• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.96.6-96
• /
• 2002

In this study an image processing system is designed and developed, which can detect and assort some defects on the surface of an object moving with high speed. For real time surface detection of high speed moving object, the fast processing should be managed and the image information including some surface features should be captured. It is difficult to acquire the noise free image due to various light sources and high speed moving materials under the environment of the general industrial site. In general, because pre-processing methods are employed for getting a noise free feature, the image processing speed has some limitation and the expensive image processing devices are required. This...

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2006년도 제5회 박판성형 SYMPOSIUM
• /
• pp.34-39
• /
• 2006

An automated surface-strain measurement system, named ASIAS, was developed by using the image processing and stereo vision techniques in the previous studies by the corresponding author and his coworkers. This system has been upgraded mainly to improve the accuracy through image enhancement, sub-pixel measurement, surface smoothing, etc., since the first version was released. The present study has still more improved the convenience of users as well as the accuracy of measurement by processing high resolution images 8 mega pixels or more which can be easily obtained from a portable digital steal camera. It is proved that high resolution image processing greatly decreases the measurement error and gives strain data without considerable deterioration of accuracy even when the deformed grids to be measured and the master grids for camera calibration are captured together in the same image, making the whole process of strain measurement much simpler.

• Journal of Advanced Marine Engineering and Technology
• /
• 제12권3호
• /
• pp.43-56
• /
• 1988

The image processing system consisted of the microcomputer IBM PC-XT and the graphic board (16 gray level and $640{\times}400$ pixels resolution) has been proposed, and the image processing softwares programmed in the BASIC and in the assembler language have been developed. The programs are consisted of the main menu and the sub menu, that have contained the subroutine for the capture for image data, the determination of region, the histogram, the change of value, the montage, the skeleton, the mask, the moving, the zoom, the disk access and the print. For the application, the photoelastic fringe data have been captured and analyzed. It was seen that the programs are available for the image processing.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.217-219
• /
• 2010

Sensor modeling is the basic step to extract and to use the information from satellite images. Sensor modeling requires ground control points. If we use a single image, we have limitations on modeling about images captured from regions that we can not approach or take GCPs. In this research, we use strip images to do sensor modeling by two methods. At first, we apply sensor modeiling to single image and apply the results by extrapolation. Next, we consider strip images to single image. As a result, we find the second method is more accurate about whole image.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2015년도 추계학술대회
• /
• pp.180-181
• /
• 2015

In this paper, we present a consistent and efficient edit propagation method that is applied for light field data. Unlike conventional sparse edit propagation, the coherency between light field sub-aperture images is fully considered by utilizing light field consistency in the optimization framework. Instead of directly solving the optimization function on all light field sub-aperture images, the proposed optimization framework performs sparse edit propagation in the extended focus image domain. The extended focus image is the representative image that contains implicit depth information and the well-focused region of all sub-aperture images. The edit results in the extended focus image are then propagated back to each light field sub-aperture image. Experimental results on test images captured by a Lytro off-the-shelf light field camera confirm that the proposed method provides robust and consistent results of edited light field sub-aperture images.

• Journal of Biosystems Engineering
• /
• 제30권5호
• /
• pp.299-305
• /
• 2005

This study was developed image processing algorithm for recognition of few teats of a cow in the image using black and white camera attached with infrared filter. Spectroscopic analysis was used for selection of a NIR filter to separate teats from udder skin in the image captured. To verify the performance of image processing algorithm was developed and NIR filter was selected, carried out an experiment with cows. NIR band-pass filter was used to pass the 975nm band of light spectrum. The image processing algorithm was developed could recognize all teats and the process time was 0.9 second to recognize the all teats and to acquire end position of teats.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1281-1287
• /
• 2016

This paper presents a method of single image dehazing and feature matching for aerial remote sensing images. In the case of a aerial image, transferring the information of the original image is difficult as the contrast leans by the haze. This also causes that the image contrast decreases. Therefore, a refined transmission map based on a hidden Markov random field. Moreover, the proposed algorithm enhances the accuracy of image matching surface-based features in an aerial remote sensing image. The performance of the proposed algorithm is confirmed using a variety of aerial images captured by a Worldview-2 satellite.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 봄 학술발표논문집 Vol.31 No.1 (B)
• /
• pp.715-717
• /
• 2004

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on a recursive error back-projection of top-down machine learning. A face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes, In addition to, a recursive error back-projection is applied to improve the accuracy of synthesized high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution one captured at a distance.

• 대한임베디드공학회논문지
• /
• 제14권3호
• /
• pp.133-142
• /
• 2019

The existing auxiliary communicating aids for the hearing-impaired have an inconvenience of using additional expensive sensing devices. This paper presents a hand image detection based algorithm to interpret the sign language of the hearing-impaired. The proposed sign language recognition system exploits the hand image only captured by the camera without using any additional gloves with extra sensors. Based on the hand image processing, the system can perfectly classify several numeric sign language representations. This work proposes a simple lightweight classification algorithm to identify the hand image of the hearing-impaired to communicate with others even further in an environment of complex background. Experimental results show that the proposed system can interpret the numeric sign language quite well with an accuracy of 95.6% on average.

• Current Optics and Photonics
• /
• 제6권3호
• /
• pp.304-312
• /
• 2022

Digital images of cultural relics captured using line scan cameras present limitations due to uneven intensity and low contrast. To address this issue, this report proposes a colour linear array image enhancement method that can maintain a constant colour. First, the colour linear array image is converted from the red-green-blue (RGB) colour space into the hue-saturation-intensity colour space, and the three components of hue, saturation, and intensity are separated. Subsequently, the hue and saturation components are held constant while the intensity component is processed using the established intensity compensation model to eliminate the uneven intensity of the image. On this basis, the contrast of the intensity component is enhanced using an improved local contrast enhancement method. Finally, the processed image is converted into the RGB colour space. The experimental results indicate that the proposed method can significantly improve the visual effect of colour linear array images. Moreover, the objective quality evaluation parameters are improved compared to those determined using existing methods.