• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.207-209
• /
• 2021

In recent years, with the development of artificial intelligence and IoT technology, automation and unmanned technology are in progress in various fields, and the importance of image processing such as object tracking, medical images and object recognition, which are the basis of this, is increasing. In particular, in systems requiring detailed data processing, noise reduction is used as a pre-processing step, but the existing algorithm has a disadvantage that blurring occurs in the filtering process. Therefore, in this paper, we propose a filter algorithm using modified spatial weights to minimize information loss in the filtering process. The proposed algorithm uses mask matching to remove AWGN, and obtains the output of the filter by adding or subtracting the output of the modified spatial weight. The proposed algorithm has superior noise reduction characteristics compared to the existing method and reconstructs the image while minimizing the blurring phenomenon.

• Journal of Biomedical Engineering Research
• /
• v.31 no.2
• /
• pp.114-122
• /
• 2010

This paper presents a method that registers a lymphoscintigraphy to the real image captured by a CMOS camera, which helps surgeons to easily and precisely detect sentinel lymph nodes for sentinel lymph node biopsy in breast cancer patients. The proposed method consists of two steps: pre-matching and image registration. In the first step, we localize fiducial markers in a lymphoscintigraphy and a real image of a four quadrant bar phantom by using image processing techniques, and then determines perspective transformation parameters by matching with the corresponding marker points. In the second step, we register a lymphoscintigraphy to a real images of patients by using the perspective transformation of pre-matching. To examine the accuracy of the proposed method, we conducted an experiment with a chest mock-up with radioactive markers. As a result, the euclidean distance between corresponding markers was less than 3mm. In conclusion, the present method can be used to accurately align lymphoscintigraphy and real images of patients without attached markers to patients, and then provide useful anatomical information on sentinel lymph node biopsy.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.10
• /
• pp.452-457
• /
• 2006

In this paper, an algorithm to detect steps in hemiplegic patients using a 3-axis accelerometer a紅ached on the trunk was proposed. The proposed algorithm consisted of the signal pre-processing, the step detector, the classification of steps and the calculation of stride time. Two FIR band-pass filters were designed and steps were measured by the combination of filtered signals in the vertical and the anteroposterior directions. In addition, the classification of steps and the calculation of stride time were computed by using the detected steps and lateral signals. For the experiment, fourteen hemiplegic patients were participated and the linear accelerations of the trunk and foot switch signals were measured synchronously. To evaluate the system performance, the detected steps and initial contacts by the foot switch were compared. The average error between the steps and initial contacts was 0.024ms and the difference of the average stride time was 0.01s. Finally, all gait events were detected exactly. Results showed that the accelerometry could use for the gait evaluation in clinical rehabilitation therapies.

• Journal of Information Science Theory and Practice
• /
• v.2 no.2
• /
• pp.6-15
• /
• 2014

Initial based disambiguation of author names is a common data pre-processing step in bibliometrics. It is widely accepted that this procedure can introduce errors into network data and any subsequent analytical results. What is not sufficiently understood is the precise impact of this step on the data and findings. We present an empirical answer to this question by comparing the impact of two commonly used initial based disambiguation methods against a reasonable proxy for ground truth data. We use DBLP, a database covering major journals and conferences in computer science and information science, as a source. We find that initial based disambiguation induces strong distortions in network metrics on the graph and node level: Authors become embedded in ties for which there is no empirical support, thus increasing their sphere of influence and diversity of involvement. Consequently, networks generated with initial-based disambiguation are more coherent and interconnected than the actual underlying networks, and individual authors appear to be more productive and more strongly embedded than they actually are.

• Journal of Practical Engineering Education
• /
• v.13 no.3
• /
• pp.435-442
• /
• 2021

In this study, a program was developed to educate the students and athletes of the school sports team on the overall knowledge of using sports data. Accordingly, existing research and requirements for using sports data were analyzed, a learning plan was designed, and an education program was developed in a step-by-step manner according to the educational requirements. In addition, as there is no research yet on data science education for school athletics and adult sports officials in existing studies, this study includes the problem definition, data collection, data pre-processing, and data analysis, as well as the additional stages of data visualization and simulation analysis. It is expected that the sports industry's interest in sports data will increase through this study.

• Transactions of Materials Processing
• /
• v.9 no.3
• /
• pp.233-241
• /
• 2000

It is well known that the quality and efficiency of the design of metal forming processes can be significantly improved with the aid of effective numerical simulations. In the present study, a two-and three-dimensional finite element simulation system, CAMP form, was developed for the analysis of metal forming processes in the PC environment. It is composed of a solver based on the thermo-rigid-viscoplastic approach and graphic user interface (GUI) based pre-and post-processors to be used for the effective description of forming conditions and graphic display of simulation results, respectively. In particular, in the case of CAMPform 2D (two-dimensional), as the solver contains an automatic remeshing module which determines the deformation step when remeshing is required and reconstructs the new mesh system, it is possible to carry out simulations automatically without any user intervention. Also, the forming analysis considers ductile fracture of the workpiece and wear of dies for better usage of the system. In the case of CAMPform 3D, general three-dimensional problems that involve complex die geometries and require remeshing can be analyzed, but full automation of simulations has yet to be achieved. In this paper, the overall structure and computational background of CAMPform will be briefly explained and analysis results of several forming processes will be shown. From the current results, it is construed that CAMPform can be used in providing useful information to assist the design of forming processes.

• Journal of Convergence for Information Technology
• /
• v.7 no.2
• /
• pp.77-82
• /
• 2017

In this paper, a new security algorithm to recognize the type of the vehicle with the vehicle image as a input image is suggested. The vehicle recognition security algorithm is composed of five core parts, such as the input image, background removal, edge areas extraction, pre-processing(binarization), and the vehicle recognition. Therefore, the final recognition rate of the security algorithm for vehicle type recognition can be affected by the function and efficiency of each step. After inputting image into a gray scale image and removing backgrounds, the binarization is performed by extracting only the edge region. After the pre-treatment process for making outlines clear, the type of vehicles is categorized into large vehicles, passenger cars and motorcycles through the ratio of height and width of the vehicle.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.372-380
• /
• 2022

This study proposes a distributed parallel processing system, called the Fast Analysis System for remote sensing daTa(FAST), for large-scale satellite image processing and analysis. FAST is a system that designs jobs in vertices and sequences, and distributes and processes them simultaneously. FAST manages data based on the Hadoop Distributed File System, controls entire jobs based on Apache Spark, and performs tasks in parallel in multiple slave nodes based on a docker container design. FAST enables the high-performance processing of progressively accumulated large-volume satellite images. Because the unit task is performed based on Docker, it is possible to reuse existing source codes for designing and implementing unit tasks. Additionally, the system is robust against software/hardware faults. To prove the capability of the proposed system, we performed an experiment to generate the original satellite images as ortho-images, which is a pre-processing step for all image analyses. In the experiment, when FAST was configured with eight slave nodes, it was found that the processing of a satellite image took less than 30 sec. Through these results, we proved the suitability and practical applicability of the FAST design.

• Korean Journal of Computational Design and Engineering
• /
• v.15 no.2
• /
• pp.115-123
• /
• 2010

We present an efficient algorithm for computing the Hausdorff distance between two planar curves. The algorithm is based on an efficient trimming technique that eliminates the curve domains that make no contribution to the final Hausdorff distance. The input curves are first approximated with biarcs within a given error bound in a pre-processing step. Using the biarc approximation, the distance map of an input curve is then approximated and stored into the graphics hardware depth-buffer by rendering the distance maps (represented as circular cones) of the biarcs. We repeat the same procedure for the other input curve. By sampling points on each input curve and reading the distance from the other curve (stored in the hardware depth-buffer), we can easily estimate a lower bound of the Hausdorff distance. Based on the lower bound, the algorithm eliminates redundant curve segments where the exact Hausdorff distance can never be obtained. Finally, we employ a multivariate equation solver to compute the Hausdorff distance efficiently using the remaining curve segments only.