• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.339-342
• /
• 2002

The feature points in the uncalibrated stereo vision should represent all the characteristics of an image in multiple resolution, have high precision, and have the robustness against mismatching. This paper proposed an algorithm which detects the corner points in multi-resolution for stereo computer vision. The algorithm has sub-pixel precision, rejects the mismatched points, and corrects the lens distortion. We show the performance of the algorithm by estimating the homography with it.

• Science of Emotion and Sensibility
• /
• v.17 no.3
• /
• pp.3-14
• /
• 2014

Since the domestic introduction of iPhone in 2009, use of smartphones rapidly increased and many tasks, previously performed by various devices, are now performed by smartphones. In this process the importance of reading little text using small smartphone screen has become highly significant. This research tested how display factors of smartphone (pixel density, sub-pixel structure, luminance) and environmental factor (illumination) affect legibility related discomfort in text reading. The results indicated that legibility related discomfort is largely affected by pixel density, where people experience inconvenience when the pixel density becomes lower than 300 PPI. Illumination has limited effect on legibility related discomfort. Participants reported more legibility related discomfort when stimulus presented in various levels of illumination rather than single illumination level. Sub-pixel structure and luminance did not affected legibility related discomfort. Based on the results we suggest lower limit resolution of smart devices (smartphones, tablet computers) of different sizes for text legibility.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.185-191
• /
• 2022

In this study, we propose a novel super-resolution neural network based on U-Net, residual neural network, and sub-pixel convolution. To prevent the loss of detailed information due to the max pooling of U-Net, we propose down-sampling and connection using sub-pixel convolution. This uses all pixels in the filter, unlike the max pooling that creates a new feature map with only the max value in the filter. As a 2×2 size filter passes, it creates a feature map consisting only of pixels in the upper left, upper right, lower left, and lower right. This makes it half the size and quadruple the number of feature maps. And we propose two methods to reduce the computation. The first uses sub-pixel convolution, which has no computation, and has better performance, instead of up-convolution. The second uses a layer that adds two feature maps instead of the connection layer of the U-Net. Experiments with a banchmark dataset show better PSNR values on all scale and benchmark datasets except for set5 data on scale 2, and well represent local area patterns.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.732-734
• /
• 2003

In the middle -resolution remote sensing, the Ground Sampled Distance(GSD) sensed and sampled by the detector is generally larger than the size of objects(or materials) of interest, in which case several objects are embedded in a single pixel and cannot be detected spatially. This study is intended to solve this problem of a hyperspectral data with high spectral resolution. We examined the detection algorithm, Linear Spectral Mixing Model, and also made a test on the Hyperion data. To find class Endmembers, we applied two methods, Spectral Library and Geometric Model, and compared them with each other.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.3
• /
• pp.181-193
• /
• 2010

The paper presents an alternative way to classical stereocorrelation. First, 2D image processing of random patterns is described. Sub-pixel displacements are determined using phase analysis. Then distortion evaluation is presented. The distortion is identified without any assumption on the lens model because of the use of a grid technique approach. Last, shape measurement and shape variation is caught by fringe projection. Analysis is based on two pin-hole assumptions for the video-projector and the camera. Then, fringe projection is coupled to in-plane displacement to give rise to 3D measurement set-up. Metrological characterization shows a resolution comparable to classical (stereo) correlation technique ($1/100^{th}$ pixel). Spatial resolution seems to be an advantage of the method, because of the use of temporal phase stepping (shape measurement, 1 pixel) and windowed Fourier transform (in plane displacements measurement, 9 pixels). Two examples are given. First one is the study of skin properties; second one is a study on leather fabric. In both cases, results are convincing, and have been exploited to give mechanical interpretation.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2006.08a
• /
• pp.1613-1617
• /
• 2006

The total light efficiencies of the novel 1.9" transflective tRGB-t/rW and tRGB-rW TFT LCDs are calculated and they are implemented by the traditional 7-mask ${\alpha}$-Si processing. Then, the two vehicles are turned on with the appropriate Sub-Pixel Rendering White (SPRW) algorithms, so they can exhibit the extra luminance without the original visual resolution loss. Their outstanding optical properties are approved by measuring the contrast ratio (C.R.) and the NTSC ratio. Because they utilize the light resource very effectively and efficiently, they are very suitable for the dark indoor and the bright outdoor environments.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.106-109
• /
• 2011

본 논문에서는 연속된 프레임을 갖는 영상의 프레임간 움직임 추정 기법을 응용하여 고해상도 영상을 획득하는 초고 해상도 기법을 제안한다. 기존의 단일 영상을 이용한 초고해상도 기법의 경우 영상에서의 고주파 대역을 찾기 위해 확률 기반의 다양한 방법이 제시되었으나 연산에 사용할 수 있는 정보가 제한적이라는 문제가 존재한다. 이러한 문제를 해결하기 위해 연속된 프레임을 이용한 다양한 초고해상도 기법이 제안되었다. 본 논문에서는 주어진 영상의 전, 후의 다수 프레임을 정하여 6-tap FIR(finite impulse response) 필터를 이용하여 프레임들의 부화소(sub-pixel)를 구한 뒤에, 부화소 정밀도의 움직임 추정을 통하여 보다 정확한 고주파성분을 복원하고자 한다. 실험을 통하여 제안하는 기법이 기존의 고등차수(bi-cubic)보간법 보다 선명한 영상을 획득할 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.1
• /
• pp.363-371
• /
• 2014

In this paper, a new super-resolution algorithm is proposed by using successive frames for generating high-resolution frames with better quality than those generated by other conventional interpolation methods. Generally, each frame used for super-resolution must only have global translation and motions of sub-pixel unit to generate good result. However, the newly proposed MSR algorithm in this paper is exempt from such constraints. The proposed algorithm consists of three main processes; motion estimation for image registration, normalization of motion vectors, and pattern analysis of edges. The experimental results show that the proposed algorithm has better performance than other conventional algorithms.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_2
• /
• pp.559-565
• /
• 2013

Spatial resolution of land covers from remotely sensed images can be increased using super-resolution mapping techniques for soft-classified land cover proportions. A further development of super-resolution mapping technique is downscaling the original remotely sensed image using super-resolution mapping techniques with a forward model. In this paper, the model for increasing spatial resolution of remote sensing multispectral image is tested with real SPOT 5 imagery at 10m spatial resolution for an area in Bac Giang Province, Vietnam in order to evaluate the feasibility of application of this model to the real imagery. The soft-classified land cover proportions obtained using a fuzzy c-means classification are then used as input data for a Hopfield neural network (HNN) to predict the multispectral images at sub-pixel spatial resolution. The 10m SPOT multispectral image was improved to 5m, 3,3m and 2.5m and compared with SPOT Panchromatic image at 2.5m resolution for assessment.Visually, the resulted image is compared with a SPOT 5 panchromatic image acquired at the same time with the multispectral data. The predicted image is apparently sharper than the original coarse spatial resolution image.