• Journal of Sensor Science and Technology
• /
• v.33 no.2
• /
• pp.112-116
• /
• 2024

Gas-sensor technology for volatile organic compounds (VOC) biomarker detection offers significant advantages for noninvasive diagnostics, including rapid response time and low operational costs, exhibiting promising potential for disease diagnosis. Colorimetric gas sensors, which enable intuitive analysis of gas concentrations through changes in color, present additional benefits for the development of personal diagnostic kits. However, the traditional method of visually monitoring these sensors can limit quantitative analysis and consistency in detection threshold evaluation, potentially affecting diagnostic accuracy. To address this, we developed a machine vision platform based on metal-organic framework (MOF) for colorimetric gas sensor arrays, designed to accurately detect disease-related VOC biomarkers. This platform integrates a CMOS camera module, gas chamber, and colorimetric MOF sensor jig to quantitatively assess color changes. A specialized machine vision algorithm accurately identifies the color-change Region of Interest (ROI) from the captured images and monitors the color trends. Performance evaluation was conducted through experiments using a platform with four types of low-concentration standard gases. A limit-of-detection (LoD) at 100 ppb level was observed. This approach significantly enhances the potential for non-invasive and accurate disease diagnosis by detecting low-concentration VOC biomarkers and offers a novel diagnostic tool.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_3
• /
• pp.1415-1425
• /
• 2018

Kompsat-5 is the first Earth Observation Satellite which is equipped with an SAR in Korea. SAR images are generated by receiving signals reflected from an object by microwaves emitted from a SAR antenna. Because the wavelengths of microwaves are longer than the size of particles in the atmosphere, it can penetrate clouds and fog, and high-resolution images can be obtained without distinction between day and night. However, there is no color information in SAR images. To overcome these limitations of SAR images, colorization of SAR images using Cycle GAN, a deep learning model developed for domain translation, was conducted. Training of Cycle GAN is unstable due to the unsupervised learning based on unpaired dataset. Therefore, we proposed MS Cycle GAN applying multi-scale discriminator to solve the training instability of Cycle GAN and to improve the performance of colorization in this paper. To compare colorization performance of MS Cycle GAN and Cycle GAN, generated images by both models were compared qualitatively and quantitatively. Training Cycle GAN with multi-scale discriminator shows the losses of generators and discriminators are significantly reduced compared to the conventional Cycle GAN, and we identified that generated images by MS Cycle GAN are well-matched with the characteristics of regions such as leaves, rivers, and land.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.197-206
• /
• 2009

The medical information system is an effective medical diagnosis assistance system which offers an environment in which medial images and diagnosis information can be shared. However, this system can only stored and transmitted information without other functions. To resolve this problem and to enhance the efficiency of diagnostic activities, a medical image classification and retrieval system is necessary. The medical image classification and retrieval system can improve efficiency in a medical diagnosis by providing disease-related images and can be useful in various medical practices by checking diverse cases. However, it is difficult to understand the meanings contained in images because the existing image classification and retrieval system has handled superficial information only. Therefore, a medical image classification system which can classify medical images by analyzing the relation among the elements of the image as well as the superficial information has been required. In this paper, we propose the method for learning and classification of brain MRI, in which the superficial information as well as the spatial information extracted from images are used. The superficial information of images, which is color, shape, etc., is called low-level image information and the logical information of the image is called high-level image information. In extracting both low-level and high-level image information in this paper, the anatomical names and structure of the brain have been used. The low-level information is used to give an anatomical name in brain images and the high-level image information is extracted by analyzing the relation among the anatomical parts. Each information is used in learning and classification. In an experiment, the MRI of the brain including disease have been used.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.2
• /
• pp.8-17
• /
• 2008

This paper proposes a robust license plate extraction method from images taken under unconstrained environments. Utilization of the color and the edge information in complementary fashion makes the proposed method deal with not only various lighting conditions, hilt blocking artifacts frequently observed in compressed images. Computational complexity is significantly reduced by applying Hough transform to estimate the skew angle, and subsequent do-skewing procedure only to the candidate regions. The true plate region is determined from the candidates under examination using clues including the aspect ratio, the number of zero crossings from vertical scan lines, and the number of connected components. The performance of the proposed method is evaluated using compressed images collected under various realistic circumstances. The experimental results show 94.9% of correct license plate extraction rate.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.1
• /
• pp.40-47
• /
• 2017

To classify the vehicle targets automatically using thermal images, there are usually two main categories of feature extraction method, local and shape feature extraction methods. Since thermal images have less texture information than color images, the shape feature extraction method is useful when the segmentation results are correct. However, if there are some errors in target segmentation, the shape feature may contain some errors, then the classification accuracy can be decreased. To overcome these problems, in this paper, we propose the segmentation reliability estimation method for target classification. The segmentation reliability can be estimated by using the difference information of average intensities and edge energies between the target and the background area. The estimated segmentation reliability is applied in the decision level fusion method of classification results using both shape and local features. Experiment results using the thermal images of the vehicle targets (main battle tank, armored personnel carrier, military truck, and an estate car) show that the proposed classification method and the segmentation reliability estimation method have a good performance in classification accuracy.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.9 no.2
• /
• pp.81-89
• /
• 2006

The purpose of this study was to evaluate the applicability of small RC(radio controlled) helicopter and single lens reflect camera as SFAP(Small Format Aerial Photography) aquisition system to monitor the vegetation coverage of wetland. The system used to take pictures of small artificial wetland were a common optical camera(Nikon F80 with manual lens whose focal length was 28mm) attached to the bottom of a RC helicopter with a 50 cubic inch size glow engine. Three hundreds pictures were taken at the altitude of 50m above the ground, from 23rd June to 7th September 2005. Four from the images were selected and scanned to digital images whose dimension were 2048${\times}$1357 pixels. Those images were processed and rectified with GCP(Ground Control Poins) and digital map, and then classified by the supervised- classification module of image processing program PG-steamer Version 2.2. The major findings were as follows ; 1. The final images processed had very high spatial resolution so that the objects bigger than 30mm like lotus(Nelumbo nucifera), rock and deck were easily identified. 2. The dominant plants of the monitoring site were Monochoria ragianlis, Typha latifolia, Beckmannia syzigachne etc. Because those species have narrow and long leaves and form irregular biomass, the individuals were hardly identifiable, but the distribution of population were easily identifiable depending on the color difference. 3. The area covered by vegetation was rapidly increased during the first month of monitoring. At the beginning of the monitoring 23th June 2005, The rate of area covered by vegetation were only 34%, but after 27 and 60 days it increased to 74%, and the 86% respectively.

• Korean Journal of Human Ecology
• /
• v.15 no.4
• /
• pp.585-595
• /
• 2006

The purpose of this study is to classify the fashion images on sportive style, to find out the difference between the image of sportive style which consumers prefer and the image of sportive style which they want to show and, finally, to analyze their purchase behavior. This research is done with survey method. The subjects of the survey are 835 females in their twenties or their thirties in Pusan area. The data are analyzed with factor analysis, Cronbach's alpha, $X^2$-test, and frequency analysis. The results of this study are as follows: first, sportive style is classified into Sexy, Romantic, Active and Modem image. Second, the results of analysis on consumers' preferring image and their wanting-to-show image to the above-mentioned image classification are as follows: firstly, the subjects' most preferring image and the image which they most want to show is Modem in1age. The second is Sexy image. But the subjects preferred having Modem image. Secondly, consumers' Individuality and apparel's Function are the important reasons to choose the sportive style. Thirdly, Modem image is the most preferred in the images of street wear. Sexy image and Active image are the preferred in the images of sports wear. Third, It is a vivid tone and a dark tone that is the color tone of sportive wear which consumers prefer. They prefer a logo- patterned sports wear, too. The consumers obtain most information on sports wear from sports wear stores. Silhouette is the most decisive design element in consumers' purchasing. The sports wear brands which the subjects prefer are Adidas and Nike.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.8
• /
• pp.459-466
• /
• 2014

Fading effect of old pictures and printings is shown up differently according to the ink property, temperature, humidity, illuminants, and so on. Faded image enhancement techniques based on illuminant estimation are proposed such as the gray world algorithm and white patch retinex methods. However, conventional simple operators are not suitable for enhancing faded images because partial fading effect is appeared differently. Thus, this paper presents a color enhancement algorithm based on integrating correction coefficients for faded images. First, the proposed method adopts local process by using multi-scale average mask. The coefficients for each multi-scale average mask are obtained to apply the gray world algorithm. Then, integrating the coefficients with weights is performed to calculate correction ratio for red and blue channels in the gray world assumption. Finally, the enhanced image is obtained by applying the integrated coefficients to the gray world algorithm. In the experimental results, the proposed method reproduces better colors for both wholly and partially faded images compared with the previous methods.

• Journal of the Korean Geographical Society
• /
• v.47 no.2
• /
• pp.282-296
• /
• 2012

This study compared effects of spatial resolution ratio in image fusion by Korea Multi-Purpose SATellite 2 (KOMPSAT II), also known as Arirang-2. Image fusion techniques, also called pansharpening, are required to obtain color imagery with high spatial resolution imagery using panchromatic and multi-spectral images. The higher quality satellite images generated by an image fusion technique enable interpreters to produce better application results. Thus, image fusions categorized in 3 domains were applied to find out significantly improved fused images using KOMPSAT 2. In addition, all fused images were evaluated to satisfy both spectral and spatial quality to investigate an optimum fused image. Additionally, this research compared Pixel-Based Image Analysis (PBIA) with the GEOgraphic Object-Based Image Analysis (GEOBIA) to make better classification results. Specifically, a roof top of building was extracted by both image analysis approaches and was finally evaluated to obtain the best accurate result. This research, therefore, provides the effective use for very high resolution satellite imagery with image interpreter to be used for many applications such as coastal area, urban and regional planning.

• Journal of the Korean Society of Costume
• /
• v.57 no.3 s.112
• /
• pp.63-77
• /
• 2007

The purpose of this study is to apply fashion design to developing dress design of mobile-phone game characters. As for the research methodology, first, market research has been carried out to extract main images from dress designs of game characters and to understand their socio-cultural meanings. Second, the fashion design, which ran be compared to the extracted images of game characters were selected. Third, analyses were done to find out the gap between the game character's dress designs and the fashion designs. The main images of game characters are revealed as erotic, romantic, heroic, grotesque. These images have been formed by psychological and socio-cultural effects such as stimulation, empathy, compensation, increase of female game player. The differences between the game character's dresses and the fashion designs are as follows; With regard to style, game dresses have silhouette distinguished from background, but fashion collection have blurred silhouette. In the aspect of color, while strong colors are mainly used in game dress, neutral rotors are preferred in fashion collection. As for texture, the expression of 'textures in game character's dress is so far limited due to the insufficient level of the concerned technology. However, the fashion design applying drape of fabrics are well-developed. Mobile-phone game players want reality in game design. Therefore, the effort to overcome the gaps between game dress and fashion design can contribute to the growth of game character design.