• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.138-140
• /
• 2004

In this study, we develop a remocon inspection automatic system using machine vision technique. By our proposed inspection system, the inspection accuracy and processing time was considerably improved.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.130.2-130
• /
• 2001

In this paper, we suggest an algorithm for the automatic measurement of concentricity and roundness using image processing technique. From the experimental results, we could find that the required measurement accuracy specification is sufficiently satisfied using our proposed method.

• 대한원격탐사학회지
• /
• 제28권4호
• /
• pp.369-392
• /
• 2012

현재까지 초분광영상을 위한 다양한 표적탐지 알고리즘이 개발 및 사용되고 있다. 그러나 표적탐지 알고리즘의 비교 및 검증 기준으로 1~2가지 영상에 적용한 탐지정확도 만을 사용하고 있어, 사용자 입장에서 그 적용성을 평가하는 데에는 한계가 있다. 본 연구의 목적은 초분광영상에 대한 표적탐지 알고리즘의 적용성을 체계적으로 분석하는 것이다. 이를 위하여 표적, 배경, 영상의 분광적 또는 복사적 특성에 관련된 5가지 기준 인자들을 정의하였고, 각 인자의 변이에 따른 6가지 기존 표적탐지 알고리즘의 탐지정확도 변화를 비교하였다. 이와 더불어 영상 크기에 따른 각 알고리즘의 처리시간을 비교하였다. 그 결과 탐지정확도 측면에서는 기준인자에 따라 적용성이 높은 알고리즘의 종류가 다르게 나타났다. 처리시간은 2차 통계값 기반 알고리즘이 다른 알고리즘에 비해 매우 크게 나타났다. 탐지정확도와 처리시간을 종합적으로 고려한 결과 사용하는 영상과 표적 그리고 배경의 특성에 따라 적용성이 높은 알고리즘의 종류가 다른 것으로 나타났다. 따라서 초분광영상에 대한 기존 표적탐지 알고리즘의 적용성은 자료의 특성 및 배경과 표적의 공간적 분광적 관계에 따라 다르게 나타나므로, 사용하는 자료의 특성과 목적에 따라 적용하는 표적탐지 알고리즘의 종류가 달라질 필요가 있다.

• 제어로봇시스템학회논문지
• /
• 제20권2호
• /
• pp.175-179
• /
• 2014

The histogram specification turns the shape of a histogram into that we want to specify. This technique can be applied usefully in various image processing fields such as machine vision. However, the histogram specification technique has its basic limits. For instance, the histogram does not have location information of pixels. Also, the accuracy of the specification drops because of quantization errors of the digitized image. In this paper, we proposed a multiresolution histogram specification method in order to improve the accuracy of specification in terms of resemblance between destination and source image. The experimental results show that the proposed method enhances the accuracy of the specification compared to the conventional methods.

• 대한원격탐사학회지
• /
• 제33권1호
• /
• pp.61-67
• /
• 2017

The detection of oil spills using radar image has been studied extensively. However, most of the proposed techniques have been focused on improving detection accuracy through the advancement of algorithms. In this study, research has been conducted to improve the accuracy of oil spill detection by improving the quality of radar images, which are used as input data to detect oil spills. Thresholding algorithms were used to measure the image improvement both before and after processing. The overall accuracy increased by approximately 16%, the producer accuracy increased by 40%, and the user accuracy increased by 1.5%. The kappa coefficient also increased significantly, from 0.48 to 0.92.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1998년도 춘계학술대회 논문집
• /
• pp.143-147
• /
• 1998

As the accuracy of manufactured goods needed high-accuracy processing has made the efficiency of NC and measurment technology develop, the innovation of machine tools has influence the development of the semi-conductor and optical technology. We can mention that a traction role of the acceleration for the development like that depends on the development of the measurement technics - Stylus instrument method, STM, SEM, Laser interferometer method - which are used for measuring the movement accuracy of machine tools. The movement error factors in movement accuracy are expressed as yaw, roll, and pitch etc. Machining center has 21 movement error factors including of 3 axies joint errors because that has 3 axies and has been measured as the standard of the unloaded condition until now inspite of getting static, dynamic, and servo-gain errors in the case of expending the error range. Therefore, this study tries to measure position accuracy according to loading on the X-Y table of the machining center.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1999년도 추계학술대회 논문집 - 한국공작기계학회
• /
• pp.221-226
• /
• 1999

It can be acquired the high effective productivity through of high speed, precision of machine tools, and then, machine tools will be got a competitive power. Industrially advanced countries already developed that the high speed feed is 50m/min using the high speed ball screw. Also, a lot of problems have happened the feed and servo drive system. It is necessary to study about the character of positioning accuracy, heat generation and high speed/accuracy control for feed/servo drive system of high speed/accuracy. In this study, we make use of high performance vertical machine center with a ball screw of large-scale-lead. Also, we'll apply the high-speed/accuracy control technology in this part of feedforward control, multi-buffering block size, etc. Using the design of the mechanical element and high-speed precision control, the basic design concept can be established.

• 한국생산제조학회지
• /
• 제8권6호
• /
• pp.98-104
• /
• 1999

As the accuracy of manufactured goods needed high accuracy processing has made the efficiency of NC and measurement technology development, the innovation of machine tools has influence the development of the semi-conductor and optical technology. The movement errors can be expressed in terms of yaw, roll an pitch etc. In the case of expanding the error range, static, dynamic and servo gain errors can be included. Machining center might have twenty-one movement errs including three types of joint errors. Those errors have been measured on the condition of just loading of standard table. Regarding these measuring methods, the mechanical compliance of the structure has not been considered. In this paper, therefor, the influences of the additional load on the positioning accuracy are investigated. The results and the techniques proposed in this study can be considered very effective and useful to compensate more correctly the positioning motion.

• 대한의용생체공학회:의공학회지
• /
• 제39권6호
• /
• pp.229-236
• /
• 2018

Liver cancer is one of the highest incidents in the world, and the mortality rate is the second most common disease after lung cancer. The purpose of this study is to evaluate the diagnostic ability of deep learning in the classification of malignant and benign tumors in CT images of patients with liver tumors. We also tried to identify the best data processing methods and deep learning models for classifying malignant and benign tumors in the liver. In this study, CT data were collected from 92 patients (benign liver tumors: 44, malignant liver tumors: 48) at the Gil Medical Center. The CT data of each patient were used for cross-sectional images of 3,024 liver tumors. In AlexNet and VggNet, the average of the overall accuracy at each image size was calculated: the average of the overall accuracy of the $200{\times}200$ image size is 69.58% (AlexNet), 69.4% (VggNet), $150{\times}150$ image size is 71.54%, 67%, $100{\times}100$ image size is 68.79%, 66.2%. In conclusion, the overall accuracy of each does not exceed 80%, so it does not have a high level of accuracy. In addition, the average accuracy in benign was 90.3% and the accuracy in malignant was 46.2%, which is a significant difference between benign and malignant. Also, the time it takes for AlexNet to learn is about 1.6 times faster than VggNet but statistically no different (p > 0.05). Since both models are less than 90% of the overall accuracy, more research and development are needed, such as learning the liver tumor data using a new model, or the process of pre-processing the data images in other methods. In the future, it will be useful to use specialists for image reading using deep learning.

• International Journal of Automotive Technology
• /
• 제6권1호
• /
• pp.53-63
• /
• 2005

We propose a fuzzy neural network (FNN) theory capable of deciding the quality of a road image prior to extracting lane-related information. The accuracy of lane-related information obtained by image processing depends on the quality of the raw images, which can be classified as good or bad according to how visible the lane marks on the images are. Enhancing the accuracy of the information by an image-processing algorithm is limited due to noise corruption which makes image processing difficult. The FNN, on the other hand, decides whether road images are good or bad with respect to the degree of noise corruption. A cumulative distribution function (CDF), a function of edge histogram, is utilized to extract input parameters from the FNN according to the fact that the shape of the CDF is deeply correlated to the road image quality. A suitability analysis shows that this deep correlation exists between the parameters and the image quality. The input pattern vector of the FNN consists of nine parameters in which eight parameters are from the CDF and one is from the intensity distribution of raw images. Experimental results showed that the proposed FNN system was quite successful. We carried out simulations with real images taken in various lighting and weather conditions, and obtained successful decision-making about $99\%$ of the time.