• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.805-807
• /
• 2011

In this paper, we propose a method to inspect defects of injection molded automotive parts. In order to inspect them, we developed and used a line detection algorithm and a defect analysis algorithm. The line detection algorithm defines center point of a laser line and the inspection algorithm determines the defects of automotive parts using pattern data of inspected objects and the data results from the line detection algorithm. We evaluated the accuracy and the processing time of inspection and they showed good performance.

• Journal of Industrial Technology
• /
• v.38 no.1
• /
• pp.41-52
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.4
• /
• pp.79-86
• /
• 2007

The shape of excessive penetration mainly depends on welding conditions(welding current and welding voltage), and welding process(groove gap and welding speed). These conditions are the major affecting factors to width and height of back bead. In this paper, back-bead prediction and weldability estimation using artificial neural network were investigated. Results are as follows. 1) If groove gap, welding current, welding voltage and welding speed will be previously determined as a welding condition, width and height of back bead can be predicted by artificial neural network system without experimental measurement. 2) From the result applied to three weld quality levels(ISO 5817), both experimented measurement using vision sensor and predicted mean values by artificial neural network showed good agreement. 3) The width and height of back bead are proportional to groove gap, welding current and welding voltage, but welding speed. is not.

• Journal of Technologic Dentistry
• /
• v.27 no.1
• /
• pp.65-71
• /
• 2005

Experimental Ti-13%Zr and Ti-13%Zr-5%Cu alloys were made in an argon-arc melting furnace. The grade 2 CP Ti was used to control. The alloys were cast into phosphate bonded $SiO_2$ investment molds using an argon-arc casting machine, and The hardness and microstructures of the castings were investigated in order to reveal their possible use for new dental casting materials and to collect useful data for alloy design. The hardness of the Ti-13%Zr-5%Cu alloy(379Hv) became higher than that of Ti-13%Zr(317Hv) alloy, and the hardness of this alloys became higher than that of CP Ti(247Hv). Increasing in the hardness of the Ti-13%Zr-5%Cu alloy was considered to be solid solution hardening as the Ti-Zr system shows a completely solid solution for both high temperature $\beta$phase and low temperature $\alpha$ phase and also the inclusion of the eutectoid structure($\alpha Ti+Ti_{2}Cu$). No martensitic structures are observed in the specimen made of CP Ti, but Ti-13%Zr and Ti-13%Zr-5%Cu alloys show a kind of martensitic structure. Ti-13%Zr-5%Cu shows the finest microstructure. From these results, it was concluded that new alloys for dental casting materials should be designed as Ti-Zr-Cu based alloys.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.755-764
• /
• 1996

A multispectral imaging system with selected wavelength optical filter was demonstrated feasible for food safety inspection. Intensified multispectral images of carcasses were obtained with visible/near-infrared optical filters(542-847 nm wavelengths) and analyzed. The analysis of textural features based on co-occurrence matrices was conducted to determine the feasibility of a multispectral image analyses for discriminating unwholesome poultry carcasses from wholesome carcasses. The mean angular second moment of the wholesome carcasses scanned at 542 nm wavelength was lower than that of septicemic (P$\leq$0.0005) and cadaver(P$\leq$0.0005) carcasses. On the other hand, for the carcasses scanned at 700nm wavelength , the feature values of septicemic and cadaver carcasses were significantly (P$\leq$0.0005) different from wholesome carcasses. The discriminant functions for classifying poultry carcasses into three classes (wholesome, septicemic , cadaver) were developed using linear and quadr tic covariance matrix analysis method. The accuracy of the quadratic discriminant models, expressed in rates of correct classification, were over 90% for the classification of wholesome, septicemic, and cadaver carcasses when textural features from the spectral images scanned at the wavelength of 542 and 700nm were utilized.

• International Journal of Precision Engineering and Manufacturing
• /
• v.5 no.1
• /
• pp.27-35
• /
• 2004

In the field of machine vision using a single camera mounted on a mobile robot, although the detection and tracking of moving objects from a moving observer, is complex and computationally demanding task. In this paper, we propose a new scheme for a mobile robot to track and capture a moving object using images of a camera. The system consists of the following modules: data acquisition, feature extraction and visual tracking, and trajectory generation. And a single camera is used as visual sensors to capture image sequences of a moving object. The moving object is assumed to be a point-object and projected onto an image plane to form a geometrical constraint equation that provides position data of the object based on the kinematics of the active camera. Uncertainties in the position estimation caused by the point-object assumption are compensated using the Kalman filter. To generate the shortest time trajectory to capture the moving object, the linear and angular velocities are estimated and utilized. The experimental results of tracking and capturing of the target object with the mobile robot are presented.

• Journal of Biosystems Engineering
• /
• v.22 no.2
• /
• pp.137-150
• /
• 1997

To investigate the feasibility of a boom sprayer in the paddy field, an experimental boom sprayer for both broadcast and directed spraying to the lower part of rice plants was developed. The droplet deposition characteristics of the boom sprayers were experimentally compared to those of power sprayer. Water sensitive papers(WSP) and a machine vision system were used to evaluate the coverage rate and droplet density. It was shown that the broadcast application by the boom sprayer was the best coverage among the tested sprayers. Coverage tate and droplet density were affected by the distance between nozzles and the sprayer ground speed, The best result was obtained when the distance of 30cm and the speed of 1.7km/hr. The directed application showed inconsistency in overall droplet distribution. The inconsistency was judged to be caused by conflict between plants and boom extenders. The power sprayer showed a very wide range of droplet size distribution, relatively larger droplets and inconsistency in cove The power sprayer was judged to be inadequate for the low-volume precision application because of inconsistency in performance and difficulty in adjusting the spraying rate. Based on the droplet coverage characteristics, it was concluded that the self-propelled boom sprayer for the broadcast application was feasible for an alternative to the power sprayer in case of low volume, precision application in paddy condition.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.304-308
• /
• 2005

본 연구는 발포수지 공정에 사용되는 가스벤트를 신발중창 금형에 자동으로 교환하는 장치에 관한 것이다. 가스벤트는 폴리우레탄과 같은 소재를 이용한 신발 미드솔 발포시 발생되는 가스를 제거하기 위한 다공질 소자로서 신발금형 상부에 삽입된다. 가스벤트는 소모성 부품으로 일정주기마다 교환이 필요하나 작업공정상 수작업에 어려움이 많아 자동화된 교환시스템이 요구된다. 하지만 삽입되는 신발중창 금형과 가스벤트간은 유격이 거의 없으므로 본 연구에서는 신발 중창 금형의 손상을 방지하고 보다 신속한 교환을 위해 가스벤트 삽입 및 추출 홈의 위치정보를 영상을 통해서 구하고, 얻어진 영상에 대한 위치 데이터를 기계적 위치 추적 시스템의 데이터로 피드백 하여 홀의 중심 위치에서 가스벤트를 삽입 및 추출하여 자동으로 교환하는 장치를 구현하였다. 영상 처리는 패턴 매칭 기법을 이용하여 홀의 중심점을 구하였고, 이를 PLC로 전송하여 기계 작동 제어 및 XY플로터를 정밀 제어하여 공정이 진행되게 하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.58-63
• /
• 2022

Recently, the improvement of computational processing ability due to the rapid development of computing technology has greatly advanced the field of artificial intelligence, and research to apply it in various domains is active. In particular, in the national defense field, attention is paid to intelligent recognition among machine learning techniques, and efforts are being made to develop object identification and monitoring systems using artificial intelligence. To this end, various image processing technologies and object identification algorithms are applied to create a model that can identify friendly and enemy weapon systems and personnel in real-time. In this paper, we conducted image processing and object identification focused on tanks among various weapon systems. We initially conducted processing the tanks' image using a convolutional neural network, a deep learning technique. The feature map was examined and the important characteristics of the tanks crucial for learning were derived. Then, using YOLOv5 Network, a CNN-based object detection network, a model trained by labeling the entire tank and a model trained by labeling only the turret of the tank were created and the results were compared. The model and labeling technique we proposed in this paper can more accurately identify the type of tank and contribute to the intelligent recognition system to be developed in the future.