• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.83-84
• /
• 2022

본 논문에서는 의약품의 효율적인 구매와 안전한 복용, 또 의약품 성분에 대한 정보 전달을 위한 시스템을 제안한다. 이 시스템에서는 약품 후면을 촬영한 영상으로부터 이미지 프로세싱을 통해 이미지에서 관심영역을 설정한 뒤, OCR 엔진인 Tesseract-OCR을 사용하여 인식한 텍스트 데이터를 통해 약품 성분을 추출하며, 식품의약품안전처에서 제공하는 의약품 안전 사용 서비스(DUR) API와 네이버 의약품 사전 검색 결과를 이용해 관련 정보들을 읽어와 출력하도록 한다. 약품의 표준 서식을 따르는 이미지를 기준으로 백 개의 이미지를 이용해 테스트하여 65%의 검출 정확도를 보였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.9
• /
• pp.1175-1182
• /
• 2013

The lock-in mode infrared thermography (IRT) technique has been developed to improve the detection capability of defects in materials with high thermal conductivity, and it has been shown to provide better detection capability than conventional active IRT. Therefore, to investigate the application of this technique to nuclear piping components, lock-in mode IRT tests were conducted on pipe specimens containing simulated wall-thinning defects. Phase images of the wall-thinning defects were obtained from the tests, and they were compared with thermal images obtained from conventional active IRT tests. It showed that the ability to size the detected wall-thinning defects in piping components was improved by using lock-in mode IRT. The improvement was especially apparent when detecting short and narrow defects and defects with slanted edges. However, the detection capability for shallow wall-thinning defects did not improve much when using lock-in mode IRT.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2000.11b
• /
• pp.81-86
• /
• 2000

본 논문에서는 순차주사 CCD 이미지 센서를 위한 개선된 경계적응적 칼라 보간 구조를 제안했다. 제안된 경계 표시자(edge indicator) 함수는 채널내 상관관계뿐만 아니라 채널간의 상관관계를 이용하며 국소적으로 나타난 왜곡된 칼라는 칼라 경계 검출법에 기반한 스위칭 알고리즘에 의해 제거됐다. 개선된 경계적응적 칼라 보간 구조는 기존의 접근 방법에 비해 주관적 화질과 객관적 화질 모두 우수한 결과를 실험적으로 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.51-57
• /
• 2021

In this paper, we propose a method to find the DoF(Depth of field) that is blurred in an image by focusing and out-focusing the camera through a efficient convolutional neural network. Our approach uses the RGB channel-based cross-correlation filter to efficiently classify the DoF region from the image and build data for learning in the convolutional neural network. A data pair of the training data is established between the image and the DoF weighted map. Data used for learning uses DoF weight maps extracted by cross-correlation filters, and uses the result of applying the smoothing process to increase the convergence rate in the network learning stage. The DoF weighted image obtained as the test result stably finds the DoF region in the input image. As a result, the proposed method can be used in various places such as NPR(Non-photorealistic rendering) rendering and object detection by using the DoF area as the user's ROI(Region of interest).

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.127-129
• /
• 2005

본 연구에서는 백라이트 유닛의 검사를 위한 머신비전 시스템을 구축한다. 시스템은 크게 하드웨어와 소프트웨어로 나눌 수 있고 하드웨어는 조명부, 영상획득부, 로봇 암 제어부로 분류된다. 조명부는 36W FPL램프로 구성되었고 조명부의 상판에 아크릴판을 거치대로 이용하여 백라이트 유닛을 거치한다. 로봇 암 제어부는 2축 로봇 암을 제어하여 로봇 암의 센서부착 지지대에 부착된 CCD 센서를 이동시킨다. 이와 동시에 영상획득부에서는 이미지를 획득하여 PC로 전송한다. 소프트웨어의 화상처리 검사 알고리즘은 일정 패턴이 있는 도광판에 대한 검사 알고리즘과 일정패턴이 없근 백라이트 유닛에 대한 검사 알고리즘으로 분리된다. 일정 패턴이 인쇄되어 있는 패널에 대한 검사 알고리즘은 모폴로지 연산을 이용하는 템플릿 체크방법과 블록 매칭 방법이 사용되었고 일정패턴이 없는 유닛에 대한 검사는 개선된 Otsu 방법을 이용하여 얼룩이나 흐릿한 결함에 대한 결함을 검출하였다. 실험결과 불균일한 결함과 밝기가 일정하지 않은 결함일지라고 90% 이상의 검출율로 뛰어난 성능을 입증하였다.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.263-271
• /
• 2016

Localizing an object in image is a common task in the field of computer vision. As the existing methods provide a detection for the single object in an image, they have an utilization limit for the use of the application, due to similar objects are in the actual picture. This paper proposes an efficient method of object localization for image recognition. The new proposed method uses color correlation back-projection in the YCbCr chromaticity color space to deal with the object localization problem. Using the proposed algorithm enables users to detect and locate primary location of object within the image, as well as candidate regions can be detected accurately without any information about object counts. To evaluate performance of the proposed algorithm, we estimate success rate of locating object with common used image database. Experimental results reveal that improvement of 21% success ratio was observed. This study builds on spatially localized color features and correlation-based localization, and the main contribution of this paper is that a different way of using correlogram is applied in object localization.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.197-207
• /
• 2023

Concrete is a widely used material due to its excellent compressive strength and durability. However, depending on the surrounding environment and the characteristics of the materials used in the construction, various defects may occur, such as cracks on the surface and subsidence of the structure. The detects on the surface of the concrete structure occur after completion or over time. Neglecting these cracks may lead to severe structural damage, necessitating regular safety inspections. Traditional visual inspections of concrete walls are labor-intensive and expensive. This research presents a deep learning-based semantic segmentation model designed to detect cracks in concrete walls. The model addresses surface defects that arise from aging, and an image augmentation technique is employed to enhance feature extraction and generalization performance. A dataset for semantic segmentation was created by combining publicly available and self-generated datasets, and notable semantic segmentation models were evaluated and tested. The model, specifically trained for concrete wall fracture detection, achieved an extraction performance of 81.4%. Moreover, a 3% performance improvement was observed when applying the developed augmentation technique.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.429-432
• /
• 2020

본 논문에서는 카메라의 포커싱과 아웃포커싱에 의해 이미지에서 뿌옇게 표현되는 DoF(Depth of field, 피사계 심도) 영역을 합성곱 신경망을 통해 찾는 방법을 제안한다. 우리의 접근 방식은 RGB채널기반의 상호-상관 필터를 이용하여 DoF영역을 이미지로부터 효율적으로 분류하고, 합성곱 신경망 네트워크에 학습하기 위한 데이터를 구축하며, 이렇게 얻어진 데이터를 이용하여 이미지-DoF가중치 맵 데이터 쌍을 설정한다. 학습할 때 사용되는 데이터는 이미지와 상호-상관 필터 기반으로 추출된 DoF 가중치 맵을 이용하며, 네트워크 학습 단계에서 수렴률을 높이기 위해 스무딩을 과정을 한번 더 적용한 결과를 사용한다. 본 논문에서 제안하는 합성곱 신경망은 이미지로부터 포커싱과 아웃포커싱된 DoF영역을 자동으로 추출하는 과정을 학습시키기 위해 사용된다. 테스트 결과로 얻은 DoF 가중치 이미지는 입력 이미지에서 DoF영역을 빠른 시간 내에 찾아내며, 제안하는 방법은 DoF영역을 사용자의 ROI(Region of interest)로 활용하여 NPR렌더링, 객체 검출 등 다양한 곳에 활용이 가능하다.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.11
• /
• pp.1133-1144
• /
• 2019

Recently, the amount of image on the Internet has rapidly increased, due to the advancement of smart devices and various approaches to effective image retrieval have been researched under these situation. Existing image retrieval methods simply detect the objects in a image and carry out image retrieval based on the label of each object. Therefore, the semantic gap occurs between the image desired by a user and the image obtained from the retrieval result. To reduce the semantic gap in image retrievals, we connect the module for multiple objects classification based on deep learning with the module for human behavior classification. And we combine the connected modules with a behavior ontology. That is to say, we propose an image retrieval system considering the relationship between objects by using the combination of deep learning and behavior ontology. We analyzed the experiment results using walking and running data to take into account dynamic behaviors in images. The proposed method can be extended to the study of automatic annotation generation of images that can improve the accuracy of image retrieval results.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.107-116
• /
• 2024

Copper Filter Dryer (CFD) are responsible for removing impurities from the circulation of refrigerant in refrigeration and cooling systems to maintain clean refrigerant, and defects in CFD can lead to product defects such as leakage and reduced lifespan in refrigeration and cooling systems, making quality assurance essential. In the quality inspection stage, human inspection and defect judgment methods are traditionally used, but these methods are subjective and inaccurate. In this paper, YOLOv7 object detection algorithm was used to detect defects occurring during the CFD Shaft pipe and welding process to replace the existing quality inspection, and the detection performance of F1-Score 0.954 and 0.895 was confirmed. In addition, the cause of defects occurring during the welding process was analyzed by analyzing the sensor data corresponding to the Timestamp of the defect image. This paper proposes a method for manufacturing quality assurance and improvement by detecting defects that occur during CFD process and analyzing their causes.