• Journal of Digital Contents Society
• /
• v.14 no.2
• /
• pp.275-282
• /
• 2013

In medical image processing field, object recognition is usually carried out by computerized processing of various input information such as brightness, shape, and pattern. If the information mentioned does not make sense, however, many limitations could occur with object recognition during computer processing. Therefore, this paper suggests effective object recognition method based on the magnetic resonance (MR) theory to resolve the basic limitations in computer processing. We propose the efficient method of robust gray-white matter segmentation by texture analysis through the Susceptibility Weighted Imaging (SWI) for contrast enhancement. As a result, an average area difference of 5.2%, which was higher than the accuracy of conventional region segmentation algorithm, was obtained.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.1
• /
• pp.42-50
• /
• 2016

Recently, researches about the communication between LED array and the camera (alias 'Visual-MIMO'), have been actively conducted, and the application to the vehicle and a smart phone is expected to be maximized. Since the bit error may occur if the ISI is severe in a LED array, it is necessary to switch from the multiplexing to the diversity mode. In this paper, according to the use or not of a reference array pattern, a method for determining the transition time to the diversity mode is suggested and verified. When using the reference pattern, it determines the transition time to the diversity mode from the multiplexing using the brightness information of the received image. If the reference array pattern is not used, the size of LED array compared to the entire image according to the distance is used and the size of the LED array at the distance of a severe ISI may be used for the determination of transition time to the diversity. Finally, the proposed method is verified through the simulation and hardware experiments as well as by analyzing the performance in accordance with the ISI level and the distance.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.681-688
• /
• 2002

This paper proposes a system detecting the area of traffic sign, which uses color rate as the information of colors, and corner point and distance rate as the information of morphology. In this system, a candidate area is extracted by performing dilation operation on the binary image made by the color rate of R, G, B components and by detecting corner point and center point through mask. The area of traffic sign with varied shapes is extracted by calculating the distance rate from center point, which is the information of morphology. The results of this experiment demonstrate that in this system which is invariable regardless of its size and location, it is possible to extract the exact area from varied traffic signs such as the shapes of triangle, circle, inverse triangle, and square as well as from the images at both day and night when brightness value is greatly different. Moreover, it demonstrates great accuracy and speed in processing.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3683-3693
• /
• 1999

Most recognition methods of car licence plate have difficulties concerning plate recognition rates and system stability in that restricted car images are used and good image capture environment is required. To overcome these difficulties, I proposed a new recognition method of car licence plates, in which both intensity variation and color information are used. For a captured car image, multiple candidate plate-bands are extracted based on the number of intensity variation. To have an equal performance on abnormally dark and bright Images. plate lightness is calculated and adjusted based on the brightness of plate background. Candidate plate regions are extracted using contour following on plate color pixels in oath plate band. A candidate region is decided as a real plate region after extracting character regions and then recognizing them. I recognize characters using template matching since total number of possible characters is small and they art machine printed. To show the efficiency of the proposed method, I tested it on 200 car images and found that the method shows good performance.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2000.02a
• /
• pp.211-211
• /
• 2000

Carbon nanotubes (CNTs) have been spotlighted as one of promising field emission displays(FEDs). For the first time, to authors knowledge, we have developed the 9" color CNT-FEDs with the resolution of 240x576 lines. The 9" CNT-FEDs with diode-type and triode-type structures are presented. The well-dispersed CNT paste was squeezed onto the metal-patterned cathode glass. For the anode plate, the Y2O2S:Eu, ZnS:Ag,Cl low-voltage phosphors were printed for red, green, and blue colors, respectively. The vacuum-packaged panel maintained the vacuum level of 1x10-7 Torr. The uniform moving images vacuum-packaged panel maintained the vacuum level of 1x10-7 Torr. The uniform moving images were demonstrated at 2 V/um. High brightness of 800, 200, and 150cd/m2 was observed on the green, red, and blue phosphors at V/um, respectively. Field emission characteristics of a triode-type CNT-FED were simulated using a finite element method. the resultant field strength on the cathode was modulated by gate bias and emitted electrons were focused on the anode. A relatively uniform emission image was experimentally achieved at the 800V anode. A relatively uniform emission image was experimentally achieved at the 800V anode and the 50-180 V gate biases. Energy distribution of electrons emitted from CNTs was measured using an energy analyzer. The maximum peak of energy curve corresponded to the Fermi energy level of CNTs. The whole fabrication processed of CNT-FEDs were fully scalable and reproducible. Our CNT-FEDs has demonstrated the high potential of large-area and full-color applications with very low cost fabrication and low power consumption.

• Journal of Biomedical Engineering Research
• /
• v.27 no.5
• /
• pp.250-259
• /
• 2006

The information of eye movement is used in various fields such as psychology, ophthalmology, physiology, rehabilitation medicine, web design, HMI(human-machine interface), and so on. Various devices to detect the eye movement have been developed but they are too expensive. The general methods of eye movement tracking are EOG(electro-oculograph), Purkinje image tracker, scleral search coil technique, and video-oculograph(VOG). The purpose of this study is to embody the algorithm which tracks the location of the gazing point at a pupil. Two kinds of location data were compared to track the gazing point. One is the reference points(infrared LEDs) which is effected from the globe. Another is the center point of the pupil which is gained with a CCD camera. The reference point was captured with the CCD camera and infrared lights which were not recognized by human eyes. Both of images which were thrown and were not thrown an infrared light on the globe were captured and saved. The reflected reference points were detected with the brightness difference between the two saved images. In conclusion, the circumcenter theory of a triangle was used to look for the center of the pupil. The location of the gazing point was relatively indicated with the each center of the pupil and the reference point.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.4
• /
• pp.161-168
• /
• 2006

In this paper, we propose a method for the pattern inspection of LCD module using the color compensation and pattern matching. The pattern matching is generally used for the inspection method of LCD module at the industry. LCD module has many defections such as the brightness difference of the back light, the optic feature of liquid crystal, the difference of the light penetrated by driving LCD and the color difference by the lighting. The conventional method without the color compensation can not solve these defections and decreases the efficiency of inspecting LCD module. The method proposed to inspect defective badness through the pattern matching after it compensated color difference of the LCD occurred by the various causes. At first, it revises with setting by standard tone of color with the LCD pattern of the reference image. And It perform the preprocessing and pattern matching algorithm on the compensated image. In experiment, we confirmed that this algorithm is useful to detect some defections of LCD module. The proposed methods was easy to detect the faulty product.

• Korean Journal of Remote Sensing
• /
• v.26 no.4
• /
• pp.439-449
• /
• 2010

This paper reports experiments and analysis work done to find out the cause of Y parallex for stereo pairs of KOMPSAT-2 images and means to improve the Y parallex problem. We could conclude that the Y parallex problem was caused by resampling errors of KOMPSAT-2 PANchromatic bands, induced by the process of warping PANchromatic band with reference to multispectral bands. We could also conclude that a rigorous warping process could improve resampling of KOMPSAT-2 PANchromatic band and remove the Y parallex problem significantly. We also confirmed that a rigorous warping process could also remove blocky brightness patterns present on KOMPSAT-2 PANchromatic band. Therefore, by implementing more rigorous warping process within KOMPSAT-2 scene generation procedures, KOMPSAT-2 geometric and radiometric quality will be improved.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.75-83
• /
• 2018

Recently, autonomous vehicles have been actively studied. Pedestrian detection and recognition technology is important in autonomous vehicles. Pedestrian detection using CNN(Convolutional Neural Netwrok), which is mainly used recently, generally shows good performance, but there is a performance degradation depending on the environment of the image. In this paper, we propose a pedestrian detection system applying long-term memory structure of hippocampal neural network based on CNN network with LGP-FL (Local Gradient Pattern-Feature Layer) added. First, change the input image to a size of $227{\times}227$. Then, the feature is extracted through a total of 5 layers of convolution layer. In the process, LGP-FL adds the LGP feature pattern and stores the high-frequency pattern in the long-term memory. In the detection process, it is possible to detect the pedestrian more accurately by detecting using the LGP feature pattern information robust to brightness and color change. A comparison of the existing methods and the proposed method confirmed the increase of detection rate of about 1~4%.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.457-462
• /
• 2021

This study is about production techniques that can improve visual immersion in VR games. First, we reviewed the theory of VR games, current status, visual and immersion through prior work, and selected samples to extract key components that can improve visual immersion in VR games. and, VR games were produced and developed by applying the concept of COVID-19, which is currently popular around the world. As a result, the resolution of technical Element's, frame rate, viewing angle, brightness of lighting, design quality, and Contextual Element's storytelling, background, directing, color, texture, interest and fun because is Significant results that can induce and improve immersion were obtained, and in the end, smooth gameplay was realized. Through this research process and results, it is expected that it will be a basic data in the field of production and development of VR games that can induce and improve users' visual immersion in the future.