• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.18-26
• /
• 2009

Image resolution enhancement algorithm is a basic technique for image enlargement and restoration. The main problem is the image quality degradation such as blurring or blocking effects. In this paper, we propose loss information estimation and image resolution enhancement method using low level interpolation method. In the proposed method, loss information is computed by downsampling -interpolation process of obtained low resolution image. We estimate loss information of high resolution image using interpolation of the computed loss information. Lastly, we add up interpolated high resolution image and the estimated loss information which is applied a weight factor. Our experiments obtained the average PSNR 1.4dB which is improved results better than conventional algorithm. Also subjective image quality is more clearness and distinctness. The proposed method may be helpful for various video applications which required improvement of image.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1392-1400
• /
• 2011

In most digital imaging applications, high-resolution images or videos are usually desired for later image processing and analysis. The image signal obtained from general imaging system occurs image degradation during the process of image acquirement caused by the optics, physical constraints and the atmosphere effects. Super-resolution reconstruction, one of the solution to address this problem, is image reconstruction technique that produces a high-resolution image from several low-resolution frames in video sequences. In this paper, we propose an improved super-resolution method using Projection onto Convex Sets (POCS) method based on Shift & Add (S&A). The image using conventional algorithms is sensitive to noise. To solve this problem, we propose a fusion algorithm of S&A and POCS. Also we solve the problem using BLPF (Butterworth Low-pass Filter) in frequency domain as optical blur. Our method is robust to noise and has sharpness enhancement ability. Experimental results show that the proposed super-resolution method has better resolution enhancement performance than other super-resolution methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.481-484
• /
• 2005

Inherent opportunities on research for restoring high resolution image from low resolution images are increasing in these days. Super resolution image reconstruction is the process of combining multiple low resolution images to form a higher resolution one. To achieve super resolution reconstruction, proper observation model which is based on subpixel shift information is required. In this context, the importance of the subpixel registration cannot be estimated because subpixel shift information cannot be obtained from original image. This paper presents a regularized adaptive super resolution reconstruction method based on phase correlated subpixel registration, where the Constrained Least Squares(CLS) Restoration is adopted as a post process.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.85-92
• /
• 2022

In this paper, we propose a technique that can express low-resolution hair and fur simulations in high-resolution without noise using ConvNet and geometric images of strands in the form of lines. Pairs between low-resolution and high-resolution data can be obtained through physics-based simulation, and a low-resolution-high-resolution data pair is established using the obtained data. The data used for training is used by converting the position of the hair strands into a geometric image. The hair and fur network proposed in this paper is used for an image synthesizer that upscales a low-resolution image to a high-resolution image. If the high-resolution geometry image obtained as a result of the test is converted back to high-resolution hair, it is possible to express the elastic movement of hair, which is difficult to express with a single mapping function. As for the performance of the synthesis result, it showed faster performance than the traditional physics-based simulation, and it can be easily executed without knowing complex numerical analysis.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.725-728
• /
• 1988

Image restoration technique using dual sensor is presented in this paper. Digital Radiography image (1024xlO24) is obtained by conventional resolution sensor. We also obtain local DR image data by high resolution sensor. Two dimensional maximum entropy power spectrum estimation (2-D ME PSE) is applied to low resolution image and high resolution image for the purpose of the power spectrum estimation of each image. A class of linear algebraic restoration filter, parametric projection filter (PPF), is derived from the power spectrums of each image. It is shown that the noise energy may be considerably reduced through the PPF.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.17-25
• /
• 2020

In the image object classification problem, low-resolution images may have a negative impact on the classification result, especially when the classification method, such as a convolutional neural network (CNN) model, is trained on a high-resolution (HR) image dataset. In this paper, we analyze the behavior of applying a classical super-resolution (SR) method such as bicubic interpolation, and a deep CNN model such as SRCNN to enhance low-resolution (LR) weeds images used for classification. Using an HR dataset, we first train a CNN model for weeds image classification with a default input size of 128 × 128. Then, given an LR weeds image, we rescale to default input size by applying the bicubic interpolation or the SRCNN model. We analyze these two approaches on the Chonnam National University (CNU) weeds dataset and find that SRCNN is suitable for the image size is smaller than 80 × 80, while bicubic interpolation is convenient for a larger image.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.3 s.96
• /
• pp.329-333
• /
• 2005

This paper is concerned with the measurement of low-frequency vibrations of structures using the image processing method. To measure the vibrations visually, the measurement system consists of a camera, an image grabber board, and a computer. The specific target installed on the structure is used to calculate the vibration of structure. The captured image is then converted into a pixel-based data and then analyzed numerically. The limitation of the system depends on the image capturing speed and the size of image. In this paper, we propose the methodology for the vibration measurement using the image processing method. The method enables us to measure the displacement directly without any contact. The current resolution of the vibration measurement is limited to sub centimeter scale. However, the frequency bandwidth and resolution can be enhanced by a high-speed and high-resolution image processing system.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.865-869
• /
• 2009

An image resolution enhancement is mainly utilized as pre-processing technique for various image processing application. It requires to decrease image quality deterioration such as blurring. In this paper, we propose an image resolution enhancement algorithm using low level interpolation. In the proposed algorithm, we calculate an error using low level interpolation, estimate an error image from the calculated error. The estimated error image is added interpolated high resolution image, it become lastly reconstruction image. Our experiments obtained the average PSNR about 1dB which is improved results better than conventional method for sensitive image quality. Also, subjective image quality with edge region is more clearness. The proposed method may be helpful for applications in various multimedia systems such as image restoration.