• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.6
• /
• pp.1482-1489
• /
• 1998

This paper aims to extract characteristics of the spectrum of fingerprint image and to apply them to image enhancement techniques in spatial frequency domain. Based on 1$\times$64 window as a processing unit and the different record lengths(32, 16, 8), the estimate of power spectrum density for each length was made. Each acquired spectrum characteristics was applied to the re-synthesis process of the fingerprint image, an improved gray scale image was obtained. In order to select an optimal predictor and the Huffman table for the fingerprint iamge, the lossless JPEG algorithm was used. Experiments were performed for extracting distribution characteristics for the each of 7 predictors from the fingerprint image and modeling processes, and the result was applied to the data compression algorithm and the selection of the optimal predictor.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.46-57
• /
• 2019

In recent research, deep learning-based methods have achieved state-of-the-art performance in various computer vision tasks. However, these methods are commonly supervised, and require huge amounts of annotated data to train. Acquisition of data demands an additional costly effort, particularly for the tasks where it becomes challenging to obtain large amounts of data considering the time constraints and the requirement of professional human diligence. In this paper, we present a data level synthetic sampling solution to learn from small and imbalanced data sets using Generative Adversarial Networks (GANs). The reason for using GANs are the challenges posed in various fields to manage with the small datasets and fluctuating amounts of samples per class. As a result, we present an approach that can improve learning with respect to data distributions, reducing the partiality introduced by class imbalance and hence shifting the classification decision boundary towards more accurate results. Our novel method is demonstrated on a small dataset of 2789 tomato plant disease images, highly corrupted with class imbalance in 9 disease categories. Moreover, we evaluate our results in terms of different metrics and compare the quality of these results for distinct classes.

• Journal of the Korea Convergence Society
• /
• v.9 no.2
• /
• pp.119-124
• /
• 2018

The augmented reality(AR) technology enables to acquire various image information at the same time by combining virtual image information with the user's viewpoint. These AR technologies have been used to visualize patients' organs and tissues during surgery and diagnosis in the fields of Image-Guide Operation, Surgical Training, and Image Diagnosis by medical convergence, and provides the most effective surgical methods. In this paper, we study the technical features and application methods of each element technology for medical fusion of AR technology. In the AR technology for medical convergence, display, marker recognition and image synthesis interface technology is essential for efficient medical image. Such AR technology is considered to be a way to drastically improve current medical technology in the fields of image guide surgery, surgical education, and imaging diagnosis.

• Journal of Convergence for Information Technology
• /
• v.11 no.12
• /
• pp.30-38
• /
• 2021

In this paper, we propose a method for extracting thermal data from thermal image and improving detection of heating equipment using the data. The main goal is to read the data in bytes from the thermal image file to extract the thermal data and the real image, and to apply the composite image obtained by synthesizing the image and data to the deep learning model to improve the detection accuracy of the heating facility. Data of KHNP was used for evaluation data, and Faster-RCNN is used as a learning model to compare and evaluate deep learning detection performance according to each data group. The proposed method improved on average by 0.17 compared to the existing method in average precision evaluation.As a result, this study attempted to combine national data-based thermal image data and deep learning detection to improve effective data utilization.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.2
• /
• pp.167-171
• /
• 2014

Using chemical vapor deposition(CVD), the synthesis of graphene was performed on poly and single crystalline Cu substrates. The growth behavior of graphene and its characterization were shown utilizing the optical microscopic image and its image analysis. As a result in the analysis of graphene growth, it was found out the graphene is growing always in particular direction in relation to the crystalline direction of a single grain in polycrystalline Cu substrate. With the image analysis it was possible to show the characterization of graphene, such as the growth direction and the number of layers showing single, double and triple layers, within the neighboring single grains in polycrystalline Cu. In addition, the relatively large area of graphene with about $3mm^2$ on Cu(111) having high quality, single layer, and single crystalline was shown along with its characterization.

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.62-70
• /
• 2013

DIBR(Depth Image Based Rendering) is a kind of view synthesis algorithm to generate images at free view points from the reference color image and its depth map. One of the main challenges of DIBR is the occurrence of holes that correspond to uncovered backgrounds at the synthesized view. In order to cover holes efficiently, two main approaches have been actively investigated. One is to develop preprocessing algorithms for depth maps or parallax maps to reduce the size of possible holes, and the other is to develop hole filling methods to fill the generated holes using adjacent pixels in non-hole areas. Most conventional preprocessing algorithms for reducing the size of holes are based on the smoothing process of depth map. Filtering of depth map, however, attenuates the resolution of depth map and generates geometric distortions. In this paper, we proposes a novel preprocessing algorithm for parallax map to improve the performance of hole-filling by avoiding the drawbacks of conventional methods.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.22 no.2
• /
• pp.179-198
• /
• 2004

Organic electroluminescent devices are light-emitting diodes in which the active materials consist entirely of organic materials. Recently, many fluorescent organic materials have been reported and the study on synthesis and application of new organic light-emitting materials has been demanded. This paper reports the optical and electrical characteristics of OLEDs using novel polymers containing biphenyl structure. First, Optical properties of novel light-emitting biphenyl derivatives doped with poly(9-vinyl carbazole)(PVK) and emitted blue, bluish green color, which is attributed to the overlap area between PL spectrum of host(PVK) and absorption spectra of guests(polymer). This is correspondent with F$\"{o}$rster energy transfer process in the blends. And, OLED devices were fabricated using poly (3,4-ethylenedioxy thiophene) (PEDOT) as a hole injection material and tris-(8-hydroxyquinoline) aluminum ($Alq_3$) as an electron transporting material. EL devices fabricated as ITO/PEDOT/PVK doped with biphenyl derivatives/$Alq_3$/Li:Al and I-V-L chatacteristics and emitting efficiency of EL devices were examined. Finally, the drift mobility of PVK doped with biphenyl derivatives and $Alq_3$ were measured by TOF technique varying applied electric field. EL efficiency was increased as the ratio of hole mobility of PVK doped with biphenyl derivatives and electron mobility of $Alq_3$ was close to one.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.182-188
• /
• 2004

This paper proposes to synthesize facial images from a few parameters for the pose and the expression of their constituent components. This parameterization makes the representation, storage, and transmission of face images effective. But it is difficult to parameterize facial images because variations of face images show a complicated nonlinear manifold in high-dimensional data space. To tackle this problem, we use an LLE (Locally Linear Embedding) technique for a good representation of face images, where the relationship among face images is preserving well and the projected manifold into the reduced feature space becomes smoother and more continuous. Next, we apply a snake model to estimate face feature values in the reduced feature space that corresponds to a specific pose and/or expression parameter. Finally, a synthetic face image is obtained from an interpolation of several neighboring face images in the vicinity of the estimated feature value. Experimental results show that the proposed method shows a negligible overlapping effect and creates an accurate and consistent synthetic face images with respect to changes of pose and/or expression parameters.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.1-8
• /
• 2021

The performance of hidden camera cameras is improving day by day due to miniaturization and advanced technology integration according to the speed of technological development of smartphones. As this external networking computing environment is advanced and diversified, exposure to hidden cameras in addition to general safety cameras is also increasing. On the other hand, the technology for detecting and preventing hidden cameras is not keeping up with the development and speed of these hidden cameras. Therefore, in this study, the heat of the hidden camera was detected using infrared thermal detection technology based on general image and thermal image synthesis technology, and the reflectance of each wavelength according to the difference in ambient temperature was analyzed to reduce the false positive rate.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.1-8
• /
• 2021

In online meetings and classes using webcams, the chromakey technique is a very necessary part to produce content. We proposed a technology that enables background synthesis without using a cloth for chromakey. The proposed method consists of three steps: an HSI image conversion step, a step of detecting a region changed from a background, and a step of replacing the background region with a chromakey and applying it. In the input video, the block average image of each frame is calculated, and the difference between the block average image of the background image and the block average image of the input image is used to detect the change area. The developed chromakey effect technology uses a technique of acquiring a background image without an object from a single camera and extracting only an object by distinguishing the moving object and the background. The proposed method is not only capable of processing even if the background has a variety of colors, but also has the seamless processing of the boundary lines of objects.