• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.7
• /
• pp.771-778
• /
• 2019

The traditional illuminance intensity detection method using a single sensor has a problem that uniformity of illuminance detection is deteriorated depending on the measurement position due to the narrow FOV characteristic. In order to overcome this problem, a method of detecting an average illuminance value through a plurality of illuminance sensors is used, but the complexity and detection error are increased. In this paper, we propose a illuminance intensity detection method based on a single image sensor with wide FOV. The proposed method can solve the problems such as system complexity and error increase of existing illuminance sensor. The test results show that the difference of average value is 12% using a illuminance sensor, 10.7% using five illuminance sensors, and 6.2% using an image sensor compared with the reference value using the color difference illuminometer. It is confirmed that the proposed method can easily and accurately detect the space illuminance with improved uniformity.

• Journal of KIISE:Databases
• /
• v.35 no.4
• /
• pp.345-355
• /
• 2008

SIFT is popularly used in computer vision application such as object recognition, motion tracking, and 3D reconstruction among various shape descriptors. However, it is not easy to apply SIFT into the image similarity search as it is since it uses many high dimensional keypoint vectors. In this paper, we present a SIFT based image similarity search method using an edge image pyramid and an interesting region detection. The proposed method extracts keypoints, which is invariant to contrast, scale, and rotation of image, by using the edge image pyramid and removes many unnecessary keypoints from the image by using the hough transform. The proposed hough transform can detect objects of ellipse type so that it can be used to find interesting regions. Experimental results demonstrate that the retrieval performance of the proposed method is about 20% better than that of traditional SIFT in average recall.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.109-114
• /
• 2021

GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.573-574
• /
• 2023

화염 영역 검출을 위해 이전 기법에서는 화재 이미지에서 연기제거 및 색상보정을 통해 이미지를 전처리하였다. 그러나 이 기법은 임계값에 영향을 많이 받고, 밝기채널을 이용하여 검출하기 때문에 밤에 일어난 화재 이미지에서는 평균이상의 퍼포먼스를 수행하지만, 주변이 밝은 대낮의 화재 이미지에서는 퍼포먼스가 줄어드는 문제가 있다. 이를 보완하고자 본 논문에서는 CycleGAN을 이용하여 낮 이미지를 밤 이미지로 바꾸어 이미지 전처리를 진행하는 기법을 제안함으로써 화염 감지의 정확도가 개선되었음을 실험을 통해 보여준다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.844-847
• /
• 2014

본 논문에서는 다양한 형태의 어플리케이션 중 스마트폰에 탑재된 카메라를 이용하여 명함을 인식할 때 발생하는 문제점을 해결하기 위한 기법을 제시하고자 한다. 스마트폰의 카메라를 이용하여 이미지를 얻을 경우 카메라의 각도에 따라 객체의 모양이 변형된다. 명함인식에서 이러한 이미지 왜곡문제는 인식률에 많은 영향을 미친다. 본 논문에서는 카메라의 각도에 따른 이미지의 왜곡 문제를 해결하기 위해 캐니 에지를 이용하여 객체를 검출하고, 검출된 객체의 간단한 정보를 이용하여 명함 영역을 검출하고, 영역 내에 명함을 검출하는 기법을 제안한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.2
• /
• pp.358-363
• /
• 2009

Text region detection from the natural scene images used in a variety of applications, many research are needed in this field. Recent research methods is to detect the text region using various algorithm which it is combination of edge based and connected component based. Therefore, this paper proposes an text region detection using edge and regional minima/maxima transformation algorithm from natural scene images, and then detect the connected components of edge and regional minima/maxima, labeling edge and regional minima/maxima connected components. Analysis the labeled regions and then detect a text candidate regions, each of detected text candidates combined and create a single text candidate image, Final text region validated by comparing the similarity and adjacency of individual characters, and then as the final text regions are detected. As the results of experiments, proposed algorithm improved the correctness of text regions detection using combined edge and regional minima/maxima connected components detection methods.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.43-50
• /
• 2017

In this paper, we are proposing improved vanishing points detection and segments labeling methods for inside wall frame detection from indoor image of a piece of having a colour RGB. A lot of research related to recognizing the frame of artificial structures from the image is being performed due to increase in demand for AR technology. But detect the inside wall frame in indoor images have many objects that caused the occlusion is still a difficult issue. Inner wall frame detection methods are usually segment labeling methods and detect vanishing point methods are used together. In order to improve the vanishing point detection method we proposed using inner wall orthogonality which forms the cube. Also we proposed labeling method using tree based learning and superpixel based segmentation method for labelingthe segments in indoor images. Finally, in experiments have shown improved results about inside wall frame detection according to our methods.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.457-466
• /
• 2010

In this paper, we propose a new method for detecting digital forgery that identify interpolated region between digital composited images. For detecting the interpolation factor and the tampered regions, we perform two algorithms: The first algorithm is to estimate the interpolation factors using the differential equation for forgery image along the horizontal, vertical, and diagonal directions, respectively; The second algorithm is to scan the interpolation factors along each direction for detection areas as the mask of the optical window size($64{\times}64$) in order to find out the forgery region. A detection map of the forgery is classified with the magnitude of estimated interpolation factors into colors. This detection map can be used to find out interpolated regions from the tampered image. Experimental results demonstrate the proposed algorithms are proven on several examples. We also show the proposed approach is to accurately detect interpolated regions from digital composite images.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.209-214
• /
• 2010

In this paper, We analyzes the image along the platform (Open Eye), through prevention of dementia or stroke patients and cognitive rehabilitation for the proposed system. This way through the camera image according to user's movement gained OpenCV image processing library, which is based on motion analysis, a part of this rehabilitation is to apply to cognitive rehabilitation. Therefore, this paper proposes a new image analysis system has been exposed to the elderly or stroke patients with dementia, their hand gestures through which patients can detect the image of the cognitive rehabilitation to help them in the analysis of the image analysis system is proposed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.411-412
• /
• 2024

본 논문에서는 인공위성 이미지 비교 알고리즘을 설계하여 국제원자력기구(IAEA)와의 안전조치협정 추가의정서에 따른 원자력 시설 부지 정보의 변동 사항을 검출하는 시험을 수행하였다. 구글 어스에서 특정 장소에 대해 촬영 시간이 다른 인공위성 이미지를 얻어 시험 데이터로 사용하고 본 논문에서 개발한 5단계 이미지 비교 알고리즘을 구동한 결과 추가되거나 사라진 건물을 추적할 수 있었다. 향후 알고리즘 성능에 중요한 역할을 하는 검출 조정값(역치) 자동 도출 기능 및 이미지 전처리 프로세스를 개선한다면 대량 이미지 분석이 필요한 업무에 활용할 수 있을 것이다.