• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.193-195
• /
• 2010

본 논문에서는 비파괴 검사를 통하여 얻어진 항공 갑판 영상에서, 조직의 이상이나 결함의 정도를 자동으로 검출하는 방법을 제안한다. 비파괴 검사를 통하여 얻어진 항공 갑판 영상에서 감마상관 변환과 $7{\times}7$ 소벨 마스크와 $13{\times}13$ 소벨 마스크를 각각 적용하여 윤곽선을 추출한다. 추출된 윤곽선 영역을 평활화와 평균 이진화 기법을 적용하여 영상을 보정한다. 보정된 영상에서 침식 연산과 팽창 연산을 이용하여 잡음을 제거한 후, 라벨링 기법을 적용하여 항공 갑판의 결함 영역을 추출한다. 본 논문에서 제안한 방법을 다양한 항공 갑판 영상을 대상으로 실험한 결과, 기존의 방법보다 항공 갑판에서 결함을 추출하는데 효과적인 것을 확인하였다.

• Proceedings of the Optical Society of Korea Conference
• /
• 2002.11a
• /
• pp.48-49
• /
• 2002

• Journal of the Korea Convergence Society
• /
• v.8 no.4
• /
• pp.273-278
• /
• 2017

Contemporary art make-up is being widely developed in line with the trends of individualization and differentiation departing from basic desires or logical thinking about the desires of human beings who ultimately pursue beauty and experiencing diversified convergence and integration befitting customer needs. Cubism that has been playing a central role at the center of art history in the $20^{th}$ century can act as a good material based on creativity with regard to expression of the art make-up. In this regard, the study was focused on creating new concepts of design and novel areas of expression by combining expressive methods of cubism with art make-up to suggest an art mask. As for a method of the study, cubism and art make-up were examined based on preceding studies, Internet data and technical books, and the expression method of cubism was divided into plural points of view, partition of shape and collage and motivated the works of Picasso for the purpose of art mask-converged design. As a result of the study, it was found out that the expression method of cubism was applicable to the art make-up, and creative art make-up converged design could be generated to make a suggestion. In this regard, it is hoped that further studies will be facilitated and that this study can be instrumental in developing art make-up design.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.44-49
• /
• 2021

Recently, due to COVID-19, studies have been popularly worked to apply neural network to mask wearing automatic detection system. For applying neural networks, the 1-stage detection or 2-stage detection methods are used, and if data are not sufficiently collected, the pretrained neural network models are studied by applying fine-tuning techniques. In this paper, the system is consisted of 2-stage detection method that contain MTCNN model for face recognition and ResNet model for mask detection. The mask detector was experimented by applying five ResNet models to improve accuracy and fps in various environments. Training data used 17,217 images that collected using web crawler, and for inference, we used 1,913 images and two one-minute videos respectively. The experiment showed a high accuracy of 96.39% for images and 92.98% for video, and the speed of inference for video was 10.78fps.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.1
• /
• pp.81-89
• /
• 2009

To support dynamic Region-of-Interest(ROI) in JPEG2000, a fast ROI mask generation is needed. In the existing methods of ROI coding, after scanning all the pixels in order and discriminating ROI, an ROI mask has been generated. Our method scans 4 pixels of the corners in one code block, and then based on those informations, scans the edges from the corners to get the boundaries of ROI and background. These informations are consisted of a distributed information of ROI and two coordinates of the pixels, which are the points the edges and the boundaries meet. These informations are transmitted to encoder and supported for fast ROI mask generation. There were no great differences between the proposed method and the existing methods in quality, but the proposed method showed superiority in speed.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.21-26
• /
• 2022

Wearing face masks is an effective measure to prevent COVID-19 infection. Infrared thermal image based temperature measurement and identity recognition system has been widely used in many large enterprises and universities in China, so it is totally necessary to research the face mask detection of thermal infrared imaging. Recently introduced MTCNN (Multi-task Cascaded Convolutional Networks)presents a conceptually simple, flexible, general framework for instance segmentation of objects. In this paper, we propose an algorithm for efficiently searching objects of images, while creating a segmentation of heat generation part for an instance which is a heating element in a heat sensed image acquired from a thermal infrared camera. This method called a mask MTCNN is an algorithm that extends MTCNN by adding a branch for predicting an object mask in parallel with an existing branch for recognition of a bounding box. It is easy to generalize the R-CNN to other tasks. In this paper, we proposed an infrared image detection algorithm based on R-CNN and detect heating elements which can not be distinguished by RGB images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.630-632
• /
• 2012

Contemporary society has evolved in the digital information age. Because of this, use of various digital images has been increased. To process these images, various digital image processing methods are used. Edge detection methods, one of those, are utilized to various areas of application such as object recognition, line detection. To detect edge, there are many methods such as Sobel, Prewitt, Laplacian. Because images which are dealt with existing methods are processed in same methods regardless the distribution of gray-level in image, edge detection property is insufficient. Therefore, In this study, to improve shortcomings of existing methods an algorithm using modified expansion mask is proposed.

• The Journal of the Korea Contents Association
• /
• v.7 no.8
• /
• pp.1-12
• /
• 2007

This paper presents a new demixing method that separates each source from a stereo sound mixture. Under the W-Disjoint Orthogonal assumption in DUET(Degenerate Unmixing Estimation Technique) algorithm. The proposed method is mainly processed in time-frequency domain by using windowed-fourier transform. In this paper there are two main contributions: a weighted mask by panning index distances and a binary mask by comparing each channel value. The former has tender demixing characteristic, and the latter has stronger demixing characteristic. In experimental results, we will show that both masks produce more robust demixing than the existing demixing methods do.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.360-365
• /
• 2005

본 논문에서는 콘크리트 표면 균열 영상에서 균열을 효율적으로 추출하기 위한 화상처리 기법과 ART1 기반 RBF 네트워크를 제안하여 균열의 방향성을 인식한다. 본 논문에서 사용된 화상처리 기법으로는 균열 영상의 빛을 보정하기 위한 모폴로지 기법인 채움(Closing)연산을 적용하고 Sobel 마스크를 적용하여 균열 영상의 에지를 추출한 후 반복 이진화를 적용하여 균열 영상을 이진화한다. 이진화 된 영상에 두 차례에 걸쳐 잡음제거를 수행하여 콘크리트 표면 균열 영상으로부터 균열을 추출한다. 본 논문에서는 추출된 균열을 ART1 기반 RBF 네트워크에 적용하여 균열의 방향성(횡방향, 종방향, $-45^{\circ}$방향, $45^{\circ}$방향)을 자동으로 인식할 수 있는 방법을 제안한다. 제안된 ART1 기반 RBF 네트워크는 입력층과 중간층으로의 학습은 ART1을 적용하고 중간층과 출력층 간의 학습은 Delta 학습 방법을 적용한다. 실제 콘크리트 균열 영상을 적용하여 실험한 결과, 콘크리트 표면 균열 영상에서 효율적으로 균열을 추출할 수 있었고 제안된 ART1 기반 RBF 네트워크가 추출된 균열의 방향성 인식에 효율적인 것을 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.11
• /
• pp.27-32
• /
• 2012

In this paper, we propose a fuzzy method that improves the existing problem of the fuzzy filtering algorithm. The proposed fuzzy filtering algorithm separates R, G, and B channels from the color image. Mask information was extracted from separated channels and the brightness of the mean value and median value for channels was applied in the function of the proposed fuzzy method to calculate the membership and achieve application in the inference rule. Also, the membership degrees of R, G, and B were used to distinguish the possibility of noise. The proposed fuzzy method selected three membership functions. If noise is distinguished, the noise is eliminated by selecting the median value or mean value as the relevant pixel value according to the degree of noise. By applying the proposed method in color images, it was verified that the proposed method is more effective in eliminating noise when compared with the conventional fuzzy filtering method.