• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.2
• /
• pp.240-244
• /
• 2007

Non-intrusive methods based on active remote IR illumination fur eye tracking is important for many applications of vision-based man-machine interaction. One problem that has plagued those methods is their sensitivity to lighting condition change. This tends to significantly limit their scope of application. In this paper, we present a new real-time eye detection and tracking methodology that works under variable and realistic lighting conditions. Based on combining the bright-pupil effect resulted from IR light and the conventional appearance-based object recognition technique, our method can robustly track eyes when the pupils are not very bright due to significant external illumination interferences. The appearance model is incorporated in both eyes detection and tracking via the use of support vector machine and the mean shift tracking. Additional improvement is achieved from modifying the image acquisition apparatus including the illuminator and the camera.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.456-463
• /
• 2004

Non-intrusive methods based on active remote IR illumination for eye tracking is important for many applications of vision-based man-machine interaction. One problem that has plagued those methods is their sensitivity to lighting condition change. This tends to significantly limit their scope of application. In this paper, we present a new real-time eye detection and tacking methodology that works under variable and realistic lighting conditions. Based on combining the bright-Pupil effect resulted from IR light and the conventional appearance-based object recognition technique, our method can robustly track eyes when the pupils ale not very bright due to significant external illumination interferences. The appearance model is incorporated in both eyes detection and tacking via the use of support vector machine and the mean shift tracking. Additional improvement is achieved from modifying the image acquisition apparatus including the illuminator and the camera.

• Current Applied Physics
• /
• v.18 no.12
• /
• pp.1496-1506
• /
• 2018

Organic/inorganic ultraviolet photodetector was fabricated using thermal evaporation technique. Organic/inorganic heterojunction based on thermally evaporated copper (II) acetylacetonate thin film of thickness 200 nm deposited on an n-type silicon substrate is introduced. I-V characteristics of the fabricated heterojunction were investigated under UV illumination of intensity $65mW/cm^2$. The diode parameters such as ideality factor, n, barrier height, ${\Phi}_B$, and reverse saturation current, $I_s$, were determined using thermionic emission theory. The series resistance of the fabricated diode was determined using modified Nord's method. The estimated values of series resistance and barrier height of the diode were about $0.33K{\Omega}$ and 0.72 eV, respectively. The fabricated photodetector exhibited a responsivity and specific detectivity about 9 mA/W and $4.6{\times}10^9$ Jones, respectively. The response behavior of the fabricated photodetector was analyzed through ON-OFF switching behavior. The estimated values of rise and fall time of the present architecture under UV illumination were about 199 ms and 154 ms, respectively. Finally, enhancing the photoresponsivity of the fabricated photodetector, post-deposition plasma treatment process was employed. A remarkable modification of the device performance was noticed as a result of plasma treatment. These modifications are representative in a decrease of series resistance and an increase of photoresponsivity and specific detectivity. The process of plasma treatment achieved an increment of external quantum efficiency from 5.53% to 8.34% at -3.5 V under UV illumination.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.6
• /
• pp.491-497
• /
• 2016

This study aims to develop a vision inspection system for screw threads. To inspect external defects in screw threads, the vision inspection system was developed using front light illumination from which bright images can be obtained. The front light system, however, requires multiple side images for inspection of the entire thread surface, which can be performed by omnidirectional optics. In this study, an omnidirectional optical system was designed to obtain annular images of screw threads using an image sensor and two reflection mirrors; one large concave mirror and one small convex mirror. Optical simulations using backward and forward ray tracing were performed to determine the dimensional parameters of the proposed optical system, so that an annular image of the screw threads could be obtained with high quality and resolution. Microscale surface defects on the screw threads could be successfully detected using the developed annular inspection system.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.823-833
• /
• 1996

An ultimate purpose of this study is to develop an automatic brown rice quality inspection system using image processing technique. In this study emphasis was put on developing an algorithm for discriminating the brown rice kernels depending on their external quality with a color image processing system equipped with an adaptor for magnifying the input image and optical fiber for oblique illumination. Primarily , geometrical and optical features of sample images were analyzed with unhulled paddy and various brown rice kernel samples such as sound, cracked, green-transparent , green-opaque, colored, white-opaque and brokens. Secondary, an algorithm for discrimination of the rice kernels in static state was developed on the basis of the geometrical and optical parameters screened by a statistical analysis(STEPWISE and DISCRIM Procedure, SAS ver.6). Brown rice samples could be discriminated by the algorithm developed in this study with an accuracy of 90% to 96% for the sound , cracked, colored, broken and unhulled , about 81% for the green-transparent and the white-opaque and about 75% for the green-opaque, respectively. A total computing time required for classification was about 100 seconds/1000 kernels with the PC 80486-DX2, 66MHz.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.203-207
• /
• 2001

In this Paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using CCD color image. To do this, we first acquire the color image from the CCD camera, and then propose the method for recognizing the expression to be represented the structural correlation of man's feature Points(eyebrows, eye, nose, mouse) It is central technology that the Process of extract, separate and recognize correct data in the image. for representation is expressed by structural corelation of human's feature Points In the Proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Had separated complexion area using color-difference of color space by method that have separated background and human's face toughly to change such as external illumination in this paper. For this, we propose an algorithm to extract four feature Points from the face image acquired by the color CCD camera and find normalization face picture and some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector. Finally, we show the Practical application possibility of the proposed method.

• Proceedings of the KIPE Conference
• /
• 2004.07a
• /
• pp.147-150
• /
• 2004

Maximum power point tracking for PV systems traditionally uses either perturbation and observation method or incremental conductance method. Both methods require modulation of the output voltage and this leads to significant power loss. In this paper, a method, which senses output circuit voltage and short circuit current and use the above two parameters for optimum control with a fuzzy controller, is introduced. The short circuit current of PV cell represents illumination, and the output circuit voltage carry on information about the temperature. PCS(power conditioning system) is controlled not only feed to inverter for stability voltage variation despite of variety external environment, but also operate in order to feeding voltage and current at maximum power point by boost type chopper.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.07a
• /
• pp.439-442
• /
• 2001

Chalcogenide glassy semiconductors(CGS) can be obtained by the melt quenching technique. We have investigated the thin film heterostructures : metal-chalcogenide glassy semiconductors, where metal is copper, and chalcogenide glassy semiconductors are glasses of the system As-Se. CU/CGS film heterostructure were produced in the vacuum evaporator by the method of vacuum thermal evaporation. Doped films are very sensitive to external actions, and this property allows developing supersensitive precision sensors of temperature, humidity, illumination, and etc. based on them. Cu/CGS film has shown that resistance strongly depend on the temperature. The ratio of resistance vs. temperature has shown over a 2 k$\Omega$/degree. The slop of temperature and resistance shows linear.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.07b
• /
• pp.727-730
• /
• 2002

Chalcogenide glassy semiconductors(CGS) can be obtained by the melt quenching technique. We have investigated the thin film heterostructures : metal-chalcogenide glassy semiconductors, where metal is copper, and chalcogenide glassy semiconductors are glasses of the system As-Se. Cu/CGS film heterostructure were produced in the vacuum evaporator by the method of vacuum thermal evaporation. Doped films are very sensitive to external actions, and this property allows developing supersensitive precision sensors of temperature, humidity, illumination, and etc. based on them. Cu/CGS film has shown that resistance strongly depend on the temperature. The slop of temperature and resistance shows linear.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.138.3-138
• /
• 2001

Because face has non-rigid structure and is influenced by illumination, we need robust face detection algorithm with the variations of external environments (orientation of lighting and face, complex background, etc.). In this paper we develop a new face detection algorithm to achieve robustness. First we transform RGB color into other color space, in which we can reduce lighting effect much. Second, hierarchical image segmentation technique is used for dividing a image into homogeneous regions. This process uses not only color information, but also spatial information. One of them is used in segmentation by histogram analysis, the other is used in segmentation by grouping. And we can select face region among the homogeneous regions by using facial features.