Accurate video text detection through classification of low and high contrast images

Detection of both scene text and graphic text in video images is gaining popularity in the area of information retrieval for efficient indexing and understanding the video. In this paper, we explore a new idea of classifying low contrast and high contrast video images in order to detect accurate boundary of the text lines in video images. In this work, high contrast refers to sharpness while low contrast refers to dim intensity values in the video images. The method introduces heuristic rules based on combination of filters and edge analysis for the classification purpose. The heuristic rules are derived based on the fact that the number of Sobel edge components is more than the number of Canny edge components in the case of high contrast video images, and vice versa for low contrast video images. In order to demonstrate the use of this classification on video text detection, we implement a method based on Sobel edges and texture features for detecting text in video images. Experiments are conducted using video images containing both graphic text and scene text with different fonts, sizes, languages, backgrounds. The results show that the proposed method outperforms existing methods in terms of detection rate, false alarm rate, misdetection rate and inaccurate boundary rate.     

Personalized text snippet extraction using statistical language models

In knowledge discovery in a text database, extracting and returning a subset of information highly relevant to a user's query is a critical task. In a broader sense, this is essentially identification of certain personalized patterns that drives such applications as Web search engine construction, customized text summarization and automated question answering. A related problem of text snippet extraction has been previously studied in information retrieval. In these studies, common strategies for extracting and presenting text snippets to meet user needs either process document fragments that have been delimitated a priori or use a sliding window of a fixed size to highlight the results. In this work, we argue that text snippet extraction can be generalized if the user's intention is better utilized. It overcomes the rigidness of existing approaches by dynamically returning more flexible start-end positions of text snippets, which are also semantically more coherent. This is achieved by constructing and using statistical language models which effectively capture the commonalities between a document and the user intention. Experiments indicate that our proposed solutions provide effective personalized information extraction services.     

支持向量机在文本特征提取中的应用研究

在文本自动分类中,针对如何进行文本特征的选择和提取这一关键和基础性工作,提出用支持向量度量词汇对分类的贡献,然后进行文本特征的提取。实验结果表明,该方法可以在确保分类信息不损失的前提下,降低向量空间的维数,提高分类器效率和分类准确率。     

Labeling design documents based on operators’ consensus—A case study of robotic design

Designers usually begin with a database to look for historical design solution, available experience and techniques through design documents, when initiating a new design. This database is a collection of labeled design documents under a few of predefined categories. However, little work has been done on labeling a relatively small number of design documents for information organization, so that most of design documents in this database can be automatically categorized.This paper initiates a study on this topic and proposes a methodology in four steps: design document collection, documents labeling, finalization of documents labeling and categorization of design database. Our discussion in this paper focuses on the first three steps. The key of this method is to collect relatively small number of design documents for manual labeling operation, and unify the effective labeling results as the final labels in terms of labeling agreement analysis and text classification experiment. Then these labeled documents are utilized as training samples to construct classifiers, which can automatically give appropriate labels to each design document.With this method, design documents are labeled in terms of the consensus of operators’ understanding, and design information can be organized in a comprehensive and universally accessible way. A case study of labeling robotic design documents is used to demonstrate the proposed methodology. Experimental results show that this method can significantly benefit efficient design information search.     

Text detection in images using sparse representation with discriminative dictionaries

Text detection is important in the retrieval of texts from digital pictures, video databases and webpages. However, it can be very challenging since the text is often embedded in a complex background. In this paper, we propose a classification-based algorithm for text detection using a sparse representation with discriminative dictionaries. First, the edges are detected by the wavelet transform and scanned into patches by a sliding window. Then, candidate text areas are obtained by applying a simple classification procedure using two learned discriminative dictionaries. Finally, the adaptive run-length smoothing algorithm and projection profile analysis are used to further refine the candidate text areas. The proposed method is evaluated on the Microsoft common test set, the ICDAR 2003 text locating set, and an image set collected from the web. Extensive experiments show that the proposed method can effectively detect texts of various sizes, fonts and colors from images and videos.     

Segmentation of historical machine-printed documents using Adaptive Run Length Smoothing and skeleton segmentation paths

In this paper, we strive towards the development of efficient techniques in order to segment document pages resulting from the digitization of historical machine-printed sources. This kind of documents often suffer from low quality and local skew, several degradations due to the old printing matrix quality or ink diffusion, and exhibit complex and dense layout. To face these problems, we introduce the following innovative aspects: (i) use of a novel Adaptive Run Length Smoothing Algorithm (ARLSA) in order to face the problem of complex and dense document layout, (ii) detection of noisy areas and punctuation marks that are usual in historical machine-printed documents, (iii) detection of possible obstacles formed from background areas in order to separate neighboring text columns or text lines, and (iv) use of skeleton segmentation paths in order to isolate possible connected characters. Comparative experiments using several historical machine-printed documents prove the efficiency of the proposed technique.     

A two-stage scheme for text detection in video images

This paper proposes a two-stage system for text detection in video images. In the first stage, text lines are detected based on the edge map of the image leading in a high recall rate with low computational time expenses. In the second stage, the result is refined using a sliding window and an SVM classifier trained on features obtained by a new Local Binary Pattern-based operator (eLBP) that describes the local edge distribution. The whole algorithm is used in a multiresolution fashion enabling detection of characters for a broad size range. Experimental results, based on a new evaluation methodology, show the promising overall performance of the system on a challenging corpus, and prove the superior discriminating ability of the proposed feature set against the best features reported in the literature.     

一种改进的文本特征选择方法的研究与设计

分析了特征选择采用互信息方法时文本分类性能较低的原因,认为与其在特征选择时倾向于选择稀有特征这一缺陷有很大关系。在此基础上,提出了一种基于分散度和平均频度的互信息特征选择方法。实验结果表明,改进后的互信息方法使文本分类性能有明显提高。     

基于二次TF* IDF的互信息文本特征选择算法研究

在分析传统互信息法缺陷的基础上,提出一种基于二次TF*IDF的互信息特征选择算法,对仅在一个类别中出现的特征词的重要程度给予再次的衡量,解决了互信息值相等而无法进行有效特征选择的问题。利用贝叶斯分类器对该方法进行验证的结果表明该算法在文本分类效率和正确率上比原有方法有一定的提高。     

基于文本相似度的网页消重策略

针对在网页检索结果中经常出现内容相同或相似的问题,提出了一种通过计算网页相似度的方法进行网页消重。该算法通过提取网页特征串,特征串的提取在参考以往特征码提取的基础上,加入了文本结构特征的提取,通过比较特征串之间差异性的基础上得到网页的相似度。经与相似方法比较,结果表明,该方法减少了时间复杂度,具有较高的查全率和查准率,适于大规模网页消重。