• Imaging Science in Dentistry
• /
• v.43 no.3
• /
• pp.185-190
• /
• 2013

Purpose: The aim of the present study was to evaluate the measurement accuracy of endodontic file length on periapical digital radiography after application of noise reduction digital enhancement. Materials and Methods: Thirty-five human single-rooted permanent teeth with canals measuring 20-24 mm in length were selected. ISO #08 endodontic files were placed in the root canals of the teeth. The file lengths were measured with a digital caliper as the standard value. Standard periapical digital images were obtained using the Digora digital radiographic system and a dental X-ray unit. In order to produce the enhanced images, the noise reduction option was applied. Two blinded radiologists measured the file lengths on the original and enhanced images. The measurements were compared by repeated measures ANOVA and the Bonferroni test (${\alpha}=0.05$). Results: Both the original and enhanced digital images provided significantly longer measurements compared with the standard value (P<0.05). There were no significant differences between the measurement accuracy of the original and enhanced images (P>0.05). Conclusion: Noise reduction digital enhancement did not influence the measurement accuracy of the length of the thin endodontic files on the digital periapical radiographs despite the fact that noise reduction could result in the elimination of fine details of the images.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

• Investigative Magnetic Resonance Imaging
• /
• v.19 no.3
• /
• pp.200-204
• /
• 2015

Image findings of hepatic lymphoma have been reported as variable, ranging from single or multiple small nodules to diffuse infiltrative patterns. On MRI, most hepatic lymphomas show T1 low signal intensity, T2 high signal intensity. Dynamic imaging reveals a hypointense appearance in the arterial phase, followed by delayed enhancement in the portal venous and transitional phase. In the hepatobiliary phase using a hepatocyte-specific contrast agent (which have recently aided in increasing the access to the focal liver lesions), hepatic lymphoma is known to exhibit low signal intensity. We report a case of hepatic lymphoma, which shows iso-signal intensity on hepatobiliary phase, using gadoxetic acid (Gd-EOB-DTPA).

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.193-198
• /
• 2022

Face Detection is one of the most important aspects of image processing, it considers a time-consuming problem in real-time applications such as surveillance systems, face recognition systems, attendance system and many. At present, commodity hardware is getting more and more heterogeneity in terms of architectures such as GPU and MIC co-processors. Utilizing those co-processors along with the existing traditional CPUs gives the algorithm a better chance to make use of both architectures to achieve faster implementations. This paper presents a hybrid implementation of the face detection based on the local binary pattern (LBP) algorithm that is deployed on both traditional CPU and MIC co-processor to enhance the speed of the LBP algorithm. The experimental results show that the proposed implementation achieved improvement in speed by 3X when compared to a single architecture individually.

• Journal of the Korean Society of Radiology
• /
• v.2 no.1
• /
• pp.23-29
• /
• 2008

The present study proposed a method that dissolves ultrasonographic images into multiple resolutions using wavelet conversion and a boundary detection filter and improves the quality of ultrasonographic images through boundary detection filtering. In order to reduce noises and strengthen edges, the proposed method adjusted selectivity coefficient by area step by step from a low resolution image obtained from wavelet converted images to a high resolution image and performed edge filtering in consideration of direction. Through this method, we generated a selective low pass filtering effect in areas except edges by decreasing the wavelet coefficient for pixels in spot areas, improved continuity by smoothing edges in the tangential direction, and enhanced contrast by thinning in the normal direction. Through an experiment, we compared the filtering method using a non linear anisotropic expansion model and the filtering method using wavelet contraction structure in single resolution.

• Journal of Veterinary Science
• /
• v.21 no.4
• /
• pp.55.1-55.11
• /
• 2020

Background: Computed tomography urography (CTU), based on the excretion of contrast medium after its injection, allows visualization of the renal parenchyma and the renal collecting system. Objectives: To determine the optimal contrast medium dose allocation ratio to apply in split-bolus CTU in dogs. Methods: This prospective, experimental, exploratory study used 8 beagles. In 3-phase CTU, unenhanced-, nephrographic-, and excretory-phase images were obtained with a single injection of 600 mg iodine/kg iohexol. In split-bolus CTU, two different contrast medium allocation ratios (30% and 70% for split CTU 1; 50% and 50% for split CTU 2) were used. Unenhanced phase image and a synchronous nephrographic-excretory phase image were acquired. Results: Although the attenuation of the renal parenchyma was significantly lower when using both split CTUs than the 3-phase CTU, based on qualitative evaluation, the visualization score of the renal parenchyma of split CTU 1 was as high as that of the 3-phase CTU, whereas the split CTU 2 score was significantly lower than those of the two others. Artifacts were not apparent, regardless of CTU protocol. The diameter and opacification of the ureter in both split CTUs were not significantly different from those using 3-phase CTU. Conclusions: Split-bolus CTU with a contrast medium allocation ratio of 30% and 70% is feasible for evaluating the urinary system and allows sufficient enhancement of the renal parenchyma and appropriate distention and opacification of the ureter, with similar image quality to 3-phase CTU in healthy dogs. Split-bolus CTU has the advantages of reducing radiation exposure and the number of CT images needed for interpretation.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1087-1098
• /
• 2023

The rapid advancement of artificial intelligence (AI) technology has led to its proactive utilization across various fields. However, this widespread adoption of AI-based systems has raised concerns about the increasing threat of attacks on these systems. In particular, deep neural networks, commonly used in deep learning, have been found vulnerable to adversarial attacks that intentionally manipulate input data to induce model errors. In this study, we propose a method to protect image classification models from visually imperceptible One-Pixel attacks, where only a single pixel is altered in an image. The proposed defense technique utilizes an autoencoder model to remove potential threat elements from input images before forwarding them to the classification model. Experimental results, using the CIFAR-10 dataset, demonstrate that the autoencoder-based defense approach significantly improves the robustness of pretrained image classification models against One-Pixel attacks, with an average defense rate enhancement of 81.2%, all without the need for modifications to the existing models.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.5
• /
• pp.379-388
• /
• 2019

Recently, a technique for acquiring spatial information data using UAV (Unmanned Aerial Vehicle) has been greatly developed. It is a very crucial issue of the GIS (Geographic Information System) mapping system that passes way point in the unmanned airframe and finally measures the accurate image and stable localization to the desired destination. Though positioning using DGPS (Differential Global Navigation System) or RTK-GPS (Real Time Kinematic-GPS) guarantee highly accurate, they are more expensive than the construction of a single positioning system using a single GPS. In the case of a low-priced single GPS system, the stability of the positioning data deteriorates. Therefore, it is necessary to supplement the uncertainty of the absolute position data of the UAV and to improve the accuracy of the current position data economically in the operating state of the UAV. The aim of this study was to present an algorithm enhancing the stability of position data in a single GPS mode of UAV with multiple GPS. First, the arrangement of multiple GPS receivers through the center of gravity of the UAV were examined. Next, MD (Mahalanobis Distance) is applied to detect instantaneous errors of GPS data in advance and eliminate outliers to increase the accuracy of previously collected multiple GPS data. Processing procedure for multiple GPS reception data by applying the center of the triangular method were presented to improve the position accuracy. Second, UAV navigation systems integrated multiple GPS through configuration of the UAV specifications were implemented. Using the unmanned airframe equipped with multiple GPS receivers, GPS data is measured with the TCM (Triangular Center Method). In addition, UAV equipped with multiple GPS were operated in study area and locational accuracy of multiple GPS of UAV with VRS (Virtual Reference Station) GNSS surveying were compared. The result showed that the error factors are compensated, and the error range are reduced, resulting in the reliability of the corrected value. In conclusion, the result in this paper is expected to realize high-precision position estimation at low cost in UAV using multiple low-cost GPS receivers.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.39-44
• /
• 2006

In this paper, search result list synthesis method is proposed using borda count method for still image retrieval based on MPEG-7 descriptors. MPEG-7 standardizes descriptors that extract feature information from media data. In many cases, using a single descriptor lacks of correctness, it is suggested to use multiple descriptors to enhance retrieval efficiency. In this paper, retrieval efficiency enhancement is achieved by combining multiple search results which are from each descriptor. In combining search result, newly calculated borda count method is proposed. Comparing current frequency compensated calculation, rank considered frequency compensation is used to score animage in database. This combining method is considered in Content based image retrieval system with relevance feedback algorithm which uses high level information from system user. In each relevance iteration step, adoptive borda count method is used to calculate score of images.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.1 no.1
• /
• pp.109-117
• /
• 1998

To obtain new information using a single remotely sensed image data is limited to extract various information. Recent trends in the remote sensing show that many researchers integrate and analyze many different forms of remotely sensed data, such as optical and radar satellite images, aerial photograph, airborne multispectral scanner data and land spectral scanners. Korean researchers have not been using such a combined dataset yet. This study intended to apply the technique of integration between optical data and radar data(SAR) and to examine the output that had been obtained through the technique of supervised classification using the result of integration. As a result, we found of better enhanced image classification results by using IHS conversion than by using RGB mixed and interband correlation.