• Journal of the Semiconductor & Display Technology
• /
• v.13 no.4
• /
• pp.49-54
• /
• 2014

This paper proposes a new color segmentation method of vehicle license plates in the RGB color space. Firstly, the proposed method shifts the histogram of an input image rightwards and then stretches the image of the histogram slide. Secondly, the method separates each of the three RGB color components and performs the adaptive threshold processing with the three components, respectively. Finally, it combines the three components under the condition of making up a segment color and removes noises with the morphological processing. The proposed method is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiments were conducted by using real vehicle images. The results show that the proposed algorithm is successful for most vehicle images. However, the method fails in some vehicles when the body and the license plate have the same color.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.4
• /
• pp.374-381
• /
• 1991

As a diagnostic image of hospitl, the utilization of digital image is steadily increasing. Image coding is indispensable for storing and compressing an enormous amount of diagnostic images economically and effectively. In this paper adaptive two stage vector quantization based on Kohonen's neural network for the compression of cardioangiography among typical angiography of radiographic image sequences is presented and the performance of the coding scheme is compare and gone over. In an attempt to exploit the known characteristics of changes in cardioangiography, relatively large blocks of image are quantized in the first stage and in the next stage the bloks subdivided by the threshold of quantization error are vector quantized employing the neural network of frequency sensitive competitive learning. The scheme is employed because the change produced in cardioangiography is due to such two types of motion as a heart itself and body motion, and a contrast dye material injected. Computer simulation shows that the good reproduction of images can be obtained at a bit rate of 0.78 bits/pixel.

• Journal of Sensor Science and Technology
• /
• v.29 no.6
• /
• pp.427-432
• /
• 2020

The most lethal foreign body in meat is a needle, and X-ray images are used to detect it. However, because the difference in thickness and fat content is severe depending on the type of meat and the part of the meat, the shade difference and contrast appear severe. This problem causes difficulty in automatic classification. In this paper, we propose a method for generating training patterns by efficient pre-processing and classifying needles in meat using a convolution neural network. Approximately 24000 training patterns and 4000 test patterns were used to verify the proposed method, and an accuracy of 99.8% was achieved.

• Journal of Welding and Joining
• /
• v.27 no.6
• /
• pp.9-16
• /
• 2009

In this paper, the coaxial monitoring system to capture image of weld pool was developed in laser-arc hybrid welding. In order to obtain the reliable image, green laser was used as a illumination system and measuring components such as band pass filter, ND (Neutral Density) filter and shutter speed was designed and optimized. Using this monitoring system, weld pool images were captured according to laser power, welding speed, welding current and interspace between laser and arc through the experiment. ANOVA (Analysis of Variation) was carried out to identify the influence of process variables on bead widths extracted from captured images of monitoring system. Welding speed and current were major factor to affect weld pool.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.30 no.3 s.246
• /
• pp.215-221
• /
• 2006

A stereoscopic particle tracking velocimetry (SPTV) technique based on the 2-frame hybrid particle tracking velocimetry (PTV) method was developed. The expansion of 2D PTV to SPTV is facilitated by the fact that the PTV method tracks individual particle centroids. To evaluate the performance and measurement accuracy of the present SPTV technique, it was applied to flow images of rigid body translation and synthetic standard images of jet shear flow and impinging jet flow. The data processing routine and measurement uncertainty of the SPTV technique are compared with those of conventional stereoscopic particle image velecimet.y (SPBV). In addition, the centroid translation effect of 2D particle image velocimetry (PIV) is defined and its effect on SPIV measurements is discussed. Compared to the SPIV method, the SPTV technique has inherited merits of concise and precise velocity evaluation procedures and provides better spatial resolution and measurement accuracy.

• Progress in Medical Physics
• /
• v.21 no.1
• /
• pp.52-59
• /
• 2010

To examine among patients with vertebral compression fracture the extent to which signal-to-noise ratio (SNR) and Apparent Diffusion Coefficient (ADC) values at the lumbar vertebral compression fracture site vary on diffusion-weighted MR images according to varying b values on the 1.5T MR device. Diffusion-weighted MR images of 30 patients with compression fracture due to chronic osteoporosis who underwent vertebral MRI from Jan. 2008 to Nov. 2009 were respectively obtained using a 1.5-T MR scanner with the b values increased from 400, 600, 800, 1,000 to $1,200\;s/mm^2$. For diffusion-weighted MR images with different b values, the signal-to-noise ratio (SNR) was assessed at three sites: the site of compression fracture of the lumbar vertebral body at L1 to L5, and both the upper and lower discs of the said fracture site, while for ADC map images with different b values, the SNR and ADC were respectively assessed at those three sites. As a quantitative analysis, diffusion-weighted MR images and ADC map images with b value of $400\;s/mm^2$ (the base b values) were respectively compared with the corresponding images with each different b value. As far as qualitative analysis is concerned, for both diffusion-weighted MR and ADC map images with b value of $400\;s/mm^2$, the extent to which signal intensity values obtained at the site of compression fracture of the lumbar vertebral body at L1 to L5 vary according to the increasing b values were examined. The quantitative analysis found that for both diffusion-weighted MR and ADC map images, as the b values increased, the SNR were relatively lowered at all the three sites, compared to the base b value. Also, it was found that as the b values increased, ADC valueswere relatively lowered at all the three sites on ADC map images. On the other hand, the qualitative analysis found that as the b values increased to more than $400\;s/mm^2$, the signal intensity gradually decreased at all the sites, while at the levels of more than $1,000\;s/mm^2$, severe image noises appeared at all of the three sites. In addition, higher signal intensity was found at the site of compression fracture of the lumbar vertebral body than at the discs. Findings showed that with the b value being increased, both the signal-to-noise ratio (SNR) and Apparent Diffusion Coefficient (ADC) values gradually decreased at all the sites of the lumbar vertebral compression fracture and both the upper and lower discs of the fracture site, suggesting that there is a possibility of a wider range of applications to assessment of various vertebral pathologies by utilizing multi b values in the diffusion-weighted MRI examination.

• Investigative Magnetic Resonance Imaging
• /
• v.5 no.2
• /
• pp.138-148
• /
• 2001

Purpose : Within a clinically acceptable time frame, we obtained the high resolution MR images of the human brain, knee, foot and wrist from 3T whole-body MRI system which was equipped with the world first 37 active shield magnet. Materials and Methods : Spin echo (SE) and Fast Spin Echo (FSE) images were obtained from the human brain, knee, foot and wrist of normal subjects using a homemade birdcage and transverse electromagnetic (TEM) resonators operating in quadrature and tuned to 128 MHz. For acquisition of MR images of knee, foot and wrist, we employed a homemade saddle shaped RF coil. Topical common acquisition parameters were as follows: matrix=$512{\times}512$, field of view (FOV) =20 cm, slice thickness = 3 mm, number of excitations (NEX)=1. For T1-weighted MR images, we used TR = 500 ms, TE = 10 or 17.4 ms. For T2-weighted MR images, we used TR=4000 ms, TE = 108 ms. Results : Signal to noise ratio (SNR) of 3T system was measured 2.7 times greater than that of prevalent 1.5T system. MR images obtained from 3T system revealed numerous small venous structures throughout the image plane and provided reasonable delineation between gray and white matter. Conclusion The present results demonstrate that the MR images from 3T system could provide better diagnostic quali\ulcorner of resolution and sensitivity than those of 1.5T system. The elevated SNR observed in the 3T high field magnetic resonance imaging can be utilized to acquire images with a level of resolution approaching the microscopic structural level under in vivo conditions. These images represent a significant advance in our ability to examine small anatomical features with noninvasive imaging methods.

• Science of Emotion and Sensibility
• /
• v.14 no.3
• /
• pp.385-394
• /
• 2011

The purpose of this research is to compare and analyze visual images between the Real garment and the 3D garment simulation with the various fabrics of flare skirts and to analyze the correlation between mechanical properties and visual images. The picture images (printed on paper) of the Real garment and the 3D garment simulation of experimental flare skirts were shown to the evaluation group of women in their 20s majoring in clothing and textiles, and were evaluated by questionnaires with 32 adjectives. SPSS Version 12.0 statistics program was utilized to analyze data. Factor analysis, One Way ANOVA, T-test and Duncan test were used to investigate visual effect of the Real garment and the 3D garment simulation. As the result of conducting factor analysis on the visual appearance, the images were driven with five factors: 'drapeability', 'attractive', 'body compensation', 'bulkiness', 'activeness'. Visual images were significantly related with mechanical properties of various fabrics, and the visual images between 3D garment simulations and real garment differed with various fabrics and their mechanical properties. Visual images of silk and polyester group, cotton, linen and wool group were significantly related with weight and thickness of kinds of fabrics.

• The Journal of Korean Society for Radiation Therapy
• /
• v.18 no.2
• /
• pp.89-96
• /
• 2006

Purpose: To study effectiveness of heterogeneity correction of internal-body inhomogeneities and patient positioning immobilizers in dose calculation, using images obtained from CT-Simulator. Materials and Methods: A water phantom($250{\times}250{\times}250mm^3$) was fabricated and, to simulate various inhomogeneity, 1) bone 2) metal 3) contrast media 4) immobilization devices(Head holder/pillow/Vac-lok) were inserted in it. And then, CT scans were peformed. The CT-images were input to Radiation Treatment Planning System(RTPS) and the MUs, to give 100 cGy at 10 cm depth with isocentric standard setup(Field Size=$10{\times}10cm^2$, SAD=100 cm), were calculated for various energies(4, 6, 10 MV X-ray). The calculated MUs based on various CT-images of inhomogeneities were compared and analyzed. Results: Heterogeneity correction factors were compared for different materials. The correction factors were $2.7{\sim}5.3%$ for bone, $2.7{\sim}3.8%$ for metal materials, $0.9{\sim}2.3%$ for contrast media, $0.9{\sim}2.3%$ for Head-holder, $3.5{\sim}6.9%$ for Head holder+pillow, and $0.9{\sim}1.5%$ for Vac-lok. Conclusion: It is revealed that the heterogeneity correction factor calculated from internal-body inhomogeneities have various values and have no consistency. and with increasing number of beam ports, the differences can be reduced to under 1%, so, it can be disregarded. On the other hand, heterogeneity correction from immobilizers must be regarded enough to minimize inaccuracy of dose calculation.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.457-464
• /
• 2019

The weight of pig is one of the main factors in determining the health and growth state of pigs, their shipment, the breeding environment, and the ration of feed, and thus measuring the pig's weight is an important issue in productivity perspective. In order to estimate the pig's weight by using the number of pig's pixels from images, acquired from a Top-view camera, the posture determining and the head removal from images are necessary to measure the accurate number of pixels. In this research, we propose the fast and accurate method to determine the pig's posture by using a fast image processing technique, find the head location by using a fast deep learning technique, and remove pig's head by using light weighted image processing technique. First, we determine the pig's posture by comparing the length from the center of the pig's body to the outline of the pig in the binary image. Then, we train the location of pig's head, body, and hip in images using YOLO(one of the fast deep learning based object detector), and then we obtain the location of pig's head and remove an outside area of head by using head location. Finally, we find the boundary of head and body by using Convex-hull, and we remove pig's head. In the Experiment result, we confirmed that the pig's posture was determined with an accuracy of 0.98 and a processing speed of 250.00fps, and the pig's head was removed with an accuracy of 0.96 and a processing speed of 48.97fps.