• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.41-46
• /
• 2023

Human urine is a process of excreting waste products in the blood, and it is easy to collect and contains various substances. Urinalysis is used to check for diseases, health conditions, and urinary tract infections. There are three methods of urinalysis: physical property test, chemical test, and microscopic test, and chemical test results can be easily confirmed using urine test strips. A variety of items can be tested on the urine test strip, through which various diseases can be identified. Recently, with the spread of smart phones, research on reading urine test strips using smart phones is being conducted. There is a method of detecting and reading the color change of a urine test strip using a smartphone. This method uses the RGB values and the color difference formula to discriminate. However, there is a problem in that accuracy is lowered due to various environmental factors. This paper applies a deep learning model to solve this problem. In particular, color discrimination of a urine test strip is improved in a smartphone using a lightweight CNN (Convolutional Neural Networks) model. CNN is a useful model for image recognition and pattern finding, and a lightweight version is also available. Through this, it is possible to operate a deep learning model on a smartphone and extract accurate urine test results. Urine test strips were taken in various environments to prepare deep learning model training images, and a urine test service application was designed using MobileNet V3.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.2
• /
• pp.165-172
• /
• 2013

In this paper, high-quality mosaic image is generated by high-resolution hyperspectral strip images using scale-invariant feature transform (SIFT) algorithm, which is one of the representative image matching methods. The experiments are applied to AISA Eagle images geo-referenced by using GPS/INS information acquired when it was taken on flight. The matching points between three strips of hyperspectral images are extracted using SIFT method, and the transformation models between images are constructed from the points. Mosaic image is, then, generated using the transformation models constructed from corresponding images. Optimal band appropriate for the matching point extraction is determined by selecting representative bands of hyperspectral data and analyzing the matched results based on each band. Mosaic image generated by proposed method is visually compared with the mosaic image generated from initial geo-referenced AISA hyperspectral images. From the comparison, we could estimate geometrical accuracy of generated mosaic image and analyze the efficiency of our methodology.

• Journal of the Korea Computer Graphics Society
• /
• v.7 no.2
• /
• pp.29-35
• /
• 2001

In general, image-based virtual environment is represented by panoramic images created by image mosaic algorithm. The cylindrical panoramic image supports the fixed-viewpoint navigation due to the constraints of construction. Shum proposed concentric mosaics to allow users to navigate freely within a circular area[10]. It is constructed by a sequence of images which is acquired from a regularly rotating camera. Concentric mosaics technique, proposed by Shum, is considered as 3D plenoptic function which is defined three parameters : distance, height and angle. In this paper, we suggest an effective method for creating concentric mosaics, in which we first align a set of strip images on the cylinder plane and stitch the aligned strips to build a panoramic image. The proposed method has no constraints such as regular panning motion of camera. Furthermore, our proposed method minimizes the use of interpolation image to create a novel view images from the concentric mosaics. It allows the result image on a novel view to have better quality with respect to the number of input images.

• Journal of Magnetics
• /
• v.3 no.2
• /
• pp.44-48
• /
• 1998

Scanning Electron Microscopy with Polarization Analysis (SEMPA) was used to image the surface magnetic domain structure of the 100 ${\mu}{\textrm}{m}$ thick 3% Si-Fe sheet. The thin-gauged 3% Si-Fe strips with magnetic induction ($B_{10}$) from 1.98 to 1.57 Tesla were prepared via conventional metallurgical processes including melting, hot-and cold-rolling, intermediate annealing and final annealing. Using SEMPA, it was observed that the $B_{10}$ (1.98 T) Tesla sample was almost composed of 180$^{\circ}$ stripe domains which are parallel to rolling direction. On the other hand the 3% Si-Fe sheet with $B_{10}$ (1.57 T) Tesla was composed of large 180$^{\circ}$stripe domains that are slanted about 30$^{\circ}$to the rolling direction and complex magnetic domain structures like tree and zigzag pattern. The 180$^{\circ}$stripe domains, which covered a major part of the sample, had (110)<001> Goss texture parallel to the rolling direction. The domain walls between 180$^{\circ}$stripe domains were the conventional Bloch type walls. On the other hand, the 90$^{\circ}$domains, which covered minor part on edge of the sample, were observed in (200) grains. The domain walls between 90$^{\circ}$domains were the Neel type walls. In high magnification, the elliptical singularity at the Neel walls was clearly observed.

• The Journal of Korean Academy of Prosthodontics
• /
• v.45 no.3
• /
• pp.303-309
• /
• 2007

Statement of problem. The effect of gold electroforming on gold alloy was not studied. Purpose. This in vitro study investigate the effect of gold electroforming on gold-silver-palladium alloy. Material and methods. Three pieces of gold strips had undergone the electroforming procedures on one side and then half of the side again electroformed. The set mode for this study was program 1 ($200{\mu}m$). And the processing time was 15min (1/20 time to form $200{\mu}m$ coping). The confocal laser scanning microscope (PASCAL 5, Carl Zeiss, Bernried, Germany) was used to measure the thickness of the pure gold layer electroformed on the gold strips. Half of the gold strip was coated two times with electroformed gold, and the other half one time. The data from the cone focal laser system was processed to get the vertical profile of the strips and the difference of the vertical height between the double coated and single coated layer was regarded as the thickness of the gold coating. The layer thickness value to built 3D image of the cone-focal laser was set $0.5{\mu}m$. Next to the measurement of the thickness of the coating, the Vicker's hardness test was done. It was performed on the double coated surface, single coated surface and non-coated surface (back side) three times each. Results. The mean thickness value gained from gold electroforming technique was measured to be $22{\mu}m$ for sample 1, $23{\mu}m$ for sample 2, $21{\mu}m$ for sample 3. In the same condition of time, power and the amount of electrolyte, the data showed no difference between samples. According to the results of variance analysis, the differences among the variations in number of coating were statistically insignificant (p>0.05), meaning that the two times of gold electroforming coating did not change the hardness of gold-silver-palladium alloy. Conclusion. The test of thickness of gold coating proved the coherency of the gold electroforming procedure, in other words, when the power, the exposed surface area, processing time and the amount of electrolytes were set same, the same thickness of gold would be coated on. The hardness test showed that the electroformed gold coating did not change the hardness of the gold-silver-palladium alloy when it is coated not more than $45{\mu}m$.

• Korean Journal of Remote Sensing
• /
• v.22 no.1
• /
• pp.63-73
• /
• 2006

Currently, in order to achieve accurate geolocation of satellite images we need to generate control points from individual scenes. This requirement increases the cost and processing time of satellite mapping greatly. In this paper we investigate the feasibility of modeling entire image strips that has been acquired from the same orbital segments. We tested sensor models based on satellite orbit and attitude with different sets of unknowns. We checked the accuracy of orbit modeling by establishing sensor models of one scene using control points extracted from the scene and by applying the models to adjacent scenes within the same orbital segments. Results indicated that modeling of individual scenes with $2^{nd}$ order unknowns was recommended. In this case, unknown parameters were position biases, drifts, accelerations and attitude biases. Results also indicated that modeling of orbital segments with zero-degree unknowns was recommended. In this case, unknown parameters were attitude biases.

• Journal of Korean Society of Transportation
• /
• v.24 no.3 s.89
• /
• pp.125-131
• /
• 2006

Recently, flowerbed median strips are being installed in urban highways for safety and scenery. In addition, efforts to enhance urban image through roadside flowerbeds and trees are being exerted for afforestation to enhance the urban environment. The sensibility of humans, such as the feeling of agreeableness of drivers must be considered when planning roads. However, not many researches on users on road environment are being conducted. Accordingly, KANSEI Engineering that is attracting attention nowadays was applied to form the image or sensibility of humans as definite object, in order to grasp the relation between the personal attributes of users and road formation with sensible factors considered when the road users evaluates the road scenery. As the result of research, streetscape was not evaluated based on individual factors such as roads, trees and buildings that form roads, but was based on sensibility image based on harmony of the overall road formation according to the changes of each factors.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.77-82
• /
• 2021

There are three types of urinalysis: physical test, chemical test, and microscopic test. Among these, the chemical urinalysis is an easily accessible method of the general public to compare the chemical reaction of urinalysis strip with a standard colorimetric table by sight or purchase the portable urinalysis machine separately. Currently, with the popularization of smartphone, research on the urinalysis service using smartphone is increasing. The urinalysis screening application is one of the urinalysis services using a smartphone. However, the RGB values of the urinalysis pad taken by the urinalysis screening application have large deviations due to the effect of lighting. Deviation of RGB value debases the accuracy of urinalysis discrimination. Therefore, in this paper, the accuracy of urinaylsis pad image discrimination is improved through CNN after classifying urinalysis strips taken by the urinalysis screening application based on smartphone by urinalysis pad items. Urinalysis strip was taken from various backgrounds to generate CNN image, and urinalysis discrimination was analyzed using the ResNet-50 CNN model.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.2
• /
• pp.143-152
• /
• 2012

It is well-known that image matching is necessary for automatic generation of 3D data such as digital surface data from aerial images. Recently developed aerial digital cameras allow to capture multi-strip images with higher overlaps and less occluded areas than conventional analogue cameras and that much of researches on multi-image matching have been performed, particularly effective methods of measuring a similarity among multi-images using point features as well as linear features. This research aims to investigate similarity measuring methods such as SSD and SNCC incorporated into a area based multi-image matching method based on vertical line locus. In doing this, different similarity measuring entities such as grey value, grey value gradient, and average of grey value and its gradient are implemented and analyzed. Further, both dynamic and pre-fixed adaptive-window size are tested and analyzed in their behaviors in measuring similarity among multi-images. The aerial images used in the experiments were taken by a DMC aerial frame camera in three strips. The over-lap and side-lap are about 80% and 60%, respectively. In the experiment, it was found that the SNCC as similarity measuring method, the average of grey value and its gradient as similarity measuring entity, and dynamic adaptive-window size can be best fit to measuring area-based similarity in area based multi-image matching method based on vertical line locus.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.3
• /
• pp.61-70
• /
• 2001

This paper presents a new method to extract semi-automatically roads from high spatial resolution satellite imagery. This method is based both on wavelet transform and on multiresolution analysis combined in the "$\grave{a}$ trous" algorithm. As an urban road network consists on different classes of streets, multiresolution processing allows to extract the streets class by class. The method was applied to a KVR-1000 image on a part of Busan Metropolitan City. The method was carried out for the road extraction of three different widths and it succeeded in extracting good fitted strips. The accuracy analysis for three types of streets was also performed. The overall accuracy in 4 pixels of width is 80.5%. The result suggests that this method can be used to update road networks in the studied urban network. In summary, the multiresolution approach based on the wavelet transform, used in this study, is regarded as one of effective methods to extract urban road network from high spatial resolution satellite images.