KIMS—A knowledge-based computer vision system for production line inspection

the aim of this paper is to discuss a generic expert system prototyped for image analysis and interpretation tasks. The system christened KIMS is a knowledge-based image management system which oversees the entire process of image processing, segmentation, feature extraction, knowledge representation along with an expandable capability for image understanding task. We discuss the architecture of KIMS, its modeling environment, and demonstrate its usefulness with photo-to-image inspection as applied to a manufacturing line.     

Knowledge-directed inspection for complex multilayered patterns

Combining the knowledge-based processing with image processing is considered a key issue in the future of visual inspection of complex patterns such as multilayered semiconductor wafers. However, present technology restricts this combination, mainly because of the exhaustively long time usually required for each type of processing. To cope with this situation, a unique knowledge-directed image processing method is proposed, in which every image processing step is controlled in real time by parametric knowledge driven by design patterns. The resulting structure of the image processor is a pipeline, in which each piece of knowledge is embodied as a combination of a hardware processing unit and control unit. In this paper the types of knowledge and their implementation are explained, and an inspection machine for logic IC wafers based on this pipelined knowledgedirected image processing is introduced.     

An IKB defect classification system for automated industrial radiographic inspection

Abstract: This paper presents work undertaken as part of a project concerned with the development of a fully automated industrial radiographic inspection system, based on both conventional image-processing techniques for the detection and analysis of defects in the radiographic image, and intelligent knowledge-based (1KB) techniques for the classification and evaluation of defect data against the quality assurance requirements of the inspection process. In this paper the 1KB defect classification system is presented. This system is based on a hierarchical frame-based knowledge representation and a backward-chaining production rule system. Examples of the frame structures, frame taxonomies and the data-driven procedures, which maintain the knowledge base are given, along with an outline of the defect classification rules and the inference mechanism for dealing with uncertainty by means of confidence factors.     

机器视觉在印刷缺陷在线检测中的应用与研究

为了提高印刷缺陷检测准确性与效率,满足缺陷检测的实时性,提出了机器视觉技术应用于印刷缺陷在线检测并研究检测过程中的相关问题.设计印刷缺陷在线检测的方案及以数字信号处理器DSP为核心的视觉在线检测系统的硬件结构组成.研究图像预处理、图像匹配与缺陷检测的算法并加以改进使其满足缺陷检测的实时性.开发印刷品缺陷视觉检测软件,对缺陷检测流程进行仿真,验证检测方案与图像处理算法的可行性.     

Process knowledge based multi-class support vector classification (PK-MSVM) approach for surface defects in hot rolling

Random surface defects occur during the hot bar rolling of steels and are identified either by manual or by automated inspection techniques. Manual inspection techniques are purely based on the process knowledge of the inspector such as the location, type and kind of defects, and the primary sources of these defects. The automated techniques, to identify and classify the defects, rely on machine vision technologies and image processing algorithms based on support vector machines, wavelets, image processing and statistical inference. Both these approaches have their own advantages and limitations. To improve the accuracy of classification of these defects a process knowledge based support vector classification scheme is proposed (called PK-MSVM) which combines feature extraction task of automated inspection with the process knowledge. The defect observation data from the imaging sensor is transformed to include this process knowledge. Three attributes of the defects – length to width ratio, longitudinal location and transverse location- are used for this transformation are they are closely related to the thermo-mechanics of the rolling process. Different formulations of the multi-class support vector machines (MSVMs) are compared for this classification with or without process knowledge based transformation: one-against-one, one-against-all and Hastie’s algorithm of multi class SVM. It is found that the new approach (PK-MSVM) performs better than traditional MSVM for all the three formulations. For the best case, the performance sees a jump of more than 100%. Thus incorporating process knowledge in identification and classification does increase the reliability of inspection considerably.     

基于FPGA图像处理技术在钢板表面缺陷检测系统中的应用

为了解决钢板表面缺陷视觉检测系统中图像处理的瓶颈问题,采用基于FPGA的嵌入式处理系统完成大数据量、实时、在线的处理任务,从而满足高速、宽幅、高分辨率的检测要求.嵌入式系统以Altera公司最新的Stratix FPGA作为核心处理器,在分析FPGA专有的硬件结构基础上,对图像处理中的模板卷积算法进行了优化设计,采用Verilog语言对算法完成建模与实现,并在Quartus Ⅱ平台进行了仿真验证.实验与算法仿真证明嵌入式处理系统的可行性与工程实用性,从而表面缺陷检测系统中的图像信息实时处理这一关键问题得以解决.     

Knowledge-based environment for investigating multicomputer architectures

Multicomputers for massively parallel processing will eventually employ billions of processing elements, each of which will be capable of communicating with every other processing element. A knowledge-based modelling and simulation environment (KBMSE) for investigating such multicomputer architecture at a discrete-event system level is described. The KBMSE implements the discrete-event system specification (DEVS) formalism in an object-oriented programming system of Scheme (a dialect), which supports building models in a hierarchical, modular manner, a systems-oriented approach not possible in conventional simulation languages. The paper presents a framework for knowledge-based modelling and simulation by exemplifying modelling a hypercube multicomputer architecture in the KBMSE. The KBMSE has been tested on a variety of domains characterized by complex, hierarchical structures such as advanced multicomputer architectures, local area computer networks, intelligent multi-robot organizations, and biologically based life-support systems.     

竹地板选片工艺的机器视觉化研究及实现

针对竹地板加工中的“选片工艺”,构建了基于机器视觉的竹片缺陷检测与颜色分拣平台,研究了竹片缺陷与颜色检测过程中图像采集、光学成像、光学照明等关键问题,设计了竹片缺陷检测及颜色识别的图像处理算法及软件流程,并探讨了竹片缺陷检测与颜色分拣平台的机械传动、分拣执行装置及电控实现。仿真实验表明,提出的竹片缺陷检测及颜色识别算法能够对采集系统摄取的竹片图像进行准确的检测与识别,能够完成竹片6种常见的缺陷检测以及4种以上的色差识别,对提高选片工艺的生产效率具有重要意义。     

Knowledge-based system for supporting statistical database management

In the development of the expert system described here, knowledge-based information processing has been approached from the point of view of database technology. The outlines and processes of arranging an economic national balances system are provided, and the problems encountered in applying the variables involved in such a process to an expert system are identified. The structure and architecture of the expert system are defined, and the problems of knowledge acquisition are discussed.     

Automatic optical inspection system for IC molding surface

Success or failure of an IC product hinges on the quality of molding process which protects chips from the harm done by external force and moisture. Defects such as cracks, dilapidations or voids may be embedding on the molding surface while a chip was being molded. Human inspection often neglects a very tiny crack or a low-contrast void. Hence an automatic optical inspection system for the integrated circuit (IC) molding surface cannot be over emphasized. The proposed system is composed of a charged coupled device, a coaxial light, a back light and a motion control unit. Based on the characteristics of statistical textures of the molding surface, a series of digital image processing is carried out, including normalization, shrinking, segmenting and Fourier based image restoration and defect identification. Training of the parameter associated with defect inspection algorithm is also discussed. Results of the experiment suggest that the inspection system works effectively with high accuracy rate of 94.2 %, contributing to the inspection quality of IC molding surface.     

基于知识的Deep Web集成环境变化处理的研究

研究了Deep Web集成环境中构件的依赖关系(执行偏序依赖和知识依赖),并在此基础上提出了一种基于知识的环境变化的处理方法,包括Deep Web集成环境变化处理模型以及适应Deep Web环境变化的动态体系结构和处理算法,可以对大规模Deep Web集成的进一步探索和走向应用提供参考.实验结果表明,该方法不仅可以处理Deep Web环境的变化,还可以大幅度提高集成系统的性能.     

一种基于知识模型的CT图像分割方法*

图像自动分割一直是医学图像处理的研究重点。系统由解剖知识模型、图像处理程序和推理机组成。模块之间的通信由黑板控制。该方法提高了医学图像分割的自动化程度和可靠性。由于具有扩展性,该方法为基于知识医学图像的处理提供一个通用的模式。     

印刷品缺陷检测的初步方案

印刷品缺陷检测技术有着重要的实际意义。介绍了基于数字图像处理的印刷品缺陷检测系统的设计,并对主要模块即图像采集及预处理、模板制作、图像对准、缺陷检测进行了分析研究。实验结果表明,充分考虑人眼视觉特性,将动态阈值法引入缺陷检测,能够显著提高印刷质量检测系统的检测精度。     

输电线路部件视觉缺陷检测综述

随着我国电网系统的不断发展，基层巡检作业负担越来越重，运维成本越来越高，如何实现输电线路部件缺陷的智能化检测变得愈发重要。同时，由于国家《新一代人工智能发展规划》的提出和国家电网"数字新基建"的部署，人工智能应用于电力设备运维的相关技术得到了快速发展，对输电线路部件视觉缺陷准确检测成为亟待解决的关键问题之一。早期基于图像处理和特征工程的部件视觉缺陷检测方法对图像质量的要求较高，无法真正应用于现实复杂的输电线路作业环境；随着深度学习的兴起，基于深度学习的检测模型可以有效地将部件目标及其缺陷从复杂的输电线路航拍图像中提取出来，既节省了人工设计特征的时间，又在性能上达到了显著提升，因此逐渐成为主流研究方法。本文首先描述了基于传统算法的输电线路关键部件视觉缺陷检测技术，回顾了深度学习的发展过程并分析了深度学习在缺陷检测领域的优缺点；围绕输电线路上3个重要的部件：绝缘子、金具以及螺栓，介绍了其定位与缺陷检测的研究现状；分析了输电线路部件缺陷检测中研究的样本不平衡问题、小目标检测问题、细粒度检测问题等几个关键问题；分析了符合电网巡检任务复杂场景需求和故障诊断标准的输电线路部件缺陷检测技术的未来发展趋势。     

Different roles and mutual dependencies of data, information, and knowledge — An AI perspective on their integration

The unclear distinction between data, information, and knowledge has impaired their combination and utilization for the development of integrated systems. There is need for a unified definitional model of data, information, and knowledge based on their roles in computational and cognitive information processing. An attempt to clarify these basic notions is made, and a conceptual framework for integration is suggested by focusing on their different roles and frames of reference within a decision-making process. On this basis, ways of integrating the functionalities of databases, information systems and knowledge-based systems are discussed by taking a knowledge level perspective to the analysis and modeling of systems behaviour. Motivated by recent work in the area of case-based reasoning related to decision support systems, it is further shown that a specific problem solving episode, or case, may be viewed as data, information, or knowledge, depending on its role in decision making and learning from experience. An outline of a case-based system architecture is presented, and used to show that a focus on the retaining and reuse of past cases facilitates a gradual and evolutionary transition from an information system to a knowledge-based system.     

Signal processing and defect analysis of pipeline inspection applying magnetic flux leakage methods

Corrosion, stresses and mechanical damage of oil and gas pipelines can result in catastrophic failures, so pipeline safety evaluation is an important problem of oil and gas transmission. To evaluate the pipeline safety, this paper described a novel magnetic flux leakage (MFL) inspection device, and the designing MFL intelligent inspection pig was used to multi-radius pipelines and variational work condition. At the same time, because signal processing and defect recognition technique is one of the most important techniques in offshore pipeline inspection MFL system, the paper also discussed its signal processing procedure. Time-frequency analysis, median and adaptive filter, and interpolation processing are adopted to preprocess MFL inspection signal. In order to obtain high sensitivity and precision, we adopted multi-sensor data fusion technique. A wavelet basis function neural network was used to recognize defect parameters. The main contribution of the article is that we presented a novel method to evaluate and predict oil pipelines’ condition through combining neural network, data fusion and expert system techniques, and through constructing a knowledge-based off-line inspection expert system, the system improved its defect recognition capability greatly.     

Hough变换在数码印花飞线检测中的应用

针对织物数码印花过程中出现的飞线问题, 以Hough变换理论为基础, 结合图像处理技术, 构建了一套数码印花飞线自动检测系统. 通过Hough变换提取出图像的直线特征信息后, 利用互相关系数检测出数码印花过程中出现的飞线问题, 最后通过人工检测和检测结果比较发现, 该系统较好地完成了数码印花飞线的自动检测.     

基于Qt与Arm NN的嵌入式喷码检测系统设计与实现

现存的喷码检测系统大多基于工控PC电脑实现,其在价格、体积、功耗、灵活性等方面存在着较大的局限性。为此,设计了一种基于Qt与Arm NN的嵌入式喷码检测系统,该系统的核心处理器采用Arm cortex-a9,搭载配置有相关软件工具的嵌入式linux操作系统,采用位置检测算法来实现软件检测待测目标的位置,通过由图像预处理、喷码区域提取、条形码识别、字符子串分割、基于卷积神经网络及caffe框架的喷码字符识别模型训练、利用Arm NN将识别模型引入到ARM端实现喷码字符识别、识别结果处理等过程组成的喷码检测算法来实现对喷码内容的检测。该系统还基于Qt多线程技术开发了具有完善系统功能的图形应用程序,便于现场生产人员使用。经相关测试表明该系统有效可行、正检率高,能够满足包装生产流水线喷码检测的实际需求。