Automatic Optical Inspection System Research Articles

IMAGE ANALYSIS PROBLEMS IN AOI SYSTEMS

Historically the electronics manufacturing market has relied on a combination of human visual inspection and electrical test methods to ensure product quality. With the advent of the personal computer, the use of machine vision in industrial applications gradually became more common. The process where optical sensors (i.e., cameras) are used to make specific pass/fail decisions is usually described as Automated Optical Inspection (AOI). There are discussed problems of designing AOI system in this paper. The main goal is to select most efficient image analysis algorithm and to study other parameters that have impact on designing a reliable AOI system.

Automatic Color Inspection for Colored Wires in Electric Cables

In this paper, an automatic optical inspection system for checking the sequence of colored wires in electric cable is presented. The system is able to inspect cables with flat connectors differing in the type and number of wires. This variability is managed in an automatic way by means of a self-learning subsystem and does not require manual input from the operator or loading new data to the machine. The system is coupled to a connector crimping machine and once the model of a correct cable is learned, it can automatically inspect each cable assembled by the machine. The main contributions of this paper are: (i) the self-learning system; (ii) a robust segmentation algorithm for extracting wires from images even if they are strongly bent and partially overlapped; and (iii) a color recognition algorithm able to cope with highlights and different finishing of the wire insulation. We report the system evaluation over a period of several months during the actual production of large batches of different cables; tests demonstrated a high level of accuracy and the absence of false negatives, which is a key point in order to guarantee defect-free productions.

Quick and efficient light control for conventional automatic optical inspection (AOI) systems

This study discusses a method to determine optimal illumination quickly in order to increase the process efficiency of automatic optical inspection (AOI) systems. Optimum searching methods were applied to find optimal illumination of a single color to enhance the quality of a monochrome image and reduce searching time. The problem was defined as optimizing 1D searching between light intensity and image sharpness. The image sharpness is the degree of distinctness of the image and is a non-linear function of the input voltage, which can be used to adjust the light intensity. We considered conventional optimum search methods, such as steepest descent, conjugate gradient, Newton’s method, bisection, and golden section. These derivative methods and direct searches were tested for a sample pattern using single color lights under coaxial illumination. The iteration for the optimal condition was 6.7% of full scanning in average. The optimal illumination was obtained using low input voltages, implying that a fine image could be obtained by applying appropriate electric energy. Additionally, we checked the possibility of applying these search methods to automatic lighting in industrial machine vision.

基于AOI逻辑运算的线性方程应用

Method for automatic optical inspection system with periodic comparison and logic operation can obtain defect point information.Because of the existence of minimal cycle comparison of Pitch decimal,we cannot get the correct comparison.The use of two points formed one line,we can construct a linear equation to simulate the original breakpoints into continuous points.Just then,whether the comparative distance is an integer,the corresponding effect is found in the gray value.Using this method to improve the accuracy of anomaly check,the adverse effect is avoided on the yield,quality and cost of the product,which has the vital significance.

The design and application of an automatic optical inspection system for the advanced fiber coupler assembly manufacturing process

In this paper an automatic optical inspection system for the advanced fiber coupler assembly manufacturing process is presented. Coupling efficiency variations were compared with axial displacement. The main standard components of light peak fiber couplers were used in the experiment to determine the corresponding offset and position of the optimal optical coupling efficiency in order to achieve a positioning effect. This study used the parameters of lens curvature, focal length and light source for validation using optical design software. An infrared CCD camera was used to extract the coupled light spot images. The curve fitting method and coupling simulation database were used for image processing and to calculate optimal coupling efficiency. Under optimal coupling efficiency, the minimum amount of movement of the translation stages was used to calculate the offset of each axle or the coupling efficiency when tilted. Moreover, a coupling efficiency database was established. The optical axle center offset in the alignment was calculated by comparing the data in the database. Finally, the optical axle center offset or tilt direction was identified through the program to achieve the position of optimal coupling efficiency.

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.

Automatic optical inspection system for 3D surface profile measurement of multi-microlenses using the optimal inspection path

In this paper, an automatic optical inspection system is proposed for measuring the three-dimensional surface profile of multi-microlenses according to the optimal inspection path. The proposed system is applicable for full and sampling inspection of microlens arrays, and has the following contributions: (1) the optimal inspection path of sampling inspection is derived by a Genetic Algorithm considering the acceleration characteristic of the XY-table. (2) The incomplete microlens fringe is removed, and the center of each microlens can be automatically positioned. (3) The phase difference of each neighboring pixel is calculated through the concept of sign reversal in order to rebuild the surface profile. According to the experimental results, the lens sag of microlenses in different sizes can be correctly measured by the proposed system, and a relative error of 3.4% (max) can be achieved. Compared with other methods, the positioning time of the proposed method is shortened by 10% to 30%, validating the practicability of this system.

An Automatic Optical Inspection System for Assembly and Evaluation of an Optical Encoder

This study presented an automatic optical inspection system for the assembly and evaluation of an optical encoder, and the system analyzed the output signal quality of the light transmission grating linear encoder. The reference grating was affixed to the side architecture of the detection system in order to maintain the correct optical path, and the main grating was driven by the x–y Precision platform. Brightness variations can be detected and recorded by a charge-coupled device (CCD) camera during grating movements, using image noise depression, background separation, and fringe calculation with new image processing algorithms. The output imaging signal of a traditional linear encoder passes through a circuit filter, where amplification and rectification form a sinusoidal waveform. This system can accurately measure the light intensity variations of the encoder through machine visioning and image processing, while simultaneously determining noise and non-uniformity. This study conducted analysis on the moire width between the gratings of the flip relationship, implemented grating alignment and adjustment, and improved the assembly position and resolution of the image, in order to obtain good quality in output signals.

Automatic defect recognition of TFT array process using gray level co-occurrence matrix

This study proposed an automatic optical inspection (AOI) system for detection of thin-film transistor (TFT) array defects. gray level co-occurrence matrix (GLCM) and MATLAB regionprops function were used to calculate 53 TFT array defect features, which were inputted into the neural network to train the defect classifier. The images to be inspected were compared with a standard image first, in order to judge whether the TFT array samples have defects. For defective images of a TFT array, the proposed defect classifier can successfully recognize five kinds of defects in the process. According to the experimental results, the defect recognition rate of proposed system is verified to be 83.3%, which can replace manual inspection and reduce the risks of false inspections due to long duration manual work. Moreover, the proposed AOI system can improve testing efficiency and reduce manufacturing costs.

Design and Control of an Optical Alignment System Using a XXY Stage Integrated with dual CCDs

The aim of this study is to investigate assembly and positioning tasks of a micro-component using a co-plane XXY stage integrated with an automatic optical inspection (AOI) system instead of manual alignment. An artificial neural algorithm is added for alignment to enhance the alignment accuracy of the system. Therefore, a servo alignment system is proposed to use the AOI system to guide the XXY stage using vision technology. The image identification system is used to make the specimen align the target specimen using dual CCDs. Since the XXY stage has no positioning feedback of the optical scale or encoder, the artificial neural network (ANN) system is used to map the relative relationship between the image position and the actual XXY stage's position.

Development of an Automatic Optical Inspection System and its Application to Defect Examination

In this paper, we have designed and integrated an automatic optical inspection system, emphasizing on software implementation of the image processing, measurement and analysis utilities. As for the hardware equipments, we design an LED illumination unit and the custom-tailored machinery. By comparing the support functions of several main import brands of the optical inspection machine, we propose an optical inspecting procedure. By using the Windows-based user interface, we implement nine inspecting software tools, namely, the average gray level tool, the thresholding tool, the positioning tool, the edge detection tool, the binary large object (BLOB) tool, the template building tool, the smart matching tool, the inspection sequence tool, and the platform operation tool. All these tools can be used in an inspection with single operation and can also be arranged in a proper sequence of operations to fulfill a complicated inspection procedure. We use several part sample images with defects provided by the supplier to verify our fulfilled system.

An automatic optical inspection system for the detection of three parallel lines in solar panel end face

This study inspected and tracked the location state of a test object in the telemetry monitoring of a wafer or solar panel, and the relevant optoelectronic devices. A CCD camera, triggered by the proposed system, captures the test target image in real time, which is transferred to the system for low-pass filtering, image binarization, spatial masking, boundary tracing, and other means of image processing. The new edge point detection algorithm is then applied to identify the edge points of three parallel lines. Three different group edge points are determined using the edge point detection algorithm, and the three groups are computed using a single linear regression equation. Multiple-linear regression is conducted to obtain the sections of straight lines of the groups that can best satisfy the expected requirements. Finally, whether the detection results are consistent with the expected requirements is determined to inspect whether the test object is consistent with the process specifications in order to reduce undesirable losses, as caused by inappropriate placement angle in subsequent manufacturing, thus, enhancing subsequent manufacturing to achieve high yield.

Automated Inspection of E-Shaped Magnetic Core Elements Using K-tSL-Center Clustering and Active Shape Models

Automated optical inspection (AOI) has been widely used in industrial Quality Assurance (QA) procedures. Multi-task inspection in high-speed AOI systems is becoming a significant problem in the design. In this paper, the design of an AOI system for E-shaped magnetic core elements is briefly described and several novel algorithms are proposed to realize defects detection by this system. First, this paper proposes a robust k-tSL-center clustering method to classify the interfaces of the element into normal and damaged areas. Second, a modified Active Shape Model (ASM) method is adopted to perform shape distortion detection in real-time. Performance evaluations are carried out on an E-shaped Magnetic Core Image Database, in which all images are captured by the designed AOI system. Experimental results show that the proposed methods are more efficient, robust and accurate than state-of-the-art methods in this application.

Lens sag and diameter measurement of large-size microlenses using sub-pixel algorithm and optical interferometry

Abstract In this paper, an automatic optical inspection system is designed specifically to measure the diameter and lens sag of large-size microlenses: 1. The proposed algorithm of measuring lens diameter locates the lens center through the Euclidean distance array, and determines the lens edge along an initiated ray using linear interpolation with sub-pixel accuracy. 2. The lens sag is calculated from a single fringe pattern of large-size microlens, in combination with the measured lens diameter. 3. According to the experiment results, the proposed system has advantages of high applicability, rapid processing speed, and good accuracy with the RMS error≤1% of measuring a large-size microlens, but without the requirement of prior training. The system architecture of non-contact measurement would not cause scratches on the lens surface and is inexpensive, thus, which is particularly suitable for the in-line inspection of industry field.

An Approach to Detection of Solder Joints on Printed Circuit Boards

To automate present Automatic Optical Inspection (AOI) systems, an intelligent method based on lightness analysis for solder joints detection is proposed in this paper. Firstly, the image taken from real printed circuit board (PCB) is preprocessed and segmented. Then, we compute the image similarity by calculating the Euclidean distance. If the similarity exceeds the threshold, we extract the lightness of solder joints by converting between RGB color mode and HLS color mode. Lastly, all the defects of solder joints are classified into several different types according to their lightness appearances. Experiment results show that the method deduced in this paper can detect accurately solder defects from different patches.

Automatic optical inspection system for the micro-lens of optical connector with fuzzy ratio analysis

This study aimed to inspect micro-lens size of optical connectors. In imaging, it can be found that the edge of a micro-lens and sharpness of the base image are different from the images of a square or straight edge. The edge of a micro-lens may be fuzzy and its gray scale distribution map may present a downtrend, making it difficult to identify the edge position.This study used a micro-lens with a diameter of 110μm as a basis reference. Furthermore, a high-precision AFM was used to obtain accurate values. The measured results were substituted into a newly proposed fuzzy ratio analysis method to deduce the fuzzy ratio and adjust edge fuzzy functions for further analysis of the micro lens edge in order to obtain more accurate results, which were used for the inspection of optical connectors to improve measurement accuracy. The experiment demonstrated that the error between the study results and the results of the commercial measurement system is lower than 1μm, and the inspection speed is faster.

An automatic optical inspection system for measuring a microlens array with an optical interferometric microscope and genetic algorithm

PurposeThe purpose of this paper is to propose an automatic optical inspection system for measuring the surface profile of a microlens array.Design/methodology/approachThe system set‐up was constructed according to the principle of the Fizeau interferometer. After capturing the ring interference fringe images of the microlens with a camera, the diameter, profile information and optical properties were analyzed through a microlens surface profile algorithm using innovative image pre‐processing with a precision of less than 0.09 micron.FindingsBy integrating with the genetic algorithm, the XY‐Table shortest moving path of the system is calculated to achieve the purpose of high‐speed inspection and automatic microlens array surface profile measurement.Originality/valueThe measurement results of this system were also compared with other systems, including the atomic force microscope and stylus profiler, to verify the measurement precision and accuracy of this system.

3D surface profile measurement of unsymmetrical microstructure using Fizeau interferometric microscope

In this paper, an automatic optical inspection system for the 3D surface profile of an unsymmetrical microstructure using Fizeau interferometer was proposed. This non-contact optical inspection system is suitable for measuring the lens sag and 3D surface profile of symmetrical and unsymmetrical microlenses. Referring to the unsymmetrical microlenses as an example, the distribution of the interference fringes is partly dense and partly rare, and is completely different from the equally dense distribution of symmetrical microlenses. Thus, a novel algorithm is proposed to solve the above mentioned problem in this paper, namely, individually determining the darkest points of the dark fringes and the brightest points of the bright fringes, and fitting these discrete points as close curves through the Bezier curve theory. As the contour lines of an unsymmetrical microlens are obtained, the 3D surface profile of the unsymmetrical microlens can be plotted correspondingly. Furthermore, the proposed system has the following advantages due to its non-contact structure. This system is specifically designed for in-line measurements according to the rapid inspection speed; it has no need to coat a reflective layer on the inspected microstructure, thus avoiding damaging the surface structure of the sample.

Development of a Control System with Soft Programmable Logic Controller (<I>I</I>/<I>O</I>) Compiling Function Embedded and Applying into Automatic Optical Inspection System

Development of a Control System with Soft Programmable Logic Controller (<I>I</I>/<I>O</I>) Compiling Function Embedded and Applying into Automatic Optical Inspection System

Novel Outlier Filtering Method for AOI Image Databases

Automated optical inspection (AOI) systems are essential in electronic manufacturing technology. These systems can inspect the products' quality quickly, accurately and without weariness. However, today employing human operators and engineers is a must to compensate the inflexibility and insufficient intelligence of AOI devices. This cooperation between machines and humans implies special difficulties in the topic of optical inspection. Several AOI systems collect and store the created inspection images. For later usage (e.g., for training the AOI algorithms), the image databases are often separated according to the inspection. Normally, these databases are disjoint and homogeneous, but because of machine and human errors, the imagebases can contain outlier images - e.g., falsely classified data which do not satisfy the specified requirements. These errors make the optimization and verification process of AOI inspection algorithms challenging, which can decrease the systems' reliability and accuracy. Currently, filtering the image databases to remove outliers is a very demanding problem. This paper deals with this question. First, we illustrate the difficulties related to AOI image databases, show their background and identify their causes. Next we present our novel outlier detection method. Our technique can find and remove the outlier images from databases of inspection images reliably, by means of image processing, statistical and clustering methods. Our algorithm does not apply training samples (training images) and minimizes - or in some cases totally eliminates -the need for human intervention. It works on several component types without any modification. Our experiments showed that our novel technique can find 99% of outlier images in average.