• Applied Microscopy
• /
• v.43 no.2
• /
• pp.88-97
• /
• 2013

Technical investigation to figure out the problems arising during in-situ heating electron backscatter diffraction (EBSD) analysis inside scanning electron microscopy (SEM) was carried out. EBSD patterns were successfully acquired up to $830^{\circ}C$ without degradation of EBSD pattern quality in steels. Several technical problems such as image drift and surface microstructure pinning were taking place during in-situ experiments. Image drift problem was successfully prevented in constant current supplying mode. It was revealed that the surface pinning problem was resulted from the $TiO_2$ oxide particle formation during heating inside SEM chamber. Surface pinning phenomenon was fairly reduced by additional platinum and carbon multi-layer coating before in-situ heating experiment, furthermore was perfectly prevented by improvement of vacuum level of SEM chamber via leakage control. Plane view in-situ observation provides better understanding on the overall feature of recrystallization phenomena and cross sectional in-situ observation provides clearer understanding on the recrystallization mechanism.

• Journal of Biosystems Engineering
• /
• v.26 no.4
• /
• pp.355-362
• /
• 2001

Uniform application of agri-chemicals will improve orchard pest management. An air-blast(orchard) sprayer designed for vineyards has been used: however, few research on the uniformity and coverage of the sprays has been reported. Distributions of spray coverage were measured with artificial targets and analyzed to enhance the efficiency of spray application. A structure was built to place water sensitive papers, sampling spray droplets blasted from the orchard sprayer. The sampling cards were collected from five directions at three distances (2.5, 3.0 and 3.5m) for two fan speeds (2,075 and 3,031 rpm), and analyzed using an image analysis system. The distribution of the coverage percent area did not follow the wind velocity pattern. The coverage by the low fan speed was more uniform and higher than that by the higher fan speed. The coverage percent area decreased with an increase of distance. The distribution of droplet density was similar to that of coverage. However, the coverage contribution by smaller droplets became more significant as the distance increased. The upward blasting distance was limited within 3m, but the limit to the ground level was expanded the distance more than 3.5m because of the concentrated droplets.

• Korean Journal of Human Ecology
• /
• v.1 no.2
• /
• pp.113-118
• /
• 1998

Clothing shape is principally described in seven factors that are composed of clothing design, clothing material, clothing size, pattern design, sewing method and body motion etc.. The aims of this study was to measurement out-line space-shape variation of clothing fitness with somato type by using the image processing. The subjects for direct anthropometric measurements were 248 female college students aged from 19 to 22. The data were statistically analyzed by principal analysis and cluster analysis. The results were obtained three somato type. Also I made skirts in order to analyzed to the out-line space-shape variation of clothing fitness with body. The effect of somato type on the shape of flare skirts was determined by the out-line space-shape variation of clothing fitness with body. The out-line space-shape variation of clothing fitness with body was observed between the node number and amplitudes of clothing wave form and node number was determined at the maxim of space-shape amplitude, and the space-shape amplitudes have related with aspect ratio of cross-sectional shape. Results for flare skirts show changes in amplitude and mean with fabrics, somato type. therefore gray-level histogram are correlated with changes out-line space-shape, differences in drape spacing and related fabric properties and their somato type. (Korean J Human Ecology 1(2):113∼110 1998)

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1486-1495
• /
• 2020

The analysis of digital microscopy images plays a vital role in computer-aided diagnosis (CAD) and prognosis. The main purpose of this paper is to develop a machine learning technique to predict the histological grades in prostate biopsy. To perform a multiclass classification, an AI-based deep learning algorithm, a multichannel convolutional neural network (MCCNN) was developed by connecting layers with artificial neurons inspired by the human brain system. The histological grades that were used for the analysis are benign, grade 3, grade 4, and grade 5. The proposed approach aims to classify multiple patterns of images extracted from the whole slide image (WSI) of a prostate biopsy based on the Gleason grading system. The Multichannel Convolution Neural Network (MCCNN) model takes three input channels (Red, Green, and Blue) to extract the computational features from each channel and concatenate them for multiclass classification. Stain normalization was carried out for each histological grade to standardize the intensity and contrast level in the image. The proposed model has been trained, validated, and tested with the histopathological images and has achieved an average accuracy of 96.4%, 94.6%, and 95.1%, respectively.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.40 no.1
• /
• pp.11-16
• /
• 2014

Objectives: The aim of this study was to evaluate the pattern of lingual split line when performing a bilateral sagittal split osteotomy (BSSO) for asymmetric prognathism. This was accomplished with the use of cone-beam computed tomography (CBCT) and three-dimensional (3D) software program. Materials and Methods: The study group was comprised of 40 patients (20 males and 20 females) with asymmetric prognathism, who underwent BSSO (80 splits; n=80) from January 2012 through June 2013. We observed the pattern of lingual split line using CBCT data and image analysis program. The deviated side was compared to the contralateral side in each patient. To analyze the contributing factors to the split pattern, we observed the position of the lateral cortical bone cut end and measured the thickness of the ramus that surrounds the mandibular lingula. Results: The lingual split patterns were classified into five types. The true "Hunsuck" line was 60.00% (n=48), and the bad split was 7.50% (n=6). Ramal thickness surrounding the lingual was $5.55{\pm}1.07$ mm (deviated) and $5.66{\pm}1.34$ mm (contralateral) (P =0.409). The position of the lateral cortical bone cut end was classified into three types: A, lingual; B, inferior; C, buccal. Type A comprised 66.25% (n=53), Type B comprised 22.50% (n=18), and Type C comprised 11.25% (n=9). Conclusion: In asymmetric prognathism patients, there were no differences in the ramal thickness between the deviated side and the contralateral side. Furthermore, no differences were found in the lingual split pattern. The lingual split pattern correlated with the position of the lateral cortical bone cut end. In addition, the 3D-CT reformation was a useful tool for evaluating the surgical results of BSSO of the mandible.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.12
• /
• pp.561-570
• /
• 2015

With the advance of IT technology, contents from digital multimedia devices and softwares are widely used and distributed. However, novice uses them for illegal purpose and hence there are needs for protecting contents and blocking illegal usage through multimedia forensics. In this paper, we present a forensic technique for identifying digital imaging source using sensor pattern noise. First, the way to acquire the sensor pattern noise which comes from the imperfection of photon detector against light is presented. Then, the way to identify the similarity of digital imaging sources is explained after estimating the sensor pattern noises from the reference images and the unknown image. For the performance analysis of the proposed technique, 10 devices including DSLR camera, compact camera, smartphone and camcorder are tested and quantitatively analyzed. Based on the results, the proposed technique can achieve the 99.6% identification accuracy.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.05a
• /
• pp.77-88
• /
• 2003

Cluster analysis has been widely used in many applications, such that data analysis, pattern recognition, image processing, etc. But clustering requires many hours to get clusters that we want, because it is more primitive, explorative and we make many data an object of cluster analysis. In this paper we propose a new clustering method, 'Clustering algorithm using a center of gravity for grid-based sample'. It is more fast than any traditional clustering method and maintains accuracy. It reduces running time by using grid-based sample and keeps accuracy by using representative point, a center of gravity.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.392-409
• /
• 2016

The aim of this paper is to examine the effectiveness of combining three popular tools used in pattern recognition, which are the Active Appearance Model (AAM), the two-dimensional discrete cosine transform (2D-DCT), and Kernel Fisher Analysis (KFA), for face recognition across age variations. For this purpose, we first used AAM to generate an AAM-based face representation; then, we applied 2D-DCT to get the descriptor of the image; and finally, we used a multiclass KFA for dimension reduction. Classification was made through a K-nearest neighbor classifier, based on Euclidean distance. Our experimental results on face images, which were obtained from the publicly available FG-NET face database, showed that the proposed descriptor worked satisfactorily for both face identification and verification across age progression.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.2
• /
• pp.217-226
• /
• 2005

Cluster analysis has been widely used in many applications, such as data analysis, pattern recognition, image processing, etc. But clustering requires many hours to get clusters that we want, because it is more primitive, explorative and we make many data an object of cluster analysis. In this paper we propose a new clustering method, 'Clustering algorithm using a center of gravity for grid-based sample'. It reduces running time by using grid-based sample and keeps accuracy by using representative point, a center of gravity.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.6
• /
• pp.537-641
• /
• 2007

In this paper, motion analysis algorithm is presented for home surveillance of the aged who lives alone. For the first step, we acquire images from a camera. To enhance the image, we use median filtering and binarize it to reduce processing time. And then morphological operations are performed to remove small blobs and small holes. At the forth step, blobs are analysed to extracts tor foreground region. Then, motions are predicted from these images by using optical tlow technique, and the predicted motion data are refined by comparing our cardboard models so as to judge behavior pattern.