• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2101-2108
• /
• 2014

Automatic fall-detection algorithms using video-data are proposed. Six types of fall-feature parameters are defined applying the optical flows extracted from differential images to principal component analysis(PCA). One fall-detection algorithm is the simple threshold method that a fall is detected when a fall-feature parameter is over a threshold, another is to use the HMM, and the other is to combine the simple threshold and HMM. Comparing the performances of three types of fall-detection algorithm, the algorithm combining the simple threshold and HMM requires less computational resources than HMM and exhibits a higher accuracy than the simple threshold method.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.02a
• /
• pp.464-464
• /
• 2010

A few years ago, for maintaining high stability and production yield of production equipment in a semiconductor fab, on-line monitoring of wafers is required, so that semiconductor manufacturers are investigating a software based process controlling scheme known as virtual metrology (VM). As semiconductor technology develops, the cost of fabrication tool/facility has reached its budget limit, and reducing metrology cost can obviously help to keep semiconductor manufacturing cost. By virtue of prediction, VM enables wafer-level control (or even down to site level), reduces within-lot variability, and increases process capability, $C_{pk}$. In this research, we have practiced VM on $SiO_2$ etch rate with optical emission spectroscopy(OES) data acquired in-situ while the process parameters are simultaneously correlated. To build process model of $SiO_2$ via, we first performed a series of etch runs according to the statistically designed experiment, called design of experiments (DOE). OES data are automatically logged with etch rate, and some OES spectra that correlated with $SiO_2$ etch rate is selected. Once the feature of OES data is selected, the preprocessed OES spectra is then used for in-situ sensor based VM modeling. ICP-RIE using 葰.56MHz, manufactured by Plasmart, Ltd. is employed in this experiment, and single fiber-optic attached for in-situ OES data acquisition. Before applying statistical feature selection, empirical feature selection of OES data is initially performed in order not to fall in a statistical misleading, which causes from random noise or large variation of insignificantly correlated responses with process itself. The accuracy of the proposed VM is still need to be developed in order to successfully replace the existing metrology, but it is no doubt that VM can support engineering decision of "go or not go" in the consecutive processing step.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.635-644
• /
• 2020

Object recognition, detection and instance segmentation based on DL (Deep Learning) have being used in various practices, and mainly optical images are used as training data for DL models. The major objective of this paper is object segmentation and building detection by utilizing multimodal datasets as well as optical images for training Detectron2 model that is one of the improved R-CNN (Region-based Convolutional Neural Network). For the implementation, infrared aerial images, LiDAR data, and edges from the images, and Haralick features, that are representing statistical texture information, from LiDAR (Light Detection And Ranging) data were generated. The performance of the DL models depends on not only on the amount and characteristics of the training data, but also on the fusion method especially for the multimodal data. The results of segmenting objects and detecting buildings by applying hybrid fusion - which is a mixed method of early fusion and late fusion - results in a 32.65% improvement in building detection rate compared to training by optical image only. The experiments demonstrated complementary effect of the training multimodal data having unique characteristics and fusion strategy.

• Journal of Mechanical Science and Technology
• /
• v.17 no.7
• /
• pp.1095-1103
• /
• 2003

The Holographic Particle Velocimetry system can be a promising optical tool for the measurements of three dimensional particle velocities. In this study, the holographic particle velocimetry system was used to measure the sizes and velocities of droplets produced by a commercial full cone spray nozzle. As a preliminary validation experiment, the velocities of glass beads on a rotating disk were measured with uncertainty analysis to identify the sources of all relevant errors and to evaluate their magnitude. The error of the particle velocity measured by the holographic method was 0.75 ㎧, which was 4.5% of the known velocity estimated by the rotating speed of disk. The spray droplet velocities ranged from 10.3 to 13.3 ㎧ with average uncertainty of ${\pm}$ 1.6 ㎧, which was ${\pm}$ 14% of the mean droplet velocity. Compared with relatively small uncertainty of velocity components in the normal direction to the optical axis, uncertainty of the optical axis component was very high. This is due to the long depth of field of droplet images in the optical axis, which is inherent feature of holographic system using forward-scattering object wave of particles.

• Korean Journal of Optics and Photonics
• /
• v.12 no.1
• /
• pp.55-60
• /
• 2001

We propose a method to extract features optically from the input pattern by use of an array of Hough transfOllli filters. Here the subparts of the input pattern are Hough-transformed by. their cOlTesponding elements of the filter array independently and simultaneously. Compared with the conventional method, in which the whole input pattern is Hough-transformed by a single optical filter, the proposed method not only provides the improved optical transform results when the input pattern becomes complex but also extracts the approximate position information of the line segment features. To show the feasibility of this approach, we fabricated a $5\times5$ filter array and performed preliminary experiments.iments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.4
• /
• pp.112-118
• /
• 2014

This paper deals with a color-based tracking of a moving object. Firstly, existing Camshift algorithm is complemented to improve the tracking weakness in the brightness change of an image which occurs in every frame. The complemented Camshift still shows unstable tracking when the objects with same color of the tracking object exist in background. In order to overcome the drawback this paper proposes the Camshift combined with KLT algorithm based on optical flow. The KLT algorithm performing the pixel-based feature tracking can complement the shortcoming of Camshift. Experimental results show that the merged tracking method makes up for the drawback of the Camshit algorithm and also improves tracking performance.

• Current Optics and Photonics
• /
• v.2 no.2
• /
• pp.140-146
• /
• 2018

In this paper, mesoscale optical surface structures are found to possess both geometric and wave optics features. The study reveals that geometric optic analysis cannot correctly predict the experimental results of light transmission or reflection by mesoscale optical structures, and that, for reliable analyses, a hybrid approach incorporating both geometric and wave optic theories should be employed. By analyzing the transmission patterns generated by the mesoscale periodic pyramid prism plates, we show that the wave optic feature is mainly ascribed to the edge diffraction effect and we estimate the relative contributions of the wave optic diffraction effect and the geometric refraction effect to the total scattering field distribution with respect to the relative dimension of the structures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1981-1995
• /
• 2021

When a person tries to conceal emotions, real emotions will manifest themselves in the form of micro-expressions. Research on facial micro-expression recognition is still extremely challenging in the field of pattern recognition. This is because it is difficult to implement the best feature extraction method to cope with micro-expressions with small changes and short duration. Most methods are based on hand-crafted features to extract subtle facial movements. In this study, we introduce a method that incorporates optical flow and deep learning. First, we take out the onset frame and the apex frame from each video sequence. Then, the motion features between these two frames are extracted using the optical flow method. Finally, the features are inputted into an improved MobileNetV2 model, where SVM is applied to classify expressions. In order to evaluate the effectiveness of the method, we conduct experiments on the public spontaneous micro-expression database CASME II. Under the condition of applying the leave-one-subject-out cross-validation method, the recognition accuracy rate reaches 53.01%, and the F-score reaches 0.5231. The results show that the proposed method can significantly improve the micro-expression recognition performance.

• Korean Journal of Optics and Photonics
• /
• v.32 no.6
• /
• pp.306-313
• /
• 2021

We study the amplification properties of an optical amplifier based on a cesium-vapor cell. An optical amplification system including cesium vapor mixed with a buffer gas is built, and its amplification feature is investigated as a function of the size of the incident beam and the temperature of the cesium-vapor cell. We observe that the optical amplification properties, such as amplification factor and extraction efficiency, change significantly depending on the temperature and beam diameter of the pump and seed light. A maximum extraction efficiency of 56% is obtained when the temperature of the cesium cell is 90 ℃, with a 200-㎛ diameter of the pump (500 mW) and seed light (10 mW). The numerical simulation of the amplification properties agrees reasonably with the results obtained from the experiment.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.12
• /
• pp.1775-1784
• /
• 2002

Fingerprint recognition technology is used in many biometrics field accordingly essential feature of fingerprint image and the study is progressing. However development is not perfect in performance of the fingerprint recognition and application of the usual life. In the paper, we study various necessity of preprocessing according to algorithm and circumstances of authentication system in automatic information machine. We prove that system circumstance and optation of fingerprints image effectively is the important factor by using optical fingerprint input device and scanning the fingerprint in ID card. And then we present correct and fast computation method for improving image and feature extraction of fingerprint. Also we study effective algorithm implementation of total system.