• Journal of the Korea Computer Graphics Society
• /
• v.23 no.2
• /
• pp.1-10
• /
• 2017

A variety of filters are applied to improve the quality of noise and low resolution medical images. This is necessary to reduce the radiation dose of the patient and to improve the utilization of the conventional spherical imaging equipment. In the conventional method, it is common to perform filtering using the CPU of the PC. However, it is difficult to produce results in real time by applying various calculations and filters to high-resolution human images using only the CPU performance of a PC used in a hospital. In this paper, we analyze the structure and performance of Intel integrated GPU in CPU and propose a method to perform image filtering using OpenCL parallel processing function. By applying complex filters with high computational complexity to medical images, high quality images can be generated in real time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.597-602
• /
• 2014

We propose hybrid-sensing system for human tracking. This system uses laser scanners and image sensors and is applicable to wide and crowded area such as hallway of university. Concretely, human tracking using laser scanners is at base and image sensors are used for human identification when laser scanners lose persons by occlusion, entering room or going up stairs. We developed the method of human identification for this system. Our method is following: 1. Best-shot images (human images which show human feature clearly) are obtained by the help of human position and direction data obtained by laser scanners. 2. Human identification is conducted by calculating the correlation between the color histograms of best-shot images. It becomes possible to conduct human identification even in crowded scenes by estimating best-shot images. In the experiment in the station, some effectiveness of this method became clear.

• Journal of Biomedical Engineering Research
• /
• v.18 no.3
• /
• pp.223-231
• /
• 1997

In this paper, an interframe coding method for volumetric medical images is proposed. By treating interslice variations as the motion of bones or tissues, we use the motion compensation (MC) technique to predict the current frame from the previous frame. Instead of a block matching algorithm (BMA), which is the most common motion estimation (ME) algorithm in video coding, image warping with biolinear transformation has been suggested to predict complex interslice object variation in medical images. When an object disappears between slices, however, warping prediction has poor performance. In order to overcome this drawback, an overlapped block motion compensation (OBMC) technique is combined with carping prediction. Motion compensated residual images are then encoded by using an embedded zerotree wavelet (EZW) coder with small modification for consistent quality of reconstructed images. The experimental results show that the interframe coding suing warping prediction provides better performance compared with interframe coding, and the OBMC scheme gives some additional improvement over the warping-only MC method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.7
• /
• pp.1292-1302
• /
• 2009

In this paper, we proposed Single Tone Detection Algorithm for prevent decoloration and color distortion of single tone image in auto white balance of mobile phone camera. Conventional auto white balance which accomplish very well using complex color images, but there are some problems if input images are single tone image or included large part of single tone. If input images are singlet one, or included large part of single tone, which cause decoloration or distorted color in output images. In this paper, we proposed single tone detection algorithm using color histogram data for solve decoloration or distorted color problems. If this algorithm is applied to auto white balance, it will be improvement in auto white balance.

• The Journal of the Korea Contents Association
• /
• v.9 no.9
• /
• pp.68-79
• /
• 2009

A variance map can be used to detect and distinguish texts from background in images. However, previous variance maps work at one level and they suffer a limitation in dealing with varieties in text size, slant, orientation, translation, and color. We present a method for robustly segmenting text regions in complex color Web images using two-level variance maps. The two-level variance maps work hierarchically. The first level finds the approximate locations of text regions using global horizontal and vertical color variances with the specific mask sizes. The second level then segments each text region using intensity variance with a local mask size, which is determined adaptively. By the second process, backgrounds tend to disappear in each region and segmentation can be accurate. Highly promising experimental results have established the effectiveness of our approach.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.715-726
• /
• 2019

With the increasing prevalence of high-resolution satellite images, the need for technology to generate accurate 3D information from the satellite images is emphasized. In order to create a digital terrain model (DTM) that is widely used in applications such as change detection and object extraction, it is necessary to extract trees, buildings, etc. that exist in the digital surface model (DSM) and estimate the height of the ground. This paper presents a method for automatically generating DTM from DSM extracted from KOMPSAT-3A stereo images. The technique was developed to detect the non-ground area and estimate the height value of the ground by using the previously constructed low-resolution topographic data. The average vertical accuracy of DTMs generated in the four experimental sites with various topographical characteristics, such as mountainous terrain, densely built area, flat topography, and complex terrain was about 5.8 meters. The proposed technique would be useful to produce high-quality DTMs that represent precise features of the bare-earth's surface.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.737-746
• /
• 2022

Utilizing weather independent SAR images along with machine learning based object detector is effective in robust vessel monitoring. While conventional SAR images often applied amplitude data from Single Look Complex, exploitation of polarimetric parameters acquired from multiple polarimetric SAR images was yet to be implemented to vessel detection utilizing machine learning. Hence, this study used four polarimetric parameters (H, p₁, DoP, DPRVI) retrieved from eigen-decomposition and two backscattering coefficients (γ₀, _VV, γ₀, _VH) from radiometric calibration; six bands in total were respectively exploited from 52 Sentinel-1 SAR images, accompanied by vessel training data extracted from AIS information which corresponds to acquisition time span of the SAR image. Evaluating different cases of combination, the use of polarimetric indexes along with amplitude values derived enhanced vessel detection performances than that of utilizing amplitude values exclusively.

• The Journal of Information Systems
• /
• v.31 no.4
• /
• pp.145-160
• /
• 2022

Purpose The purpose of this study is to develop a virtual try-on deep learning model that can efficiently learn front and back clothes images. It is expected that the application of virtual try-on clothing service in the fashion and textile industry field will be vitalization. Design/methodology/approach The data used in this study used 232,355 clothes and product images. The image data input to the model is divided into 5 categories: original clothing image and wearer image, clothing segmentation, wearer's body Densepose heatmap, wearer's clothing-agnosting. We advanced the HR-VITON model in the way of Mixed-Precison, Gradient Accumulation, and sharing model weights. Findings As a result of this study, we demonstrated that the weight-shared MP-GA HR-VITON model can efficiently learn front and back fashion images. As a result, this proposed model quantitatively improves the quality of the generated image compared to the existing technique, and natural fitting is possible in both front and back images. SSIM was 0.8385 and 0.9204 in CP-VTON and the proposed model, LPIPS 0.2133 and 0.0642, FID 74.5421 and 11.8463, and KID 0.064 and 0.006. Using the deep learning model of this study, it is possible to naturally fit one color clothes, but when there are complex pictures and logos as shown in <Figure 6>, an unnatural pattern occurred in the generated image. If it is advanced based on the transformer, this problem may also be improved.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• Composites Research
• /
• v.36 no.6
• /
• pp.395-401
• /
• 2023

In this study, finite element modeling of unidirectional composite materials of the computed tomography (CT) was conducted using a supervised learning-based segmentation technique. Firstly, Micro-CT scan was performed to obtain the raw volume of unidirectional composite materials, providing microstructure information. From the CT volume images, actual microstructure of the cross-section of unidirectional composite materials was extracted by the labeling process. Then, a U-net deep learning model was trained with a small number of raw images as inputs and their labeled images as outputs to generate a segmentation model. Subsequently, most of remaining images were input to the trained U-net deep learning model to segment all raw volume for identifying complex microstructure, which was used for the generation of finite element model. Finally, the fiber volume fraction of the finite element model was compared with that of experimentally measured volume to validate the appropriateness of the proposed method.