• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• 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.

• Journal of the Korean Society for Advanced Composite Structures
• /
• v.6 no.3
• /
• 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
• /
• v.7 no.4
• /
• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.237-242
• /
• 2016

This paper introduces a method of measuring the displacement of a cable-stayed bridge using digital image processing (DIP). The validity of the DIP technique was confirmed by comparing the results with those obtained using a displacement meter and ANSYS analysis. The normalized cross-correlation (NCC) coefficient was used. 100 kgf and 200 kgf loading experiments were carried out, which showed that when the displacement is large, the reliability of the DIP technique is increased. That is, when the load was increased from 100 kgf to 200kgf, it decreased from 31% to 14% compared to the ANSYS results and from 14% to 4% compared to the displacement meter results. Therefore, the image processing method is able to measure the displacement sufficiently accurately.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.09a
• /
• 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.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.275-280
• /
• 2004

In this paper, we propose automatic subtraction radiography algorithms to overcome conventional subtraction radiography's defects by applying image processing technique. In order to reach these goals, this paper suggests the image alignment method that is necessary for getting subtraction image and ROI(Region Of Interest) focused on a selection method using the structure characteristics in target images. Therefore, we use these methods because they give accurary, consistency and objective information or data to results. According to the results, easily and visually we can identify fine difference int the affected parts wether they have problems or not.

• Geomechanics and Engineering
• /
• v.17 no.6
• /
• 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.