• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.5
• /
• pp.423-431
• /
• 2016

In general LPR(License Plate Recognition) in outdoor image is not so simple differently from in the image captured from manmade environment, because of geometric shape distortion and large illumination changes. this paper proposes three techniques for LPR in outdoor images captured from CCTV. At first, a serially connected multi-stage Adaboost LP detector is proposed, in which different complementary features are used. In the proposed detector the performance is increased by the Haar-like Adaboost LP detector consecutively connected to the MB-LBP based one in serial manner. In addition the technique is proposed that makes image processing easy by the prior determination of LP type, after correction of geometric distortion of LP image. The technique is more efficient than the processing the whole LP image without knowledge of LP type in that we can take the appropriate color to gray conversion, accurate location for separation of text/numeric character sub-images, and proper parameter selection for image processing. In the proposed technique we use DBN(Deep Belief Network) to achieve a robust character recognition against stroke loss and geometric distortion like slant due to the incomplete image processing.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.473-478
• /
• 2005

The gastric cancer takes the great part of the cancer occurrence and the mortality from cancer in Korea, and the early detection of gastric cancer is very important in the treatment and convalescence. This paper. for the early detection of gastric cancer, Proposes the analysis system of endoscopic image of the stomach that detects the abnormal region by using the change of color in the image and provides the surface tissue information to the detector. While the advanced inflammation and the cancer may be easily detected, the early inflammation and the cancer have a difficulty in detection and require the more attention lot detection. This paper, at first, converts the endoscopic image to the Image of IHb(Index of Hemoglobin) model and removes noises incurred by illumination, and next, automatically detects the regions suspected as cancer and provides the related information to the detector, or provides the surface tissue information for the regions appointed by the detector. This paper does not intend to provide the final diagnosis of the detected abnormal regions as gastric cancer, but provides the supplementary mean that reduces the load and mistaken diagnosis of the detector by automatically detecting the abnormal regions being not easily detected by human eyes and providing the additional information for the diagnosis. The experiments using practical endoscopic images for performance evaluation showed that the proposed system is effective in the analysis of endoscopic image of the stomach.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.162-177
• /
• 2020

The perception of traffic environment based on various sensors in autonomous driving system has a direct relationship with driving safety. Recently, as the perception model based on deep neural network is used due to the development of machine learning/in-depth neural network technology, a the perception model training and high quality of a training dataset are required. However, there are several realistic difficulties to collect data on all situations that may occur in self-driving. The performance of the perception model may be deteriorated due to the difference between the overseas and domestic traffic environments, and data on bad weather where the sensors can not operate normally can not guarantee the qualitative part. Therefore, it is necessary to build a virtual road environment in the simulator rather than the actual road to collect the traning data. In this paper, a training dataset collection process is suggested by diversifying the weather, illumination, sensor position, type and counts of vehicles in the simulator environment that simulates the domestic road situation according to the domestic situation. In order to achieve better performance, the authors changed the domain of image to be closer to due diligence and diversified. And the performance evaluation was conducted on the test data collected in the actual road environment, and the performance was similar to that of the model learned only by the actual environmental data.

• Journal of Hydrogen and New Energy
• /
• v.23 no.4
• /
• pp.364-372
• /
• 2012

Transient mixing states of two different fuel oils, dimethylformamide (DMF) oil and JetA1 oil, were investigated by using a color image processing and a neural network. A tank ($D{\times}H$, $310{\times}370mm$) was filled with JetA1 oil. The DMF oil was filled at a top tank, and was mixed with the JetA1 oil in the tank mixing tank via a sudden opening which was performed by nitrogen gas with 1.9 bar. An impeller was rotated with 700 rpm for mixing enhancements of the two fuel oils. To visualize the mixing state of the DMF oil with the JetA1 oil, the DMF oil was coated with Rhodamine B whose color was red. A LCD monitor was used for uniform illumination. The color changes of the DMF oil were captured by a camcoder and the images were transferred to a host computer for quantifying the information of color changes. The color images of two mixed oils were captured with the camcoder. The R, G, B color information of the captured images was used to quantify the concentration of the DMF oil. To quantify the concentration of the DMF oil in the JetA1 oil, a calibration of color-to-concentration was carried out before the main experiment was done. Transient mixing states of DMF oil with the JetA1 oil since after the sudden infiltration were quantified and characterized with the constructed visualization technique.

• Korean Journal of Optics and Photonics
• /
• v.4 no.1
• /
• pp.15-21
• /
• 1993

This paper describes the design and development of a KrF excimer laser stepper and discusses the detailed system parameters and characterization data obtained from the performance test. We have developed a deep UV step-and-repeat system, operating at 248 nm, by retrofitting a commercial modules such as KrF excimer laser, precision wafer stage and fused silica illumination and 5X projection optics of numerical aperture 0.42. What we have developed, to the basic structure, are wafer alignment optics, reticle alignment system, autofocusing/leveling mechanisms and environment chamber. Finally, all these subsystem were integrated under the control of microprocessor-based controllers and computer. The wafer alignment system comprises the OFF-AXIS and the TTL alignment. The OFF-AXIS alignment system was realized with two kinds of optics. One is the magnification system with the image processing technique and the other is He-Ne laser diffraction type system using the alignment grating on the wafer. 'The TTL alignment system employs a dual beam inteferometric method, which takes advantages of higher diffraction efficiency compared with other TTL type alignment systems. As the results, alignment accuracy for OFF-AXIS and TTL alignment system were obtained within 0.1 $\mu\textrm{m}$/ 3 $\sigma$ for the various substrate on the wafers. The wafer focusing and leveling system is modified version of the conventional systems using position sensitive detectors (PSD). This type of detection method showed focusing and leveling accuracies of about $\pm$ 0.1 $\mu\textrm{m}$ and $\pm$ 0.5 arcsec, respectively. From the CD measurement, we obtained 0.4 $\mu\textrm{m}$ resolution features over the full field with routine use, and 0.3 $\mu\textrm{m}$ resolution was attainable under more strict conditions.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.28 no.9
• /
• pp.343-349
• /
• 2016

Due to the recent increase in lighting energy consumption in buildings, there are a growing number of studies seeking solutions this problem. The effectiveness of light-shelves as natural lighting systems to solve this problem has been recognized, and various studies regarding such systems are being carried out currently. However, the lighting efficiency of light-shelves decreases if illumination intensity is low-such as at night time, and it also obstructs the views of building occupants. Therefore, the purpose of this study is to examine a movable drawer type light-shelf which allows for the width of the reflector to be adjusted and verify its performance through a simulated test-bed. The following conclusions were reached. 1) The purpose of this study is to solve the problem previously associated with the light-shelf system- of obstructed views-by responding to external environments and minimizing the width of the light-shelf at night time when the efficiency of the light-shelf declines. 2) The proper variables of the movable drawer type light-shelf which enables the width adjustment of the reflector were ascertained in this study according to four solar terms : a width of 0.6 m at an angle of $20^{\circ}$, a width of 0.4m with an angle of $20^{\circ}$, and a width of 0.1 m with an angle of $20^{\circ}$ were determined for the summer solstice, fall/spring equinoxes, and winter solstice respectively; revealing that width adjustment of the light-shelf is a significant factor. 3) The movable drawer type light-shelf which enables${\backslash}$width adjustment of the reflector suggested in this study can reduce the lighting energy consumption by 18.7% and 14.3% in comparison to previous light-shelves with a fixed width of 0.3 m and 0.6m, indicating that it is effective for saving energy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.3
• /
• pp.359-364
• /
• 2011

The study uses department of the sensitivity and fuzzy reasoning, one of artificial intelligence algorithms, so that develop LED lighting system based on fuzzy reasoning for systematical control of the LED color temperature. In the area of sensitivity engineering, by considering the relation between color and emotion expressed as an adjective word, the corresponding sensitivity word can be determined, By taking into consideration the relation between the brain wave measured from the human brain and the color temperature, the preferred lesson subject can be determined. From the decision of the sensitivity word and the lesson subject, we adjust the color temperature of RGB (Red, Green, Blue) LED. In addition, by using the information of the latitude and the longitude from GPS(Global Positioning System), we can calculate the on-line moving altitude of sun. By using the sensor information of both temperature and humidity, we can calculate the discomfort index. By considering the altitude of sun as well as the value of the discomfort index, the illumination of W(white) LED and the color temperature of RGB LED can be determined. The (LED) sensitivity lighting control system is bulit up by considering the sensitivity word, the lesson subject, the altitude of sun, and the discomfort index The developed sensitivity lighting control system leads to more suitable atmosphere and also the enhancement of the efficiency of lesson subjects as well as business affairs.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.1
• /
• pp.1-8
• /
• 2009

The objective of this study is to design a system that automatically monitors the state of interior spaces like offices where lots of people are coming and going through image data and environment data, which includes temperature, humidity, and other conditions, and implement and test related application programs. In practice, there are lots of image data automatically obtained by unmanned equipments, such as certain types of CCTVs, for monitoring situation in usual interior spaces. This image data can be used as a more effective manner by establishing a system that recognizes situation in specific interior spaces based on the relationship between image and environment data. For instance, it is possible to perform unmanned on/off controls for various electronic equipments, such as air conditioners, lights, and other devices, through analyzing the data acquisited from environment sensors (temperature, humidity, and illumination) as dynamic states are not maintained for a specified period of time. For implementing these controls, this study analyzes environment data acquisited from temperature and humidity sensors and image data input from wireless cameras to recognize situation and that can be used to automatically control environment variables configured by users. Experiments were applied in a laboratory where unmanned controls were effectively performed as automatic on/off controls for the air conditioner and lights installed in the laboratory as certain motions were detected or undetected for a specified period of time.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.1
• /
• pp.29-38
• /
• 2005

The fluid animation procedure consists of physical simulation and visual rendering. In the physical simulation of fluids, the most frequently used practices are the numerical simulation of fluid particles using particle dynamics equations and the continuum analysis of flow via Wavier-Stokes equation. Particle dynamics method is fast in calculation, but the resulting fluid motion is conditionally unrealistic The method using Wavier-Stokes equation, on the contrary, yields lifelike fluid motion when properly conditioned, yet the complexity of calculation restrains this method from being used in real-time applications. Global illumination is generally successful in producing premium-Duality rendered images, but is also excessively slow for real-time applications. In this paper, we propose a rapid fluid animation method incorporating enhanced particle dynamics simulation method and pre-integrated volume rendering technique. The particle dynamics simulation of fluid flow was conducted in real-time using Lennard-Jones model, and the computation efficiency was enhanced such that a small number of particles can represent a significant volume. For real-time rendering, pre-integrated volume rendering method was used so that fewer slices than ever can construct seamless inter-laminar shades. The proposed method could successfully simulate and render the fluid motion in real time at an acceptable speed and visual quality.