• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.686-688
• /
• 2020

본 논문에서는 U-Net 모델을 이용하여 정교하고 반복되는 패턴을 가진 인쇄물에 대한 비지도 학습을 통한 딥러닝 기반 이상치탐지(Anomaly Detection) 방법을 제안하였다. 인쇄물(카드)의 비정상 패턴 검출을 위하여 촬영한 영상으로부터 카드 영역을 분리한 이미지로 구성된 Dataset을 구축하였고 정상 이미지와 동일한 이미지를 출력하기 위해, 정상 이미지와 마스크 이미지 쌍의 Training dataset을 U-Net으로 학습하였다. Test dataset의 이미지를 입력으로 넣어 생성된 마스크 결과를 원본 마스크 이미지와 비교하여 이상 여부를 판단하는 본 논문의 방법이 정상, 비정상 인쇄물을 잘 구분하는 것을 확인하였다. 또한 정상과 비정상 이미지 각각을 학습한 지도학습 기반 CNN 분류 방법을 입력 영상과 복원 영상 간의 복원 오차를 비교하여 객체의 이상 여부를 판별하는 본 논문의 방법과 비교 평가하였다. 본 논문을 통해 U-Net을 사용하여 별도로 데이터에 대한 label 취득 없이 이상치를 검출할 수 있음을 확인할 수 있었다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.219-223
• /
• 2004

본 논문에서는 여러 생체 인식 시스템 중 지문 인식에 관한 연구를 기술한다 지문 입력장치를 통해 입력 받은 영상을 이용하여 개인의 식별을 위해 방향성과 특징점 정보를 이용, 매칭을 실시한다. 지문의 매칭은 1 차로 소벨 마스크와 창틀 마스크를 이용한 방향성 매칭과 2 차로 특징점 정보를 이용한 매칭 2 단계로 이루어 진다 방향성 정보를 이용한 매칭 방법에서는 가장 널리 알려진 소벨 마스크 보다 창틀 마스크가 더 정확한 것으로 판별 되었으며, 특징점 정보를 이용한 알고리즘에서는 상당한 의사 특징점을 제거 할 수 있었다 신뢰할 수 있는 방향성 검출 알고리즘과 특징점을 검출하기 위한 연구를 하였으며, 지문영상의 특징점으로는 끝점과 분기점을 사용하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2A
• /
• pp.105-112
• /
• 2012

Face detection at a distance faces is very challenging since images are often degraded by blurring and noise as well as low resolution. This paper proposes an improved face detection method with AdaBoost filtering and sequential testing stages with color and shape information. The conventional AdaBoost filter detects face regions but often generates false alarms. The face detection method is improved by adopting sequential testing stages in order to remove false alarms. The testing stages comprise skin-color test and variable edge-mask filtering. The skin-color filtering is composed of two steps, which involve rectangular window regions and individual pixels to generate binary face clusters. The size of the variable edge-mask is determined by the ellipse which is estimated from the face cluster. The validation of the horizontal and vertical ratio of the mask is also investigated. In the experiments, the efficacy of the proposed algorithm is proved by images captured by a CCTV and a smart-phone

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.82-83
• /
• 2012

본 논문에서는 세라믹을 비파괴 검사하여 얻어진 영상에서 세라믹의 결함을 검출하는 방법을 제안한다. 비파괴 검사를 통하여 얻어진 영상의 윤곽선을 추출하기 위하여 Prewitt 마스크를 적용한다. 그리고 비파괴 검사 영상의 잡음 비율을 최소화하기 위해 결함이 겹쳐진 윤곽선을 기준으로 감마 처리를 수행하고 임계치 이진화 기법을 적용하여 구간별로 결함을 검출한다. 구간별 결함을 통합하여 결함을 검출한다. 검출한 결함에 Grassfire 기법을 적용하여 미세한 잡음을 제거한다. 본 논문에서 제안된 방법의 성능을 평가하기 위해 비파괴 검사에 적용되는 영상을 대상으로 실험한 결과, 제안된 방법이 기존의 결함 검출 방법보다 결함 검출에 있어서 효과적인 것을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.404-406
• /
• 2013

An image edge has been utilized as preprocessing procedure in various field such as object detection, object recognition. there are Sobel, Prewitt, Roberts, Laplacian as conventional edge detection methods. existing methods are implement is simple, but edge detection characteristics is insufficient in impulse noise area. Therefore, to compensate the defect of conventional methods, in this paper, an edge detection algorithm using modified mask is proposed.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.8 s.350
• /
• pp.1-5
• /
• 2006

At-wavelength inspection system of extreme Ultra-violet lithography was developed and the inspection results were compared with the optical mask inspection system by cross correlation experiments. In at-wavelength EUV mask inspection system, a raster scan of focused euv light is used to illuminate euv light to mask blank and specularly and non-specularly reflected euv light are detected by photo diode and microchannel plate. The cross correlation results between at-wavelength inspection tool and optical inspection tool shows strong correlation. Far-field scattering fringe pattern from programmed phase and opqque defect, which were detected by phosphor plate and CCD camera shows that distinct diffraction fringes were observed with fringe spacing dependent on the defect size.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.218-223
• /
• 2013

The performances of previous edge detection methods such as Sobel, Prewitt, and LoG(Laplacian of Gaussian) are insufficient for images degraded in AWGN(additive white Gaussian noise). Therefore, in this paper, we proposed an edge detection algorithm using a modified coefficient masks with gradient masks and distance weight mask. In order to confirm and verify the performance of the proposed algorithm, we simulated and compared proposed algorithm to conventional methods on various standard images added AWGN with a standard deviation ${\sigma}$=15, 30 and proposed algorithm shows superior edge detection characteristics in processed images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.900-902
• /
• 2015

In the modern society, according to the advancement in digital image processing technology, edge detection is being utilized in various application sectors such as smart device and medical, etc. In existing edge detection methods, there are Sobel, Prewitt, Roberts and Laplacian, etc, which uses the mask. These previous methods are easy to implement but shows somewhat insufficient results. Therefore, in order to compensate the problems of existing methods, in this paper, an algorithm that detects the edge using the local mask and morphological operation was proposed and the detection performance was compared against the previous methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.2
• /
• pp.308-314
• /
• 2006

A line scan camera is applied to enhance COG(Chip On Glass) inspection accuracy to be measured a few micro unit. The foreign substance detection among various faulty factors has been the most difficult technology in the faulty automatic inspection step since COG pattern is very miniature and complexity. In this paper, we proposed two step area segmentation template matching method to increase matching speed. Futhermore to detect foreign substance(such as dust, scratch) with a few micro unit, the new method using gradient mask and AND operation was proposed. The proposed 2 step template matching method increased 0.3 - 0.4 second matching speed compared with conventional correlation coefficient. Also, the proposed foreign substance applied masks enhanced $5-8\%$ faulty detection rate compared with conventional no mask application method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.204-209
• /
• 2013

The image processing has been applied to various fields along with development of visual media. The boundary parts in which brightness of image dramatically changes are important factors in order to analysis characteristics of image because edge contains important information and significant features. A number of researches for detecting these edges have been conducted and conventional edge detection methods using relationship between adjacent pixels are that operation speed is superior, but the edge detection characteristics are insufficient because they use fixed mask without considering gray-level variation. In this paper, the novel algorithm using grey-level variation of image in mask is proposed.