• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.191-196
• /
• 2005

Although the technology for emotion recognition is important one which was demanded in various fields, it still remains as the unsolved problems. Especially, there is growing demand for emotion recognition technology based on racial image. The facial image based emotion recognition system is complex system comprised of various technologies. Therefore, various techniques such that facial image analysis, feature vector extraction, pattern recognition technique, and etc, are needed in order to develop this system. In this paper, we propose new emotion recognition system based un previously studied facial image analysis technique. The proposed system recognizes the emotion by using the fuzzy classifier. The facial image database is built up and the performance of the proposed system is verified by using built database.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.10a
• /
• pp.149-150
• /
• 2009

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1105-1106
• /
• 2011

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.365-366
• /
• 2013

• Nutritional Sciences
• /
• v.7 no.4
• /
• pp.241-246
• /
• 2004

This study investigated the influence of weight perception on weight management strategies including diet and exercise in Korean female adolescents. Junior (J) and senior (S) high school girls were divided in two groups; those who had $\leq$100% (BI) and > 100% (AI) of ideal weight (J-BI, n=376, 14.8 yr, 46.1 kg; J-AI, 11=128, 15.0 yr, 57.4 kg; S-BI, n=325, 17.4 yr, 50.1 kg; and S-AI, n=133, 17.5 yr, 58.2 kg, mean values). Questionnaires to assess weight perception, desire to lose weight, body image, eating behavior, weight control strategies and physical activity (PPA) were administered J-AI(9.4 kg) and S-AI(9.8 kg) desired to lose weight more than J-BI(2.5 kg) and S-BI(3.6 kg), respectively (p < 0.001). 85% of J-AI and 93% of S-AI perceived their weight being above average and 23% of J-BI and 34% of S-BI responded similarly (p < 0.001). Body dissatisfaction index (BDI) and eating attitude (EAT26) scores were lower in J-BI(9.7, 12.0) vs. J-AI(16.4, 14.7) and S-BI(12.4, 12.4) vs. S-AI(19.5, 15.4) (p < 0.001). However, PPA was not different for J-BI vs. J-AI, and S-BI vs. S-AL Only 17, 18, 9, and 15% of J.BI, J.AI, S-BI, and S-AI, respectively, exercised regularly. PPA and BDI were only slightly correlated in J-BI(r=0.194, p < 0.005) and S-BI(r=0.220, p < 0.005). Even that the majority of Korean female adolescents perceived they were heavy and desired to lose weight, appropriate exercise and physical activities were not practiced.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.8
• /
• pp.643-649
• /
• 2016

This paper presents a new image cache algorithm for real-time implementation of high-resolution color image warping. The cache memory is divided into four cache memory modules for simultaneous readout of four input image pixels in consideration of the color filter array (CFA) pattern of an image sensor and CFA image warping. In addition, a pipeline structure from the cache memory to an interpolator is shown to guarantee the generation of an output image pixel at each system clock cycle. The proposed image cache algorithm is applied to an FPGA-based real-time color image warping, and experimental results are presented to show the validity of the proposed method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.6
• /
• pp.455-461
• /
• 2002

Object-based image retrieval method is addressed. A new image segmentation algorithm and image comparing method between segmented objects are proposed. For image segmentation, color and texture features are extracted from each pixel in the image. These features we used as inputs into VQ (Vector Quantization) clustering method, which yields homogeneous objects in terns of color and texture. In this procedure, colors are quantized into a few dominant colors for simple representation and efficient retrieval. In retrieval case, two comparing schemes are proposed. Comparing between one query object and multi objects of a database image and comparing between multi query objects and multi objects of a database image are proposed. For fast retrieval, dominant object colors are key-indexed into database.

• Electronics and Telecommunications Trends
• /
• v.35 no.4
• /
• pp.65-80
• /
• 2020

In this article, we review the study trends of three-dimensional (3D) displays that can display stereoscopic images from the perspective of a display device. 3D display technology can be divided into light field, holographic, and volume displays. Light field display is a display that can reproduce the intensity and direction of light or 'ray' in each pixel. It can display stereoscopic images with less information than a holographic display and does not require coherence of the light source. Therefore, it is expected that it will be commercialized before the holographic display. Meanwhile, the holographic display creates a stereoscopic image by completely reproducing the wavefront of an image using diffraction in terms of wave characteristics of light. This technology is considered to be able to obtain the most complete stereoscopic image, and the digital holographic display using a spatial light modulator (SLM) is expected to be the ultimate stereoscopic display. However, the digital holographic display still experiences the problem of a narrow viewing angle due to the finite pixel pitch of the SLM. Therefore, various attempts have been made at solving this problem. Volumetric display is a technology that directly creates a stereoscopic image by forming a spatial pixel, which is known as a volumetric pixel, in a physical space, and has a significant advantage in that it can easily solve the problem of the viewing angle. This technology has already been tested for commercial purposes by several leading companies. In this paper, we will examine recent research trends regarding these 3D displays and near-eye display that is emerging as a significant application field of these technologies.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.1
• /
• pp.9-13
• /
• 2002

A pool image processing measurement method has been developed to improve the examination efficiency and to minimize the errors of dimensional measurements of spent fuel assemblies in pool. Diameter and length measurements of mock-up fuel rods using the image processing system are $-0.24{\pm}0.03mm,\;0.34{\pm}0.06mm$ on the basis of the true value and their maximum errors are within -0.3 and 0.4mm, respectively, According to the result of dimensional measurement of spent fuels in pool, the upper and lower part diameter and mid part diameter of fuel rods of the J44 fuel assembly irradiated for 2 cycles in the Kori-2 nuclear reactor were decreased by about 2.0 and 3.0% in comparison with design values, respectively. The length of fuel rods was elongated by about 0.4%. The change behavior of diameter and length. of fuel rods of the F02 fuel assembly irradiated for 3 cycles in the Kori-1 nuclear reactor showed a trend similar to the results of J44.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.592-600
• /
• 2016

AAPM CT performance for special medical equipment quality control checks using a standard phantom for evaluation, using the evaluator's subjective assessment as to minimize errors due computerized assessment program to evaluate their usefulness. Phantom for evaluation AAPM CT Performance Phantom: was used, the default shooting conditions are the same as quality control checks. And, we use IMAGE J to evaluate the program. Quantitative evaluation with CT attenuation coefficient and the noise measurement, the uniformity measurement, the slice thickness measurement, contrast resolution of the measurement, a phantom image of the spatial resolution determined by the evaluation program is evaluated as self-extracting the result after processing the image, CT uniformity measurement for the evaluation that was smaller and the standard deviation of a video image processing more uniform slice thickness measurements it is difficult to evaluate due to the difference of the ratio of the measured value of the phantom image. Contrast resolution was measured cylindrical diameter 6th evaluate the shape of a circle obtained a mean value and a standard deviation of diameters, the spatial resolution of the group of source, including acceptance criteria automatically extracted result as a result of both the number of the extracted circularIt appeared. Evaluate the source image and video processing, and video to qualitative evaluation by gross were processed video image is shown excellent results. If the evaluators in order to minimize the errors of subjective judgment based on the results of the above should be done with a quantitative evaluation and qualitative evaluation utilizes a computerized assessment program is considered that further evaluation be made more efficient.