Visual extraction of information from web pages

In this paper we present a graphical software system that provides an automatic support to the extraction of information from web pages. The underlying extraction technique exploits the visual appearance of the information in the document, and is driven by the spatial relations occurring among the elements in the page. However, the usual information extraction modalities based on the web page structure can be used in our framework, too. The technique has been integrated within the Spatial Relation Query (SRQ) tool. The tool is provided with a graphical front-end which allows one to define and manage a library of spatial relations, and to use a SQL-like language for composing queries driven by these relations and by further semantic and graphical attributes.     

A general theory of spatial relations to support a graphical tool for visual information extraction

In this paper we present a general spatial composition framework which allows one to model the graphical objects and the spatial relations of a large class of visual languages. The new formalism has been implemented within the SRQ tool, a software system for the Visual Information Extraction, enabling it to work on a wider range of domains. In particular, in the paper we describe the application of SRQ to geospatial data.     

Internet-based interactive HDTV

Traditional interactive TV systems depend on expensive hardware, proprietary formats, and a closed-loop end-to-end approach, which greatly limits scalability and extensibility of TV services. In this paper, we present the HDControl interactive Internet TV architecture that achieves an open service model and combines high-quality video with flexible user control using two key software real-time algorithms: visual information embedding (VIE) algorithm and resynchronization algorithm. Experimental results in our HDTV testbed have confirmed the feasibility and efficiency of our proposed algorithms.     

离散型制造企业刀具信息提取及固化方法研究

为了提高离散型制造企业刀具要素回归固化的效率,提出一种以数控程序为载体的快速固化刀具的方法,该方法通过定义刀具的编码规则,针对不同数控系统设计基于正则表达式的信息抽取算法,准确定位换刀位置和提取刀具注释信息,模拟刀具选型过程,建立了基于规则的刀具选配模型,以刀具注释信息作为选配模型输入自动完成刀具选配,获取完整刀具信息...     

Dynamic visual features for audio–visual speaker verification

The cascading appearance-based (CAB) feature extraction technique has established itself as the state-of-the-art in extracting dynamic visual speech features for speech recognition. In this paper, we will focus on investigating the effectiveness of this technique for the related speaker verification application. By investigating the speaker verification ability of each stage of the cascade we will demonstrate that the same steps taken to reduce static speaker and environmental information for the visual speech recognition application also provide similar improvements for visual speaker recognition. A further study is conducted comparing synchronous HMM (SHMM) based fusion of CAB visual features and traditional perceptual linear predictive (PLP) acoustic features to show that higher complexity inherit in the SHMM approach does not appear to provide any improvement in the final audio–visual speaker verification system over simpler utterance level score fusion.     

雷达遥感建筑物震害信息提取方法综述

合成孔径雷达遥感具有全天时、全天候工作的能力,在地震灾害应急中发挥了重要作用。回顾了雷达遥感建筑物震害信息提取技术的发展历史,总结了各种用于建筑物震害信息提取的雷达卫星的参数特征以及使用雷达遥感提取建筑物震害信息的震例。介绍了目前应用的各种雷达遥感建筑物震害信息提取方法,包括目视解译和计算机自动信息提取两种,其中后者包括基于纹理特征和极化特征的单时相方法、基于强度特征和相干特征的多时相方法。比较了这些方法的适用性和不足,并探讨了雷达遥感建筑物震害信息提取方法的发展趋势。     

面向模式的分布式软件构架可视化建模

主要阐述了面向模式的分布式软件构架的概念、原理和常用构架模式的特点。重点研究了提出的面向模式的软件构架建模语言、可视化建模工具的设计原理、功能及特点等,并以一个具体应用实例展示了该建模工具的实用性。     

RGB-D语义分割：深度信息的选择使用

目的 在室内场景语义分割任务中,深度信息会在一定程度上提高分割精度。但是如何更有效地利用深度信息仍是一个开放性问题。当前方法大都引入全部深度信息,然而将全部深度信息和视觉特征组合在一起可能对模型产生干扰,原因是仅依靠视觉特征网络模型就能区分的不同物体,在引入深度信息后可能产生错误判断。此外,卷积核固有的几何结构限制了卷积神经网络的建模能力,可变形卷积(deformable convolution, DC)在一定程度上缓解了这个问题。但是可变形卷积中产生位置偏移的视觉特征空间深度信息相对不足,限制了进一步发展。基于上述问题,本文提出一种深度信息引导的特征提取(depth guided feature extraction, DFE)模块。方法 深度信息引导的特征提取模块包括深度信息引导的特征选择模块(depth guided feature selection, DFS)和深度信息嵌入的可变形卷积模块(depth embedded deformable convolution, DDC)。DFS可以筛选出关键的深度信息,自适应地调整深度信息引入视觉特征的比例,在网络模型需要时将深度信息嵌...     

Using mutual information for appearance-based visual path following

In this paper we propose a new way to achieve a navigation task (visual path following) for a non-holonomic vehicle. We consider an image-based navigation process. We show that it is possible to navigate along a visual path without relying on the extraction, matching and tracking of geometric visual features such as keypoint. The new proposed approach relies directly on the information (entropy) contained in the image signal. We show that it is possible to build a control law directly from the maximization of the shared information between the current image and the next key image in the visual path. The shared information between those two images is obtained using mutual information that is known to be robust to illumination variations and occlusions. Moreover the generally complex task of features extraction and matching is avoided. Both simulations and experiments on a real vehicle are presented and show the possibilities and advantages offered by the proposed method.     

基于视觉特征的网页信息抽取方法研究

面对大规模异构网页,基于视觉特征的网页信息抽取方法普遍存在通用性较差、抽取效率较低的问题。针对通用性较差的问题,该文提出了基于视觉特征的使用有监督机器学习的网页信息抽取框架WEMLVF。该框架具有良好的通用性,通过对论坛网站和新闻评论网站的信息抽取实验,验证了该框架的有效性。然后,针对视觉特征提取时间代价过高导致信息抽取效率较低的问题,该文使用WEMLVF,分别提出基于XPath和基于经典包装器归纳算法SoftMealy的自动生成信息抽取模板的方法。这两种方法使用视觉特征自动生成信息抽取模板,但模板的表达并不包含视觉特征,使得在使用模板进行信息抽取的过程中无需提取网页的视觉特征,从而既充分利用了视觉特征在信息抽取中的作用,又显著提升了信息抽取的效率,实验结果验证了这一结论。     

The Briefing Associate: easing authors into the Semantic Web

The Semantic Web has clear benefits for information consumers, but for authors it typically means added work with no immediate payoff. This article describes Briefing Associate (BA), a tool that eases the effort by automating markup within a popular commercial off-the-shelf (COTS) application. The BA is a descendent of the Design Editor, an application for producing visual, domain-specific design environments. Both tools are implemented as extensions of Microsoft's PowerPoint, which, as this paper describes, is a key factor in our research.     

载体独立的深度光照水印算法

随着多媒体技术的发展与完善，数字产品的版权保护需求逐步增大。数字水印是一种保护数字产品版权的有效手段，它一般是通过在数字载体（如文本、图像等）中添加重要标识信息（即数字水印），使载体带有标识信息，但又不影响载体的正常使用。常见的数字水印嵌入方案是通过采用特定算法对载体进行修改来嵌入水印信息的。而在实际的应用场景中，有很多待保护的图像或物件（如艺术画作等）是不允许修改的。基于此背景，提出了一种新的载体独立的深度光照水印算法，在嵌入端通过可见光调制的方法来表达水印信息，从而实现在不对原始载体进行修改的前提下进行水印信息嵌入，并达到版权保护的目的。通过对人眼视觉系统进行分析，提出了基于交替式投影的水印模板图案来嵌入水印信息，使嵌入过程既不需要对原始载体进行修改，也不会影响人眼的视觉感官。而在提取端，设计了基于残差连接的水印提取网络，对采集的水印图像经透视变换后送入该网络来进行水印信息提取。实验在多种条件下进行，并与3种基准算法进行了对比。实验结果表明，所提算法生成的水印图像具有较小的视觉失真，且对“投影-拍摄”过程具有很强的鲁棒性。在不同距离、角度、光照等条件下，水印提取网络具有很高的水印信息提取准确率，且相比其他通用网络具有一定的优越性。     

网站拓扑结构提取技术的研究与应用

大多数的网站体积庞大、结构复杂,因此要考察与网站相关的问题比较有效的方法是进行网站信息可视化。而可视化的一个关键问题就是如何对网站拓扑结构等一些基础数据进行提取和表示。该文提出了一种网站拓扑结构及基本信息的提取方法。其中包括提取过程中一些复杂问题的解决方案、关键技术以及数据的表示和存储结构等。介绍了基于这种方法所开发的一个网站拓扑结构自动提取工具,以及利用该工具所进行的应用试验。     

On the Automatic Recovery of Style-Specific Architectural Relations in Software Systems

The cost of maintaining a software system over a long period of time far exceeds its initial development cost. Much of the maintenance cost is attributed to the time required by new developers to understand legacy systems. High-level structural information helps maintainers navigate through the numerous low-level components and relations present in the source code. Modularization tools can be used to produce subsystem decompositions from the source code but do not typically produce high-level architectural relations between the newly found subsystems. Controlling subsystem interactions is one important way in which the overall complexity of software maintenance can be reduced.We have developed a tool, called ARIS (Architecture Relation Inference System), that enables software engineers to define rules and relations for regulating subsystem interactions. These rules and relations are called Interconnection Styles and are definedusing a visual notation. The style definition is used by our tool to infer subsystem-level relations in designs being reverse engineered from source code.In this paper we describe our tool and its underlying techniques and algorithms. Using a case study, we describe how ARIS is used to reverse engineer high-level structural information from a real application.     

Comparing and combining a semantic tagger and a statistical tool for MWE extraction

Automatic extraction of multiword expressions (MWEs) presents a tough challenge for the NLP community and corpus linguistics. Indeed, although numerous knowledge-based symbolic approaches and statistically driven algorithms have been proposed, efficient MWE extraction still remains an unsolved issue. In this paper, we evaluate the Lancaster UCREL Semantic Analysis System (henceforth USAS (Rayson, P., Archer, D., Piao, S., McEnery, T., 2004. The UCREL semantic analysis system. In: Proceedings of the LREC-04 Workshop, Beyond Named Entity Recognition Semantic labelling for NLP tasks, Lisbon, Portugal. pp. 7–12)) for MWE extraction, and explore the possibility of improving USAS by incorporating a statistical algorithm. Developed at Lancaster University, the USAS system automatically annotates English corpora with semantic category information. Employing a large-scale semantically classified multi-word expression template database, the system is also capable of detecting many multiword expressions, as well as assigning semantic field information to the MWEs extracted. Whilst USAS therefore offers a unique tool for MWE extraction, allowing us to both extract and semantically classify MWEs, it can sometimes suffer from low recall. Consequently, we have been comparing USAS, which employs a symbolic approach, to a statistical tool, which is based on collocational information, in order to determine the pros and cons of these different tools, and more importantly, to examine the possibility of improving MWE extraction by combining them. As we report in this paper, we have found a highly complementary relation between the different tools: USAS missed many domain-specific MWEs (law/court terms in this case), and the statistical tool missed many commonly used MWEs that occur in low frequencies (lower than three in this case). Due to their complementary relation, we are proposing that MWE coverage can be significantly increased by combining a lexicon-based symbolic approach and a collocation-based statistical approach.     

Generating graphical applications from state-transition visual specifications

In graphical applications, visual representations are mostly used in an ad hoc fashion with little or no underlying formal support. Due to this, no common methodology for handling visual and diagrammatic representations has emerged and formal techniques for their support are underdeveloped. Usually, a programmer develops a graphical application by applying a general-purpose visual programming environment and ad hoc implementing the application requirements. Then, big efforts are often required when the application has to be successively modified or extended. In this paper, we present a finite-automaton-based formalism for the specification of rapid application development (RAD) visual applications, which provides a formal basis in the visual application generation. A prototype tool, based on this approach, has been developed and it is currently being experimented on a variety of case studies.     

视觉信息处理中的马尔可夫随机场

由于视觉信息处理中存在大量的不确定性,概率图模型在计算机视觉领域有着广泛的应用,备受广大学者的关注。许多视觉问题都可以通过建立概率图模型进行求解,随着高效求解算法的提出和发展,马尔可夫随机场在解决计算机视觉领域的大规模数据问题中具有很大的优势。首先简要地介绍了概率图模型的概念,然后对马尔可夫随机场模型的定义、特性和推导求解进行了分析和讨论,在此基础上,以马尔可夫随机场在视觉信息的应用为线索,对目前基于马尔可夫随机场的计算机视觉信息处理的主要技术进行了概述和比较研究。     

Event based indexing of broadcasted sports video by intermodalcollaboration

In this paper, we propose event-based video indexing, which is a kind of indexing by its semantical contents. Because video data is composed of multimodal information streams such as visual, auditory, and textual [closed caption (CC)] streams, we introduce a strategy of intermodal collaboration, i.e., collaborative processing taking account of the semantical dependency between these streams. Its aim is to improve the reliability and efficiency in contents analysis of video. Focusing here on temporal correspondence between visual and CC streams, the proposed method attempts to seek for time spans in which events are likely to take place through extraction of keywords from the CC stream and then to index shots in the visual stream. The experimental results for broadcasted sports video of American football games indicate that intermodal collaboration is effective for video indexing by the events such as touchdown (TD) and field goal (FG)     

人身保险知识图谱的构建与应用

辅助投保人了解保险产品的条款是保险应用关注的热点问题之一, 借助知识图谱技术辅助人身保险业务开展是一种可行的方法. 本文首先从多源数据中提取并构建人身保险知识图谱LIKG. 具体而言, 构建BERT-IDCNN-BiLSTM-CRF模型提取非结构化文本数据的实体, 通过多种短文本相似度算法以及集成排序算法完成实体对齐; 设计并使用Bootstrapping和分类预测两阶段抽取方法对保险产品进行属性填充. 然后, 根据构建的LIKG, 设计开发原型系统, 该系统使用实体抽取和属性抽取算法提供知识获取功能、设计CF-IIF指标提供属性推荐功能以及实现可视化界面帮助用户快速掌握人身保险产品的信息, 展示LIKG的应用价值.