KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Subject: search.filters.subject.Defect detection

Search Results

Now showing 1 - 6 of 6
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    FAST DEFECT DETECTION FOR GLASS BOTTLE USING AUTOENCODER AND ERROR THRESHOLD
    (2024-06-01)
    Hanskunatai, Anantaporn
    ;
    Jaiyen, Saichon
    ;
    Claypo, Niphat
    Glass bottle defect detection is an important part of quality control process in any glass manufacturing industry. The bottles must be inspected before packaging. Machine vision for glass bottle defect detection is the technology and method to inspect and analyze the defects for images automatically. Machine vision requires high-ability method to detect the defect and reject the bottle with the defect quickly. In this paper, defect detection framework for glass bottle defect detection tasks using autoencoders and error threshold is proposed. The fast detection method, a small autoencoder neural network architecture was designed with only good bottle images to train an autoencoder neural network. The decoded images are representations of normal bottle images and calculate threshold errors value. Defect detection is done by comparing the error between the normal background image and the encoded images to a threshold error from the training set. The performance of our method was compared to several other methods: VGG16, MobileNetV3, ADA, edge detection and image threshold. The experimental results show that our method yields 80% of accuracy on the body dataset and 92% of accuracy on the neck dataset. The average training time of our method is faster than that of all other neural network-based methods. From the experimental results, we can conclude that our defect detection framework outperforms other approaches both in accuracy and training time for defect detection on the side wall of a glass bottle.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Unified histogram equalization for defect detection on air bearing surfaces
    (2017-02-01)
    Kunakornvong, Pichate
    ;
    Sooraksa, Pitikhate
    Delivery of zero-defect products to customers in due time is key to customer satisfaction. This paper presents a new machine vision system for detecting the defects on the air bearing surface of the head gimbal assembly (HGA). The paper presents two contributions: a practical software implementation by using unified histogram equalization, and a defect detection algorithm with a block matrix technique and texture analysis. In order to test the algorithm with a real-time system, a high speed capsule conveyor was built as a new, fast in-line conveyor for transporting capsules containing HGAs. According to the experimental results, the defect detection was drastically enhanced and the performance of the proposed algorithm was satisfactory for use in a real assembly line. In other words, the visual subsystem was successful at capturing moving parts during image acquisition and at equalizing the acquired image. This new system can be used to replace a slow-speed detection system in order to increase the unit per hour production of an industrial assembly line.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A practical low-cost machine vision sensor system for defect classification on air bearing surfaces
    (2017-01-01)
    Kunakornvong, Pichate
    ;
    Sooraksa, Pitikhate
    In this paper, we present a newly adapted machine vision method and a practical low-cost machine vision sensor for defect classification of the air bearing surfaces (ABSs) of a hard disk drive, which controls the flying height of the recording heads moving above a disk in operation. A defective ABS can cause poor reading and writing performance; hence, it is necessary to verify its integrity before assembling it into the final product. The proposed sensor system was designed and implemented to detect defects by an effective combination of image segmentation and block matrix techniques as well as classifying them using an expert system under dark- and bright-field conditions. Our system processes subregions of interest and sub-blocks in parallel so that they can take advantage of multiple processor cores. From the trial runs, the small fractional error and low average processing time suggested that our proposed system is effective and can be used in an industrial assembly line.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Machine vision for defect detection on the air bearing surface
    (2016-08-16)
    Kunakornvong, Pichate
    ;
    Sooraksa, Pitikhate
    Air Bearing Surface (ABS) is a part on HDD responsible to control the flying height during read/write data. The defect on ABS causes poor performance, therefore it is necessary to verify the part before assembly to the final products. This paper presents a practical approach for machine vision to detect defect on the air bearing surface (ABS) of a head gimble assembly. Detail design on imaging system and contamination detection is provided. The proposed system is designed and implemented to detect the defect on ABS using image segmentation techniques with generation of block matrices. To determine defect in paralleled processing architecture, sub blocks and sub-ROI are allocated and employed. The results show the effectiveness of the designed system which can be deployed in the industrial assembly lines.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    System development for orange surface defect detection using image processing
    (2015-01-01)
    Rerkratn, Apinai
    ;
    Cheypoca, Thepjit
    ;
    Kaewpoonsuk, Anucha
    ;
    Kamsri, Thawatchai
    This paper presents system development for orange surface defect detection using image processing. The proposed system consists of conveyer belt, Ultraviolet (UV) lamp, CCD Camera, electronic circuits, interface card and computer. K-means clustering and thresholding techniques are used for inspection of surface defect. The image segments are employed to calculate area of surface defect. The experimental results show that the proposed system can be detection of surface defect.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Analytical learning based on a meta-programming approach for the detection of object-oriented design defects
    (2012-09-10)
    Mekruksavanich, Sakorn
    ;
    Yupapin, Preecha P.
    ;
    Muenchaisri, Pornsiri
    This study proposed a new defect-detection approach using a declarative meta-programming technique to analytical learning for object-oriented software. The extrapolating patterns are generated using analytical learning in which certain design defect characteristics can be understood through deductive learning. This study uses declarative meta-programming to represent the specific object-oriented components as logic rules with which design defects can finally be described. Using the two complementary techniques, the object-oriented software is transformed into the narrow related problem domain, in which design defect problems can be managed and simplified. The approach is validated by detecting design defects in certain open-source systems. The results obtained exhibit a superior precision to the conventional method. In application, the proposed strategy can be recognised as a flexible and automated system for detecting software design defects which many object-oriented software systems are able to use. © 2012 Asian Network for Scientific Information.