Showing papers on "Visual inspection published in 2007"

A Real-Time Visual Inspection System for Railway Maintenance: Automatic Hexagonal-Headed Bolts Detection

Abstract: Rail inspection is a very important task in railway maintenance, and it is periodically needed for preventing dangerous situations. Inspection is operated manually by trained human operator walking along the track searching for visual anomalies. This monitoring is unacceptable for slowness and lack of objectivity, as the results are related to the ability of the observer to recognize critical situations. The correspondence presents a patent-pending real-time Visual Inspection System for Railway (VISyR) maintenance, and describes how presence/absence of the fastening bolts that fix the rails to the sleepers is automatically detected. VISyR acquires images from a digital line-scan camera. Data are simultaneously preprocessed according to two discrete wavelet transforms, and then provided to two multilayer perceptron neural classifiers (MLPNCs). The "cross validation" of these MLPNCs avoids (practically-at-all) false positives, and reveals the presence/absence of the fastening bolts with an accuracy of 99.6% in detecting visible bolts and of 95% in detecting missing bolts. A field-programmable gate array-based architecture performs these tasks in 8.09 mus, allowing an on-the-fly analysis of a video sequence acquired at 200 km/h

COLIBRI: A vision-guided UAV for surveillance and visual inspection

Abstract: UAVs (Unmanned Aerial Vehicles) are becoming more popular for civil task due to their unique flight capabilities. The video shows several capabilities of a platform used as main research testbed of computer vision for unmanned aerial vehicles. Four major research areas are explored in the present work as visual servoing, trajectory planning, power line inspection and stereo-based visual navigation.

Real-time Automated Visual Inspection using Mobile Robots

Abstract: We present a framework to perform novelty detection using visual input in which a mobile robot first learns a model of normality in its operating environment and later uses this to highlight uncommon visual features that may appear. This ability is of great importance for both robotic exploration and inspection tasks, because it enables the robot to allocate computational and attentional resources efficiently to those features which are novel. At the heart of the proposed system is the image encoding mechanism which uses local colour statistics from regions selected by a biologically-inspired model of visual attention. Our approach works in real-time with a wide, unrestricted field of view and is robust to image transformations. Experiments conducted in an engineered scenario demonstrate the efficiency and functionality of our method.

COLIBRI: A vision-Guided UAV for Surveillance and Visual Inspection

Abstract: UAVs (unmanned aerial vehicles) are becoming more popular for civil task due to their unique flight capabilities. The video shows several capabilities of a platform used as main research testbed of computer vision for unmanned aerial vehicles. Four major research areas are explored in the present work as visual servoing, trajectory planning, power line inspection and stereo-based visual navigation.

Development of an inspection system for cracks in a concrete tunnel lining

Abstract: Over the last several decades, many concrete tunnels have been constructed for roads, highways, and railways. For safety in concrete tunnels, periodic inspections have been conducted using nondestructive testing technologies and techniques. However, nondestructive tests cannot replace visual inspection because of their slow and complicated procedures. For this reason, their use has been limited to precision inspections. Visual methods of assessment also require significant time commitments, and they produce subjective results regarding measured crack data. This study proposes an inspection system for the rapid measurement of cracks in tunnel linings and provides an objective method for assessing crack data for safety purposes. The system consists of both image data acquisition and analysis systems. The acquisition system takes images with charge-coupled device (CCD) line-scan cameras. The analysis system extracts crack information from the acquired images using image processing. Measured crack information...

Visual inspection apparatus, visual inspection method, and peripheral edge inspection unit that can be mounted on visual inspection apparatus.

Abstract: This visual inspection apparatus has a macro-inspection section and a micro-inspection section. In the micro-inspection section, a inspection stage and a microscope are loaded into a loading plate. The inspection stage can be moved in any directions of the X, Y, and Z directions, and can also be rotated in the θ direction. Moreover, a peripheral edge inspection section that acquires an enlarged image of a peripheral edge of wafer W is fixed to the loading plate. The peripheral edge inspection section is arranged so as to image the peripheral edge of wafer W held by the inspection stage.

Portable inspection device, portable inspection system, inspection method, and program

Abstract: PROBLEM TO BE SOLVED: To provide a portable inspection device, a portable inspection system, an inspection method and a program for performing the inspection work with higher accuracy with safety in the inspection work. SOLUTION: A portable inspection device 2 is provided for communicating via an inspection server 3 for recording measurement data showing the result of measuring an operating state of the inspection object and a network 11. This portable inspection device 2 has an inspection information recording part 34 in which the inspection information including the information showing the method of measuring the measurement data is recorded in advance, a voice output part 107 for outputting by voice the information showing the measuring method at least among the inspection information, a measurement data acquisition part 109 for acquiring the measurement data based on the measuring method, and a control data acquisition part 110 for acquiring the control data for controlling the operation of the inspection object when the measurement data acquisition part acquires the measurement data from the inspection server. The measurement data and the control data are used to determine if the inspection object normally operates or not. COPYRIGHT: (C)2009,JPO&INPIT

Visual inspection method, device therefor, and image processing evaluation system

Abstract: PROBLEM TO BE SOLVED: To provide a technology capable of improving substantial sensitivity by suppressing false reports, while keeping the whole defect capturing rate high, in order to solve the problem wherein high-sensitivity inspection becomes impossible because many false reports are detected when the sensitivity is set high in visual inspection. SOLUTION: This method has a constitution wherein an image characteristic quantity is calculated based on an image of a detected defect, and a coordinate characteristic quantity is calculated based on a position coordinate of the detected defect, and false report determination is performed following a decision tree comprising threshold processing to either of the image characteristic quantity and the coordinate characteristic quantity. Resultantly, since discrimination between an actual defect and a false report can be performed accurately by performing the false report determination following the decision tree by utilizing the image characteristic quantity and the coordinate characteristic quantity, high-sensitivity inspection becomes possible, while suppressing false reports. COPYRIGHT: (C)2009,JPO&INPIT

Method of alignment for efficient defect review

Abstract: An inspection system includes a SEM visual inspection apparatus for detecting a defect in a semiconductor sample in steps of manufacturing a semiconductor device and a review apparatus for observing, at a high resolution, the defect in the semiconductor sample detected by the SEM visual inspection apparatus The system has a function of transmitting an alignment dictionary image as one of alignment parameters to be set by the SEM visual inspection apparatus using an inspection recipe to the review apparatus

Development of an inspection system for cracks in a concrete tunnel lining

Abstract: Over the last several decades, many concrete tunnels have been constructed for roads, highways, and railways. For safety in concrete tunnels, periodic inspections have been conducted using nondestructive testing technologies and techniques. However, nondestructive tests cannot replace visual inspection because of their slow and complicated procedures. For this reason, their use has been limited to precision inspections. Visual methods of assessment also require significant time commitments, and they produce subjective results regarding measured crack data. This study proposes an inspection system for the rapid measurement of cracks in tunnel linings and provides an objective method for assessing crack data for safety purposes. The system consists of both image data acquisition and analysis systems. The acquisition system takes images with charge-coupled device (CCD) line-scan cameras. The analysis system extracts crack information from the acquired images using image processing. Measured crack information includes the thickness, length, and orientation of cracks. To improve the accuracy of crack recognition, the geometric properties and patterns of cracks in concrete structures should be applied to image processing. This proposed system was verified through a series of experiments in both laboratory and field environments. (A)

Behavior-based control system of a mobile robot for the visual inspection of ventilation ducts

Abstract: The paper deals with the implementation of a behavior-based control and learning controller for autonomous inspection robots. The presented control architecture is designed to be used in the mobile robot (Amigo) for the visual inspection of ventilation systems. The main aim of the authors’ study is to propose a behavior-based controller with neural network-based coordination methods. Preliminary results are promising for further development of the proposed solution. The method has several advantages when compared with other competitive and/or co-operative approaches due to its robustness and modularity.

Health Assessment and Maintenance Strategy for Bridge Management Systems: Lessons Learned in Taiwan

Abstract: Usually the rating values are determined by visual inspection in most of the bridge management systems (BMSs). A visual inspection is not very objective, and can sometimes result in a different assessment of element condition that may lead to improper prioritization for corrective action. Our novel evaluation results in a more objective condition rating based on visual inspection data. In order to provide an easier way to arrange and prioritize the maintenance schedule among the bridges, the health condition of a bridge needs to be diagnosed in a more practical and more accurate manner. This work utilized systematic classification and statistical analysis based on the thousands of sets of existing bridge inspection data collected in Taiwan over the past five years, with the following goals in mind: (1) develop a normal zone in the health condition shown on the diagnostic figure, and identify the health situation for the bridge using a specific inspection condition; (2) determine the time when the bridge will be in the worst situation, then determine the proper time for maintenance to be carried out; (3) introduce a new data process and innovative model into the BMS in Taiwan, as it will definitely be an asset to be able to estimate reliable maintenance costs in the future.

Remote inspection, measurement and handling for LHC

Abstract: Personnel access to the LHC tunnel will be restricted to varying extents during the life of the machine due to radiation, cryogenic and pressure hazards. The ability to carry out visual inspection, measurement and handling activities remotely during periods when the LHC tunnel is potentially hazardous offers advantages in terms of safety, accelerator down time, and costs. The first applications identified were remote measurement of radiation levels at the start of shut-down, remote geometrical survey measurements in the collimation regions, and remote visual inspection during pressure testing and initial machine cool-down. In addition, for remote handling operations, it will be necessary to be able to transmit several real-time video images from the tunnel to the control room. The paper describes the design, development and use of a remotely controlled vehicle to demonstrate the feasibility of meeting the above requirements in the LHC tunnel. Design choices are explained along with operating experience to-date and future development plans.

Sewer asset management: from visual inspection survey to dysfunction indicators

Abstract: Asset management is an increasing concern for wastewater utilities and companies. Criteria are developed for supporting the definition of investigation and rehabilitation programs. Dysfunction indicators contribute to the calculation of criteria, using expert rules. These indicators are mostly based on visual inspections, which provide major information. However, difficulties remain in the translation of visual inspection survey into dysfunction indicators. This article presents a methodological approach aiming to fill this lack. In the framework of the French RERAU program (Rehabilitation of urban sewer networks) a methodological approach has been developed in order to convert visual inspections of sewer segments into four possible condition grades {1, 2, 3, 4}, grade 4 corresponds to the worse condition. Three complementary procedures are thus executed: (a) expert rules based on sequences of observation codes, (b) comparison of single score to threshold and (c) rules based on analysis of segment profiles (scores distribution). An experiment lead in the Bas-Rhin (France) illustrates the different steps of the methodological approach and the applicability of the RERAU methodology on CCTV data. Moreover, confrontation between expert assessment of sewer segments (condition grade) and calculated scores has demonstrated the necessity of considering diagnosis imperfection, which may lead to misclassification in some cases. The algorithm proposed in this article aims to minimize a cost function with costs assigned to false positive diagnosis test (segment classified in worse condition than experts' opinion) and false negative diagnosis test (segment classified in better condition than experts' opinion). The algorithm is described in detail and applied to an example. Thus imprecision of assessment is taken into account: the threshold is chosen as to be the most efficient (in term of cost). This approach is generally applicable to numerous domains, when levels of performance need to be defined.

Aviation inspection assistant device

Abstract: PROBLEM TO BE SOLVED: To provide an aviation inspection assistant device capable of safely performing aviation inspection, automatically listening information required for inspection, and certainly and efficiently performing inspection. SOLUTION: The aviation inspection assistant device comprises an inspection section Pr for performing the inspection among flight routes; an air transportation section Tr; a route setting means for setting an inspection object; an inspection assistant means for guiding the discrimination of an iron tower and the past inspection record and recording the present inspection result when an aircraft approaches the individual iron tower in the inspection section Pr; and a mode switching means for activating the inspection assistant means during the aircraft flies the inspection section Pr. Since the inspection assistant means is automatically activated by the mode switching means when the aircraft approaches the inspection section Pr, the inspection can be certainly performed by making the aircraft approaching the inspection object. Further, since the inspection assistant means guides the discrimination and also guides the past inspection record regarding the individual iron tower which the aircraft approaches, an inspector can automatically obtain information required for the inspection, therefore, attention can be concentrated to the monitoring of the inspection object. COPYRIGHT: (C)2009,JPO&INPIT

Machine vision for railroad equipment undercarriage inspection using multi-spectral imaging

Abstract: Current practices for inspection of railcars and locomotives include both manual and automated systems. However, inspection of railroad equipment undercarriages is almost entirely a manual process. Visual inspections by humans are performed either in a pit or trackside. The equipment is usually stopped over the pit or run slowly past the trackside inspector. In the latter case, it is not possible for a human to have an unobstructed view of the undercarriage as a train rolls by. Automated inspection by electronic systems has the potential to overcome certain limitations of human inspection. The report describes the Innovations Deserving Exploratory Analysis (IDEA) project conducted to develop a new approach to undercarriage inspection by means of machine vision analysis. This approach uses multispectral imaging from cameras viewing the undercarriage from a below-the-track perspective. Imaging using both visible and infrared spectra provides a means by which incipient failure detection can be addressed. Detection of missing, damaged, and foreign objects can also be identified using this approach. By extracting frames from video recordings in both spectra, panoramic images of the entire train can be created and analyzed. These images are further subdivided into individual railcar panoramas that can be matched to templates of railcars in known good condition to detect missing and foreign objects. More detailed diagnosis can be provided by using specific component-level templates allowing identification of damaged and overheated subcomponents. In addition, comparisons can be made of duplicate component systems during operation, such as disk brakes, to discover thermal outliers indicating improper function. A prototype of this machine vision inspection system has been developed and tested at a passenger car service and inspection facility. This investigation demonstrates the feasibility of a machine vision system to provide undercarriage inspection capabilities, as the train passes over the pit, aiding inspection crews and repair personnel. The system provides a clear and unobstructed visible spectrum assessment of the undercarriage in addition to an assessment from the thermal spectrum as well. The joint analysis of these undercarriage views can provide automatic detection of components in need of repair and also those that may be over worked or near failure. This allows the inspector to be aware of indications indicative of component problems that are developing, which may fail in the future. Therefore the system has potential for providing advanced warning, allowing additional time for repair personnel to plan repairs prior to possible in-service failures.

Evaluation of interaction devices for projector based virtual reality aircraft inspection training environments

Abstract: The Aircraft maintenance and inspection is a complex system wherein humans play a key role in ensuring the worthiness of the aircraft Traditional visual inspection training consisted mainly of on-the-job training (OJT) While OJT provides novice inspectors with the hands-on experience critical to effective transfer, it lacks the ability to provide real-time feedback and exposure to various scenarios in which to inspect With advances in technology, computer simulators have been developed to train the novice inspector and reduce the learning curve inherent with transitioning from the classroom to the workforce Advances in graphics and virtual reality (VR) technology have allowed for an increase the sense of involvement in using these simulators Though these simulators are effective, their deployment in aircraft maintenance training schools is limited by the high cost of VR equipment This research investigates the effectiveness of different interaction devices for providing projector based simulated aircraft maintenance inspection training

Visual inspection method and visual inspection device

Abstract: PROBLEM TO BE SOLVED: To provide a visual inspection method and a visual inspection device capable of setting an inspection domain regardless of the shape of an inspection object, and performing visual inspection of the inspection object with extremely high accuracy. SOLUTION: This visual inspection method has a process for acquiring an imaged image, a process for generating a master image and an extended master image, a process for determining the inspection domain based on an approximate straight line acquired by approximating by a line a sequence of points constituted of the center part, and the fringe part of the inspection object and a plurality of change points where each output brightness value is changed, a process for generating an inspection domain image P5 acquired by extracting the brightness value of each pixel in a domain corresponding to the inspection domain from the imaged image, a process for generating a non-inspection target domain image P7 acquired by setting the brightness value of each pixel in a non-inspection target domain so as to suppress a brightness value change in the non-inspection target domain when being synthesized with inspection domain image P5, and a process for generating a synthetic image P8 acquired by synthesizing the inspection domain image P5 with the non-inspection target domain image P7. COPYRIGHT: (C)2007,JPO&INPIT

Visual inspection apparatus

Abstract: PROBLEM TO BE SOLVED: To provide a visual inspection apparatus capable of high-accuracy detection, even if the number of imaging means is reduced. SOLUTION: The visual inspection apparatus for visual inspection of an object to be inspected (C) is provided with an imaging means (3), arranged in such a way as to image the main inspection surface, when the object to be inspected (C) is viewed from a specific direction and is further provided with alteration means (4-7) for altering the direction of light from a sub-inspection surface, in such a way that images of the sub-inspection surface, when the object to be inspected (C) is viewed from a direction different from the specific direction, is captured in the imaging means (3). The visual inspection apparatus is yet further provided with optical path redundancy means (10, 12) for making a second optical path redundant, in order to make the optical path length of the second optical path, from the main inspection surface of the object to be inspected (C) to the imaging means (3) match the optical path length of a first optical path, from the sub-inspection surface of the object to be inspected (C) to the imaging means (3). COPYRIGHT: (C)2009,JPO&INPIT

Analyses of stone surfaces by optical methods

Abstract: Ornamental stone products are generally used for decorative cladding. A major quality parameter is their aesthetical appearance, which directly impacts their commercial value. The surface quality of stone products depends on the presence of defects both due to the unpredictability of natural materials and to the actual manufacturing process. This work starts reviewing the literature about optical methods for stone surface inspection. A classification is then proposed focusing on their industrial applicability in order to provide a guideline for future investigations. Three innovative systems are proposed and described in details: a vision system, an optical profilometer and a reflectometer for the inspection of polished, bushhammered, sand-blasted, flame-finished, waterjet processed, and laser engraved surfaces.

Overview of 3D registration techniques including loop minimization for the complete acquisition of large manufactured parts and complex environments

Abstract: 3D modelling is becoming an important research topic for visual inspection in automatic quality control. Through visual inspection it is possible to determine whether a product fulfills the required specifications or whether it contains surface or volume imperfections. Although some process such as color analysis can be achieved by 2D techniques, more challenging tasks such as volume inspection of large and complex objects/scenes may require the use of accurate 3D registration techniques. 3D Simultaneous Localization and Mapping has become a very important research topic not only in the computer vision community for quality control applications but also in the robotics field for solving problems such as robot navigation and registration of large surfaces. Although their techniques differ slightly depending on the application, both communities tend to solve similar problems by means of different approaches. This paper presents a survey of the techniques used by the robotics and computer vision communities in which every approach has been compared pointing out their pros and cons and their potential applications.

Visual inspection apparatus and visual inspection method

Abstract: The present invention is related to a visual inspection apparatus which can perform various adjustments simply and rapidly. The visual inspection apparatus includes a wafer holder for holding a wafer to be movable in the X, Y, and Z directions and rotatable about the Z axis and a peripheral edge imaging section used to observe a peripheral edge of the wafer W, which are disposed close to each other. A computer for controlling the visual inspection apparatus includes an inspection controller for performing a process of making a visual inspection of the peripheral edge of the wafer W pursuant to a recipe and an interrupt processor for stopping the inspection pursuant to the recipe and receiving a change in inspection condition from scroll bars when an inspector selects an interrupt process.

In-line automatic inspection device and in-line automatic inspection system

Abstract: PROBLEM TO BE SOLVED: To save a space in the periphery of a production line, to enhance inspection efficiency, and to reduce a cost. SOLUTION: This in-line automatic inspection device/system is provided with an upstream conveying part for conveying an inspection object along a conveying route, an inspection part arranged adjacently each other to be adjacent in a downstream of the upstream conveying part, for supporting incliningly the inspection object to carry out visual inspection, and for allowing passing of the inspection object in the downstream, a downstream conveying part arranged adjacently each other to be adjacent in the downstream of the inspection part, and for conveying the inspection object after inspected to the downstream along the conveying route, an upstream transfer part for transferring the inspection object from the upstream conveying part to the inspection part, and a downstream transfer part for transferring the inspection object from the inspection part to the downstream conveying part. The inspection part is provided with a turning mechanism for inclining a work table to allow the visual inspection. COPYRIGHT: (C)2008,JPO&INPIT

Intelligent visual inspection of bottling production line through Neural Network

Abstract: This paper presents research done on developing an intelligent visual inspection system for automatic inspection of bottling production line. The objective of this research is to enhance on modeling, integrating, and implementation of intelligent visual inspection system in the process of quality control in industrial manufacturing. The system will inspect each individual product in real-time process. Levenberg-Marquardt backpropagation neural network has been applied for this system to differentiate between acceptable and unacceptable product, for example, the misplacement of a bottle cap. A simulation of the operation was attempted in the Robotics System Laboratory of Industrial Computing Department, Universiti Kebangsaan Malaysia. The experiments were done by using developed software (Real-TIVI) and hardware, i.e. conveyor belt, adjustable halogen lamp, personal computer, web camera (webcam) to capture the image, and plastic bottle as an object of visual inspection. From this experiment, the maximum regular speed of a rotating object was 106 rpm. The result shows the system is accurate to determine between acceptable (normal) and non-acceptable (no cap or misplace of cap) during the maximum speed when the distance between webcam and the object was at 15 cm. keywords: Bottling Production Line, Neural Network, Quality Control, Visual Inspection 1.0 IntroductIon In industrial manufacturing, product inspection is an important step in the production process. Since product reliability is of utmost importance in most mass production facilities, 100 percent product inspection of all parts, subassemblies, and finished product is often being attempted. The most difficult task for inspection is inspecting by visual appearance. Visual inspection seeks to identify both functional and cosmetic defects. The visual inspection in most manufacturing process depends mainly on human operators whose performance is generally inadequate and variable. Advances in technology have resulted in better, cheaper image analysis equipment, which enable the use of affordable automated visual inspection system [1]. The major advantages of automatic operation are speed and diagnostic capabilities. There has been extensive research in the area of visual inspection system. These activities include, among others, delicate electronics component manufacturing, quality textile production, metal product finishing, glass manufacturing, machine parts, printing products and granite quality inspection, integrated circuits (IC) manufacturing and many others [29]. Visual inspection technology improves productivity and quality management and provides a competitive advantage to industries that employ this technology. The requirements for the design and development of a successful visual inspection system vary depending on the application domain and are related to the tasks to be accomplished, environment, speed, etc. For example, in visual inspection applications, the system must be able to differentiate between acceptable and unacceptable variations or defects in products, while in other applications, the system must enable users to solve guidance and alignment tasks or, verify measurement and assembly tasks. 1.1 proBlem statement There exists no industrial vision system capable of handling all tasks in every application field. Only once the requirements of a particular application domain are specified, then appropriate decisions for the design and development of the application can be taken [10]. The first problem to solve in automated visual inspection task is to understand what kind of information the visual inspection system is to retrieve and how this translates into measurements or features at the images. The artificial intelligence techniques have been applied for visual inspection to differentiate between acceptable and unacceptable (reject) products. This paper presents a neural network application to recognise between accepted and rejected products in the real-time visual inspection system, especially in bottling production line. Journal The Institution of Engineers, Malaysia (Vol. 68, No.4, December 2007) 57 (Date received: 19.2.2008) rIza sulaIman and anton s. praBuwono Journal The Institution of Engineers, Malaysia (Vol. 69, No.4, December 2008) 58 2. related work 2.1 Image processIng tools Image processing is usually performed within rectangles, circles or along lines and arcs. Image processing operators include filtering (e.g. smoothing, sharpening), edge detection, threshold, morphological operations, etc. Such operations can be used to improve image quality (e.g. reduce noise, improve contrast) and to enhance or separate certain image features (e.g. regions, edges) from the background. Image processing operations transform an input image to another image having the desired characteristics. Image analysis is related to the extraction and measurement of image features and transforms these image features to numbers, vectors, character strings, etc. For example, lines, regions, characters, holes, rips, tears can be gauged or counted. The ultimate goal of image analysis is geared towards pattern recognition, i.e. the extraction of features that can be used by classifiers to recognise or classify objects [10]. A comparative chart of some of the most popular image processing tools and a proposed technology (Real-TIVI) is given in the Table 1. software package library Visual programming command line dedicated hardware source code IPL Lib Yes Yes No Yes No Sherlock32/MVTools Yes Yes No Yes Yes Image-Pro plus Yes Yes No No No OPTIMAS Yes Yes No No No WiT Yes Yes Optional Yes No PC Image Flow Yes Yes Datacube Yes No Intel Image Processing Lib. Yes No MMX No HALCON Yes Yes No No No VISION97 Yes Yes (frame grabber) No No AdOculos Yes Yes No No MIL Yes Yes Matrox Yes No Rhapsody Yes No No Yes No Real-TIVI Yes Yes No No Yes table 1 : comparison of some of the most image processing tools and real-tIVI 2.2 neural network approach Neural networks are being successfully applied across a wide range of application domains in business, medicine, geology and physics to solve problems of prediction, classification and control. Neural networks are composed of a number of similar elementary processing units (neurons) connected together into a network [11]. Neurons are arranged in layers with the input data initialising the processing at the input layer. The processed data of each layer passes through the network towards the output layer. Neural networks adapt the weights of their neurons during a training period based on examples, often with a known desired solution (supervised training). After sufficient training, the neural network is able to relate the problem data to the appropriate solution spaces, i.e. generate input/ output relations, thus offering a viable solution to a new problem through examples [12]. Neural networks are capable of handling a variety of image classification tasks in industrial vision environments, ranging from simple gauging to advanced classification problems, such as fault detection, optical character recognition, operation prediction, engine monitoring and control, etc. They can be used either as standalone techniques e.g. wood [13], seam [3], and surface roughness inspection [14], or in conjunction with other methods (e.g. solder joint inspection) [15]. Neural networks have been applied in all classes of quality inspection, namely dimensional quality [16,15,17], surface quality [3,14,18,19], structural quality [20] and operational quality [21]. They are applicable in almost every situation where a relationship between input and output parameters exists, even in cases where this relationship is very complex and cannot be expressed or handled by mathematical or other modeling means. Table 2 summarises features of the most commonly used neural network tools and the proposed system. IntellIgent VIsual InspectIon of BottlIng productIon lIne through neural network Journal The Institution of Engineers, Malaysia (Vol. 69, No.4, December 2008) 59 3.0 sYstem desIgn and modelIng A software program for work for image processing in defect detection of real-time visual inspection system has been developed. The developed program is called Real-Time Intelligent Visual Inspection (Real-TIVI). The program will start at image acquisition and will go through a series of processes before the results can be output. Figure 1 shows the Real-TIVI software framework, which was developed. The process starts with image acquisition, where image will be captured, followed by preprocessing the captured image captured to reduce noises. Images are then enhanced to ease the analysing process. After the image have been enhanced, the edges of image are then determined. Lastly, according to the parameter of edges, the status of a bottle in the bottling process can be determined by using neural network and action can be taken to follow up this result [23]. 3.1 confIguratIon suBsYstem The content of a configuration subsystem is video configuration module. Video configuration module used to configure the information e.g. to choose proper webcam device, image brightness, image colour, etc. This module is also used to configure the information such as image size and image resolution. In this system, image size is fixed i.e. 352 x 280 pixels, and the image input format is in grayscale. 3.2 Image processIng suBsYstem Image processing subsystem consists of some modules as shown in Figure 1, i.e.: Figure 1 : real-tIVI software framework package name types of neural network Industrial applications package or library user Interface code generation/ dll Brain Maker Backpropagation Software package Graphical C Neuro Solution Recurrent backpropagation, Backpropagation through time Summaries of applications included Software package Graphical C++/DLL G2 NeurOnline Backpropagation, RBF, Rho, Auto associative Detailed petrochemical application included Software package Graphical objec

Visual inspection method and visual inspection device of film carrier tape for electronic component mounting

Abstract: PROBLEM TO BE SOLVED: To provide a visual inspection method and a visual inspection device of a film carrier tape for electronic component mounting by which an optimum condition can be found, the inspection of various kinds of visual defects can be speedily performed, and there is no need to repeat additional inspection two or three times when various kinds of visual defects in the film carrier tape for electronic component mounting are inspected by using reflected light. SOLUTION: The visual inspection device is provided with a horizontal irradiation means 34 which applies light in an approximately horizontal direction at a large incident angle β with respect to the normal line direction of the film carrier tape T, and an upper side irradiation means 70 which applies light at a small incidence angle α with respect to the normal line direction. The irradiation means 34 and 70 are so arranged that the incidence direction with respect to an inspection section can be changed. Defects generated on the surface of the tape T are detected by irradiating them with two types of light simultaneously or separately by the two irradiation means 34 and 70 which are arranged in appropriate positions and reading the reflected light. COPYRIGHT: (C)2007,JPO&INPIT

Edge inspection device

Abstract: PROBLEM TO BE SOLVED: To provide an edge inspection device having an inexpensive simple structure, and equipped with the convenience of being mounted on an optical observation device for executing inspection on an edge of a substrate by using the function of the observation device. SOLUTION: In this simply structured edge inspection device, a plurality of reflecting mirrors 2, 3, and 4 are held by a mirror hold part 5 so as to provide limits of observational view making detour to the edge 7a of the substrate and to both sides connected to the edge 7a, and a mirror evacuation mechanism 10 (with a mirror hoisting mechanism included) is provided for therefrom evacuating/moving the hold part 5. With this inspection device mounted on a real-image microscope serving as the optical observation device 11, an image is created which is obtained by turning a defect into a real image throughout a range of the edge 7a of the substrate from its surface to backside to simply perform inspection/determination by visual inspection. COPYRIGHT: (C)2007,JPO&INPIT

Visual inspection device for electronic component

Abstract: PROBLEM TO BE SOLVED: To provide a visual inspection device for an electronic component capable of inspecting precisely in a short time a visual defective part such as a crack, a chip or the like in a chip component, a package with an element included in its inside or the like. SOLUTION: The visual inspection device includes a plurality of illumination means 3, 4 for irradiating an inspection object 1, an imaging part 5 comprising an imaging element and an optical system for imaging the inspection object 1 illuminated with the illumination means 3, 4, and an image processor 5a for judging the presence of a defect in an appearance shape, based on a picked-up image of the inspection object 1, the plurality of illumination means 3, 4 comprises the first illumination mean 3 for irradiating the inspection object 1 from the whole circumferential direction of a side face, and the second illumination mean 4 for irradiating it from an upper face direction, and the first illumination mean 3 and the second illumination mean 4 are constituted as illumination means with hues different each other. COPYRIGHT: (C)2008,JPO&INPIT