Automated Refinement of Automated Visual Inspection Algorithms

1998

Automatic visual inspection is one of the primary applications of computer vision. Machine vision inspection requires efficient processing time and accurate results. In order to achieve efficiency and accuracy with a reasonable cost , it is important to choose the right architecture of the system.The paper presents the choices and a concrete architecture of a module ,with some aspects regarding application development and possible applications.

Computer Integrated Manufacturing Systems, 1994

Abstract The integration of quality into management of advanced manufacturing systems has not typically included automated approaches. With the advent of automated inspection and quality tools such as coordinate measuring machines and other dimensional measuring equipment, the linkage with integrated manufacturing systems seems natural. This paper shows the functional relationship of computer aided process planning to automated inspection process planning. The series of functional activities within each of these ...

IEEE Transactions on Systems, Man, and Cybernetics, 1992

Abstruct-The problem of determining if a given twodimensional (2-D) automated visual inspection system using binary images is capable of inspecting a specified part to the design specifications is addressed. This is accomplished by modeling the error inherent in the visual inspection system. The error defines a process capability zone that is compared to the part design specifications.

2018

During pre-flight inspection, technical competency is required to identify obstructions and observable damage that may impact on the airworthiness of aircraft. This can be challenging for ground crew who may be limited by time, manpower, or views of an aircraft. In this paper, we describe an R&D project that is designed to visually inspect the surface of aircraft using commercially available cameras. Providing a high-level description, we touch on some of the approaches used to identify different types of surface defects, including how this information is visualized back to the end user. The goal of this research is to work towards a more automated process of inspection using computer vision solutions. Subsequently, with an industry focused on reducing manpower and operational costs, the ability to automate the detection and documentation of aircraft defects is a relevant and timely issue.

SPIE Proceedings, 2003

A key problem in using automatic visual surface inspection in industry is training and tuning the systems to perform in a desired manner. This may take from minutes up to a year after installation, and can be a major cost. Based on our experiences the training issues need to be taken into account from the very beginning of system design. In this presentation we consider approaches for visual surface inspection and system training. We advocate using a nonsupervised learning based visual training method.

Mathematical and Computer Modelling, 1994

The demand to minimize the number of defects along with the increasing availability of computerized vision systems has made the on-line inspection of all production parts a feasible option in modern manufacturing systems. Vision systems enable noncontact, and thus, nondestructive measurements. An image of the production part is electronically obtained and stored in digital form in a computer. In most cases, the image is then processed to identify the local edges of the object. At a higher image processing level, information on local edges is used to obtain the boundaries of the object. Measurements on the computationally obtained boundary can then be performed mathematically, allowing tests to verify the shape and dimensions of the production part. It is the purpose of this paper to investigate and present methods for the determination of shapes and the use of this information for on-line quality inspection.

2006

Automated visual inspection is defined as a quality control task that determines automatically if a product, or test object, deviates from a given set of specifications using visual data. In the last 25 years, many research directions in this field have been exploited, some very different principles have been adopted and a wide variety of algorithms have been appeared in the literature. However, automated visual inspection systems still suffer from i) detection accuracy, because there is a fundamental trade off between false alarms and miss detections; and ii) strong bottleneck derived from mechanical speed and from high computational cost. For this reasons, automated visual inspection remains an open question. In this sense, Automated Multiple View Inspection, a robust method that uses redundant views of the test object to perform the inspection task, is opening up new possibilities in inspection field by taking into account the useful information about the correspondence between the different views. This strategy is very robust because in first step it identifies potential defects in each view and in second step it finds correspondences between potential defects, and only those that are matched in different views are detected as real defects. In this paper, we review the advances done in this field giving an overview of the multiple view methodology and showing experimental results obtained on real data.

Expert Systems, 2002

Computers & Industrial Engineering, 1989

This paper discusses the role of inspection in automated manufacturing. Also presented is an introduction to computerized coordinate measuring machines and their performance, since these constitute the most advanced inspection equipment available to industry today.

Journal of Intelligent Manufacturing, 2024

This paper proposes and implements a novel pipeline for the self-reconfiguration of a flexible, reconfigurable, CAD-based, and autonomous Vision Inspection System (VIS), expanding upon the modular framework theoretically outlined in (Lupi, F., Maffei, A., & Lanzetta, M. (2024). CAD-based Autonomous Vision Inspection Systems. Procedia Computer Science, 232, 2127–2136. https://doi.org/10.1016/J.PROCS.2024.02.033.). The pipeline automates the extraction and processing of inspection features manually incorporated by the designer into the Computer Aided Design (CAD) 3D model during the design stage, in accordance with Model Based Design (MBD) principles, which, in turn, facilitate virtuous approaches such as concurrent engineering and design for (Dfx), ultimately minimizing the time to market. The enriched CAD, containing inspection annotations (textual or dimensional) attached to geometrical entities, serving as the pipeline’s input, can be exported in a neutral file format, adhering to the Standard for Product Data Exchange (STEP) Application Protocol (AP)242, regardless of the modeling software used. The pipeline’s output is a Reconfiguration (ReCo) file, enabling the flexible hardware (e.g., robotic inspection cell) and software components of the VIS to be reconfigured via software (programmable). The main achievements of this work include: (i) demonstrating the feasibility of an end-to-end (i.e., CAD-to-ReCo file) pipeline that integrates the proposed software modules via Application Programming Interfaces (API)s, and (ii) formally defining the ReCo file. Experimental results from a demonstrative implementation enhance the clarity of the paper. The accuracy in defect detection achieved a 96% true positive rate and a 6% false positive rate, resulting in an overall accuracy of 94% and a precision of 88% across 72 quality inspection checks for six different inspection features of two product variants, each tested on six samples.

IAES International Journal of Robotics and Automation (IJRA), 2023

Companies have developed various systems to improve their processes. These processes' focus has been to produce more quantity in less time. To accomplish this task, it is important to also consider defects. Defective products can cause delays in the production line, rework, and the loss of money, time, and resources. This project focused on developing an integrated inspection system. Previous research has been done regarding types of vision systems, in-line inspections, and feedback data collection. A programmable logic controller (PLC) was used to control when the conveyor belt starts and stops. When the object has reached a certain position, the camera detects if the object passed or failed the process. If the object fails, the robot will pick up the bottle and take it out of the line. Human-machine interface (HMI) was also integrated, which shows how many bottles have passed and failed with a light that will indicate if a certain object has passed or failed. Feedback from the inspection process can help solve potential issues from different machines and processes. The testbed was designed, integrated, and tested in the paper to perform a feedback analysis for the production line. The setup consisted of MicroLogix PLC, Fanuc robot LR Mate 200iD and Cognex camera.

The South African Journal of Industrial Engineering, 2012

The significance of inspection processes increases when producing parts with high levels of customer input. These processes must adapt to variations in significant product characteristics. Mass customisation and reconfigurable manufacturing are currently being researched as ways to respond to high levels of customer input. This paper presents the research and development of modular inspection equipment that was designed to meet the on-line quality requirements of mass customisation and reconfigurable manufacturing environments. Simulated results were analysed for application in an industrial environment. The implementation of the equipment in South Africa is briefly discussed. The research indicates that manufacturers need only invest in the required equipment configurations when they are needed for on-line inspection.

Machine Vision and Applications, 2000

The continuing development of machine vision is initiating a change from human to machine vision for inspection purposes. This paper concentrates on a general analysis graph within a systematic automated visual inspection concept that speeds up the development of such systems by increasing the flexibility. The detection of primitives is separated from the model-based analysis process. Together with an object-specific description, the analysis graph is instantiated to perform the inspection. The analysis graph can be seen as a "recipe" for solving industrial applications, stating which kind of decisions have to be made at which stage.

Robotics and Computer-Integrated Manufacturing, 2013

This paper presents the development of an automation migration strategy in transforming a manual visual inspection work cell into a semi-automated one for a medical device manufacturer in China. The object under study is a washer/magnet subassembly used in an air release valve. These two circular components must be bonded concentrically and then inspected with bare eyes by a human inspector. Such inspection process was prone to error as the inspector struggled to keep up with the production cycle time. The methodology employed in this research consists of four steps. First, we examined the cost of rework through the Pareto analysis. The results indicated that the washer/magnet misalignment accounted for more than 40% of valve defects and thus deserved immediate attention. Next, we conducted two Kappa analyses to evaluate repeatability and reproducibility of the human inspectors assigned to perform the inspection tasks. The results showed that the human inspectors failed to pass these tests and a suitable automation solution must be sought. Afterwards, efforts were made to develop a vision based semi-automated concentricity inspection station to eliminate human inspection errors. Hardware setup, software algorithms, lighting and other supporting devices are presented in this paper as well as potential savings for such an installment. Finally, we conducted an economical analysis to compare the semi-automated solution with a fully automated one to identify the best automation migration strategy. The analysis results showed that the semi-automated solution was a favorable choice due to a shorter payback period and its ease of reinstallation if the factory is to be relocated.

2002

Visual assembly inspection can provide a low cost, accurate, and efficient solution to the automated assembly inspection problem, which is a crucial component of any automated assembly manufacturing process. The performance of such an inspection system is heavily dependent on the placement of the camera and light source. This article presents new algorithms that use the CAD model of a finished assembly for placing the camera and light source to optimize the performance of an automated assembly inspection algorithm. This general-purpose algorithm utilizes the component material properties and the contact information from the CAD model of the assembly, along with standard computer graphics hardware and physically accurate lighting models, to determine the effects of camera and light source placement on the performance of an inspection algorithm. The effectiveness of the algorithms is illustrated on a typical mechanical assembly.