Automated Visual Inspection System for Mass Production of Hard Disk Drive Media (original) (raw)

Visual Inspection Technology in the Hard Disc Drive Industry

2015

A presentation of the use of computer vision systems to control manufacturing processes and product quality in the hard disk drive industry. Visual Inspection Technology in the Hard Disk Drive Industry is an application-oriented book borne out of collaborative research with the worlds leading hard disk drive companies. It covers the latest developments and important topics in computer vision technology in hard disk drive manufacturing, as well as offering a glimpse of future technologies.

Vertical Edge Detection-Based Automatic Optical Inspection of HGA Solder Jet Ball Joint Defects

ECTI Transactions on Computer and Information Technology (ECTI-CIT), 1970

The Head Gimbal Assembly (HGA) is an essential hard disk drive (HDD) component allowing data to be read from and written to the media. Defects on the HGA may affect the data read/write process and reduce the quality of the HDD. Therefore, HGA inspection needs to be improved during HDD manufacturing. This paper describes an image processing method that automate the optical inspection of HGA solder jet ball joint defects. Vertical edge detection methods are proposed for identifying defects. The performance of the vertical edge detection method is compared to a Sobel-based method, Roberts' method and a Prewitt's method. The methods were tested with 18,123 HGA images. The experimental results show that the vertical edge detection method outperforms the other methods, which had an accuracy of 99.3%, as compared to the Sobel based method, with an accuracy of 80% and 78.2 for Roberts' method and 65.9 for Prewitt's method.

Automated visual fault inspection of optical elements using machine vision technologies

Journal of Applied Engineering Science, 2018

Light-emitting diode (LED) lenses are one kind of common optical elements applied in many modern electronic devices. The LED lens with textured and uneven surface is hard to inspect appearance faults. This research suggests a wavelet packet transform-based partial least squares method to inspect visual faults of optical lenses with textured and uneven surfaces. Three major procedures are conducted to complete the process of fault detection. Firstly, a testing image is transformed to wavelet pack domain and the wavelet characteristics of the sub-band images are extracted. Secondly, the partial least squares scheme is used to multivariate transform with wavelet characteristics to obtain latent images. Thirdly, the latent images are fi tted by a regression model to produce a predicted image. After comparing with the original image, we can obtain the residual image where the appearance faults have been separated. Thus, the intricate faults embedded in the complicated appearances of optical lenses could be precisely identifi ed by the suggested method. The effectiveness and accuracy of the developed method are confi rmed by expert assessments, as well as by comparative analysis with the known methods in the fi eld of spatial localizations and classifi cation effects of fault inspection.

IJERT-Design & Development of an Image Processing Algorithm for Automated Visual Inspection System

International Journal of Engineering Research and Technology (IJERT), 2013

https://www.ijert.org/design-development-of-an-image-processing-algorithm-for-automated-visual-inspection-system https://www.ijert.org/research/design-development-of-an-image-processing-algorithm-for-automated-visual-inspection-system-IJERTV2IS100446.pdf Automated Visual Inspection is an important solution for manufacturing industries to decrease the investment in the inspection process for manufactured product. By the help of vision system the inspection process of the product is conduct, there is an increment in production rate and decrement in the required labour. This research article is described to design and development of an image processing algorithm using MATLAB® software that can help to reduce the defect detection time and compensate for variation in the product for different production line. The developed algorithm uses image processing tool box and absolute mean deviation in MATLAB® software.

Automation of Visual Inspection Using Image Processing

Industrial Engineering Journal

With current era of the Automobile industry, the product is manually or visually checked by using check list there is difficulty in inspection due to dependence on human skills and lack of ergonomic applications which cause fatigue. Inspection is one of the primary segments of the industrial parts production process. Machine vision is a present day strategy to inspect produced parts and it is a subcategory of engineering machinery, dealing with issues of information technology, optics, mechanics and industrial automation. Machine vision systems are used increasingly to solve problems of industrial inspection. This paper introduces an automatic vision based defect inspection or detection and dimensional measurement. The system identifies defects (Part Miss, Part Location, Welding Defects and grinding defects etc.) which usually occur in an assembly Structure component. The image processing technique used for Defect detection and algorithms developed for defect detection and linear dimension measurement. Various types of sensors were interfaced with the vision hardware and the part handling mechanism, to complete the total automated vision based inspection system. This system is an accurate, repeatable, fast and cheap solution for industries. This image processing technique is finished utilizing MATLAB programming. This work presents a strategy which decreases the manual work.

Defect Detection and Classification of Optical Components : A Review

Optics engineering is a field that is rapidly changing, inventive, and developing. To address the growing demand for optical components, product quality requirements must be maintained. Automatic optical inspection (AOI) is a non-destructive technology used in product quality inspection. This technology is regarded reliable and may be used to replace human inspectors who are tired and bored while doing inspection chores. Hardware and software configurations make comprise a fully automated optical inspection system. The hardware setup is responsible for acquiring the digital picture, while the software portion implements an inspection algorithm to extract the attributes of the collected images and categories them as defected or non-defective depending on the user requirements. To distinguish between faulty and excellent items, a sorting system might be utilized. This study examines the numerous AOI systems utilized in the electronics, microelectronics, and optoelectronics sectors. The imaging, pre-processing, feature extraction, and classification technologies used to detect flaws in optical components are reviewed.

Automatic inspection of defects in plain and texture surfaces

The image processing used for visual inspection and quality control in a serial production is described in this paper. We used the discrete wavelet transform -DWT in our failure detection algorithm. To achieve robustness as well as good sensitivity of the algorithm, we divide the images into segments. The difference of the wavelet coefficients maxima for the given segment for images of the tile with and without defects was used for defect detection. The analysis of detection capabilities is done for different segment sizes, different detection sensitivity levels -DSL and for two orthogonal wavelets.

Automated Industrial Inspection of Optical Lenses Using Computer Vision

2011

An LED (Light-Emitting Diode) lens with a transparent and curved surface is more difficult to detect surface defects than electronic components by current computer vision systems. The purpose of this research is to apply the block discrete cosine transform (BDCT), Hotelling 2 T statistic, and grey clustering method to detect visual defects of LED lenses. An image with equal sized blocks is converted to DCT domain and some representative energy features of each DCT block are extracted. These energy features of each block are integrated by the 2 T statistic and the suspected defect blocks can be determined by the multivariate statistical method. Then, the grey clustering algorithm is conducted to further confirm the block locations of the real defects. Finally, a simple segmentation method is applied to separate the defect areas. Experimental results demonstrate the defect detection rate of the proposed method is better than those of current techniques.

Automatic optical inspection for detecting defects on printed circuit board inner layers

International Journal of Advanced Manufacturing Technology, 2005

This paper studies automatic optical inspection for detecting defects on the printed circuit board inner layer. The development of this study can be divided into five stages, they are reference image rebuilding, inspection image normalization, image subtraction, defects separation and defect classification. In the image subtraction stage, the difference between the reference image from the printed circuit board design and the inspected image is checked for defects. Each defect region is separated using a defect outer boundary tracing method. A boundary state transition method is proposed to classify the defect types. This system can recognize eight defect types, open, mouse bite, pinhole, missing conductor, short, spur, excess copper and missing hole. In addition, a comparison with the methods described in the literature is made, proving that the proposed method produces better results .

A visual inspection system for quality control of optical lenses

International Journal of Physical Sciences, 2011

This paper proposes a quality inspection system for optical lenses using computer vision techniques. The system is able to inspect LED (Light-Emitting Diode) lenses visually and to validate their quality level automatically based on the defect severity. The optical inspection system applies the block discrete cosine transform (BDCT), Hotelling 2 T statistic, and grey clustering technique to detect visual defects of LED lenses. A spatial domain image with equal sized blocks is converted to DCT (Discrete Cosine Transform) domain and some representative energy features of each DCT block are extracted. These energy features of each block are integrated by the 2 T statistic and the suspected defect blocks can be determined by the multivariate statistical method. Then, the grey clustering algorithm based on the block grey relational grades is conducted to further confirm the block locations of real defects. Finally, a simple segmentation method is applied to set a threshold for distinguishing between defective areas and uniform regions. Experimental results show the defect detection rate of the proposed method is 94.64% better than those of traditional spatial and frequency domain techniques.