Using topic models for OCR correction

Despite several decades of research in document analysis, recognition of unconstrained handwritten documents is still considered a challenging task. Previous research in this area has shown that word recognizers perform adequately on constrained handwritten documents which typically use a restricted vocabulary (lexicon). But in the case of unconstrained handwritten documents, state-of-the-art word recognition accuracy is still below the acceptable limits. The objective of this research is to improve word recognition accuracy on unconstrained handwritten documents by applying a post-processing or OCR correction technique to the word recognition output. In this paper, we present two different methods for this purpose. First, we describe a lexicon reduction-based method by topic categorization of handwritten documents which is used to generate smaller topic-specific lexicons for improving the recognition accuracy. Second, we describe a method which uses topic-specific language models and a maximum-entropy based topic categorization model to refine the recognition output. We present the relative merits of each of these methods and report results on the publicly available IAM database.     

Ensemble of keyword extraction methods and classifiers in text classification

Automatic keyword extraction is an important research direction in text mining, natural language processing and information retrieval. Keyword extraction enables us to represent text documents in a condensed way. The compact representation of documents can be helpful in several applications, such as automatic indexing, automatic summarization, automatic classification, clustering and filtering. For instance, text classification is a domain with high dimensional feature space challenge. Hence, extracting the most important/relevant words about the content of the document and using these keywords as the features can be extremely useful. In this regard, this study examines the predictive performance of five statistical keyword extraction methods (most frequent measure based keyword extraction, term frequency-inverse sentence frequency based keyword extraction, co-occurrence statistical information based keyword extraction, eccentricity-based keyword extraction and TextRank algorithm) on classification algorithms and ensemble methods for scientific text document classification (categorization). In the study, a comprehensive study of comparing base learning algorithms (Naïve Bayes, support vector machines, logistic regression and Random Forest) with five widely utilized ensemble methods (AdaBoost, Bagging, Dagging, Random Subspace and Majority Voting) is conducted. To the best of our knowledge, this is the first empirical analysis, which evaluates the effectiveness of statistical keyword extraction methods in conjunction with ensemble learning algorithms. The classification schemes are compared in terms of classification accuracy, F-measure and area under curve values. To validate the empirical analysis, two-way ANOVA test is employed. The experimental analysis indicates that Bagging ensemble of Random Forest with the most-frequent based keyword extraction method yields promising results for text classification. For ACM document collection, the highest average predictive performance (93.80%) is obtained with the utilization of the most frequent based keyword extraction method with Bagging ensemble of Random Forest algorithm. In general, Bagging and Random Subspace ensembles of Random Forest yield promising results. The empirical analysis indicates that the utilization of keyword-based representation of text documents in conjunction with ensemble learning can enhance the predictive performance and scalability of text classification schemes, which is of practical importance in the application fields of text classification.     

Impact of online handwriting recognition performance on text categorization

Today, there is an increasing demand of efficient archival and retrieval methods for online handwritten data. For such tasks, text categorization is of particular interest. The textual data available in online documents can be extracted through online handwriting recognition; however, this process produces errors in the resulting text. This work reports experiments on the categorization of online handwritten documents based on their textual contents. We analyze the effect of word recognition errors on the categorization performances, by comparing the performances of a categorization system with the texts obtained through online handwriting recognition and the same texts available as ground truth. Two well-known categorization algorithms (kNN and SVM) are compared in this work. A subset of the Reuters-21578 corpus consisting of more than 2,000 handwritten documents has been collected for this study. Results show that classification rate loss is not significant, and precision loss is only significant for recall values of 60–80% depending on the noise levels.     

Spoken query based word spotting in digitized Tamil documents

This paper presents an integrated approach to spot the spoken keywords in digitized Tamil documents by combining word image matching and spoken word recognition techniques. The work involves the segmentation of document images into words, creation of an index of keywords, and construction of word image hidden Markov model (HMM) and speech HMM for each keyword. The word image HMMs are constructed using seven dimensional profile and statistical moment features and used to recognize a segmented word image for possible inclusion of the keyword in the index. The spoken query word is recognized using the most likelihood of the speech HMMs using the 39 dimensional mel frequency cepstral coefficients derived from the speech samples of the keywords. The positional details of the search keyword obtained from the automatically updated index retrieve the relevant portion of text from the document during word spotting. The performance measures such as recall, precision, and F-measure are calculated for 40 test words from the four groups of literary documents to illustrate the ability of the proposed scheme and highlight its worthiness in the emerging multilingual information retrieval scenario.     

A collaborative desktop tagging system for group knowledge management based on concept space

The advent of internet has led to a significant growth in the amount of information available, resulting in information overload, i.e. individuals have too much information to make a decision. To resolve this problem, collaborative tagging systems form a categorization called folksonomy in order to organize web resources. A folksonomy aggregates the results of personal free tagging of information and objects to form a categorization structure that applies utilizes the collective intelligence of crowds. Folksonomy is more appropriate for organizing huge amounts of information on the Web than traditional taxonomies established by expert cataloguers. However, the attributes of collaborative tagging systems and their folksonomy make them impractical for organizing resources in personal environments.This work designs a desktop collaborative tagging (DCT) system that enables collaborative workers to tag their documents. This work proposes an application in patent analysis based on the DCT system. Folksonomy in DCT is built by aggregating personal tagging results, and is represented by a concept space. Concept spaces provide synonym control, tag recommendation and relevant search. Additionally, to protect privacy of authors and to decrease the transmission cost, relations between tagged and untagged documents are constructed by extracting document’s features rather than adopting the full text.Experimental results reveal that the adoption rate of recommended tags for new documents increases by 10% after users have tagged five or six documents. Furthermore, DCT can recommend tags with higher adoption rates when given new documents with similar topics to previously tagged ones. The relevant search in DCT is observed to be superior to keyword search when adopting frequently used tags as queries. The average precision, recall, and F-measure of DCT are 12.12%, 23.08%, and 26.92% higher than those of keyword searching.DCT allows a multi-faceted categorization of resources for collaborative workers and recommends tags for categorizing resources to simplify categorization easier. Additionally, DCT system provides relevance searching, which is more effective than traditional keyword searching for searching personal resources.     

Locally discriminative topic modeling

Topic modeling is a powerful tool for discovering the underlying or hidden structure in text corpora. Typical algorithms for topic modeling include probabilistic latent semantic analysis (PLSA) and latent Dirichlet allocation (LDA). Despite their different inspirations, both approaches are instances of generative model, whereas the discriminative structure of the documents is ignored. In this paper, we propose locally discriminative topic model (LDTM), a novel topic modeling approach which considers both generative and discriminative structures of the data space. Different from PLSA and LDA in which the topic distribution of a document is dependent on all the other documents, LDTM takes a local perspective that the topic distribution of each document is strongly dependent on its neighbors. By modeling the local relationships of documents within each neighborhood via a local linear model, we learn topic distributions that vary smoothly along the geodesics of the data manifold, and can better capture the discriminative structure in the data. The experimental results on text clustering and web page categorization demonstrate the effectiveness of our proposed approach.     

基于朴素贝叶斯模型的中文关键词提取算法研究

提出了一种基于朴素贝叶斯模型的中文关键词提取算法。该算法首先通过训练过程获得朴素贝叶斯模型中的各个参数,然后以之为基础,在测试过程完成关键词提取。实验表明,相对于传统的if*idf方法,该算法可从小规模的文档集中提取出更为准确的关键词,而且可灵活地增加表征词语重要性的特征项,因而具有更好的可扩展性。     

联机手写维吾尔文字母识别方法

通过分析维吾尔文字母自身的结构和书写特点,提出一种联机手写维吾尔文字母识别方案,并选择在手写汉字识别技术中所提出来的归一化、特征提取及常用的分类方法,从中找出最佳的技术选择。在实验对比中,采用8种不同的归一化预处理方法,基于坐标归一化的特征提取 (NCFE) 方法,以及改进的二次分类函数(MQDF)、判别学习型二次判别函数(DLQDF)、学习矢量量化(LVQ)、支持向量机(SVM)4种分类器。同时,再考虑字符在文档中的空间几何特征,进一步提高识别性能。在128个维吾尔文字母类别、38 400个测试样本的实验中,正确识别率最高达89。08%,为进一步研究面向维吾尔文字母特性的识别技术奠定重要基础。     

Contextual keyword extraction by building sentences with crowdsourcing

Automatic keyword extraction from documents has long been used and proven its usefulness in various areas. Crowdsourced tagging for multimedia resources has emerged and looks promising to a certain extent. Automatic approaches for unstructured data, automatic keyword extraction and crowdsourced tagging are efficient but they all suffer from the lack of contextual understanding. In this paper, we propose a new model of extracting key contextual terms from unstructured data, especially from documents, with crowdsourcing. The model consists of four sequential processes: (1) term selection by frequency, (2) sentence building, (3) revised term selection reflecting the newly built sentences, and (4) sentence voting. Online workers read only a fraction of a document and participated in sentence building and sentence voting processes, and key sentences were generated as a result. We compared the generated sentences to the keywords entered by the author and to the sentences generated by offline workers who read the whole document. The results support the idea that sentence building process can help selecting terms with more contextual meaning, closing the gap between keywords from automated approaches and contextual understanding required by humans.     

支持检索关键词语义扩展的可排序密文检索方案

针对云计算环境下已有的密文检索方案不支持检索关键词语义扩展、精确度不够、检索结果不支持排序的问题，提出一种支持检索关键词语义扩展的可排序密文检索方案。首先，使用词频逆文档频率（TF-IDF）方法计算文档中关键词与文档之间的相关度评分，并对文档不同域中的关键词设置不同的位置权重，使用域加权评分方法计算位置权重评分，将相关度评分与位置权重评分的乘积设置为关键词在文档索引向量上相应位置的取值；其次，根据WordNet语义网对授权用户输入的检索关键词进行语义扩展，得到语义扩展检索关键词集合，使用编辑距离公式计算语义扩展检索关键词集合中关键词之间的相似度，并将相似度值设置为检索关键词在文档检索向量上相应位置的取值；最后，加密产生安全索引和文档检索陷门，在向量空间模型（VSM）下进行内积运算，以内积运算的结果为密文检索文档的排序依据。理论分析和实验仿真表明，所提方案在已知密文模型和已知背景知识模型下是安全的，且具备对检索结果的排序能力；与多关键字密文检索结果排序（MRSE）方案相比，所提方案支持关键词语义扩展，查询准确率比MRSE方案更加准确可靠，而检索时间则与MRSE方案相差不大。     

Handwritten Chinese text editing and recognition system

This paper describes a handwritten Chinese text editing and recognition system that can edit handwritten text and recognize it with a client-server mode. First, the client end samples and redisplays the handwritten text by using digital ink technics, segments handwritten characters, edits them and saves original handwritten information into a self-defined document. The self-defined document saves coordinates of all sampled points of handwriting characters. Second, the server recognizes handwritten document based on the proposed Gabor feature extraction and affinity propagation clustering (GFAP) method, and returns the recognition results to client end. Moreover, the server can also collect the labeled handwritten characters and fine tune the recognizer automatically. Experimental results on HIT-OR3C database show that our handwriting recognition method improves the recognition performance remarkably.     

融合LeNet-5改进的扫描文档手写日期识别

研究LeNet-5在扫描文档中手写体日期字符识别的应用,由于文档扫描的过程中会引入各种噪声,特别是光照和颜色干扰,直接使用LeNet-5算法不能取得较好效果。先在整份文档中对特定待识别字符的进行定位和划分,并对划分出的字符图像进行去噪、灰度化和二值化处理等预处理,接着将字符图像分割成一个个单个字符,然后在LeNet-5网络基础上结合模型匹配法实现对手写体日期字符的识别。分析在不同参数组合下的识别效果,调整算法模型参数有效地提升了模型对于实际对象的性能,实现出一种能够对手写体日期字符集实现较好识别效果的算法。实验结果表明了算法的有效性,并应用于具体工程实践。     

新的关键字提取算法研究

传统的关键字提取算法往往是基于高频词提取的,但文档中的关键字往往并不都是高频词,因此还需要从非高频词集中找出关键字.把一篇文档抽象为一个图:结点表示词语,边表示词语的同现关系;并基于文档的这种拓扑结构,提出了一种新的关键字提取算法,并和传统的关键字提取算法作了比较,在精确率,覆盖率方面均有不错的效果.     

Automatic writer identification framework for online handwritten documents using character prototypes

This paper proposes an automatic text-independent writer identification framework that integrates an industrial handwriting recognition system, which is used to perform an automatic segmentation of an online handwritten document at the character level. Subsequently, a fuzzy c-means approach is adopted to estimate statistical distributions of character prototypes on an alphabet basis. These distributions model the unique handwriting styles of the writers. The proposed system attained an accuracy of 99.2% when retrieved from a database of 120 writers. The only limitation is that a minimum length of text needs to be present in the document in order for sufficient accuracy to be achieved. We have found that this minimum length of text is about 160 characters or approximately equivalent to 3 lines of text. In addition, the discriminative power of different alphabets on the accuracy is also reported.     

多级PSO神经网络在手写体字符识别中的应用

提出一种用于手写体字符识别的三级神经网络模型，各子神经网络均用粒子群优化算法(PSO)训练。在该模型中，各个神经网络与不同的图像特征提取方法相结合；识别时，三个神经网络先串联再并联。该模型充分有效地利用了各种特征信息，从实验结果看，也达到了较好的辨识目的。文中主要讨论手写字符图像的特征提取、粒子群优化算法及其在网络训练上的应用，最后分析了识别结果并与采用改进BP训练算法的综合识别效果进行了比较。     

Mining the interests of Chinese microbloggers via keyword extraction

Microblogging provides a new platform for communicating and sharing information among Web users. Users can express opinions and record daily life using microblogs. Microblogs that are posted by users indicate their interests to some extent. We aim to mine user interests via keyword extraction from microblogs. Traditional keyword extraction methods are usually designed for formal documents such as news articles or scientific papers. Messages posted by microblogging users, however, are usually noisy and full of new words, which is a challenge for keyword extraction. In this paper, we combine a translation-based method with a frequency-based method for keyword extraction. In our experiments, we extract keywords for microblog users from the largest microblogging website in China, Sina Weibo. The results show that our method can identify users’ interests accurately and efficiently.     

Offline handwritten Amharic word recognition

This paper describes two approaches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are a set of primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by a dataset of unconstrained handwritten documents collected from various sources, and promising results are obtained.