• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.10a
• /
• pp.164-169
• /
• 2002

Recently, LCD(Liquid Crystal Display) is the display product widely used on various fields of industry. This is generally composed of many parts. Among many parts, polarizer film control the intensity of the transmitted light according to the degree of rotation of the polarizer axis. Therefore, this film must be free from defects. But it contains many defects such as the defects caused by dust or different thing, adhesive badness, scratch. Presently, the inspection of these defects is depending on the sight of operator. In this paper, we propose the vision system composed of telecentric lens and optical mirror. This system use the coaxial illumination and the light is specularly reflected on the optical mirror. And we develop the image processing algorithm using the threshold and morphological technique.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.6
• /
• pp.37-42
• /
• 2007

The purpose of this research is stability estimation of plant structure through classification and recognition about welding flaw in SWP(Spiral Welding Pipe). And, In this research, we used nondestructive test based on ultrasonic test as inspection method, and made up 2-axes inspection robot in order to control of ultrasonic probe on the SWP surface, and programmed to image processing and probabilistic neural network(PNN) classifying code by MATLAB programming. Through this process, we proved efficiency on the system of SWP stability Estimation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.4
• /
• pp.247-252
• /
• 2016

In this paper, we propose a new defect detection technology for micro-defect on the surface of steel products. Due to depth and size of microscopic defect, slop of surface and vibration of strip, the conventional optical method cannot guarantee the detection performance. To solve the above-mentioned problems and increase signal to noise ratio, a novel retro-schlieren method that consists of retro reflector and knife edge is proposed. Moreover dual switching lighting method is also applied to distinguish uneven micro defects and surface noise. In proposed method, defective regions are represented by a black and white pattern. This pattern is detected by a defect detection algorithm with Gabor filter. Experimental results by simulator for sample defects of cold rolled steel show that the proposed method is effective.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.789-792
• /
• 2000

Marine chlorella (Nannochloropsis oculata) is cultivated at the fish farming association of experimental fishery laboratory. In the culture of the chlorella, it is necessary to count the number of chlorella in order to understand the condition of increase. For that purpose, we develop automatic chlorella counter using the image processing and the neural network. Its effectiveness is confirmed through the experiment.

• Journal of International Society for Simulation Surgery
• /
• v.1 no.2
• /
• pp.83-86
• /
• 2014

Purpose This paper was purposed to suggest the method to produce the supportive helmet (head correction) for the infants who are suffering from plagiocephaly and to evaluate the level of transformation through 3D model. Method Either of CT or X-ray restored images has been used in making the supportive helmet (Head correction) in general, but these methods of measuring have problems in cost and safety. 3D surface measurement technology was suggested to solve such matters. Results It was to design the transformed model of the head within 0.7cm in average by scanning the surface of head and performing 3D restoration with marching cube and the changing rate of the head was compared in numerical data with 3D model. Conclusion The suggested methods displayed the better performance than the conventional method in respect of the speed and cost.

• Journal of Communications and Networks
• /
• v.7 no.1
• /
• pp.65-75
• /
• 2005

In this paper, we consider a scenario in which the source has been offered QoS guarantees subject to token-bucket regulation. The rate of the source should be controlled such that it conforms to the token-bucket regulation, and also the distortion obtained is the minimum. We have developed an optimal scheduling algorithm for offline (like pre-recorded video) sources with convex distortion function and which can not tolerate any delay. This optimal offline algorithm has been extended for the real-time online source by predicting the number of packets that the source may send in future. The performance of the online scheduler is not substantially degraded as compared to that of the optimal offline scheduler. A sub-optimal offline algorithm has also been developed to reduce the computational complexity and it is shown to perform very well. We later consider the case where the source can tolerate a fixed amount of delay and derive optimal offline algorithm for such traffic source.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1990.10a
• /
• pp.23-25
• /
• 1990

In this paper, a system to measure tree degradation of three dimensional phenomena in organic insulating materials using image processing system is discussed. Using a computerized tomography method, volume of tree immediately after tree initiation, as well as changes in the configuration of the tree were measured, which up to now have been difficult to measure. The specimens used an acrylic acid resin. As a result, it was possible to record the cross sections of the tree, and to describe the volume of the tree by the three dimensional measurement.

• Journal of Sensor Science and Technology
• /
• v.29 no.6
• /
• pp.427-432
• /
• 2020

The most lethal foreign body in meat is a needle, and X-ray images are used to detect it. However, because the difference in thickness and fat content is severe depending on the type of meat and the part of the meat, the shade difference and contrast appear severe. This problem causes difficulty in automatic classification. In this paper, we propose a method for generating training patterns by efficient pre-processing and classifying needles in meat using a convolution neural network. Approximately 24000 training patterns and 4000 test patterns were used to verify the proposed method, and an accuracy of 99.8% was achieved.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.346-348
• /
• 2003

In this study, we attempted to estimate the discharge of the Amazon River branches from JERS-1/SAR images, which are independent of the weather. We visualized some traces of the Amazon River branches, transformed river shapes into a one-dimensional signal, and calculated the characteristics of the river shapes such as the meandering wavelength and the amplitude with Fourier and wavelet analysis. Then, we related the characteristics of the river shapes with the existing discharge data and derived some regression equations. Finally, we estimated the discharge of the Amazon River branches from the SAR images.

• Archives of Plastic Surgery
• /
• v.32 no.5
• /
• pp.582-588
• /
• 2005

Digital imaging is emerging as a standard method for patient documentation in clinical setting. Managing patient expectations before aesthetic surgery can greatly improve patient satisfaction after surgery. The patient who visited for plastic surgery wants a predicted figure after the operation. A virtual plastic surgery software is necessary in order to satisfy the desire of patients. Adobe $Photoshop^{(R)}$ is the professional standard in desktop digital imaging, offers indispensable new features for graphic and web design, photography, and video. Using imaging technology, it takes just minutes to realistically simulate the results of double eyelid operation, liposuction, rhinoplasty or any other aesthetic procedure. The aim of this study is to analyze the significance of the digital image processing and to introduce the virtual plastic surgery using Adobe $Photoshop^{(R)}$.