• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1100-1105
• /
• 2006

Severe distortions of colors in the obtained images have made it difficult for color codes to expand their applications. To reduce the effect of color distortions on reading colors, it will be more desirable to statistically process as many pixels in the individual color region as possible, than relying on some regularly sampled pixels. This process may require segmentation, which usually requires edge detection. However, edges in color codes can be disconnected due tovarious distortions such as zipper effect and reflection, to name a few, making segmentation incomplete. Edge linking is also a difficult process. In this paper, a more efficient approach to reducing the effect of color distortions on reading colors, one that excludes precise edge detection for segmentation, was obtained by employing the k-means clustering algorithm. And, in detecting color codes, the properties of both six safe colors and grays were utilized. Experiments were conducted on 144, 4M-pixel, outdoor images. The proposed method resulted in a color-code detection rate of 100% fur the test images, and an average color-reading accuracy of over 99% for the detected codes, while the highest accuracy that could be achieved with an approach employing Canny edge detection was 91.28%.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.1
• /
• pp.77-84
• /
• 2013

Most research on the inkjet printing technology has focused on the development of inkjet head itself, and of process, not on the landing accuracy of the droplets to a target. Thus, this paper presents the modeling and experimental verification on the static landing accuracy and precision of the droplets from the magnetostrictive inkjet head. A simple model based on the angle deviation of a nozzle tip and on a distance to a substrate is considered, assuming that there is no ambient effect. The angle deviation of the nozzle tip is determined by using its digital image with the aid of a pixel calculation program, and the distance to the substrate is set to 1 mm. Three experiments have planned and preformed. The first experiment is to collect the initial data for the landing distribution of the droplets. The second experiment is to collect the repeatability data of the stage used. Then, these data are used to rederive the equation for the final landing position of the droplet. The final experiment is to verify the equation and to show the calibration results. The respective landing accuracy of the droplet after calibration on the x-axis and on y axis has improved from $338.51{\mu}m$ and $-133.63{\mu}m$ to $7.06{\mu}m$ and $13.11{\mu}m$. The respective percent improvement on the x-axis and on y axis reaches about 98 and about 90. The respective landing precision of the droplet after calibration on the x-axis and on y axis has improved from ${\pm}182.6{\mu}m$ and ${\pm}182.88{\mu}m$ to ${\pm}24.64{\mu}m$ and ${\pm}42.76{\mu}m$. The respective percent improvement on the x-axis and on y axis reaches about 87 and about 77.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.2
• /
• pp.11-18
• /
• 2020

Recently, a series of studies on virtual try-on (VTON) using images have been published. A comparison study analyzed representative methods, SCMM-based non-deep learning method, deep learning based VITON and CP-VITON, using costumes and user images according to the posture and body type of the person, the degree of occlusion of the clothes, and the characteristics of the clothes. In this paper, we tackle the problems observed in the best performing CP-VTON. The issues tackled are the problem of segmentation of the subject, pixel generation of un-intended area, missing warped cloth mask and the cost function used in the learning, and limited the algorithm to improve it. The results show some improvement in SSIM, and significantly in subjective evaluation.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.27-34
• /
• 2013

Background subtraction is one of the key techniques for automatic video content analysis, especially in the tasks of visual detection and tracking of moving object. In this paper, we present a new sample-based technique for background extraction that provides background image as well as background model. To handle both high-frequency and low-frequency events at the same time, multiple interval background models are adopted. The main innovation concerns the use of a confidence factor to select the best model from the multiple interval background models. To our knowledge, it is the first time that a confidence factor is used for merging several background models in the field of background extraction. Experimental results revealed that our approach based on multiple interval sampling works well in complicated situations containing various speed moving objects with environmental changes.

• Journal of the Korean Geotechnical Society
• /
• v.36 no.9
• /
• pp.45-55
• /
• 2020

X-ray computed tomography (CT) is very useful for the quantitative evaluation of internal structures, particularly defects in rock samples, such as pores and fractures. In situ CT allows 3D imaging of a sample subjected to various external treatments such as loading and therefore enables observation of changes that occur during the loading process. We reviewed state-of-the-art of in situ CT applications for geomaterials. Two triaxial cells made using relatively low density but high strength materials were developed aimed at in situ CT scanning during hydro-mechanical laboratory testing of rocks. Preliminary results for in situ CT imaging of granite and sandstone samples with diameters ranging from 25 mm to 50 mm show a resolution range of 34~105 ㎛ per pixel pitch, indicating the feasibility of in situ CT observations for internal structural changes in rocks at the micrometer scale. Potassium iodide solution was found to improve the image contrast, and can be used as an injection fluid for hydro-mechanical testing combined with in situ CT scanning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.4
• /
• pp.707-715
• /
• 2008

This paper proposes an algorithm for efficient compression gray-level images by entropy encoder. The issue of the proposed method is to replace original data of gray-level images with particular ranked data. For this, first, before encoding a stream of gray-level values in an image, the proposed method counts co-occurrence frequencies for neighboring pixel values. Then, it replaces each pay value with particularly ranked numbers based on the investigated co-occurrence frequencies. Finally, the ranked numbers are transmitted to an entropy encoder. The proposed method improves the performance of existing entropy coding by transforming original gray-level values into rank based images using statistical co-occurrence frequencies of gray-level images. The simulation results, using gray-level images with 8-bits, show that the proposed method can reduce bit rate by up to 37.85% compared to existing conventional entropy coders.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.2
• /
• pp.337-343
• /
• 2007

Since three-dimensional (3D) images reconstructed in interval imaging technique are related to the resolution of elemental images, there has been a problem that ray information of elemental images increases largely in order to obtain high-resolution 3D images. In this paper, to overcome this problem, a new unidirectional integral imaging based on pinhole model is proposed. Proposed method provides a new type of unidirectional elemental images, which are simply obtained by magnifying single horizontal pixel line of each elemental image to the vertical size of lenslet using ray analysis based on pinhole model and used to display 3D images. In proposed method, reduction effect of the ray information of elemental images can be obtained by scarifying vortical parallax. Feasibility of the proposed scheme is experimentally demonstrated and its results are presented.

• Korean Journal of Remote Sensing
• /
• v.16 no.1
• /
• pp.73-86
• /
• 2000

Commonly-used methods for camera modelling of pushbroom images were implemented and their performances were assessed. The models include Vector Propagation) model, Gugan and Downman(GD)'s model, Orun and Natarajan(ON)'s model, and Direct Linear Transformation(DLT) model The models were tested on a SPOT full-scene over Seoul. The number of ground control points(GCP) used range from 1 to 23. For less than 6 GCPs all other models fail except VP, with VP's accuracy being 2.7 pixels. With mode than 6 GCPs ON shows the best accuracy with 1pixel accuracy while the accuracy of VP is 1.5 pixels. GD fails in most cases due to the correlation among model parameters. The accuracy of DLT does not converge but fluctuates between 1 and 4 pixels subject to GCPs used. VP has an advantage in that its results can be used for the estimation of satellite orbit. Unresolved topics are: to remove errors in GCPs from the aforementioned accuracy value; to improve the performance of VP.

• Korean Journal of Remote Sensing
• /
• v.13 no.2
• /
• pp.85-98
• /
• 1997

A geometric model of pushbroom-type linear CCD camera images is proposed in this paper. At present, this type of cameras are used for obtaining almost all kinds of high-resolution optical images from satellites. The proposed geometric model includes not only a forward transformation which is much more efficient. An inverse transformation function cannot be derived analytically in a closed form because the focal point of an image varies with time. In this paper, therefore, an iterative algorithm in which a focal point os converged to a given pixel position is proposed. Although the proposed model can be applied to any pushbroom-type linear CCD camera images, the geometric model of the high-resolution multi-spectral camera on-board KITSAT-3 is used in this paper as an example. The flight model of KITSAT-3 is in development currently and it is due to be launched late 1998.

• Korean Journal of Remote Sensing
• /
• v.19 no.2
• /
• pp.159-169
• /
• 2003

This paper presents a method for automatic 3-d building reconstruction using high resolution aerial imagery. First, by using edge preserving filtering, noise is eliminated and then images are segmented by watershed algorithm, which preserves location of edge pixels. To extract line segments between control points from boundary of each region, we calculate curvature of each pixel on the boundary and then find the control points. Line segment linking is performed according to direction and length of line segments and the location of line segments is adjusted using gradient magnitudes of all pixels of the line segment. Coplanar grouping and pplygonal patch formation are performed per region by selecting 3-d line segments that are matched using epipolar geometry and flight information. The algorithm has been applied to high resolution aerial images and the results show accurate 3D building reconstruction.