• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.6C
• /
• pp.793-800
• /
• 2004

In this paper, we propose a new automatic pipe grading algorithm for an efficient management of transmission pipe under the ground. Since the conventional transmission pipe evaluation was conducted by subjective decision made by an individual operator, it was difficult to grade them by means of numerical methods and also hard to realistically construct numerical database system. To solve these problems, we Int obtain some information on the current condition of pipes' sections by shooting laser beam at a regular rate and then apply grading algorithm after complete calculation of minimum diameter of pipe. We use some of preprocessing techniques to reduce noise and also use various color models to consider special conditions of each inner pipe. The measurement of pipes' minimum diameter and decision of grade are performed through a detailed processing stages. By some experimental results performed in the field, we show that over 90 percent of correct grade decisions are made by the proposed algorithm.

• Journal of Advanced Navigation Technology
• /
• v.15 no.5
• /
• pp.833-838
• /
• 2011

X-ray device used in the diagnosis has made possible to have more effective and accurate diagnosis, powered by the development of various devices. Based on this, X-ray device has become the most basic and essential diagnostic equipment in clinical medicine. At present, in the image acquisition field using X-ray, the use of Digital radiography which is useful in the acquisition time reduction and transfer of images and is possible to have the dose reduction has expanded. With the structure using one detector, this DR device has disadvantages in that it needs structural changes unlike existing X-ray and the detector should be moved to the desired position depending on the shooting location. Therefore, in this study, using BLDC(Brushless direct current) motor and PID(Proportional integral differential) control method, the automatic control system of 3-axis which is upward and downward, left and right and rotation of detector where having the most movement in DR was designed and produced and its performance was evaluated.

• 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.

• Journal of the Korean Society of Radiology
• /
• v.10 no.6
• /
• pp.443-450
• /
• 2016

In this study, we are using a computer tomography image of the abdomen, as an experimental linear research for the image of the fatty liver patients texture features analysis and computer-aided diagnosis system of implementation using the ROC curve analysis, from the computer tomography image. We tried to provide an objective and reliable diagnostic information of fatty liver to the doctor. Experiments are usually a fatty liver, via the wavelet transform of the abdominal computed tomography images are configured with the experimental image section, shows the results of statistical analysis on six parameters indicating a feature value of the texture. As a result, the entropy, average luminance, strain rate is shown a relatively high recognition rate of 90% or more, the control also, flatness, uniformity showed relatively low recognition rate of about 70%. ROC curve analysis of six parameters are all shown to 0.900 (p = 0.0001) or more, showed meaningful results in the recognition of the disease. Also, to determine the cut-off value for the prediction of disease six parameters. These results are applicable from future abdominal computed tomography images as a preliminary diagnostic article of diseases automatic detection and eventual diagnosis.

• Journal of the Korean Society of Radiology
• /
• v.9 no.6
• /
• pp.369-374
• /
• 2015

In this study we proposed a texture feature analysis algorithm that distinguishes between a normal image and a diseased image using CT images of some brain hemorrhage patients, and generates both Eigen images and test images which can be applied to the proposed computer aided diagnosis system in order to perform a quantitative analysis for 6 parameters. And through the analysis, we derived and evaluated the recognition rate of CT images of brain hemorrhage. As the results of examining over 40 example CT images of brain hemorrhage, the recognition rates representing a specific texture feature-value are as follows: some appeared to be as high as 100% including average gray level, average contrast, smoothness, and Skewness while others showed a little low disease recognition rate: 95% for uniformity and 87.5% for entropy. Consequently, based on this research result, if a software that enables a computer aided diagnosis system for medical images is developed, it will lead to the availability for the automatic detection of a diseased spot in CT images of brain hemorrhage and quantitative analysis. And they can be used as computer aided diagnosis data, resulting in the increased accuracy and the shortened time in the stage of final reading.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.233-238
• /
• 2017

Automatic identification of disease in plants from their leaves is one of the most challenging task to researchers. Diseases among plants degrade their performance and results into a huge reduction of agricultural products. Therefore, early and accurate diagnosis of such disease is of the utmost importance. The advancement in deep Convolutional Neural Network (CNN) has change the way of processing images as compared to traditional image processing techniques. Deep learning architectures are composed of multiple processing layers that learn the representations of data with multiple levels of abstraction. Therefore, proved highly effective in comparison to many state-of-the-art works. In this paper, we present a plant disease identification methodology from their leaves using deep CNNs. For this, we have adopted GoogLeNet that is considered a powerful architecture of deep learning to identify the disease types. Transfer learning has been used to fine tune the pre-trained model. An accuracy of 85.04% has been recorded in the identification of four disease class in Apple plant leaves. Finally, a comparison with other models has been performed to show the effectiveness of the approach.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.5
• /
• pp.1601-1607
• /
• 2010

This paper presents FMEA (Failure Mode Effect Analysis) for maintenance of mail sorting machine which is for automatic sorting of mail. We suggest the update method of regular diagnosis item and period for maintenance of mail sorting machine using the risk priority number which is calculated by severity, occurrence, and detection of failure mode of mail sorting machine, and shows FMEA adoption example of letter sorting machine. This paper also describes the current maintenance system and status of mail sorting machine in the domestic postal logistics environment, and FMEA adoption step. The proposed maintenance using FMEA will be adapted for more easy and efficiency maintenance of mail sorting machine.

• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1635-1648
• /
• 2008

The extraction of important features in cancer cell image analysis is a key process in grading renal cell carcinoma. In this study, we applied three-dimensional (3D) texture feature extraction methods to cell nuclei images and evaluated the validity of them for computerized cell nuclei grading. Individual images of 2,423 cell nuclei were extracted from 80 renal cell carcinomas (RCCs) using confocal laser scanning microscopy (CLSM). First, we applied the 3D texture mapping method to render the volume of entire tissue sections. Then, we determined the chromatin texture quantitatively by calculating 3D gray-level co-occurrence matrices (3D GLCM) and 3D run length matrices (3D GLRLM). Finally, to demonstrate the suitability of 3D texture features for grading, we performed a discriminant analysis. In addition, we conducted a principal component analysis to obtain optimized texture features. Automatic grading of cell nuclei using 3D texture features had an accuracy of 78.30%. Combining 3D textural and 3D morphological features improved the accuracy to 82.19%. As a comparative study, we also performed a stepwise feature selection. Using the 4 optimized features, we could obtain more improved accuracy of 84.32%. Three dimensional texture features have potential for use as fundamental elements in developing a new nuclear grading system with accurate diagnosis and predicting prognosis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.928-930
• /
• 2020

본 논문은 인공지능 플랫폼 기반의 요로결석 진단을 위한 CT 영상 데이터 자동판독 시스템에 대해 기술하고자 한다. 제안한 시스템은 웹 기반의 플랫폼을 기반으로 하며, 인공지능 기반의 진단 알고리즘을 장착하여 빠르게 요로결석 환자의 스크리닝에 목적을 두고 있다. 병원정보시스템의 PACS와 EMR과 연계와 Deep learning 진단 알고리즘을 적용한 요로결석 자동판독 시스템을 개발하였다. 특히, 기 구축된 인공지능 플랫폼을 통해 추출한 데이터셋을 기반으로 진단 알고리즘 개발 방법과 수행 결과를 보인다. 제안한 시스템은 요로결석 진단과 수술여부에 의사결정지원 시스템으로 임상에서 활용될 것으로 기대하고 있다.

• Progress in Medical Physics
• /
• v.23 no.4
• /
• pp.279-284
• /
• 2012

The X ray has been widely used in both diagnosis and treatment. Recently, a miniature X ray tube has been developed for radiotherapy. The miniature X ray tube is directly inserted into the body irradiated, so that X rays can be guided to a target at various incident angles according to collimator geometry and, thus, minimize patient dose. If such features of the miniature X ray tube can be applied to development of X ray imaging as well as radiation treatment, it is expected to open a new chapter in the field of diagnostic X ray. However, the miniature X ray tube requires an added filter and a collimator for diagnostic purpose because it was designed for radiotherapy. Therefore, a collimator and an added filter were manufactured for the miniature X ray tube, and mounted on. In this study, we evaluated beam characteristics of the miniature X ray tube for diagnostic X ray system and accuracy of measuring the HVL. We used the Si PIN Photodiode type Piranha detector (Piranha, RTI, Sweden) and estimated the HVL of the miniature X ray tube with added filter and without added filter. Through an another measurement using Al filter, we evaluated the accuracy of the HVL obtained from a direct measurement using the automatic HVL calculation function provided by the Piranha detector. As a result, the HVL of the miniature X ray tube was increased around 1.9 times with the added filter mounted on. So we demonstrated that the HVL was suitable for diagnostic X ray system. In the case that the added filter was not mounted on, the HVL obtained from use of the automatic HVL calculation function provided by Piranha detector was 50% higher than the HVL estimated using Al filter. Therefore, the HVL automatic measurement from the Piranha detector cannot be used for the HVL calculation. However, when the added filter was mounted on, the HVL automatic measurement value using the Piranha detector was approximately 15% lower than the estimated value using Al filter. It implies that the HVL automatic measurement can be used to estimate the HVL of the miniature X ray tube with the added filter mounted on without a more complicated measurement method using Al filter. It is expected that the automatic HVL measurement provided by the Piranha detector enables to make kV-X ray characterization easier.