Sequential Defect Detection According to Defect Possibility in TFT-LCD Panel Image

Abstract

In TFT-LCD panel images, defects are typically detected by using a large difference in the brightness compared to the background. In this paper, we propose a sequential defect detection algorithm according to defect possibility caused by difference of brightness. By using this method, pixels with high defect probabilities are preferentially detected and defects with a large brightness difference are accurately detected. Also, limited defects with a small brightness difference is detected more reliably, eventually minimizing the degree of over-detection. We have experimentally confirmed that our proposed method showed an excellent detection result for detecting limited defects as well as defects with a large brightness difference.

Adaptive Defect Detection Method based on Skewness of the Histogram in LCD Image

“…. 자동 검사 시스템에 적용하기 위한 기존의 대표적인 결함 검출 방법으로는 Gabor 필터를 이용하는 방법 [6] , Otsu 방법 [7] , 평균과 표준편차를 이용한 방법 방법으로는 STD 방법 [8] 과 순차적 STD 방법 [9] 이 있다. 이용한 평탄화 기법을 사용한다 [6] .…”

Adaptive Detection of Unusual Heartbeat According to R-wave Distortion on ECG Signal

“…의 가변 불응기(refractory period:  ), 그리고 이웃한 파형 간의 첨도(kurtosis:  )를 사용하여 정확한 R-peak를 검출하는 방법을 적용한다 [7] . 검출하는 방법을 제안한다 [8] . 출 방식을 사용한다 [7] .…”