• Journal of the Korea Computer Industry Society
• /
• v.3 no.7
• /
• pp.901-914
• /
• 2002

In this paper, We propose an efficient automatic caption detection and location method, caption recognition using FE-MCBP(Feature Extraction based Multichained BackPropagation) neural network for content based retrieval of video. Frames are selected at fixed time interval from video and key frames are selected by gray scale histogram method. for each key frames, segmentation is performed and caption lines are detected using line scan method. lastly each characters are separated. This research improves speed and efficiency by color segmentation using local maximum analysis method before line scanning. Caption detection is a first stage of multimedia database organization and detected captions are used as input of text recognition system. Recognized captions can be searched by content based retrieval method.

• Journal of the Korean Society of Radiology
• /
• v.17 no.7
• /
• pp.1049-1055
• /
• 2023

The purpose of this study was to investigate the association of twinkling artifacts according to the types of urinary stones in color Doppler ultrasound. For two types of urinary stones with different colors, the degree of occurrence of color Doppler twinkling artifact in water tank was analyzed, and the surface condition and composition of the stones were analyzed. The composition of Calcium and phosphorus were the most frequent components in white and brown stones excluding carbon and oxygen. Twinkling artifacts of color Doppler appear stronger in brown stone. The higher the phosphorus content of the stones, the shorter the twinkling artifact appears, so it is possible to predict the main composition of stones.

• Journal of Sensor Science and Technology
• /
• v.11 no.2
• /
• pp.93-101
• /
• 2002

The quality of agricultural products is classified with various factors which are measured and determined by destructive and/or nondestructive method. NIR spectrum analysis method is used to determine internal qualities such as a brix and an acidity. CCD color camera is used to measure external quality like color and a size of fruit. Today, nondestructive methods are widely researched. The quality and the grade of fruit loaded into a cup automatically and measured in real time by camera and NIR system is determined by infernal and external factors. This paper proposes modified boundary tracking algorithm which detects the contour of fruit's color image and make chain code faster than conventional method. The chain code helps compute a size of fruit image and find multiple loading of a fruit in single cup or fruit between two cups. The designed classification system sorts a citrus at speed of 8 fruit/s, with evaluating a brix, an acidity and a size grade.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.10a
• /
• pp.243-247
• /
• 1998

전자현미경 영상인 유방암 조직세포의 암 분포 정도를 알기 위해, 조직세포중 암이 퍼진 부분과 그렇지 않은 부분에 대해 정량적 분석과 세포수에 의한 분석을 비교하여 보았다. 유방암 조직세포의 면역조직화함염색에서 암이 있는 세포핵은 갈색으로 나타났고, 그렇지 않은 세포는 푸른색으로 나타났다. 이것은 환자를 진단하고 예지하는데 있어서 중요한 요인으로 작용하지만 지금까지는 의사의 주관적인 생각이 다분히 포함된 판단에 의존할 수 밖에 없었다. 의료영상이미지의 시각적 표현을 위해 RGB칼라를 HLS칼라로 변환하여 사용하였으며, 이것은 시각적으로 좀 더 쉽게 갈색세포핵과 푸픈색 세포핵을 구분하게 해 주었다. 두 세포핵을 분리하기 위해 히스트그램의 임계치와 Box classification의 두 알고리즘의 사용하여 추출하였다. 그리고 추출한 세포핵들에 대해 각각 정량적인 분석과 세포수에 의한 분석을 하였다. 이러한 실험은 시각적 병리정밀검사에 좋은 보조도구로 사용될 수 있을 것이다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.494-496
• /
• 1999

본 논문에서는 SV(Support Vector Machine)과 3단의 칼라 원형 조명장치를 이용한 효율적인 납땜 검사 시스템을 제안한다. 원형 조명장치를 이용하여 납땜부의 표면의 경사도에 의해서 생기는 명암의 분포로부터 납땜 검사를 위한 특징값을 추출한다. SVM은 추출된 특징값을 이용하여 납땜 영상을 정의된 타입중의 하나로 분류한다. SVM은 두 부류의 경계를 최대로 하는 최적경계를 학습하므로 납땜 영상과 같이 각 부류의 경계가 모호한 문제에 대해서 적은 수의 학습 데이터를 사용해도 우수한 성능을 나타낸다. 제안된 시스템은 현산업에서 사용되고 있는 다양한 표면실장형 부품에 대해서 적용해 본 결과 적은 학습 데이터에도 효율적으로 적용될 수 있음을 보였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.607-609
• /
• 2000

본 논문에서는 SVM(Support Vector Machine)과 3단의 칼라 원형 조명장치를 이용한 효율적인 납땜 검사시스템을 제안한다. 원형 조명장치를 이용하여 납땜부의 표면의 경사도에 의해서 생기는 명암의 분포로부터 납땜 검사를 위한 특징값을 추출한다. SVM은 추출된 특징값을 이용하여 납땜 영상을 정의된 타입중의 하나로 분류한다. SBM은 두 부류의경계를 최대로 하는 최적경계를 학습하므로 납땜 영상과 같이 각 부류의 경계가 모호한 문제에 대해서 적은 수의 학습 데이터를 사용해도 우수한 성능을 나타낸다. 제안된 시스템은 현산업에서 사용되고 있는 다양한 표면실장형 부품에 대해서 적용해 본 결과 적은 학습 데이터에도 효율적으로 적용될 수 있음을 보였다.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.22 no.49
• /
• pp.135-142
• /
• 1999

The objective of this paper is to provide an automatic color image testing system capable of synthetically testing a color element like a color tone and a luminance for a color image displayed on the screen, using a CCD camera and a microprocess. The system consists of a CCD camera, a line conveyor, a camera driving part, a remocon, a remote sensing part, a display and a PC including a color vision board and a CPU board. By applying the system to a process, reliability for a testing result can be improved and the absolute criterion to judge a part can be made.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.587-591
• /
• 2001

This paper deals with inspect algorithm using visual system. One of the major problems that arise during polymer production is the estimation of the noise of the color product.(bad pallets) An erroneous output can cause a lot of losses (production and financial losses). Therefore new methods for real-time inspection of the noise are demanded. For this reason, we have presented a development of vision system algorithm for the defect inspection of PE color pallets. First of all, in order to detect the edge of object, the differential filter is used. And we apply to the labelling algorithm for feature extraction. This algorithm is designed for the defect inspection of pallets. The labelling algorithm permits to separate all of the connected components appearing on the pallets. Labelling the connected regions of a image is a fundamental computation in image analysis and machine vision, with a large number of application. Also, we suggested vision processing program in window environment. Simulations and experimental results demonstrate the performance of the proposal algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.

• Korean Journal of Veterinary Research
• /
• v.41 no.3
• /
• pp.413-419
• /
• 2001

This study was performed to evaluate the renal hemodynamics using color Doppler ultrasonography in dogs with unilateral experimental hydronephrosis treated with transarterial embolization of the renal artery (TAE-RA). Experimental hydronephrosis was induced by ligation of unilateral ureter in 12 dogs. The mean resistive index (RI) value of kidney was significantly increased at 4, 9, 17 days after ligation of ureter. Unilateral hydronephrosis was established in 12 dogs at 17 days after ligation of ureter. Renal artery embolization was performed using selective catheterization in the hydronephrotic kidney of seven dogs and EKG, $SpO_2$body temperature, pulse, and respiratory rate were within normal ranges during procedures. There were no dogs expired after TAE-RA and no side effects associated with regurgitation of iohexol-ethanol solution. In color Doppler ultrasonographic findings, there was no blood flow into the embolized kidneys treated by TAE-RA, however, blood flow signal was found in contralateral normal kidney of dogs treated with TAE-RA compared to that of normal kidney in normal control group. It is concluded that TAE-RA does not affect the hemodynamics of contralateral normal kidney in dogs with experimental hydronephrosis and color Doppler ultrasonography is simple and non-invasive modality for the monitoring of the revascularization of the renal artery after TAE-RA.