (1978); 2) texture features associated with each candidate threshold are extracted from the run-length histogram of the accordingly binarized image; 3) the optimal threshold is selected so that desirable document texture features are preserved. Experiments with 9,000 machine printed address blocks from an unconstrained US mail stream demonstrated that over 99.6 percent of the images were successfully binarized by the new thresholding method, appreciably better than those obtained by typical existing thresholding techniques. Also, a system run with 500 troublesome mail address blocks showed that an 8.1 percent higher character recognition rate was achieved with our algorithm as compared with Otsu's algorithm     

Handwritten word recognition with character and inter-characterneural networks

An off-line handwritten word recognition system is described. Images of handwritten words are matched to lexicons of candidate strings. A word image is segmented into primitives. The best match between sequences of unions of primitives and a lexicon string is found using dynamic programming. Neural networks assign match scores between characters and segments. Two particularly unique features are that neural networks assign confidence that pairs of segments are compatible with character confidence assignments and that this confidence is integrated into the dynamic programming. Experimental results are provided on data from the U.S. Postal Service.     

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。     

Handprinted word recognition on a NIST data set

An approach to handprinted word recognition is described. The approach is based on the use of generating multiple possible segmentations of a word image into characters and matching these segmentations to a lexicon of candidate strings. The segmentation process uses a combination of connected component analysis and distance transform-based, connected character splitting. Neural networks are used to assign character confidence values to potential character within word images. Experimental results are provided for both character and word recognition modules on data extracted from the NIST handprinted character database.     

Address block location on envelopes using Gabor filters

The large volume of mail and the increased cost of handling it has made postal automation an important domain for pattern recognition and computer vision research. A substantial amount of work is being done to design an automatic mail sorting system which can read and interpret the destination address on a mail piece and direct it to the appropriate bin. Robust optical character recognition (OCR) systems are now available which can read printed characters with great accuracy (> 99%). But, in order to read the destination address, the region in the image containing the address must first be located. Even though several approaches to address block location have been proposed in the literature, it remains a difficult problem. A simple method is presented for automatically identifying regions in envelope images which are candidates for being the destination address. The envelope image is considered to contain different textured regions, one of which corresponds to the text-content in the image. Thus, a texture-based segmentation method is used to identify the regions of text in the image. The method for texture discrimination is based on Gabor filters which have been successfully used earlier for a variety of texture classification and segmentation tasks. It is shown that only a small number of even-symmetric Gabor filters are needed in this application. The success of the texture-based segmentation algorithm for identifying address blocks is demonstrated on a number of test images. These results also demonstrate the invariance of the method to the orientation of text in the envelope image and the variations in the size and font of the text.     

手写中文信封的地址行字符切分算法

在手写体中文信封处理系统中,地址行字符切分是实现地址行识别的关键步骤。本文根据邮政信封地址行字符的特点,有针对性的提出了一种字符切分算法。首先对地址行图像利用投影、求连通区域、笔划穿越数分析等基于字符结构的方法进行初始切分,得到基本字段序列;然后通过对相邻的基本字段进行组合形成多条候选切分路径,再通过识别的可信度和邮政目标地址库的先验知识信息对路径进行评价分析,从而得到最优的切分路径。该算法经过邮政分拣机采集的实际信封图像测试,纯地址行识别正确率达到78.61%,地址行识别与邮政编码识别相结合的分拣正确率达到95.42%。     

A lexicon driven approach to handwritten word recognition forreal-time applications

A fast method of handwritten word recognition suitable for real time applications is presented in this paper. Preprocessing, segmentation and feature extraction are implemented using a chain code representation of the word contour. Dynamic matching between characters of a lexicon entry and segment(s) of the input word image is used to rank the lexicon entries in order of best match. Variable duration for each character is defined and used during the matching. Experimental results prove that our approach using the variable duration outperforms the method using fixed duration in terms of both accuracy and speed. Speed of the entire recognition process is about 200 msec on a single SPARC-10 platform and the recognition accuracy is 96.8 percent are achieved for lexicon size of 10, on a database of postal words captured at 212 dpi     

An adaptive approach to offline handwritten word recognition

An adaptive handwritten word recognition method is presented. A recursive architecture based on interaction between flexible character classification and deductive decision making is developed. The recognition process starts from the initial coarse level using a minimum number of features, then increases the discrimination power by adding other features adaptively and recursively until the result is accepted by the decision maker. For the computational aspect of a feasible solution, a unified decision metric, recognition confidence; is derived from two measurements: pattern confidence, evaluation of absolute confidence using shape features, and lexical confidence, evaluation of the relative string dissimilarity in the lexicon. Practical implementation and experimental results in reading the handwritten words of the address components of US mail pieces are provided. Up to a 4 percent improvement in recognition performance is achieved compared to a nonadaptive method. The experimental result shows that the proposed method has advantages in producing valid answers using the same number of features as conventional methods     

Shape-based word recognition

We describe a process of word recognition that has high tolerance for poor image quality, tunability to the lexical content of the documents to which it is applied, and high speed of operation. This process relies on the transformation of text images into character shape codes, and on special lexica that contain information on the shape of words. We rely on the structure of English and the high efficiency of mapping between shape codes and the characters in the words. Remaining ambiguity is reduced by template matching using exemplars derived from surrounding text, taking advantage of the local consistency of font, face and size as well as image quality. This paper describes the effects of lexical content, structure and processing on the performance of a word recognition engine. Word recognition performance is shown to be enhanced by the application of an appropriate lexicon. Recognition speed is shown to be essentially independent of the details of lexical content provided the intersection of the occurrences of words in the document and the lexicon is high. Word recognition accuracy is dependent on both intersection and specificity of the lexicon. Received May 1, 1998 / Revised October 20, 1998     

Holistic verification of handwritten phrases

In this paper, we describe a system for rapid verification of unconstrained off-line handwritten phrases using perceptual holistic features of the handwritten phrase image. The system is used to verify handwritten street names automatically extracted from live US mail against recognition results of analytical classifiers. Presented with a binary image of a street name and an ASCII street name, holistic features (reference lines, large gaps and local contour extrema) of the street name hypothesis are “predicted” from the expected features of the constituent characters using heuristic rules. A dynamic programming algorithm is used to match the predicted features with the extracted image features. Classes of holistic features are matched sequentially in increasing order of cost, allowing an ACCEPT/REJECT decision to be arrived at in a time-efficient manner. The system rejects errors with 98 percent accuracy at the 30 percent accept level, while consuming approximately 20/msec per image on the average on a 150 MHz SPARC 10     

Scene Text Recognition Using Similarity and a Lexicon with Sparse Belief Propagation

Scene text recognition (STR) is the recognition of text anywhere in the environment, such as signs and storefronts. Relative to document recognition, it is challenging because of font variability, minimal language context, and uncontrolled conditions. Much information available to solve this problem is frequently ignored or used sequentially. Similarity between character images is often overlooked as useful information. Because of language priors, a recognizer may assign different labels to identical characters. Directly comparing characters to each other, rather than only a model, helps ensure that similar instances receive the same label. Lexicons improve recognition accuracy but are used post hoc. We introduce a probabilistic model for STR that integrates similarity, language properties, and lexical decision. Inference is accelerated with sparse belief propagation, a bottom-up method for shortening messages by reducing the dependency between weakly supported hypotheses. By fusing information sources in one model, we eliminate unrecoverable errors that result from sequential processing, improving accuracy. In experimental results recognizing text from images of signs in outdoor scenes, incorporating similarity reduces character recognition error by 19 percent, the lexicon reduces word recognition error by 35 percent, and sparse belief propagation reduces the lexicon words considered by 99.9 percent with a 12X speedup and no loss in accuracy.     

Handwritten Chinese text recognition by integrating multiple contexts

This paper presents an effective approach for the offline recognition of unconstrained handwritten Chinese texts. Under the general integrated segmentation-and-recognition framework with character oversegmentation, we investigate three important issues: candidate path evaluation, path search, and parameter estimation. For path evaluation, we combine multiple contexts (character recognition scores, geometric and linguistic contexts) from the Bayesian decision view, and convert the classifier outputs to posterior probabilities via confidence transformation. In path search, we use a refined beam search algorithm to improve the search efficiency and, meanwhile, use a candidate character augmentation strategy to improve the recognition accuracy. The combining weights of the path evaluation function are optimized by supervised learning using a Maximum Character Accuracy criterion. We evaluated the recognition performance on a Chinese handwriting database CASIA-HWDB, which contains nearly four million character samples of 7,356 classes and 5,091 pages of unconstrained handwritten texts. The experimental results show that confidence transformation and combining multiple contexts improve the text line recognition performance significantly. On a test set of 1,015 handwritten pages, the proposed approach achieved character-level accurate rate of 90.75 percent and correct rate of 91.39 percent, which are superior by far to the best results reported in the literature.     

一种笔段序列匹配联机汉字识别方法

文中针对行书体汉字的识别,提出一种笔段序列匹配汉字识别方法。选择笔段数、笔段书写顺序、笔段位置作为主要的识别特征。首先,在预处理阶段,为了减小汉字类内分散性,采用笔段密度均衡化非线性规整法对笔段位置进行了非线性规整;进而在笔段序列的基础上,采用动态规划算法寻找待识笔段序列与候选笔段序列的最优匹配路径;根据此路径,得到匹配笔段集,缺少笔段和多余笔段;然后计算出待识字与每个候选字的识别距离;最后,对识     

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.     

基于神经和模糊方法的邮件地址识别

提出了一种基于神经和模糊方法的手写体邮件地址的识别方案。     

Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings

In integrated segmentation and recognition of character strings, the underlying classifier is trained to be resistant to noncharacters. We evaluate the performance of state-of-the-art pattern classifiers of this kind. First, we build a baseline numeral string recognition system with simple but effective presegmentation. The classification scores of the candidate patterns generated by presegmentation are combined to evaluate the segmentation paths and the optimal path is found using the beam search strategy. Three neural classifiers, two discriminative density models, and two support vector classifiers are evaluated. Each classifier has some variations depending on the training strategy: maximum likelihood, discriminative learning both with and without noncharacter samples. The string recognition performances are evaluated on the numeral string images of the NIST special database 19 and the zipcode images of the CEDAR CDROM-1. The results show that noncharacter training is crucial for neural classifiers and support vector classifiers, whereas, for the discriminative density models, the regularization of parameters is important. The string recognition results compare favorably to the best ones reported in the literature though we totally ignored the geometric context. The best results were obtained using a support vector classifier, but the neural classifiers and discriminative density models show better trade-off between accuracy and computational overhead.     

Affine-invariant recognition of gray-scale characters using globalaffine transformation correlation

Describes a technique of gray-scale character recognition that offers both noise tolerance and affine-invariance. The key ideas are twofold. First is the use of normalized cross-correlation as a matching measure to realize noise tolerance. Second is the application of global affine transformation (GAT) to the input image so as to achieve affine-invariant correlation with the target image. In particular, optimal GAT is efficiently determined by the successive iteration method using topographic features of gray-scale images as matching constraints. We demonstrate the high matching ability of the proposed GAT correlation method using gray-scale images of numerals subjected to random Gaussian noise and a wide range of affine transformation. Moreover, extensive recognition experiments show that the achieved recognition rate of 94.3 percent against rotation within 30 degrees, scale change within 30 percent, and translation within 20 percent of the character width along with random Gaussian noise is sufficiently high compared to the 42.8 percent offered by simple correlation