• Database Research
• /
• 제34권3호
• /
• pp.148-158
• /
• 2018

The optical character recognition (OCR) is a technique to extract and recognize texts from images. It is an important preprocessing step in data analysis since most actual text information is embedded in images. Many OCR engines have high recognition accuracy for images where texts are clearly separable from background, such as white background and black lettering. However, they have low recognition accuracy for images where texts are not easily separable from complex background. To improve this low accuracy problem with complex images, it is necessary to transform the input image to make texts more noticeable. In this paper, we propose a method to segment an input image into text lines to enable OCR engines to recognize each line more efficiently, and to determine the final output by comparing the recognition rates of CLAHE module and Two-step module which distinguish texts from background regions based on image processing techniques. Through thorough experiments comparing with well-known OCR engines, Tesseract and Abbyy, we show that our proposed method have the best recognition accuracy with complex background images.

• Journal of the Korean Geotechnical Society
• /
• 제26권3호
• /
• pp.59-68
• /
• 2010

Systematic risk management is necessary in grand scaled urban construction because of the existence of complicated and various risk factors. Problems of obstructions, adjacent structures, safety, environment, traffic and geotechnical properties need to be solved because urban construction is progressed in limited space not as general earthwork. Therefore the establishment of special risk management system is necessary to manage not only geotechnical properties but also social and cultural uncertainties. This research presents the technique analysis by the current state of risk management technique. Risk factors were noticed and the importance of each factor was estimated through survey. The systemically categorized database was established. Risk extraction module, matrix and score module were developed based on the database. Expected construction budget and time distribution can be computed by Monte Carlo analysis of probabilities and influences. Construction budgets and time distributions of before and after response can be compared and analyzed 80 the risks are manageable for entire whole construction time. This system will be the foundation of standardization and integration. Procurement, efficiency improvement, effective time and resource management are available through integrated management technique development and application. Conclusively decrease in cost and time is expected by systemization of project management.

• Journal of the Korea Institute of Building Construction
• /
• 제17권6호
• /
• pp.545-557
• /
• 2017

The study is about the efficient alternative to concrete surface in the field of visual inspection technology for deteriorated infrastructure. By combining industrial drones and deep learning based image analysis techniques with traditional visual inspection and research, we tried to reduce manpowers, time requirements and costs, and to overcome the height and dome structures. On board device mounted on drones is consisting of a high resolution camera for detecting cracks of more than 0.3 mm, a lidar sensor and a embeded image processor module. It was mounted on an industrial drones, took sample images of damage from the site specimen through automatic flight navigation. In addition, the damege parts of the site specimen was used to measure not only the width and length of cracks but white rust also, and tried up compare them with the final image analysis detected results. Using the image analysis techniques, the damages of 54ea sample images were analyzed by the segmentation - feature extraction - decision making process, and extracted the analysis parameters using supervised mode of the deep learning platform. The image analysis of newly added non-supervised 60ea image samples was performed based on the extracted parameters. The result presented in 90.5 % of the damage detection rate.

• Analytical Science and Technology
• /
• 제24권5호
• /
• pp.352-359
• /
• 2011

An analytical method for solvent-free determination of benzene, toluene, ethylbenzene, and xylenes (BTEX) in water using repetitive membrane extractions coupled to cryofocusing and GC-MS was derived. BTEX compounds that permeated through a nonporous silicone membrane from the aqueous phase and evaporated into the acceptor phase were purged into a cryofocusing trap ($-100^{\circ}C$) with helium gas. The BTEX compounds, thus enriched in the trap, were thermally desorbed into a capillary column GC and detected using an MS. The flow rate of the donor phase (30 mL water) was set at 10 mL/min, and membrane extractions, accomplished by returning the water drained from the extraction module to the sample container, were repeated three times at $20{\pm}2^{\circ}C$. Although recoveries (%) were variable, from the highest for benzene (approximately 80%) to the lowest for ethylbenzene and xylenes (3.5-10%), the method showed satisfactory precision (RSD 2.2-10%) with good-linearity calibration curves ($r^2$ 0.9976-0.9997 in 1-100 ${\mu}g$/L range) for all of the compounds. The method detection limits (MDLs) ranged from 0.16 to 1.8 ${\mu}g$/L. The results showed the method's advantages such as short analysis time and overall simplicity without solvent compared to the conventional techniques.

• Journal of the Korea Society of Computer and Information
• /
• 제28권10호
• /
• pp.1-8
• /
• 2023

If there is a defect in the wheel bearing, which is a major part of the car, it can cause problems such as traffic accidents. In order to solve this problem, big data is collected and monitoring is conducted to provide early information on the presence or absence of wheel bearing failure and type of failure through predictive diagnosis and management technology. System development is needed. In this paper, to implement such an intelligent wheel hub bearing maintenance system, we develop an embedded system equipped with sensors for monitoring reliability and soundness and algorithms for predictive diagnosis. The algorithm used acquires vibration signals from acceleration sensors installed in wheel bearings and can predict and diagnose failures through big data technology through signal processing techniques, fault frequency analysis, and health characteristic parameter definition. The implemented algorithm applies a stable signal extraction algorithm that can minimize vibration frequency components and maximize vibration components occurring in wheel bearings. In noise removal using a filter, an artificial intelligence-based soundness extraction algorithm is applied, and FFT is applied. The fault frequency was analyzed and the fault was diagnosed by extracting fault characteristic factors. The performance target of this system was over 12,800 ODR, and the target was met through test results.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• 제42권4호
• /
• pp.45-52
• /
• 2005

This paper presents the characterization of through hole vias on printed circuit board (PCB) through the time domain and frequency domain measurements. The time domain measurement was performed on a single via using the TDR, and the model parameters were extracted by the fitting simulation using HSPICE. The frequency domain measurement was also performed by using 2 port VNA, and the model parameters were extracted by fitting simulation with ADS. Using the ABCD matrices, the do-embedding equations were derived probing in the same plane in the VNA measurement. Based on the single via characterization, the differential via characterization was also performed by using TDR measurements. The time domain measurements were performed by using the odd mode and even mode sources in TDR module, and the Parameter values were extracted by fitting with HSPICE. Comparing measurements with simulations, the maximum calculated differences were $14\%$ for single vias and $17\%$ for differential vias.

• Journal of Internet Computing and Services
• /
• 제13권1호
• /
• pp.65-74
• /
• 2012

Cloud services are used for improving business. Moreover, customer relationship management(CRM) approaches use social networking as tools to enhance services to customers. However, most cloud systems do not support the semantic structures, and because of this, vital information from social network sites is still hard to process and use for business strategy. This paper proposes a collaboration framework based on social semantic web for cloud system. The proposed framework consists of components to support social semantic web to provide an efficient collaboration system for cloud consumers and service providers. The knowledge acquisition module extracts rules from data gathered by social agents and these rules are used for collaboration and business strategy. This paper showed the implementations of processing of social network site data in the proposed semantic model and pattern extraction which was used for the virtual grouping of cloud service providers for efficient collaboration.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제11권12호
• /
• pp.5113-5119
• /
• 2010

Anthropometry has been broadly explored in various fields including automobile industry, home electronic appliances, medical appliances and sports goods with aiming at reaching satisfaction to consumer's need and efficiency. However, current technologies to measure a human body still have barriers in which the methods mostly seem to be contingent on expensive devices such as scanner and digital measuring instruments and to be directly touchable to the body when obtaining body size.. Therefore, in this paper, we present a general method to automatically extract size of body from a real body image acquired from a camera and to utilize it into recommend systems including clothing and bicycle fitting. At first, Haar-like features and AdaBoost algorithm are employed to detect body position. Then features of body can be recognized using AAM. Finally clothing and bicycle recommending modules have been implemented and experimented to validate the proposed method.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2008년도 학술대회 논문집 정보 및 제어부문
• /
• pp.155-156
• /
• 2008

This research measures EEG signals which are generating on head skin and extracts brain concentration level related with brain activity. We develop concentration wireless transmission system for controlling hardware by using this signal. Two channels are used for measuring EEG signal on front head and Biopac system with MP-100 and EEG100C was used for measuring EEG signal, amplifying and filtering the signal. LabView 8.5 was also used for FFT transformation, frequency and spectrum analysis of the measure EEG signal. As a result, ${\alpha}$ wave, ${\beta}$ wave, ${\theta}$ wave and ${\delta}$ wave were classified. we extracted the concentration index by adapting concentration extraction algorithm. This concentration index was transferred into lego automobile device by wireless module and applied for BCI application.

• Journal of Broadcast Engineering
• /
• 제23권5호
• /
• pp.656-668
• /
• 2018

VR (Virtual Reality) is one of the important research topics in the field of multimedia application system. The quality of the visual data composed from multiple pictures depends on the performance of stitching technique. The stitching module consists of feature extraction, mapping of those, warping, seam finding, and blending. In this paper, we proposed a preprocessing scheme to provide the efficient mask for seam finder. Incorporating of the proposed mask removes the distortion, such as ghost and blurring, in the stitched image. The simulation results show that the proposed algorithm outperforms other conventional techniques in the respect of the subjective quality and the computational complexity.