• 전기학회논문지
• /
• 제64권1호
• /
• pp.82-89
• /
• 2015

The researches of image recognition have been processed traditionally. Especially, face recognition technology has been received attractions with advance and applied to various areas according as camera sensor embedded into many devices such as smart phone. In this study, we design and develop a feature vector generation technique of face for making animation caricatures using methods for face detection which are previous stage of face recognition. At first, we detect both face region and detailed eye region of component element by Viola&Johns's realtime detection method which are called as ROI(Region Of Interest). And then, we generate feature vectors of eye region by utilizing factors as opposed to the periphery and by using appearance information of eye. At this point, we focus on the embedded information in many color spaces to overcome the problems which can be occurred by using one color space. We propose a feature vector generation method using information from many color spaces. Finally, we experiment the test of feature vector generation by the proposed method with enough quantity of sample picture data and evaluate the proposed method for factors of estimating performance such as error rate, accuracy and generation time.

• 전자공학회논문지
• /
• 제53권1호
• /
• pp.153-158
• /
• 2016

본 논문에서는 집중호우, 태풍, 허리케인과 같은 자연재해로 인한 낙과된 배 봉지를 자동으로 검출할 수 있는 알고리즘을 구현하였다. 검출 대상인 배 봉지는 글자가 인쇄된 회색 계열로, 수출용 배를 대량으로 생산하는 상주와 나주의 대규모 농원들에서 주로 사용한다. 제안한 알고리즘은 먼저 영상에서 관심영역을 설정하고, 설정한 관심 영역에 대해 유채색 영역을 제거한 후 형태학적 연산을 사용하여 잡음이나 이상 영역을 제거하여 낙과 영역을 검출한다. 이 낙과 영역을 분석하고 계수하여 낙과 피해 규모를 산정한다. 실험영상으로는 2014년 상주와 나주 배농원에서 촬영한 영상을 사용하였다. 제안한 기법은 실험영상에 대해 90% 이상의 검출 성능을 얻었으며, 알고리즘 구성이 간단해서 실시간 하드웨어 적용 및 모바일 디바이스를 활용한 구현도 가능하다.

• 한국정보처리학회논문지
• /
• 제6권12호
• /
• pp.3710-3717
• /
• 1999

무인 자율 주행 시스템의 개발에는 전방의 장애물 검출 및 거리 계산이 필수적이다. 전방 장애물 검출시 입력 영상에는 검출하고자 하는 도로면 상의 물체뿐만 아니라 도로 주변에 가로수, 표지판 둥 관심 외적인 요소들이 함께 존재한다. 이러한 관심 외적인 요소들을 제거하기 위해 탐색 영역을 차선의 안쪽으로 제안시켜 계산 시간을 단축하고 관심의 대상이 되는 물체만 검출하는 것이 필요하다. 본 논문에서는 관심의 대상이 되는 전방 장애물 검출을 위하여, 탐색영역을 제한하는 간단하고 효율적인 차선 검출 알고리즘을 제시한다. 제안된 알고리즘은 Hough 변환을 이용하여 차선으로 추측된 영역에 수평탐색 영역과 2차 곡선의 근사화를 이용하여 정확하게 직선 차선 및 곡률을 지닌 차선을 검출하게 된다. 실험 결과로부터 제안한 알고리즘이 직선의 차선 뿐만 아니라 곡률을 지닌 차선 검출을 효과적으로 수행할 수 있는 실시간 시스템에 적합하다는 것을 보여준다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제10권2호
• /
• pp.74-78
• /
• 2018

Recently, due to decrease hardware prices and the development of technology, analog signage has been changing to digital signage for providing content such as advertisements, videos. Furthermore, in order to provide advertisements and contents to users more effectively, technical researches are being conducted in various industries. In addition, including digital signage that uses displays, it can be seen that it provides advertisements and contents using diverse devices such as LED signage, smart pads, and smart phones. However, most digital signage is installed in one place to provide contents and provides interactivity through simple events such as manual content provision or touch. So, in this paper, we suggest a new object detection algorithm based on an adjacent frames based image correction algorithm for interactive building signage.

• 전기학회논문지
• /
• 제67권12호
• /
• pp.1678-1684
• /
• 2018

Dental caries is one of the most popular oral disease. The aim of automatic dental cavity detection system is helping dentist to make accurate diagnosis. It is very important to separate cavity from the teeth in the detection system. In this paper, We compared two active contour algorithms, Snake and DRLSE(Distance Regularized Level Set Evolution). To improve performance, image is selected ROI(region of interest), then applied bilateral filter, Canny edge. In order to evaluate the algorithms, we applied to 7 tooth phantoms from incisor to molar. Each teeth contains two cavities of different shape. As a result, Snake is faster than DRLSE, but Snake has limitation to compute topology of objects. DRLSE is slower but those of performance is better.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.

• 반도체디스플레이기술학회지
• /
• 제22권4호
• /
• pp.108-112
• /
• 2023

Precision manufacturing technology is rapidly developing due to the extreme miniaturization of semiconductor processes to comply with Moore's Law. Accurate and precise alignment, which is one of the key elements of the semiconductor pre-process and post-process, is very important in the semiconductor process. The center detection of wafer align marks plays a key role in improving yield by reducing defects and research on accurate detection methods for this is necessary. Methods for accurate alignment using traditional image sensors can cause problems due to changes in image brightness and noise. To solve this problem, engineers must go directly into the line and perform maintenance work. This paper emphasizes that the development of AI technology can provide innovative solutions in the semiconductor process as high-resolution image and image processing technology also develops. This study proposes a new wafer center detection method through variable thresholding. And this study introduces a method for detecting the center that is less sensitive to the brightness of LEDs by utilizing a high-performance object detection model such as YOLOv8 without relying on existing algorithms. Through this, we aim to enable precise wafer focus detection using artificial intelligence.

• 한국ITS학회:학술대회논문집
• /
• 한국ITS학회 2006년도 제5회 추계학술대회 및 정기총회
• /
• pp.260-264
• /
• 2006

• Journal of Electrical Engineering and information Science
• /
• 제1권2호
• /
• pp.9-14
• /
• 1996

The goal of this research is to provide a practical algorithm for outlining the left ventricular cavity in digital subtraction angiography. The proposed algorithm is based on the elliptic approximation and ML (Maximum Likelihood) estimate, and it produces a good results regarding execution time, robustness against noise, accuracy, and range of position of ROI (Regions Of Interest).

• 대한핵의학회지
• /
• 제21권1호
• /
• pp.9-16
• /
• 1987

It is well-known that hepatic scintigraphv have been found to be less sensitive and specific in the detection of the diffuse hepatocellular diseases than that of the space-occupying lesions. To obtain the higher diagnostic specificity and sensitivity, we, using the computer quantitation, have attempted to analyze hepatic and extrahepatic $^{99m}Tc-tin$ colloid uptake patterns in various diffuse hepatocellular diseases retrospectively. The studied groups consisted of 116 cases of normal, 67 cases of acute hepatitis, 112 cases of chronic hepatitis, 61 cases of liver cirrhosis, 47 cases of fatty liver, 12 cases of hepatoma and 9 cases of metastasis, making total 424 cases. Scintigraphic imagings were obtained in the anterior, right lateral and posterior projections using high-resolution collimation, and simultaneously these gamma data were acquisited into the computer system. Both large region of interest (ROI) using light pen and ROI computer program were placed over right lobe, left lobe of liver, spleen and cardiac blood pool. Total counts in ROI were divided by the number of pixels in the ROI, and mean count rate per pixels calculated. Mean right-lobe counts were divded by mean-left lobe counts to determine right-to-left hepatic lobe ratio and mean spleen counts were divided by mean liver counts to determine spleen to liver ratio. The results were as follows. 1) Of 424 cases, 292 were male and 132 were female. The majority of age distribution was in $30\sim49$ (54.5%). 2) Inter-observer between two independant operators and inter-method between drawing by light-pen and ROI computer program variations were not significant. 3) The uptake count values (per pixel) determined at each area in normal group were $106.53{\pm}18.35$ in right lobe, $79.00{\pm}13.82$ in left lobe, $17.52{\pm}8.31$ in spleen and $8.09{\pm}3.43$ in cardiac blood pool. 4) In liver cirrhosis, right lobe uptake was decreased but spleen and cardiac blood pool uptakes were increased (p<0.01). 5) Right-to-left hepatic lobe uptake ratio was $1.37{\pm}0.24$ in normal group and significantly low in chronic hepatitis, liver cirrhosis and fatty liver, and more or less low in acute hepatitis. 6) Spleen-to-right hepatic lobe uptake ratio was $0.17{\pm}0.09$ in normal group and high in chronic hepatitis and liver cirrhosis. 7) The computer-quantitation of hepatic and extrahepatic uptake patterns thought to be sensitive and useful method in the interpretation of liver scintigram.