Young-Bok Joo

Robust and consistent defect size measuring method in Automated Vision Inspection system

Automatic Vision Inspection (AVI) systems automatically detect defect features and measure their sizes via camera vision. AVI systems usually report different measurements on same defect with some variations on position or rotation mainly because we get different image. It is caused by possible variations from image acquisition process including optical factors, non-uniform illumination, random noises, and so on. For this reason, conventional area based defect measuring method has a problem on robustness and consistency. In this paper, we propose a new defect size measuring method to overcome this problem. We utilize volume information which is completely ignored in the area based defect measuring method. We choose a cylinder shape as a defect model for experiment. The results show that our proposed method dramatically improves robustness and consistency of defect size measurement. Given proper modeling, the proposed volume based measuring method can be applied to various types of defect.

A Defect Inspection Method in TFT-LCD Panel Using LS-SVM

Normally, to extract the defect in TFT-LCD inspection system, the image is obtained by using line scan camera or area scan camera which is achieved by CCD or CMOS sensor. Because of the limited dynamic range of CCD or CMOS sensor as well as the effect of the illumination, these images are frequently degraded and the important features are hard to decern by a human viewer. In order to overcome this problem, the feature vectors in the image are obtained by using the average intensity difference between defect and background based on the weber`s law and the standard deviation of the background region. The defect detection method uses non-linear SVM (Supports Vector Machine) method using the extracted feature vectors. The experiment results show that the proposed method yields better performance of defect classification methods over conveniently method.

Target extraction in FLIR image using Bi-modality of local characteristic and Chamfer distance

In this paper, target extraction method in FLIR(forward-looking infrared) images based on fuzzy thresholding which used bi-modality and adjacency to determine membership value is proposed. The bi-modality represents how a pixel is classified into a part of target using distribution of pixel values in a local region, and The adjacency is a measure to represent how each pixel is far from the target region. First, membership value is calculated using above two measures, and then fuzzy thresholding is performed to extract the target. To evaluate performance of proposed target extraction method, we compare other segmentation methods using various FLIR tank image. Experimental results show that the proposed algorithm is a good segmentation performance.

Defect Detection Method using Human Visual System and MMTF

Abstract: AVI (Automatic Vision Inspection) systems automatically detect defect features and measure their sizes via camera vision. Defect detection is not an easy process because of noises from various sources and optical distortion. In this paper the acquired images from a TFT panel are enhanced with the adoption of an HVS (Human Visual System). A human visual system is more sensitive on the defect area than the illumination components because it has greater sensitivity to variations of intensity. In this paper we modified an MTF (Modulation Transfer Function) in the Wavelet domain and utilized the characteristics of an HVS. The proposed algorithm flattens the inner illumination components while preserving the defect information intact. Keywords: automatic inspection, defect, detection, modulated transfer function, HVS I. 서론 머신 비전 기술은 영상을 기반으로 하는 자동결함 검사시스템 분야에서 생산성 향상과 품질 관리 자동화에 기여해 왔다[1]. 일반적으로 시각적 검사와 품질 제어는 전문적인 목시 검사자들에 의해 수행되어 왔다. 하지만 목시 검사자는 검사가 정확한 반면에 쉽게 지치고 검사 속도가 느리며 당일의 기분과 컨디션에 따라 검사 품질에 일관성이 떨어 질 수 있으며 인건비가 들어가므로 비용이 많이 든다. 이러한 점을 개선하기 위해 자동 결함 검사 시스템(automatic vision inspection system)이 도입되었다. 이 시스템은 인간의 시각 및 인지 시스템을 모방하여 비전 센서(camera)를 탑재하여 실시간으로 영상을 획득하여 영상 분석을 통해 결함을 자동으로 탐지하여 그 위치나 크기, 모양 혹은 배경과의 명암차 등 그 결함에 대한 정보를 추출하고 자동으로 보고하는 시스템이다. 최근 수 십 년 동안 자동결함 검사시스템은 그 활용도가 뛰어나 많은 응용 분야에서 활발히 연구가 되어 왔다[2]. 특히 영상 처리 및 분석과 프로세서의 기술이 발전함에 따라 신속 정확한 검사가 가능하게 되었다. 특히 영상 처리 및 분석 여기서기술은 검사 성능을 좌우하는 매우 중요한 기술로서 다양한 결함 추출 알고리듬이 개발되어 왔다[3,4,7,8,9]. 하지만 영상 획득 과정에서의 다양한 원인의 잡음과 광학적 왜곡으로 인해 Field에서 요구하는 신뢰성 있는 결함 검출은 그리 쉬운 문제가 아니다. 본 연구에서는 TFT-LCD 표면 영상에 대하여 실제 인간 시각이 인지하는 특성을 반영한 영상 개선을 수행하였다. 인간 시각은 TFT-LCD 표면 영상의 내부 조명성분 보다는 결함 정보에 더 민감하게 반응하는데, 이는 인간 시각이 고주파 상에서 일어나는 변화보다 TFT-LCD 영상 내 휘도 흐름 (불균일도)과 같은 저주파 상에서의 휘도 변화에 대한 감지력이 더 뛰어나기 때문이다. 이에 본 연구에서는 이러한 인간 시각의 특성을 함수화 한 MTF (Modulation Transfer Function)를 웨이브렛 도메인에 적합하게 수정하고, 이를 통해 내부 조명을 평탄하게 모델링하면서 결함정보는 보존하는 알고리즘을 설계하였다. II 장에서는 수정된 MTF (Modulation Transfer Function) 에 대해서 설명하고 III 장에서는 HVS (Human Visual System, 인간지각시스템)에 대해 간단히 설명한다. IV 장에서는 MMTF와 HVS를 이용한 결함 추출 방법에 대해 설명하고 V 장에서는 실험 결과를 분석하였다. 마지막으로 VI 장에서 결론을 맺는다. II. MODIFIED MODULATION TRANSFER FUNCTION 식 (1)은 주파수 f 에 대한 MTF의 특성을 수식화 한 것이다. Hf f f

TFT-LCD Defect Detection Using Multi-level Threshold and Probability Density Function

TFT-LCD image consists of ununiform background, random noises and target defect signal components. Defects in TFT-LCD have some intensity variations compared to background region. It is sometimes difficult for human inspectors to figure out. In this paper, we propose multi-level threshold scheme for detection of the real defect using probability density function with Parzen Window. The experimental results show that the proposed algorithms produce promising results and can be applied to automated inspection systems for finding defects in the TFT-LCD image.

Polaroid Film Defect Detection Using 2D - Continuous Wavelet Transform

In this paper, we propose an effective method to extract background components in automated vision inspection system for polarized film used in TFT LCD display panels. The test image signals are typically composed of three components such as ununiform background, random noises and target defect signals. It is important to analyze the background signal for accurate extraction of defect components. Two dimensional continuous wavelets with first derivative gaussian is used. This methods can be applied for reliable extraction of defect signal by elimination of the background signal from the original image. The proposed method outperforms over conventional FFT methods.

Statistical Prediction of False Alarm Rates in Automatic Vision Inspection System

AVI (Automatic Vision Inspection) systems automatically detect defect features and measure their sizes via camera vision. It is important to predict the performance of an AVI to meet customer`s specification in advance. Also the prediction can indicate the level of current performance of an AVI system. In this paper, we propose a statistical method for prediction of false alarm rate regarding inconsistency of defect size measurement process. For this purpose, only simple experiments are needed to measure the defect sizes for certain number of times. The statistical features from the experiment are utilized in the prediction process. Therefore, the proposed method is swift and easy to implement and use. The experiment shows a close prediction compared to manual inspection results.