• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.693-699
• /
• 2023

Ultrasound is widely used in the medical field for non-destructive and non-invasive disease diagnosis. In order to improve the disease diagnosis accuracy of diagnostic medical images, improving spatial resolution is a very important factor. In this study, we aim to model the super resolution convolutional neural network (SRCNN) algorithm in ultrasound images and analyze its applicability in the medical diagnostic field. The study was conducted as an experimental study using Field II simulation and open source clinical liver hemangioma ultrasound imaging. The proposed SRCNN algorithm was modeled so that end-to-end learning can be applied from low resolution (LR) to high resolution. As a result of the simulation, we confirmed that the full width at half maximum in the phantom image using a Field II program was improved by 41.01% compared to LR when SRCNN was used. In addition, the peak to signal to noise ratio (PSNR) and structural similarity index (SSIM) evaluation results showed that SRCNN had the excellent value in both simulated and real liver hemangioma ultrasound images. In conclusion, the applicability of SRCNN to ultrasound images has been proven, and we expected that proposed algorithm can be used in various diagnostic medical fields.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.144-154
• /
• 2013

This paper proposes a new super-resolution algorithm where sharpness enhancement is merged in order to improve overall visual quality of up-scaled images. In the learning stage, multiple dictionaries are generated according to sharpness strength, and a proper dictionary among those dictionaries is selected to adapt to each patch in the inference stage. Also, additional post-processing suppresses boosting of artifacts in input low-resolution images during the inference stage. Experimental results that the proposed algorithm provides 0.3 higher CPBD than the bi-cubic and 0.1 higher CPBD than Song's and Fan's algorithms. Also, we can observe that the proposed algorithm shows better quality in textures and edges than the previous works. Finally, the proposed algorithm has a merit in terms of computational complexity because it requires the memory of only 17% in comparison with the previous work.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.264-272
• /
• 2010

Example-based super resolution is a method to restore a high resolution image from low resolution images through training and retrieval of image patches. It is not only good in its performance but also available for a single frame low-resolution image. However, its time complexity is very high because it requires lots of comparisons to retrieve image patches in restoration process. In order to improve the restoration speed, an efficient patch retrieval algorithm is essential. In this paper, we applied various high-dimensional feature retrieval methods, available for the patch retrieval, to a practical example-based super resolution system and compared their speed. As well, we propose to apply the multi-phase candidate reduction approach to the patch retrieval process, which was successfully applied in character recognition fields but not used for the super resolution. In the experiments, LSH was the fastest among conventional methods. The multi-phase candidate reduction method, proposed in this paper, was even faster than LSH: For $1024{\times}1024$ images, it was 3.12 times faster than LSH.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.12-19
• /
• 2017

In this paper a super-resolution time delay estimation algorithm that estimates the time delays of spread spectrum signals using sparse signal reconstruction approach is introduced. So far, the correlation method has been mostly used to estimate the time delays of spread spectrum signals. However it fails to accurately estimate the time delays in the case where the signals are spaced within approximately 1 PN chip duration and a further processing should be applied to the correlation outputs in order to enhance the resolution capability. Recently sparse signal approaches attract much interest in the area of directions-of-arrival estimation, of which SPICE is the most representative. Thus we introduce a super-resolution time delay estimation algorithm based on the SPICE approach and compare its performance with that of MUSIC algorithm by applying them to the ISO/IEC 24730-2.1 RTLS system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.264-267
• /
• 2015

본 논문에서는 개선된 고속의 Back Projection 기법과 에지맵 보간을 이용한 단일영상 기반의 초해상도(super resolution) 영상을 생성하는 알고리즘을 제안한다. 본 논문에서 제안하는 알고리즘은 영상의 색채 왜곡을 방지하기 위해 RGB 컬러 도메인에서 HSV 컬러 도메인으로 변경하여 밝기정보인 V만 이용한다. 먼저 잡음제거와 속도 향상을 위해 개선된 고속 back projection을 이용해 영상을 확대 재구성한다. 이와 함께 LoG(laplacian of gaussian) 필터링을 이용하여 에지 맵을 추출한다. 에지의 정보와 back projection의 결과를 이용하여 고해상도 영상을 재구성한다. 제안하는 알고리즘을 이용하여 복원한 영상은 부자연스러운 인공물을 효과적으로 제거하고, blur현상을 줄여 에지 정보를 보정하고 강조해준다. 또한 실험을 통해 제안하는 알고리즘이 기존의 보간법과 전통적인 back projection 결과보다 주관적인 화질이 우수하고 객관적으로 우수한 성능을 나타내는 것을 입증한다.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.1
• /
• pp.10-15
• /
• 2015

This paper proposes the parallel implementation of a self-similarity based image SR (super-resolution) algorithm using OpenCL. The SR algorithm requires tremendous computations to search for a similar patch. This becomes a bottleneck for the real-time conversion from a FHD image to UHD. Therefore, it is imperative to accelerate the processing speed of SR algorithms. For parallelization, the SR process is divided into several kernels, and memory optimization is performed. In addition, two GPUs are used for further acceleration. The experimental results shows that a GPGPU implementation can speed up over 140 times compared to a single-core CPU. Furthermore, it was confirmed experimentally that utilizing two GPUs can speed up the execution time proportionally, up to 277 times.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.137-147
• /
• 2023

LiDAR is used in autonomous driving and various industrial fields to measure the size and distance of an object. In addition, the sensor also provides intensity images based on the amount of reflected light. This has a positive effect on sensor data processing by providing information on the shape of the object. LiDAR guarantees higher performance as the resolution increases but at an increased cost. These conditions also apply to LiDAR intensity images. Expensive equipment is essential to acquire high-resolution LiDAR intensity images. This study developed artificial intelligence to improve low-resolution LiDAR intensity images into high-resolution ones. Therefore, this study performed parameter analysis for the optimal super-resolution neural network model. The super-resolution algorithm was trained and verified using 2,500 LiDAR intensity images. As a result, the resolution of the intensity images were improved. These results can be applied to the autonomous driving field and help improve driving environment recognition and obstacle detection performance

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.703-712
• /
• 2019

Single image Super-Resolution (SISR) aims to generate a visually pleasing high-resolution image from its degraded low-resolution measurement. In recent years, deep learning - based super - resolution methods have been actively researched and have shown more reliable and high performance. A typical method is WaveletSRNet, which restores high-resolution images through wavelet coefficient learning based on feature maps of images. However, there are two disadvantages in WaveletSRNet. One is a big processing time due to the complexity of the algorithm. The other is not to utilize feature maps efficiently when extracting input image's features. To improve this problems, we propose an efficient single image super resolution method, named RDB-WaveletSRNet. The proposed method uses the residual dense block to effectively extract low-resolution feature maps to improve single image super-resolution performance. We also adjust appropriated growth rates to solve complex computational problems. In addition, wavelet packet decomposition is used to obtain the wavelet coefficients according to the possibility of large scale ratio. In the experimental result on various images, we have proven that the proposed method has faster processing time and better image quality than the conventional methods. Experimental results have shown that the proposed method has better image quality by increasing 0.1813dB of PSNR and 1.17 times faster than the conventional method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.2
• /
• pp.270-278
• /
• 1993

This paper is presented the phonetic segmentation alg9rithm of the Korean speech signals which is finded the exact pitch using the super resoluton pitch determination and is compared corss-correlation to threshold each pitch period. The features of the proposed algorithm are infinite resolution and high reliability, and also can separate transient or silent segment. The algorithm is instrumental to speech processing applications which require vector quantization and speech recognition. The presented algorithm is implemented by 386-MATLAB on PC 386/DX and is verified the exact pitch period and the phonetic segmentation of speech signals.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.12
• /
• pp.1013-1020
• /
• 2013

In this paper the super-resolution time delay estimation algorithms based on eigen-analysis are developed for spread spectrum signals along with their comparative performance analysis. First, we shall develop super-resolution time delay estimation algorithms using the representative eigen-analysis based AOA (angle-of-arrival) estimation algorithms such as MUSIC, Minimum-Norm, and ESPRIT, and apply them to the ISO/IEC 24730-2.1 real-time locating system (RTLS) employing a direct sequence spread spectrum (DS-SS) technique to compare their performances in RTLS environments. Simulation results illustrate that all the three algorithms can resolve multipath signals whose delay differences are even smaller than the Rayleigh resolution limit. Simulation results also show that MUSIC and Minimum-Norm provide a similar performance while ESPRIT is inferior to both algorithms in RTLS environments.