• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.5
• /
• pp.303-313
• /
• 2021

Recently, quality control of the Liquefied Natural Gas Carrier (LNGC) cargo hold and block-erection interference areas using 3D scanners have been performed, focusing on large shipyards and the international association of classification societies. In this study, as a part of the research on LNGC cargo hold quality management advancement, a study on deep-learning-based scaffolding system 3D point cloud object detection and post-processing were conducted using a LNGC cargo hold 3D point cloud. The scaffolding system point cloud object detection is based on the PointNet deep learning architecture that detects objects using point clouds, achieving 70% prediction accuracy. In addition, the possibility of improving the accuracy of object detection through parameter adjustment is confirmed, and the standard of Intersection over Union (IoU), an index for determining whether the object is the same, is achieved. To avoid the manual post-processing work, the object detection architecture allows automatic task performance and can achieve stable prediction accuracy through supplementation and improvement of learning data. In the future, an improved study will be conducted on not only the flat surface of the LNGC cargo hold but also complex systems such as curved surfaces, and the results are expected to be applicable in process progress automation rate monitoring and ship quality control.

• Investigative Magnetic Resonance Imaging
• /
• v.23 no.2
• /
• pp.114-124
• /
• 2019

Purpose: We investigate biases in the assessments of left ventricular function (LVF), by compressed sensing (CS)-cine magnetic resonance imaging (MRI). Materials and Methods: Cardiovascular cine images with short axis view, were obtained for 8 volunteers without CS. LVFs were assessed with subsampled data, with compression factors (CF) of 2, 3, 4, and 8. A semi-automatic segmentation program was used, for the assessment. The assessments by 3 CS methods (ITSC, FOCUSS, and view sharing (VS)), were compared to those without CS. Bland-Altman analysis and paired t-test were used, for comparison. In addition, real-time CS-cine imaging was also performed, with CF of 2, 3, 4, and 8 for the same volunteers. Assessments of LVF were similarly made, for CS data. A fixed compensation technique is suggested, to reduce the bias. Results: The assessment of LVF by CS-cine, includes bias and random noise. Bias appeared much larger than random noise. Median of end-diastolic volume (EDV) with CS-cine (ITSC or FOCUSS) appeared -1.4% to -7.1% smaller, compared to that of standard cine, depending on CF from (2 to 8). End-systolic volume (ESV) appeared +1.6% to +14.3% larger, stroke volume (SV), -2.4% to -16.4% smaller, and ejection fraction (EF), -1.1% to -9.2% smaller, with P < 0.05. Bias was reduced from -5.6% to -1.8% for EF, by compensation applied to real-time CS-cine (CF = 8). Conclusion: Loss of temporal resolution by adopting missing data from nearby cardiac frames, causes an underestimation for EDV, and an overestimation for ESV, resulting in underestimations for SV and EF. The bias is not random. Thus it should be removed or reduced for better diagnosis. A fixed compensation is suggested, to reduce bias in the assessment of LVF.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.865-871
• /
• 2022

In this paper, we propose a method of extracting prostate region using morphological characteristics of ultra-sonic image of prostate. In the first step of the proposed method, the edge area of the prostate image is extracted. The histogram of ultra-sonic image is used to extract base objects to detect the upper edge of prostate region by altering the contrast of the image, then, the lower edges of the extracted base objects are connected by using monotone cubic spline interpolation to extract the upper edge. Step 2, Otsu's binarization is applied to the region under the extracted upper edge of the prostate ultra-sonic image to extract the lower edge of prostate. In the last step, the upper and the lower edges are connected to extract prostate region and by comparing the extracted region of prostate with the one measured manually, the result showed that the morphological characteristics of prostate in ultrasonic image can be utilized to extract the prostate region.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.230-240
• /
• 2022

Sharing of online videos via internet is an emerging and important concept in different types of applications like surveillance and video mobile search in different web related applications. So there is need to manage personalized web video retrieval system necessary to explore relevant videos and it helps to peoples who are searching for efficient video relates to specific big data content. To evaluate this process, attributes/features with reduction of dimensionality are computed from videos to explore discriminative aspects of scene in video based on shape, histogram, and texture, annotation of object, co-ordination, color and contour data. Dimensionality reduction is mainly depends on extraction of feature and selection of feature in multi labeled data retrieval from multimedia related data. Many of the researchers are implemented different techniques/approaches to reduce dimensionality based on visual features of video data. But all the techniques have disadvantages and advantages in reduction of dimensionality with advanced features in video retrieval. In this research, we present a Novel Intent based Dimension Reduction Semi-Supervised Learning Approach (NIDRSLA) that examine the reduction of dimensionality with explore exact and fast video retrieval based on different visual features. For dimensionality reduction, NIDRSLA learns the matrix of projection by increasing the dependence between enlarged data and projected space features. Proposed approach also addressed the aforementioned issue (i.e. Segmentation of video with frame selection using low level features and high level features) with efficient object annotation for video representation. Experiments performed on synthetic data set, it demonstrate the efficiency of proposed approach with traditional state-of-the-art video retrieval methodologies.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.151-160
• /
• 2023

The Hadith is the second source of Islamic jurisprudence after Qur'an. Both sources are indispensable for muslims to practice Islam. All Ahadith are collected and are written. But most books of Hadith contain Ahadith that can be weak or rejected. So, quite a long time, scholars of Hadith have defined laws, rules and principles of Hadith to know the correct Hadith (Sahih) from the fair (Hassen) and weak (Dhaif). Unfortunately, the application of these rules, laws and principles is done manually by the specialists or students until now. The work presented in this paper is part of the automatic treatment of Hadith, and more specifically, it aims to automatically process the chain of narrators (Hadith Isnad) to find its different components and affect for each component its own tag using a statistical method: the Hidden Markov Models (HMM). This method is a power abstraction for times series data and a robust tool for representing probability distributions over sequences of observations. In this paper, we describe an important tool in the Hadith isnad processing: A chunker with HMM. The role of this tool is to decompose the chain of narrators (Isnad) and determine the tag of each part of Isnad (POI). First, we have compiled a tagset containing 13 tags. Then, we have used these tags to manually conceive a corpus of 100 chains of narrators from "Sahih Alboukhari" and we have extracted a lexicon from this corpus. This lexicon is a set of XML documents based on HPSG features and it contains the information of 134 narrators. After that, we have designed and implemented an analyzer based on HMM that permit to assign for each part of Isnad its proper tag and for each narrator its features. The system was tested on 2661 not duplicated Isnad from "Sahih Alboukhari". The obtained result achieved F-scores of 93%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1131-1141
• /
• 2023

Objective: Cortical iron deposition has recently been shown to occur in Alzheimer's disease (AD). In this study, we aimed to evaluate how cortical gray matter iron, measured using quantitative susceptibility mapping (QSM), differs in the clinical cognitive impairment spectrum. Materials and Methods: This retrospective study evaluated 73 participants (mean age ± standard deviation, 66.7 ± 7.6 years; 52 females and 21 males) with normal cognition (NC), 158 patients with mild cognitive impairment (MCI), and 48 patients with AD dementia. The participants underwent brain magnetic resonance imaging using a three-dimensional multi-dynamic multi-echo sequence on a 3-T scanner. We employed a deep neural network (QSMnet+) and used automatic segmentation software based on FreeSurfer v6.0 to extract anatomical labels and volumes of interest in the cortex. We used analysis of covariance to investigate the differences in susceptibility among the clinical diagnostic groups in each brain region. Multivariable linear regression analysis was performed to study the association between susceptibility values and cognitive scores including the Mini-Mental State Examination (MMSE). Results: Among the three groups, the frontal (P < 0.001), temporal (P = 0.004), parietal (P = 0.001), occipital (P < 0.001), and cingulate cortices (P < 0.001) showed a higher mean susceptibility in patients with MCI and AD than in NC subjects. In the combined MCI and AD group, the mean susceptibility in the cingulate cortex (β = -216.21, P = 0.019) and insular cortex (β = -276.65, P = 0.001) were significant independent predictors of MMSE scores after correcting for age, sex, education, regional volume, and APOE4 carrier status. Conclusion: Iron deposition in the cortex, as measured by QSMnet+, was higher in patients with AD and MCI than in NC participants. Iron deposition in the cingulate and insular cortices may be an early imaging marker of cognitive impairment related neurodegeneration.

• Tunnel and Underground Space
• /
• v.31 no.5
• /
• pp.374-384
• /
• 2021

In this study, we propose a new approach for automatic fracture detection in CT scan images of rock specimens. This approach is built on top of two-stage object detection deep learning algorithm called Faster R-CNN with a major modification of using rotated bounding box. The use of rotated bounding box plays a key role in the future work to overcome several inherent difficulties of fracture segmentation relating to the heterogeneity of uninterested background (i.e., minerals) and the variation in size and shape of fracture. Comparing to the commonly used bounding box (i.e., axis-align bounding box), rotated bounding box shows a greater adaptability to fit with the elongated shape of fracture, such that minimizing the ratio of background within the bounding box. Besides, an additional benefit of rotated bounding box is that it can provide relative information on the orientation and length of fracture without the further segmentation and measurement step. To validate the applicability of the proposed approach, we train and test our approach with a number of CT image sets of fractured granite specimens with highly heterogeneous background and other rocks such as sandstone and shale. The result demonstrates that our approach can lead to the encouraging results on fracture detection with the mean average precision (mAP) up to 0.89 and also outperform the conventional approach in terms of background-to-object ratio within the bounding box.