• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.661-669
• /
• 2022

The purpose of this study is to compare and analyze Deep Learning (DL) and Digital Image Processing (DIP) techniques using the results of the glottis segmentation of the two methods followed by the quantification of the asymmetric degree of the vocal cord mucosa. The data consists of 40 normal and abnormal images. The DL model is based on Deeplab V3 architecture, and the Canny edge detector algorithm and morphological operations are used for the DIP technique. According to the segmentation results, the average accuracy of the DL model and the DIP was 97.5% and 94.7% respectively. The quantification results showed high correlation coefficients for both the DL experiment (r=0.8512, p<0.0001) and the DIP experiment (r=0.7784, p<0.0001). In the conclusion, the DL model showed relatively higher segmentation accuracy than the DIP. In this paper, we propose the clinical applicability of this technique applying the segmentation and asymmetric quantification algorithm to the glottal area in the laryngoscopic images.

• 복합신소재구조학회 논문집
• /
• 제6권3호
• /
• pp.20-25
• /
• 2015

This paper introduces a digital image processing(DIP) method as a method for measuring the displacement of pylon. The comparison of DIP results and ANSYS analysis results verified the validity of the image processing technique. Normalized cross-correlation(NCC) coefficient was used and experiments were performed three times. It shows that the displacement difference was 22% and 5% compared to ANSYS results. Therefore, the image processing method is expected to be able to measure the displacement of pylon sufficiently.

• Geomechanics and Engineering
• /
• 제7권4호
• /
• pp.375-401
• /
• 2014

It is generally accepted that material heterogeneity has a great influence on the deformation, strength, damage and failure modes of rock. This paper presents numerical simulation on rock failure process based on the characterization of rock heterogeneity by using a digital image processing (DIP) technique. The actual heterogeneity of rock at mesoscopic scale (characterized as minerals) is retrieved by using a vectorization transformation method based on the digital image of rock surface, and it is imported into a well-established numerical code Rock Failure Process Analysis (RFPA), in order to examine the effect of rock heterogeneity on the rock failure process. In this regard, the numerical model of rock could be built based on the actual characterization of the heterogeneity of rock at the meso-scale. Then, the images of granite are taken as an example to illustrate the implementation of DIP technique in simulating the rock failure process. Three numerical examples are presented to demonstrate the impact of actual rock heterogeneity due to spatial distribution of constituent mineral grains (e.g., feldspar, quartz and mica) on the macro-scale mechanical response, and the associated rock failure mechanism at the meso-scale level is clarified. The numerical results indicate that the shape and distribution of constituent mineral grains have a pronounced impact on stress distribution and concentration, which may further control the failure process of granite. The proposed method provides an efficient tool for studying the mechanical behaviors of heterogeneous rock and rock-like materials whose failure processes are strongly influenced by material heterogeneity.

• 한국산학기술학회논문지
• /
• 제17권5호
• /
• pp.237-242
• /
• 2016

본 논문은 돌산대교 모형 사장교에 하중을 주었을 때 발생되는 변위를 측정하기 위한 방법으로 디지털 영상처리 방법을 도입하여 실험을 하였다. 돌산대교 모형 사장교는 30:1로 축소한 경우로 길이 15.5m, 너비 400mm이다. 실험 방법은 영상처리 결과를 ANSYS 해석결과와 변위계 측정결과를 비교, 분석하여 영상처리 기법의 타당성을 검증하였다. 본 실험에 적용된 영상처리 기법은 상호상관 계수를 적용하였으며, 실험 조건은 100kgf 재하 하였을 때의 변위와 200kgf 재하 하였을 때의 변위를 측정하는 실험을 수행하였다. 분석 결과 하중이 추가적으로 증가하여 발생되는 변위가 커질수록 영상처리에 대한 신뢰성도 증가하는 것으로 나타났다. 즉, 하중이 100kgf에서 200kgf으로 증가할 때, ANSYS 결과대비 오차율이 31%에서 14%로 감소하였으며, 변위계 결과대비 오차율 역시 17%에서 4%로 감소하였다. 200kgf 재하시 14%, 4%의 차이를 보이고 있어, 영상처리 기법으로 충분히 변위를 측정할 수 있을 것으로 판단된다. 향후 연구로는 동영상 파일로 부터 고유진동수를 측정하는 방법에 대해서 연구하고자 한다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 추계 학술발표회
• /
• pp.1177-1181
• /
• 2010

Unsaturated soil can describe soil particles, air-water and contact face between air and water. The providing a simple method to predict water content in Geotechnical mechanics is very important. In this experiment, DIP (Digital Image Processing) and electrical resistivity techniques were used simultaneously to predict the saturation degree, and the results of two techniques will be compared each other to get conclusion. The experiment was carried out for Jumunjin standard sand. The picture of experimental column of soil and water was taken at different times, then using DIP technique to measure Color number-the height of capillary in soil column. At the same time, measure electrical resistivity of the soil.

• 정보처리학회논문지B
• /
• 제11B권3호
• /
• pp.275-280
• /
• 2004

본 논문은 디지털 방사선 영상에 영상처리기법을 이용하여 기존의 수동적인 방법으로 개인차를 유발했던 차영상 진단방법을 자동화하는 알고리즘 방법을 제안한다. 이를 위해 차영상 획득 이전에 수행될 투 영상의 정렬방법과 치과용 디지털 방사선영상내의 구조적 특징을 이용하여 관심영역을 선정할 수 있는 방법론을 제안하고, 이를 이용하여 영역에 대한 차정보 표시 및 이에 대한 수치적 근거를 제시함으로써 기존의 방법이 갖지 못한 결과의 일관성 및 객관성을 갖도록 하였다. 구현결과 인간의 시각으로 판별하기 어려운 미세한 차이의 표시 및 환부의 이상발생여부를 확연히 구분할 수 있었다.

• Geomechanics and Engineering
• /
• 제17권6호
• /
• pp.565-572
• /
• 2019

Spatial variability is an inherent characteristic of soil, and auto-correlation length (ACL) is a very important parameter in the reliability or probabilistic analyses of geotechnical engineering that consider the spatial variability of soils. Current methods for estimating the ACL need a large amount of laboratory or in-situ experiments, which is a great obstacle to the application of random field theory to geotechnical reliability analysis and design. To estimate the ACL reasonably and efficiently, we propose a micro-structure based numerical simulation method. The quartet structure generation set algorithm is used to generate stochastic numerical micro-structure of soils, and scanning electron microscope test of soil samples combined with digital image processing technique is adopted to obtain parameters needed in the QSGS algorithm. Then, 2-point correlation function is adopted to calculate the ACL based on the generated numerical micro-structure of soils. Results of a case study shows that the ACL can be estimated efficiently using the proposed method. Sensitivity analysis demonstrates that the ACL will become stable with the increase of mesh density and model size. A model size of $300{\times}300$ with a grid size of $1{\times}1$ is suitable for the calculation of the ACL of clayey soils.