• 전자공학회논문지CI
• /
• 제40권2호
• /
• pp.38-44
• /
• 2003

본 논문에서는 임베디드 리눅스를 이용한 Strong Arm CPU 기반의 독립형 영상처리모듈 개발에 대하여 기술한다. 독립형 영상처리모듈은 실시간으로 영상 데이터를 받아 thresholding, edge detection, image enhancement등의 영상처리 알고리듬을 수행하는 임베디드 장치이다. 개발된 독립형 영상처리모듈의 성능을 나타내기 위하여 비슷한 성능의 PC와 영상처리 알고리듬의 수행시간을 서로 비교한 결과 만족할 만한 결과를 얻었다. 본 논문은 임베디드 리눅스가 PDA들의 인터넷 장비에서뿐만 아니라, 산업용 장비에서도 응용될 수 있는 가능성을 제시하였다.

• 한국자동차공학회논문집
• /
• 제25권2호
• /
• pp.219-226
• /
• 2017

This paper addresses the effective and quantitative image DB construction for the development of front looking camera systems. The automotive industry has expanded the capability of front camera solutions that will help ADAS(Advanced Driver Assistance System) applications targeting Euro NCAP function requirements. These safety functions include AEB(Autonomous Emergency Braking), TSR(Traffic Signal Recognition), LDW(Lane Departure Warning) and FCW(Forward Collision Warning). In order to guarantee real road safety performance, the driving image DB logged under various real road conditions should be used to train core object classifiers and verify the function performance of the camera system. However, the driving image DB would entail an invalid and time consuming task without proper guidelines. The standard working procedures and design factors required for each step to build an effective image DB for reliable automotive front looking camera systems are proposed.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 추계학술대회논문집
• /
• pp.327-329
• /
• 2000

This paper is concerned with the development of vibration measurement using the image processing. With the advance of the personal computer and the image processing device, it becomes possible to measure vibrations by converting the image into motion data. The image stored in the computer is based on pixels. Hence, the efficient technique which can compute vibrational motions from pixel data should be developed. In this study, we will show the feasibility of the image processing technique for vibration measurement. The experimental results show that vibrations can be measured from image data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4255-4269
• /
• 2019

This paper proposes an image generation method using a Multi Discriminator Generative Adversarial Net (MDGAN) as a next generation 2D game sprite creation technique. The proposed GAN is an Autoencoder-based model that receives three areas of information-color, shape, and animation, and combines them into new images. This model consists of two encoders that extract color and shape from each image, and a decoder that takes all the values of each encoder and generates an animated image. We also suggest an image processing technique during the learning process to remove the noise of the generated images. The resulting images show that 2D sprites in games can be generated by independently learning the three image attributes of shape, color, and animation. The proposed system can increase the productivity of massive 2D image modification work during the game development process. The experimental results demonstrate that our MDGAN can be used for 2D image sprite generation and modification work with little manual cost.

• 한국군사과학기술학회지
• /
• 제19권1호
• /
• pp.66-75
• /
• 2016

Stereoscopic image generated by depth image-based rendering(DIBR) for surveillance robot and camera is appropriate in a low bandwidth network. The image is very important data for the decision-making of a commander and thus its integrity has to be guaranteed. One of the methods used to detect manipulation is to check if the stereoscopic image is taken from the original camera. Sensor pattern noise(SPN) used widely for camera identification cannot be directly applied to a stereoscopic image due to the stereo warping in DIBR. To solve this problem, we find out a shifted object in the stereoscopic image and relocate the object to its orignal location in the center image. Then the similarity between SPNs extracted from the stereoscopic image and the original camera is measured only for the object area. Thus we can determine the source of the camera that was used.

• 한국지구과학회지
• /
• 제23권8호
• /
• pp.707-721
• /
• 2002

사이드 스캔 소-나 시스템을 이용하여 태안반도 부근 신두리 해역에서 해저면 음향영상 자료를 획득하였다. 후방산란 음향강도와 해저퇴적물의 물성에 대한 상호관계를 연구하였다. 그리고 위의 두 자료 모두 해저수심과 각각 비교해석 하였다. 해저퇴적물의 물성 대부분은 음향강도와 좋은 상관관계를 보이고 있지만, 퇴적물의 분포양상은 암반노출지역을 제외하고는 해저면 음향영상과 정확하게 일치하지는 않았다. 해저수심은 해저면 음향영상의 분포형태에 영향을 미치고 있었을 뿐만 아니라, 해저퇴적물의 물성 분포에서도 선형적인 관계를 보이고 있었다.

• 한국콘텐츠학회논문지
• /
• 제11권8호
• /
• pp.68-76
• /
• 2011

최근 소비자의 화질에 대한 높은 관심으로 관련 시장 경쟁력이 가열되었으며, 이에 따라 제조사는 고객만족을 위한 제품을 개발하는 방향으로 진보하고 있다. 그러나 제품의 객관적 성능 향상이 실제 소비자가 인지하는 화질의 선호도에 항상 긍정적인 영향을 미친다고 단정하기 어렵다. 또한 선행연구를 통해 객관적 성능 평가 방법과 주관적 화질 평가 결과 간의 상관관계를 찾기 어려웠다. 그러므로 객관적 화질 재현 성능이 이미지 선호도에 미치는 영향을 파악하여 감상자가 선호하는 화질에 대해 분석할 필요가 있다. 따라서 본 논문에서는 객관적 화질 평가 요소들을 측정하고 이러한 수치들이 이미지 선호도와 어떠한 관계를 갖고 있는지 분석하고자 하였다. 이와 같은 연구를 위해 ISO에서 규정하고 있는 화질 평가 방법을 사용하여 이미지의 선호도를 측정하였으며 이러한 결과가 객관적 화질 평가 요소들과 어떠한 상관관계를 갖고 있는지 통계적으로 분석하였다. 이와 같은 결과는 화질을 향상시키는 요소를 분석할 수 있으며 단순한 고화질 추구를 위한 성능 개발뿐만 아니라 감상자가 선호하는 화질을 파악하여 개발에 도움이 될 수 있는 실질적인 연구로 기대된다.

• Journal of Information Processing Systems
• /
• 제19권3호
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• 한국군사과학기술학회지
• /
• 제17권5호
• /
• pp.703-710
• /
• 2014

An Image-Based Target Tracker maintains LOS(Line Of Sight) to a target by controlling azimuth and elevation gimbals of an ISS(Inertially Stabilized System). Its controller produces the gimbals commands of the ISS using tracking errors provided by an image tracker. The control performance of the target tracker with PI controller generally used for tracking controller is limited because of bandwidth limitation by time delay yielded by image capture and processing of the image tracker. In this paper, tracking controller using target states estimator is proposed which can enhance the tracking performance under the highly dynamic maneuvering conditions of the ISS and the target. Simulation results show that the proposed method can improve the tracking performance than that with only PI controller.

• 한국군사과학기술학회지
• /
• 제23권3호
• /
• pp.257-266
• /
• 2020

It is very important to share tactical information such as video, images, and text messages among soldiers for situational awareness. Under the wireless environment of the battlefield, the available bandwidth varies dynamically and is insufficient to transmit high quality images, so it is necessary to minimize the distortion of the area of interests such as targets. A natural operating method for soldiers is also required considering the difficulty in handling while moving. In this paper, we propose a natural ROI(region of interest) setting and image compression method for effective image sharing among soldiers. We verify the proposed method through prototype system design and implementation of eye gaze detection and ROI-based image compression.