Showing papers on "Visual inspection published in 2012"

Applications of computer vision techniques in the agriculture and food industry: a review

Abstract: Over the last decades, parallel to technological development, there has been a great increase in the use of visual inspection systems. These systems have been widely implemented, particularly in the stage of inspection of product quality, as a means of replacing manual inspection conducted by humans. Much research has been published proposing the use of such tools in the processes of sorting and classification of food products. This paper presents a review of the main publications in the last ten years with respect to new technologies and to the wide application of systems of visual inspection in the sectors of precision farming and in the food industry.

Visual inspection methods for cervical cancer prevention.

Abstract: The need for simple, cost-effective screening approaches for cervical cancer prevention in low-resource countries has led to the evaluation of visual screening with 3–5% acetic acid. The low reproducibility and wide variation in accuracy reflect the subjective nature of the test. Pooled sensitivity, specificity, positive and negative predictive values were 80%, 92%, 10% and 99%, respectively, for detecting cervical intraepithelial neoplasia grade 2 or worse lesions. Realistic sensitivity of a quality- assured single visual inspection with acetic acid is around 50%. A single round of visual inspection with acetic acid screening has been associated with a 25–35% reduction in cervical cancer incidence and the frequency of cervical intraepithelial neoplasia grade 2 or worse lesions in randomised-controlled trials. Despite all its limitations, implementing visual inspection with acetic acid screening in low-resource countries may provide a pragmatic approach to building up human resources and infrastructure that may facilitate the highly anticipated low-cost, rapid human papilloma virus testing in the near future.

Visual inspection : a review of the literature.

Abstract: This report provides a review of 212 documents published in the visual inspection literature from the 1950s to the present. The inspection task is defined and characterized and trends in inspection research are reviewed. The prevailing twocomponent model of inspection and various techniques to measure inspection performance are discussed. The majority of the report reviews the parameters that may impact inspection performance and describes the relevant findings from the literature. The report concludes with a re-iteration of the value of inspection research and a summary of the major recommendations for improving inspection performance.

Spectral image classification of rooftop condition for use in property insurance

Abstract: A method and apparatus is disclosed for applying high resolution spectral imaging (hyperspectral or multispectral) to property characterization, specifically rooftop classification of type and condition using reference data for insurance applications. The system can also be used to classify the condition of vegetation and property hazards. Classifying rooftop type and condition using remote spectral imaging greatly improves quantitative accuracy of roof inspections and decreases the cost of inspection across large geographic domains. By comparing the spatially subset spectral reflection of rooftops to a reference spectra, the rooftop type and condition can be accurately assessed. The aerial inspection produces uniform and consistent data can be ingested into property insurance evaluations for many different uses. The cost of residential property inspections and re-inspections performed via manual visual inspection is reduced and a geospatial database for the targeted residential and commercial property region that can be used for sustained property assessment is created.

Development of a Visual Inspection Data Collection Tool for Evaluation of Fielded PV Module Condition

Abstract: A visual inspection data collection tool for the evaluation of fielded photovoltaic (PV) modules has been developed to facilitate describing the condition of PV modules with regard to field performance. The proposed data collection tool consists of 14 sections, each documenting the appearance or properties of a part of the module. This report instructs on how to use the collection tool and defines each attribute to ensure reliable and valid data collection. This tool has been evaluated through the inspection of over 60 PV modules produced by more than 20 manufacturers and fielded at two different sites for varying periods of time. Aggregated data from such a single data collection tool has the potential to enable longitudinal studies of module condition over time, technology evolution, and field location for the enhancement of module reliability models.

Visual Inspection Method and Apparatus and Image Analysis System

Abstract: A visual inspection method and apparatus detecting a defect with the use of a detected signal obtained by illuminating one of a light and an electron beam onto a substrate to be inspected The visual inspection method and apparatus includes calculation of an image feature based on an image of the detected defect, calculation of a coordinate feature based on position information of the detected defect, and outputting of real defect information by performing false alarm judgment by processing with respect to one of the image feature and the coordinate feature

Fabric Inspection System using Artificial Neural Networks

Abstract: Fabric inspection system is important to maintain the quality of fabric. Fabric inspection is carried out manually with human visual inspection for a long time. The work of inspectors is very tedious and consumes time and cost.To reduce the wastage of cost and time, automatic fabric inspection is required. This paper proposes an approach to recognize fabric defects in textile industry for minimizing production cost and time. The Fabric inspection system first acquires high quality vibration free images of the fabric. Then the acquired images are subjected to defect segmentation algorithm. The output of the processed image is used as an input to the Artificial Neural Network (ANN) which uses back propagation algorithm to calculate the weighted factors and generates the desired classification of defects as an output. The weaving machine is one of the easiest and fastest ways of producing cloth and textile pieces. The automated defect detection and identification system enhance the product quality and result in improved quality to meet both the customer demand and to reduce the cost associated with off-quality. This process also reduces the manual work load associated with the inspection process. Off-line monitoring system has its own disadvantages when it is compared with that of on-line monitoring system. In the off-line monitoring system the produced fabric is taken to the inspection frame where the quality of the fabric is analyzed and the fabric is transfer to the successive process. But in the on-line monitoring system the inspection of the fabric is done simultaneously while the fabric is being produced. This paper describes about fault detection, positioning and classification of the faults occur in the weaving machine during weaving by using the principle of image processing, an automatic

In-service Inspection Guidelines for Composite Aerospace Structures

Abstract: The in-service inspection of composite aerospace st ructures is reviewed, using the results of an evalu ation of promising, mobile non-destructive inspection (NDI) methods. The evaluation made use of carbon fibre reinforced specimens representative for primary composite aerospace structures, including relevant dam age types such as impact damage, delaminations and disbonds. A range of NDI methods were evaluated such as visual inspection, vibration analysis, phased array ultrasonic inspection, shearography and thermograp hy inspection. Important aspects of the evaluation wer e the capability for defect detection and character ization, portability of equipment, field of view, couplant r equirements, speed of inspection, level of training required and the cost of equipment. The paper reviews the damage tolerance design approach for composites, and conc ludes with guidelines for the in-service inspection of co mposite aerospace structures.

Semi-autonomous visual inspection of vessels assisted by an unmanned Micro Aerial Vehicle

Abstract: Vessel maintenance entails periodic visual inspections of internal and external parts of the hull in order to detect the typical defective situations affecting metallic structures, such as cracks, coating breakdown, corrosion, etc. The main goal of the EU-FP7 project MINOAS is the automation of the inspection process, currently undertaken by human surveyors, by means of a fleet of robotic agents. This paper overviews a semi-autonomous approach to the inspection problem consisting of an autonomous Micro Aerial Vehicle (MAV) to be used as part of this fleet and which is in charge of regularly supplying images that can effectively teleport the surveyor from a base station to the areas of the hull to be inspected. Specific image processing software to analyze those images and assist the surveyor during the repair/no repair decision making process is also contributed. The control software approach adopted for the MAV, including self-localization and obstacle avoidance, is described and discussed, and experimental results in this regard are as well reported.

Machine Vision System for Automated Visual Inspection of Tile's Surface Quality

Abstract: Visual inspection of material’s surface quality is an important quality determining step in industries dealing with surfaces as the prime feature of their product, for instance, plywood, metal, tiles, glass ware and many more. Primarily surfaces are inspected for smoothness and roughness quality. However, defects may arise in form of cracks, spots, holes, presence of excess material, flatness and shape of edges etc. A human inspection system can effectively challenge this task to a good accuracy. But with human system, there is an issue of fatigueness that arises over a long period of time. And in that case, the quality of inspection is biased towards either side. To avoid this biased inspection, a novel vision system based on image processing is proposed here. In the presented paper work, a case of tile industry has been tested out. The tiles surfaces are very sensitive to any of the defects as mentioned above. And a small defect on surface of a tile may lead to huge loss to the manufacturer. An automated visual inspection system inspects the tile’s surface for any crack, hole, spot, presence of any foreign material or excess material. The objective of the proposed paper work is to develop an automatic machine vision system that could visually inspect the tile’s surface to determine the quality as per the set standards. The work involves the extraction of defects from the surface using image processing techniques that are based on statistical properties of the defects observed on surfaces.

A Flexible PCB Inspection System Based on Statistical Learning

Abstract: With the large variations in appearance for different kinds of defects in Printed Circuit Boards (PCBs), conventional rule-based inspection algorithms become insufficient for detecting and classifying defects. In this study, an automated PCB inspection system based on statistical learning strategies is developed. First, the partial Hausdorff distance is used to ascertain the positions of defects. Next, the defect patterns are categorized using the Support Vector Machine (SVM) classifier. Defects without regularities in appearance, which cannot be categorized, are identified through the regional defectiveness by comparing the block-wise probability distributions. Experimental results on a real visual inspection platform show that the proposed system is very effective for inspecting a variety of PCB defects.

Road Surface Assessment of Pothole Severity by Close Range Digital Photogrammetry Method

Abstract: Roads, in particular bitumen pavements are essential as major transportation and communication ways in modern civilizations. Nevertheless due to weather impacts and also loads from vehicles, surface of these roads often faces serious deterioration or distress from time to time. Rehabilitation and road maintenance work is not only time-consuming, but it also creates traffic disturbances and is also very costly. Problems such as lacking of data reading consistency and time-consuming have made the current visual inspection method to be less competent. Therefore, an effective road surface assessment method is proposed in this study to assess the severity level of pothole formation based on national guidelines, published by the Public Works Department. Ten random pothole samples were chosen randomly and their severity levels were assessed through both the conventional visual approach and the photogrammetric method. The study reveals that digital close range photogrammetry method can be used as the alternative way in visual assessment of pothole severity using typical d I gital camera, thus making the visual inspection easier, safer and more systematic. The proposed method has shown accuracy of 100% regardless of the types of digital camera used.

A Statistical Method for Crack Detection from Vibrothermography Inspection Data

Abstract: Nondestructive evaluation methods are widely used in quality control processes for critical components in systems such as aircraft engines and nuclear power plants. These same methods are also used in periodic field inspection to assure that the system continues to be reliable while it is in service. This paper describes a detection algorithm to automatically analyze vibrothermography sequence-of-image inspection data used to detect cracks in jet engine fan blades. Principal components analysis is used for dimension reduction. Then the fitted coefficients of the first principal component are processed by using robust regression to produce studentized residuals that are used in the crack-detection rules. We also show how to quantify the probability of detection for the algorithm. The detection algorithm is both computationally efficient and accurate. It correctly identified several cracks in our experimental data that were not detected by the standard human visual inspection method.

Location based automobile inspection

Abstract: A dynamic inspection system determines a location of a technician with respect to an inspection vehicle and determines active voice commands to which it responds to based on that location. The technician can perform a vehicle inspection by providing voice commands to the dynamic inspection system, which can increase the technician's efficiency. Further, as the dynamic inspection system's active commands are customized for the location of the technician, the dynamic inspection system can filter out sound that does not include active voice commands, potentially increasing the accuracy of its voice recognition capability.

Visual Inspection Device, Visual Inspection Method, And Computer Program

Abstract: Inputs of a plurality of images constituting a group of images of items regarded as non-defective items are previously accepted and stored, and a defect threshold for detecting a defective portion of an inspection object is set based on the plurality of stored images. A defect amount to be compared with a determination threshold for making a non-defective/defective determination on the inspection object is calculated with respect to each of the plurality of stored images based on the set defective threshold, and whether or not each of the calculated defect amounts is an outlier is tested by use of at least one of a parametric technique and a non-parametric technique. Outlier information for specifying an image whose defect amount has been tested to be the outlier is displayed and outputted.

Data exploration combining visual inspection and analytic search

Abstract: A computer device displays a graph of a data set. The computer device includes a hybrid data analysis and visualization tool to query implicit properties of data items in the data set that are not evident upon visual inspection of the graph of the data set itself. The hybrid data analysis and visualization tool combines the graph of the data set with analog representations of data query results for visual data exploration.

Image Processing Based Automatic Visual Inspection System for PCBs

Abstract: The on-line or automatic visual inspection of PCB is basically a very first examination before its electronic testing. This inspection consists of mainly missing or wrongly placed components in the PCB. If there is any missing electronic component then it is not so damaging the PCB. But if any of the component that can be placed only in one way and has been soldered in other way around, then the same will be damaged and there are chances that other components may also get damaged. To avoid this, an automatic visual inspection is in demand that may take care of the missing or wrongly placed electronic components. In the presented paper work, an automatic machine vision system for inspection of PCBs for any missing component as compared with the standard one has been proposed. The system primarily consists of two parts: 1) the learning process, where the system is trained for the standard PCB, and 2) inspection process where the PCB under test is inspected for any missing component as compared with the standard one. The proposed system can be deployed on a manufacturing line with a much more affordable price comparing to other commercial inspection systems.

Design for inspection of concrete bridges

Abstract: In order to achieve durable concrete bridges, adequate measures need to be considered already in the design phase. An evaluation of common deteriorations in concrete structures leads to the conclusion that visual inspection is and will remain the method to be applied first. More refined and complementing methods will result in similar requirements for design. Therefore, the role of inspections in bridge management has to be identified and future methods of inspection and condition survey have to be anticipated. The main focus is a safe and convenient access to all concrete surfaces, hollow boxes, and decisive structural parts like bearings and expansion joints. Some of those measures are even worth to be considered for existing bridges when these are significantly modified due to bad conditions or new requirements.

A flexible visual inspection system combining pose estimation and visual servo approaches

Abstract: This paper presents a system framework to realize the automatic visual inspection with random initial object poses. A series of Computer Graphics (CG) images rendered in OpenGL are compared with a real scene image from a fixed environment camera. With an iterative heuristic search approach for the maximum similarity in these comparisons, robust 3D object pose estimation has been obtained to place an inspection camera to its new initial pose. Then a visual servo technique is used to accurately place this camera so that a reliable visual inspection can be carried out. Contrast with those feature-based or texture-based approaches where textures are required, only the object's geometry information is needed in this framework, therefore this system can deal with the untextured objects (for instance metal parts) well. This paper describes the system configuration and operational procedure in detail. Experiments results are presented to evaluate the system performance.

Innovative Bridge Assessment Methods using Image Processing and Infrared Thermography Technology

Abstract: Identifying appropriate applications for technology to assess the health and safety of bridges is an important issue for bridge owners around the world. Traditionally, highway bridge conditions have been monitored by visual inspection with structural deficiencies being manually identified and classified by qualified engineers and inspectors. With traditional on-site inspections, qualified inspectors are performing close-up visual inspections and sounding tests, often from crane suspended lifting cages or built-in inspection staging; invariably putting inspectors at some safety risk. The need for safer inspection methods calls for new innovations in bridge inspection technologies. One of the solutions for this issue is leveraging non-destructive technologies as well as experimental approaches for a more advanced and efficient inspection process. Due to advancements in technology and computer science, new technologies are becoming more and more cost effective, and some of the technologies are ready to be applied for onsite bridge assessment practices. NEXCO-West, one of major toll road operators in Japan has been working to develop efficient nondestructive highway bridge inspection methods using high definition video (HDV) digital image and Infrared (IR) thermography technologies.

Overview: Methods of Automatic Fabric Defect Detection

Abstract: Fabric inspection has an importance to prevent the risk of delivering inferior quality product. Automated inspection systems are much needed in the textile industry, especially when the quality control of products is a significant problem. The fabric defects inspection process is carried out from a long time with human visual inspection that proves to be insufficient and costly. Hence in order to reduce the cost and wastage of time, automatic fabric defect detection is required. Robust and efficient fabric defect detection algorithms are used for inspection. This paper presents different methods of fabric defect detection to extract the different features from the fabric. Thus, the inspection of 100% fabric is necessary mainly because of two reasons, first to determine its quality and second to detect any disturbance in the weaving process. 1. Introduction Fabric defect detection is a quality control process that aims at identifying and locating defect of fabric. Human inspection is the traditional means to assure the quality of fabric. It helps instant correction of small defects, but human error occurs due to fatigue and fine defects are often undetected. Therefore, automated inspection of fabric defect becomes a natural way to improve fabric quality and reduce labor costs. In the textile industry, before any shipments are sent to customers, inspection is needed for maintaining the fabric quality. The most challenging industrial inspection problems deal with the textured materials such as textile web, paper, and wood. The inspection problem encountered in textured materials become texture analysis problems at microscopic levels. Textured materials take many forms and while there is a remarkable similarity in overall automation requirements for visual inspection, the cost-effective solutions are application specific and generally require extensive research and development efforts. Defect detection in web materials normally depends upon identification of regions that differ from a uniform background. The web inspection problems are also associated with textured materials such as textile, ceramics, plastics, etc. The characterization of defects in textured materials is generally not clearly defined. The textured materials can be further divided into uniform, random, or patterned textures. Brazakovic et al. (6) have detailed a model-based approach for the inspection of random textured materials. The problem of printed textures (e.g., printed fabrics, printed currency, and wallpaper) requires the evaluation of color uniformity and consistency of printed patterns, in addition to any discrepancy in the background texture. Textile quality control involves the detection of defects that cause a distortion of the basic structure of the material that shows a high degree of periodicity. Performance and assessment are never constant and effectiveness decreases quickly with fatigue. Due to the very slow speed of human visual inspection compared to production rate, automatic inspection is more important than ever. Many researchers have worked on the automation of inspection systems. For a weaving plant, in harsh economic times, first quality fabric plays the main role to insure survival in a competitive marketplace. First quality fabric is totally free of major defects and virtually free of minor structural or surface defects. Second quality fabric is fabric that may contain a few major defects and/or several minor structural or surface defects. Nickoloy et al. (8) have shown that the investment in the automated fabric inspection system is economically attractive when reduction in personnel cost and associated benefits are considered.

Touch screen screen-printed circuit automatic optic inspection system

Abstract: The invention discloses a touch screen screen-printed circuit automatic optic inspection system, and a touch screen screen-printed circuit AOI system for short. The system is composed of an imaging subsystem, an image collecting subsystem, a motion controlling subsystem, and a software subsystem. The software subsystem comprises an image collection controlling unit, an image processing and analyzing unit, a defect detecting unit, a modeling unit, and the like. With the AOI system provided by the invention, an automatic optic inspection task of large batches of screen-printed products can be achieved. Users place the products on the system, and high-precision, high-speed and no-omission inspections of all the screen-printed circuits can be achieved by the AOI system. Compared to an artificial visual inspection method, the system provides an inspection scheme with high efficiency, low cost, high reliability, and high automation degree.

Visual inspection equipment and visual inspection program

Abstract: PROBLEM TO BE SOLVED: To provide visual inspection equipment capable of obtaining an accurate inspection result, while reducing accumulation of fatigue on a subject's one eye, and a visual inspection program.SOLUTION: Visual inspection equipment includes image displays (13L and 13R) that present light for suppression of dark adaptation to both of a subject's eyes (L and R), and image displays (13L and 13R) that present a target to the subject's eye (L or R) or both of his/her eyes so that the target can be presented to the other eye R before completion of a visual inspection for the one eye L.

A magnetic climbing robot for marine inspection services

Abstract: Currently, the inspection of sea-going vessels is performed manually. Ship surveyors do a visual inspection; in some cases they also use cameras and non-destructive testing methods. Prior to a ship surveying process a lot of scaffolding has to be provided in order to make every spot accessible for the surveyor. In this work a robotic system is presented, which is able to access many areas of a cargo hold of a ship and perform visual inspection without any scaffolding. The paper also describes how the position of the acquired data is estimated with an optical 3D tracking unit and how critical points on the hull can be marked via a remote controlled marker device. Furthermore first results of onboard tests with the system are provided.

Automated visual inspection system for mass production of hard disk drive media

Abstract: Manual visual inspection is currently used in the modern Hard Disk assembly process. This research shows a feasible design to automate the visual inspection process based on wavelength dependant detection. Two defect detection algorithms, one - computationally simple and another - complex, are explored in this paper. The developed system meets the performance of the current manual inspection method while providing high accuracy in targeted defects.

Development of a Visual Inspection Checklist for Evaluation of Fielded PV Module Condition

Abstract: A visual inspection checklist for the evaluation of fielded photovoltaic (PV) modules has been developed to facilitate collection of data describing the field performance of PV modules. The proposed inspection checklist consists of 14 sections, each documenting the appearance or properties of a part of the module. This tool has been evaluated through the inspection of over 60 PV modules produced by more than 20 manufacturers and fielded at two different sites for varying periods of time. Aggregated data from a single data collection tool such as this checklist has the potential to enable longitudinal studies of module condition over time, technology evolution, and field location for the enhancement of module reliability models.

Online visual inspection system for cold-forged product

Abstract: The invention discloses an online visual inspection system for a cold-forged product The online visual inspection system comprises an image acquisition module, a sorting device and an image data processing module, wherein the image acquisition module is arranged in a dark box, and mainly comprises an inspection platform, a charge coupled device (CCD) camera and a light source; the CCD camera faces a product positioned on the inspection platform; the light source acquires parallel back lights, and is arranged behind the product positioned on the inspection platform; the image data processing module mainly comprises a computer and a human-machine interaction interface connected with the computer; and sizes and shapes of standard products are pre-stored in the computer The online visual inspection system has the advantages that the image acquisition module is used for acquiring images of the products and transmitting image data to the computer in the image data processing module; the computer controls the sorting device to sort qualified products and unqualified products according to the comparison result between the image data and the data, which is pre-stored in the computer, of the standard products; and furthermore, the online visual inspection system is easy to inspect, high in inspection efficiency and high in inspection precision, and the manual interference is low

Actuatable visual inspection device

Abstract: A visual inspection device for inspecting interior passages of a system is disclosed herein. In an embodiment, the visual inspection device includes a visual inspection tool and a tube having a lumen disposed therein, the visual inspection tool being disposed at a distal end of the tube. A plurality of actuators are disposed along an axial extent of an exterior of the tube, and a locomotor is disposed on an exterior of the tube. A locator for tracking a location of the visual inspection tool is also provided as part of the visual inspection device.