Restoring warped document images through 3D shape modeling

Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. From a technical point of view, this shape from shading (SFS) problem in real-world environments is characterized by 1) a proximal and moving light source, 2) Lambertian reflection, 3) nonuniform albedo distribution, and 4) document skew. Taking all these factors into account, we first build practical models (consisting of a 3D geometric model and a 3D optical model) for the practical scanning conditions to reconstruct the 3D shape of the book surface. We next restore the scanned document image using this shape based on deshading and dewarping models. Finally, we evaluate the restoration results by comparing our estimated surface shape with the real shape as well as the OCR performance on original and restored document images. The results show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly.     

重油微反控制系统—多线程技术的应用

以Microsoft Visual C 6.0为开发工具,应用Win95/98提供的多线程技术,在重油微反控制软件中实现了软件的实时控制性能。通过源代码剖析,详细阐述了多线程编程的实现方法以及如何安全地在多个线程间共享数据和通信。     

基于MATLAB的化工课程设计软件开发

在MATLAB平台上开发化工原理课程设计软件。本文以冷却塔设计为例介绍了该软件的主要内容结构和功能 ,它具有操作简单、使用方便、效率高、数值稳定性好等特点 ,使计算结果可视化     

电视与红外传感器对机动目标的分布式航迹融合

基于当前统计模型对机动目标进行建模,并用统计的方法对机动目标的多条航迹进行关联和融合,从跟踪性能以及结构的可靠性和可用性上分析了分布式融合结构是目标跟踪最经济和最合理的选择。最后计算机仿真中验证了此结构的实用性和有效性。     

A new strategy for optimizing the parameters updating algorithm of fuzzy neural controller

Fuzzy neural controllers have the advantages of ease for knowledge expression and the ability of self-learning, and are able to control adaptively by updating the fuzzy rules and the membership functions. Nevertheless, the long training time usually discourages their practical applications in industry and the parameters over-updating may make system oscillate extensively. In this paper, a new strategy for optimizing the parameters updating algorithm of fuzzy neural controller is proposed. The only effect of parameters which affects the control performance significantly are updated. Also, based on fuzzy inference, the updating step is adjusted adaptively in accordance with the error and the change of error of the system. Two examples are simulated in order to conform the effectiveness and applicability of the strategy proposed in this paper.     

用VC++创建选择位图的组合框控件

本文详细地介绍了用ＶＣ＋＋创建选择位图组合框控件的原理和实现过程,并通过结合具体的例子介绍了使用该控件的步骤和方法。     

测定外延层电阻率的面接触方法研究

评论了美国科学家C.C. Allen等于1966年发表的“测定外延层电阻率的点接触方法”之论文的局限性,从而提出了本方法。本方法从理论上解一维Poisson方程并与C.C。Allen法的公式相比较,获得某些公式。文中导出了面接触方法雪崩击穿电压V_(Ba)~∞(V)及点接触方法雪崩击穿电压V_(Bp)~∞(V)的比值为V_(Ba)~∞=0.456;同时还导出了点接触方法外延层耗尽层宽度为t_(min p)(μm)和面接触方法外延层耗尽层宽度t_(mina(μm)的比值为t_(minp)/t_(mina)=2.565。在实践上,为证实两种模型的功能,利用两种探针进行了对比测试。一种是通常被采用的点接触锇尖探针:另一种是利用φ0.8±0.1mm的银针,在银针顶上吸上φ0.4±0.1mm的汞球,以实现面接触。理论和实验吻合良好。     

应用人工神经网络进行电力系统动态安全评价的新方法

本文提出了一种应用人工神经网络进行电力系统动态安全评价的新方法。把故障前系统的稳态运行参数作为特征量,摇摆过程中发电机转子间的最大相对摇摆角作为系统稳定性的量度,并证明了它们之间呈连续映射关系。随后表明了用三层前向网络实现这类映射的可行性。为减少神经网络的训练时间,本文提出了网络“分解—集结”方法和映射与分类相结合的思想。6机22节点系统的试验结果表明了本文提出方法的有效性。     

神经网络自适应噪声对消的研究

基于神经网络中自适应线性单元(ADALINE),结合传统自适应噪声对消原理,提出了一种基于ADALINE的改进型自适应噪声对消器。经仿真和实例证明,具有很强的噪声滤除能力和鲁棒性。