• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.701-720
• /
• 2023

Aerial objects are more challenging to segment than normal objects, which are usually smaller and have less textural detail. In the process of segmentation, target objects are easily omitted and misdetected, which is problematic. To alleviate these issues, we propose local aggregation feature pyramid networks (LAFPNs) and pyramid integrated context modules (PICMs) for aerial object segmentation. First, using an LAFPN, while strengthening the deep features, the extent to which low-level features interfere with high-level features is reduced, and numerous dense and small aerial targets are prevented from being mistakenly detected as a whole. Second, the PICM uses global information to guide local features, which enhances the network's comprehensive understanding of an entire image and reduces the missed detection of small aerial objects due to insufficient texture information. We evaluate our network with the MS COCO dataset using three categories: airplanes, birds, and kites. Compared with Mask R-CNN, our network achieves performance improvements of 1.7%, 4.9%, and 7.7% in terms of the AP metrics for the three categories. Without pretraining or any postprocessing, the segmentation performance of our network for aerial objects is superior to that of several recent methods based on classic algorithms.

• Convergence Security Journal
• /
• v.22 no.1
• /
• pp.29-38
• /
• 2022

The importance of prevention of epidemics is increasing due to the serious spread of infectious diseases. For prevention of epidemics, we need to focus on the non-contact industry. Therefore, in this paper, a face recognition door lock that controls access through non-contact is designed and developed. First very simple features are combined to find objects and face recognition is performed using Haar-based cascade algorithm. Then the texture of the image is binarized to find features using LBPH. An non-contact door lock system which composed of Raspberry PI 3B+ board, an ultrasonic sensor, a camera module, a motor, etc. are suggested. To verify actual performance and ascertain the impact of light sources, various experiment were conducted. As experimental results, the maximum value of the recognition rate was about 85.7%.

• Korean journal of food and cookery science
• /
• v.18 no.2
• /
• pp.225-231
• /
• 2002

This study was carried out to investigate the possibility of improving the texture and flavor of Dasik by adding various types of sugar (syrup, honey) and flavor ingredients (omija, chija, coffee, green tea extract) to rice powder. Dasik samples were prepared, and the sensory quality and physical characteristics of those were compared. The moisture content of Dasik added with syrup was higher than that of honey. Coffee Dasik with syrup was the highest (23.6) in moisture content. In sensory quality, the omija and coffee Dasik showed the highest score in flavor quality (p<.001). Omija Dasik with honey and coffee Dasik with syrup showed the highest scores in overall acceptability (6.4, 6.2). Green tea Dasik with syrup showed the highest value in the lightness (L) of color. Omija Dasik with syrup showed the highest value in the redness (a) of color Chija Dasik was the highest in the yellowness(b) of color. In physical characteristics, the hardness was negatively correlated with the moistness, tenderness, and texture acceptability in sensory quality(p〈0.001). The cohesiveness was positively correlated with the overall acceptability in sensory quality (p〈0.01). In the relation of texture characteristics and sensory quality, the higher the moisture content, the lower the hardness and springiness were, but the higher the brittleness and the cohesiveness were(p〈.001). Overall, omija and coffee Dasik appeared to have desirable flavor, taste and overall acceptability.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.1
• /
• pp.77-84
• /
• 2020

This study is apply 3D spatial information per traditional landscape space by comparing spatial information data created using a small drone and 3D scanner used for 3D spatial information construction for efficient preservation and management of traditional landscaping space composed of areas such as scenic sites and traditional landscape architectures. The analysis results are as follows. First, aerial photogrammetry data is less accurate than 3D scanners, but it was confirmed to be more suitable for monitoring landscape changes by reading RGB images than 3D scanners by texture mapping using digital data in constructing orthographic image data. Second, the orthographic image data constructed by aerial photogrammetry in a traditional landscaping space consisting of a fixed area, such as Gwanghalluwon Garden, produced visually accurate and precise results. However, as a result of the data extraction, data for trees, which is one of the elements that make up the traditional landscaping, was not extracted, so it was determined that 3D scanning and aerial surveying had to be performed in parallel, especially in areas where trees were densely populated. Third, The surrounding trees in Soswaewon Garden caused many errors in 3D spatial information data including topographic data. It was analyzed that it is preferable to use 3D scanning technology for precise measurement rather than aerial photogrammetry because buildings, landscaping facilities and trees are dense in a relatively small space. When 3D spatial information construction data for a traditional landscaping space composed of area using a small drone and a 3D scanner free from temporal and spatial constraints and compared the data was compared, the aerial photogrammetry is effective for large site such as Hahoe Village, Gyeongju and construction of a 3D space using a 3D scanner is effective for traditional garden such as Soswaewon Garden.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.4
• /
• pp.131-144
• /
• 2015

This research proposes a prototype for visualizing radar rainfall data using the unity 3D engine. The mashup of radar data with topographic information is necessary for the 3D visualization of the radar data with high quality. However, the mashup of a huge amount of radar data and topographic data causes the overload of data processing and low quality of the visualization results. This research utilized the Unitiy 3D engine, a widely used engine in the game industry, for visualizing the 3D topographic data such as the satellite imagery/the DEM(Digital Elevation Model) and radar rainfall data. The satellite image segmentation technique and the image texture layer mashup technique are employed to construct the 3D visualization system prototype based on the topographic information. The developed protype will be applied to the disaster-prevention works by providing the radar rainfall data with the 3D visualization based on the topographic information.

• Journal of radiological science and technology
• /
• v.26 no.1
• /
• pp.71-82
• /
• 2003

In this paper, I proposed a classifier of liver cirrhotic step using T1-weighted MRI(magnetic resonance imaging) and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were obtained in Pusan National University Hospital from June 2001 to december 2001. And the number of data was 46. We extracted liver region and nodule region from T1-weighted MR liver image. Then objective interpretation classifier of liver cirrhotic steps in T1-weighted MR liver images. Liver cirrhosis classifier implemented using hierarchical neural network which gray-level analysis and texture feature descriptors to distinguish normal liver and 3 types of liver cirrhosis. Then proposed Neural network classifier teamed through error back-propagation algorithm. A classifying result shows that recognition rate of normal is 100%, 1type is 82.3%, 2type is 86.7%, 3type is 83.7%. The recognition ratio very high, when compared between the result of obtained quantified data to that of doctors decision data and neural network classifier value. If enough data is offered and other parameter is considered, this paper according to we expected that neural network as well as human experts and could be useful as clinical decision support tool for liver cirrhosis patients.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.4 no.1
• /
• pp.35-59
• /
• 2002

The purpose of the study is to clarify the relationship between hair style and personal character. This is elucidated by using the standard model of their preferred hair style to their individual to their personality. The study is primarily centered around college woman, who reside in Young dong area. The research suggested that In the age group 19-25 subjects preferred their hair to be shoulder length or longer. This is in contrast to the older age group preferring a shorter hair style. Certainly most subjects under the age of 25 preferred their natural hair texture as opposed to permed hair fashioned by older subject. Difference is personality traits was not a factor here. There is a relationship between personality traits, personal background and whether or not subjects dyed or decolored their hair. Subjects responded "yes" which means that they are easily affected by the two factors. The response to the other question of which color they chose, if they dyed and decolored, was that the most of the cases preferred brown color because brown is a natural looking hair color. Their responses from the question "what kind of style they want, if they can change their style differently", they preferred a fashionable hair style. In most cases, individual responded that they change their hair style once in every two or three months. Of all the personality traits, 48.1% were adventurous, changingtheir hair style more than once in every 6 months. The main reason they change their hair style is that they are bored with their old style. In the under 25 age group, the cost of changing their hair style is usually paid for by the subjects parents, however a few responded that they paid for themselves. Over the age of 25 years 80% usually paid for themselves. Additionally students who supported themselves financially paid for hair restyling themselves. When changing a hair style most subjects consider that new hair style should go with their existing image. "What kind of image they want to show others？" almost all of them responded that they want to look sophisticated and fashionable, In the age group 25 and over who belong to the upper class want their hair to look healthy and a full of body. They also responded about their changing their hair style to show a different appearance positively,fferent appearance positively.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.1
• /
• pp.213-223
• /
• 2017

Recently, the air quality of South Korea has deteriorated and public interest has been increasing. Various observation means are used for the monitoring of the atmospheric environment, but it relies on the experience and judgment of the observer in the absence of spatial information on the emission facilities. The purpose of this study was to determine the availability of using drones for monitoring air pollutant emission facilities. A texture transformation method was applied to the drone ortho image to detect the small gas emission facility and the slope data calculated by the digital surface model (DSM) was used to reduce the false alarm ratio. As a result, it shows the possibility of using drones in the detection of small gas emission facilities by showing about 80% of positive detection ratio and 40% of false alarm ratio. In the future, various researches are required to the improve positive detection ratio and the reduction of the false alarm ratio. Based on these results, it is necessary to construct a database including 3D spatial information of air pollutant emission facilities.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.396-404
• /
• 2014

The field of searching clothing, which is very difficult due to the nature of the informal sector, has been in an effort to reduce the recognition error and computational complexity. However, there is no concrete examples of the whole progress of learning and recognizing for cloth, and the related technologies are still showing many limitations. In this paper, the whole process including identifying both the person and cloth in an image and analyzing both its color and texture pattern is specifically shown for classification. Especially, deformable search descriptor, LBPROT_35 is proposed for identifying the pattern of clothing. The proposed method is scale and rotation invariant, so we can obtain even higher detection rate even though the scale and angle of the image changes. In addition, the color classifier with the color space quantization is proposed not to loose color similarity. In simulation, we build database by training a total of 810 images from the clothing images on the internet, and test some of them. As a result, the proposed method shows a good performance as it has 94.4% matching rate while the former Dense-SIFT method has 63.9%.

• Korean Journal of Remote Sensing
• /
• v.27 no.4
• /
• pp.435-444
• /
• 2011

The land cover map derived from spectral features of high resolution optical images has low spectral resolution and heterogeneity in the same land cover class. For this reason, despite the same land cover class, the land cover can be classified into various land cover classes especially in vegetation area. In order to overcome these problems, detailed vegetation classification is applied to optical satellite image and SAR(Synthetic Aperture Radar) integrated data in vegetation area which is the result of pre-classification from optical image. The pre-classification and vegetation classification were performed with MLC(Maximum Likelihood Classification) method. The hierarchical land cover classification was proposed from fusion of detailed vegetation classes and non-vegetation classes of pre-classification. We can verify the facts that the proposed method has higher accuracy than not only general SAR data and GLCM(Gray Level Co-occurrence Matrix) texture integrated methods but also hierarchical GLCM integrated method. Especially the proposed method has high accuracy with respect to both vegetation and non-vegetation classification.