• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.501-503
• /
• 2022

초해상이란 해상도가 낮은 영상을 해상도가 높은 영상으로 합성하는 기술이다. 딥러닝은 영상의 해상도를 높이는 초해상 기술에도 응용되며 실현은 2아4년에 발표된 SRCNN(Super Resolution Convolutional Neural Network) 모델로부터 시작됐다. 이후 오토인코더 (Autoencoders) 구조로는 SRCAE(Super Resolution Convolutional Autoencoders), 합성된 영상을 실제 영상과 통계적으로 구분되지 않도록 강제하는 GAN (Generative Adversarial Networks) 구조로는 SRGAN(Super Resolution Generative Adversarial Networks) 모델이 발표됐다. 모두 SRCNN의 성능을 웃도는 모델들이나 그중 가장 높은 성능을 끌어내는 SRGAN 조차 아직 완벽한 성능을 내진 못한다. 본 논문에서는 SRGAN의 성능을 개선하기 위해 사전 훈련된 특징 추출기(Pre-trained Feature Extractor) VGG(Visual Geometry Group)-19 모델을 변경하고, 기존 모델과 성능을 비교한다. 실험 결과, VGG-19 모델보다 윤곽이 뚜렷하고, 실제 영상과 더 가까운 영상을 합성할 수 있는 모델을 발견할 수 있을 것으로 기대된다.

• Journal of Soil and Groundwater Environment
• /
• v.7 no.2
• /
• pp.3-11
• /
• 2002

The objective of this study was to survey the oil contamination around the Mountain Baegun at Uiwang city to obtain the preliminary data for bioremediation. For measuring the oil concentrations and physical properties from soil, we analyzed BTEX. TPH and pH, organic content, water content, pormeability coefficient, gravity, porosity and used the purge & trap method for analyzing BTEX. Using the Accelerated Solvent Extractor, we pretreated the samples and then analyzed TPH using GC-FID as soon as possible. From the analysis results, maximum concentration of TPH was 24.773mg/kg and BTEX was 101.7mg/kg. The results of TPH at the Mountain Baegun were higher than the enforcement standard of soil contamination(Korea) and the BTEX concentrations were also higher than the advisory standard of soil contamination(Korea). From these results, the Mountain Baegun may requires to remedy the oil-contaminated soil. In addition, we performed the field bioremediation test for five weeks at the Mountain Baegun using the microbial additives that were developed by our laboratory. From the results of the field test, we could find the about 95% of the oil was removed from the contaminated soil in five weeks. So we consider that it is the one of the useful solutions to remedy the oil-polluted site.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.12 no.4
• /
• pp.18-25
• /
• 1993

This paper is to aim the microdefect evaluation of If package into a quantitative from NDI's image processing of ultrasonic wave. (1) Automatically repeated discrimination analysis method can be devided in the category of all kind of defects on IC package, and also can be possible to have a sampling of partial delamination. (2) It is possible that the information of edge section in silicon chip surrounding can be extractor by the partial image processing of IC package. Also, the crack detection is possible between the resin part and lead frame.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.64-68
• /
• 2007

본 논문은 영상의 메타데이터를 RDF를 이용하여 표현, 저장하고, SPARQL을 이용하여 검색하는 솔루션을 구현하여, RDF와 SPARQL을 통한 멀티미디어 파일의 메타데이터 관리 방안을 제시한다. 솔루션은 Jena2 프레임워크 기반으로 구현하였으며, Controller, EXIF Extractor, Metadata Schema, RDF Generator, Repository Manager, SPARQL Executor의 모듈로 구성된다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.8
• /
• pp.998-1009
• /
• 1988

A Hierarchical Circuit Extract Algotithm, which efficiently extract circuits from VLSI mask pattern information, is programmed. Quad-tree is used as a data structure which includes various CIF circuit elements and instances. This system is composed of CIF input routine, Quad-tree making routine, Transistor finding routine and Connection list making routine. This circuit extractor can extract circuit with hierarchical structure of circuit. This system is designed using YACC and LEX. By programming this algorithm with C language and adopting to various circuits, the effectiveness of this algorithm is showed.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.769-772
• /
• 1998

This paper present an efficient techniques for visual inspection of taped electronic parts, suitable for real time implementation. The main environments of developed system are IBM-compatible personal computer, frame grabber, digital input-output board. It is connected to the programmable logic controller unit of the taping machine in real time. Using a queuing structure, operator or extractor machine can remove easily the defect one from production line. Also, we design a new illumination system for sacquring shape and subface features of object. Therefore, it redue pre-processing step and processing time.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.29A no.1
• /
• pp.48-59
• /
• 1992

This paper presents the design of a layout processing system that performs circuit and symbolic extraction from hierarchical designs containing arbitrarily shaped layout. The system is flexible enough to deal with various technologies, MOS or bipolar, by providing extraction rules in the form of technology files. In this paper, new efficient algorithms for trapezoidal decomposition of polygon and symbolic path extraction using trapezoidal template are proposed for symbolic extraction. Circuit and symbolic extractor is developed as an integrated design environment of SOLID system.

• Journal of Pharmaceutical Investigation
• /
• v.6 no.2
• /
• pp.83-87
• /
• 1976

Microanalysis of rodenticide by visible absorption method was attempted. The following procedure was found to be very simple and to give accurate results. RH-28787 was added to dimethylformamide (DMF), and extracted after stirring for about 20 minutes in extractor $(30^{\circ}C)$. After extraction, the absorbance of DMF solution, was measured at 346 nm by using spectrophotometer. The result agrees closely with the experimentally determined value by means of the gas chromatograph.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.11
• /
• pp.37-44
• /
• 2008