• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.351-360
• /
• 2022

Image blurring is a phenomenon that occurs due to factors such as movement of a subject and shaking of a camera. Recently, the research for image deblurring has been actively conducted based on convolution neural networks. In particular, the method of guiding the restoration process via the difference between blur and sharp images has shown the promising performance. This paper proposes a novel method for improving the deblurring performance based on the distortion information. To this end, the transformer-based neural network module is designed to guide the restoration process. The proposed method efficiently reflects the distorted region, which is predicted through the global inference during the deblurring process. We demonstrate the efficiency and robustness of the proposed module based on experimental results with various deblurring architectures and benchmark datasets.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.1
• /
• pp.13-19
• /
• 2003

There are active researches on automated guided vehicles(AGV) generally used in flexible manufacturing system(FMS) or automated warehouse systems(AWS). Because existing AGV uses magnetic tapes, electric wire, RF or laser as guidelines, its installation and modification require a lot of money and time. The present study implemented AGV that detects paths marked with 50mm Yellow tape using a mono-color CCD camera. Because it uses color tape, it is easy and inexpensive to install and change lines. This study presented the structure of the developed AGV, the image Processing technique for detecting guidelines by ing the characteristics of color, and the result of operating AGV.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1221-1229
• /
• 2022

In this work, the guided wave de-bonding area-detecting technique was studied for application to containment liner plates in nuclear power plant areas. To apply this technique, an appropriate Lamb wave mode, symmetric and longitudinal dominance, was verified by the frequency shifting technique. The S0 2.7 MHz mm Lamb wave mode was chosen to realize quantitative experimental results and their visualization. Results of the bulk wave, longitudinal wave mode, and comparison experiments indicate that the wave mode was able to distinguish between the de-bonded and bonded areas. Similar to the bulk wave cases, the bonded region could be distinguished from the de-bonded region using the Lamb wave approach. The Lamb wave technique results showed significant correlation to the de-bonding area. As the de-bonding area increased, the Lamb wave energy attenuation effect decreased, which was a prominent factor in the realization of quantitative tomographic visualization. The feasibility of tomographic visualization was studied via the application of Lamb waves. The reconstruction algorithm for the probabilistic inspection of damage (RAPID) technique was applied to the containment liner plate to verify and visualize the de-bonding condition. The results obtained using the tomography image indicated that the Lamb wave-based RAPID algorithm was capable of delineating debonding areas.

• Journal of the Korean Society of Radiology
• /
• v.84 no.6
• /
• pp.1220-1232
• /
• 2023

The prostate cancer diagnosis has traditionally been based on a systematic biopsy method in which tissue samples are randomly obtained from the prostate 10-12 sites. However, there are concerns as the method can fail to diagnose all prostate cancers or lead to over-detection of clinically insignificant cancers. MRI-guided prostate targeted biopsy has been proposed to address these shortcomings. This method involves identifying suspicious lesions using MRI and performing targeted biopsies under ultrasound or MRI guidance. We review the methods of MRI-based targeted biopsy and discuss recent guidelines and trends in prostate cancer diagnosis.

• Journal of the Korean Society of Radiology
• /
• v.84 no.6
• /
• pp.1233-1243
• /
• 2023

Percutaneous ultrasound-guided biopsy is useful for the pathologic confirmation of variable body lesions to establish diagnostic and therapeutic approaches. However, deep pelvic lesions are a challenge for pathologic diagnoses because of the presence of the bowel, bladder, major vessels, and pelvic bones which make a percutaneous approach difficult and dangerous. In female, the vagina is elastic and near the pelvic internal organs. Therefore, transvaginal ultrasound may serve as an effective and safe guide for the pathologic diagnosis of pelvis lesions. This review aimed to introduce the indications for, and the method of transvaginal ultrasoundguided biopsy, and to describe the reported diagnostic accuracy and safety.

• Journal of Korean Port Research
• /
• v.14 no.3
• /
• pp.303-312
• /
• 2000

In this paper, we describe an image processing algorithm which is able to recognize the road lane. This algorithm performs to recognize the interrelation between AGV and the other vehicle. We experimented on AGV driving test with color CCD camera which is setup on the top of vehicle and acquires the digital signal. This paper is composed of two parts. One is image preprocessing part to measure the condition of the condition of the lane and vehicle. This finds the information of lines using RGB ratio cutting algorithm, the edge detection and Hough transform. The other obtains the situation of other vehicles using the image processing and viewport. At first, 2 dimension image information derived from vision sensor is interpreted to the 3 dimension information by the angle and position of the CCD camera. Through these processes, if vehicle knows the driving conditions which are lane angle, distance error and real position of other vehicles, we should calculate the reference steering angle.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.208-211
• /
• 2004

Landmark matching is one of an important algorithm for navigation of satellite images. This paper proposes a fast landmark matching algorithm using a MGLI (Moving Guide-Line Image). For searching the matched point between the landmark chip and a part of image, correlation matrix is used generally, but the full-sized correlation matrix has a drawback requiring plenty of time for matching point calculation. MGLI includes thick lines for fast calculation of correlation matrix. In the MGLI, width of the thick lines should be determined by satellite position changes and navigation error range. For the fast landmark matching, the MGLI provides guided line for a landmark chip we want to match, so that the proposed method should reduce candidate areas for correlation matrix calculation. This paper will show how much time is reduced in the proposed fast landmark matching algorithm compared to general ones.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2707-2715
• /
• 1999

Recently, there have been researches to automate processing and analysing images in the medical field using image processing technique, a fast communication network, and high performance hardware. In this paper, we propose a system to be able to analyze morphological abnormality of red-blood cells for peripheral blood image using image processing techniques. To do this, we segment red-blood cells in the blood image acquired from microscope with CCD camera and then extract UNL fourier features to classify them into 15 classes. We reduce the number of multi-variate features using PCA to construct a more efficient classifier. Our system has the best performance in recognition rate, compared with two other algorithms, LVQ3 and k-NN. So, we show that it can be applied to a pathological guided system.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.43-54
• /
• 2018

Images taken in haze weather are characteristic of low contrast and poor visibility. The process of reconstructing clear-weather image from a hazy image is called dehazing. The main challenge of image dehazing is to estimate the transmission map or depth map for an input hazy image. In this paper, we propose a single image dehazing method by utilizing the Generative Adversarial Network(GAN) for accurate depth map estimation. The proposed GAN model is trained to learn a nonlinear mapping between the input hazy image and corresponding depth map. With the trained model, first the depth map of the input hazy image is estimated and used to compute the transmission map. Then a guided filter is utilized to preserve the important edge information of the hazy image, thus obtaining a refined transmission map. Finally, the haze-free image is recovered via atmospheric scattering model. Although the proposed GAN model is trained on synthetic indoor images, it can be applied to real hazy images. The experimental results demonstrate that the proposed method achieves superior dehazing results against the state-of-the-art algorithms on both the real hazy images and the synthetic hazy images, in terms of quantitative performance and visual performance.

• Journal of Periodontal and Implant Science
• /
• v.26 no.3
• /
• pp.771-778
• /
• 1996

The assessment of alveolar bone changes on dental radiographs to indicate progression of periodontal diseases or healing response to therapy is routine procedure. However, the diagnostic accuracy in detecting small alveolar bone changes is very limited. Recently, guided bone regeneration therapy is popular, but the quantification of new bone is somewhat difficult with conventional evaluation method. To quantificate the amount of new bone, various evaluating methods have been introduced including histomorphometry, radiomorphometry, biochemical analysis, X-ray probe microanalysis, scanning electron microscope backscatter method. In this study, guided bone regeneration using resorbable membrane with & without PDGF-BB is quatificated through histomorphmetry to evaluate the efficacy of histomorphometric analysis. 4 beagle dogs and 8 Sprague-Dawley rats were selected as experimental animals. In beagle dog experiment, $4{\times}4mm$ Class II defects were created in maxillary both second premolars, and biodegradable membrane containing PDGF-BB(experimental group) were covered over one defect, and same membrane without PDGF-BB(control group) were covered over the other defect. At 2 weeks, 5 weeks after surgery, each beagle dogs were sacrificed, and the tissues were treated by undecalcified fixation. In Sprague-Dawley rat experiment, 5mm round defect were created in temporal bone, the same membranes were covered on the defects. At 1 week, 2 weeks after surgery, each rats were sacrificed, and undecalcified fixation were taken. After grinding tissue specimen, we analyse them histomorphometrically using image analysis system. In beagle dog 2 weeks specimens, new bone formation area were $0.03123mm^2$ in experimental group,and $0.03012mm^2$ in control group. At 5 weeks specimens, $0.15324mm^2$ in experimental group, and $0.09123mm^2$ in control group. In Sprague-Dawley rat specimens, new bone fomation area were $0.20448mm^2$ in 1 week experimental group, $0.03604mm^2$ in 1 week control group. At 2 weeks specimens, $0.46349mm^2$ in experimental group, $0.17741mm^2$ in control group. The results indicated that histomorphometric analysis of new bone formation using image analysis system is very effective quantification method to evaluate the efficacy of treatment modalities.