• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1405-1419
• /
• 2018

An image fusion method is proposed on the basis of depth model segmentation to overcome the shortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deep Boltzmann machine is used to perform the priori learning of infrared and visible target and background contour, and the depth segmentation model of the contour is constructed. The Split Bregman iterative algorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then, the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and the corresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results of MATLAB indicates that the proposed algorithm can obtain the fusion result of both target and background contours effectively, with a high contrast and noise suppression in subjective evaluation as well as great merits in objective quantitative indicators.

• 대한기계학회논문집A
• /
• 제37권4호
• /
• pp.569-579
• /
• 2013

이 연구에서는 스마트폰과 Wi-Fi통신을 이용한 로봇의 조종과 장착된 카메라를 통한 영상처리 기술에 대하여 서술하였다. 제안된 로봇은 바퀴와 4족을 환경에 따라서 선택적으로 사용할 수 있도록 메커니즘을 구성하였다. 카메라의 스트림 데이터 중 이미지 데이터만을 이용하도록 네트워크를 형성하였으며 영상처리 기법을 응용하여 약병을 구분하고, 로봇 팔을 이용하여 약병을 사용자에게 전달해주는 로봇 메커니즘에 대해서도 서술한다. 본 논문에서 개발된 영상처리 알고리즘과 처리는 별도의 컴퓨터 없이 스마트폰만을 이용하여 구현이 가능하도록 설계하였으며 스마트폰의 강력한 기능과 연산능력을 최대로 활용하여 약병 로봇의 지능화 및 소형화 방안을 제시하였다.

• 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.

• 한국항행학회논문지
• /
• 제16권6호
• /
• pp.910-919
• /
• 2012

본 논문에서는 고정익 무인항공기의 온보드 영상처리 시스템 개발에 대하여 개발과정에 대해 기술하고, 비행실험을 통한 실험결과를 토대로 하여 성능을 검증하고자 하였다. 시스템 개발보드는 ARM 프로세서가 탑재된 영상처리용 보드에 임베디드 리눅스를 포팅하였다. 목표물 추적을 위한 영상처리 알고리즘으로는 비교적 간단한 알고리즘인 색상 기반 알고리즘을 적용하여, 지상에 있는 특정 색상의 물체를 추적하도록 하였다. 개발된 시스템의 성능검증을 위해 실험실에서 제작한 무인항공기에 탑재하여 비행실험을 수행하였으며, 실시간 성능 향상을 위해 영상처리 알고리즘 및 임베디드 리눅스의 커널에 대한 최적화 작업을 수행하였다. 비행실험 결과, 4픽셀 이내의 오차범위에서 지속적으로 목표물을 추적하는 것을 확인하였다.

• 한국컴퓨터정보학회논문지
• /
• 제28권8호
• /
• pp.31-38
• /
• 2023

딥러닝 기반 영상 처리 기술 중 최근 활발히 연구되어 많은 성능 향상을 이룬 기술 중 하나는 스타일 전이 (Style Transfer) 기술이다. 스타일 전이 기술은 콘텐츠 영상과 스타일 영상을 입력받아 콘텐츠 영상의 스타일을 변환한 결과 영상을 생성하는 기술로 디지털 콘텐츠의 다양성을 확보하는데 활용할 수 있어 중요성이 커지고 있다. 이런 스타일 전이 기술의 사용성을 향상하기 위해서는 안정적인 성능의 확보가 중요하다. 최근 자연어 처리 분야에서 트랜스포머 (Transformer) 개념이 적극적으로 활용됨에 트랜스포머의 기반이 되는 어텐션 맵이 스타일 전이 기술 개발에도 활발하게 적용되어 연구되고 있다. 본 논문에서는 그중 대표가 되는 SANet과 AdaAttN 기술을 분석하고 향상된 스타일 전이 결과를 생성 할 수 있는 새로운 어텐션 맵 기반 구조를 제안한다. 결과 영상은 제안하는 기술이 콘텐츠 영상의 구조를 보존하면서도 스타일 영상의 특징을 효과적으로 적용하고 있음을 보여준다.

• Journal of Information Processing Systems
• /
• 제12권1호
• /
• pp.83-99
• /
• 2016

The latest research on the image-based fingerprint matching approaches indicates that they are less complex than the minutiae-based approaches when it comes to dealing with low quality images. Most of the approaches in the literature are not robust to fingerprint rotation and translation. In this paper, we develop a robust fingerprint matching system by extracting the circular region of interest (ROI) of a radius of 50 pixels centered at the core point. Maximizing their orientation correlation aligns two fingerprints that are to be matched. The modified Euclidean distance computed between the extracted orientation features of the sample and query images is used for matching. Extensive experiments were conducted over four benchmark fingerprint datasets of FVC2002 and two other proprietary databases of RFVC 2002 and the AITDB. The experimental results show the superiority of our proposed method over the well-known image-based approaches in the literature.

• 한국정보기술응용학회:학술대회논문집
• /
• 한국정보기술응용학회 2005년도 6th 2005 International Conference on Computers, Communications and System
• /
• pp.91-97
• /
• 2005

Bones are dynamic structures, being supported by muscles, tendons, and ligaments. When some or all the structures are disturbed i.e. in fractures, the alignment of the bone in respect to the rest of the body is deranged. This gives rise to axial as well as rotational deformity in three dimensional planes. The correct alignment and position of the long bones are to be maintained to heal the bone in the best possible anatomical and functional position. The objective of this research is to address the problems in the current practice involving surgeon, assistant, fluoroscopy and crude mechanical means and to see if a robotic solution exists to solve the problems of manipulating and reducing long bone fractures. This paper presents various design aspects of the proposed surgeon-instructed, image-guided and robotic system including the system design specification, robot design and analysis, motion control and implementation, and x-ray image processing and incorporation in CAD environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.236-239
• /
• 1995

It is useful to simulate the human visual function for the purpose of image-processing. In this study, the hardware of the spatial filter with the sensitivity of lateral inhibition is realized by the combination of optical parts with electronic circuits. The diffused film with the characteristics of Gaussian type is prepared as a spatial filter. An object's image is convoluted with the spatial filter. From the difference of the convoluted images, the zero-cross position is detected at video rate. The edge of object is extracted in real-time by the use of this equipment. The resolution of edge changes with the value of the standard deviation of diffused film. In addition, it is possible to extract a directional edge selectively when the spatial filter with directional selectivity is used instead of Gaussian type of spatial filter.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1999년도 추계학술대회 논문집 - 한국공작기계학회
• /
• pp.119-124
• /
• 1999

This paper presents new approach to technology pattern recognition of camera back cover and test of soldering. In real-time implementing of pattern recognition camera back cover and test of soldering, the MVB-03 vision board has been used. Image can be captured from standard CCD monochrome camera in resolutions up to 640$\times$480 pixels. Various options re available for color cameras, a synchronous camera reset, and linescan cameras. Image processing os performed using Texas Instruments TMS320C31 digital signal processors. Image display is via a standard composite video monitor and supports non-destructive color overlay. System processing is possible using c30 machine code. Application software can be written in Borland C++ or Visual C++

• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.277-283
• /
• 2021

This paper addresses the problem of vision-based mask filter inspection for mask production systems. Machine learning-based approaches can be considered to solve the problem, but they may not be applicable to mask filter inspection if normal and anomaly mask filter data are not sufficient. In such cases, handcrafted image processing methods have to be considered to solve the problem. In this paper, we propose a hierarchical correlation-based approach that combines handcrafted image processing methods to detect anomaly mask filters. The proposed approach combines image rotation, cropping and resizing, edge detection of mask filter parts, average blurring, and correlation-based decision. The proposed approach was tested and analyzed with real mask filters. The results showed that the proposed approach was able to successfully detect anomalies in mask filters.