• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.262-265
• /
• 2007

Preliminary results are reported on ship detection using coherence images computed from cross-correlating images of multi-look-processed dual-polarization data (HH and HV) of ENVISAT ASAR. The traditional techniques of ship detection by radars such as CFAR (Constant False Alarm Rate) rely on the amplitude data, and therefore the detection tends to become difficult when the amplitudes of ships images are at similar level as the mean amplitude of surrounding sea clutter. The proposed method utilizes the property that the multi-look images of ships are correlated with each other. Because the inter-look images of sea surface are covered by uncorrelated speckle, cross-correlation of multi-look images yields the different degrees of coherence between the images and water. The polarimetric information of ships, land and intertidal zone are first compared based on the cross-correlation between HH and HV. In the next step, we examine the technique when the dual-polarization data are split into two multi-look Images.

• Proceedings of the KSRS Conference
• /
• 2008.03a
• /
• pp.180-184
• /
• 2008

Preliminary results are reported on ship detection using coherence images computed from crosscorrelating images of multi-look-processed dual-polarization data (HH and HV) of ENVISAT ASAR. The traditional techniques of ship detection by radars such as CFAR (Constant False Alarm Rate) rely on the amplitude data, and therefore the detection tends to become difficult when the amplitudes of ships images are at similar level as the mean amplitude of surrounding sea clutter. The proposed method utilizes the property that the multi-look images of ships are correlated with each other. Because the inter-look images of sea surface are covered by uncorrelated speckle, crosscorrelation of multi-look images yields the different degrees of coherence between the images and water. The polarimetric information of ships, land and intertidal zone are first compared based on the cross-correlation between HH and HV. In the next step, we examine the technique when the dual-polarization data are split into two multi-look images.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.2
• /
• pp.180-187
• /
• 2007

In this paper, we propose an automatic method which combines two or more images acquired by camera on the air-vehicle into a larger image mosaics. The shift, scaling, rotation factors between two images can be calculated by using the correspondences between the points of the images. In order to estimate these factors, we find the relative positions of two images with respect to each other by using the SIFT descriptor and the RANSAC algorithm. After estimating the factors, the images can be merged into a single image mosaic by warping the target image. To avoid seams when mosaics are constructed from overlapped images, we apply the average gray level value of points within a overlapped zone. We have tested our proposed method on various image sets and have confirmed that our method produced good result subjectively.

• Proceedings of the Optical Society of Korea Conference
• /
• 2009.02a
• /
• pp.263-264
• /
• 2009

We propose a method synthesizing elemental images and sub-images for the integral imaging using phase-shifting digital holography. From acquired single 4-step phase-shifting digital holography, we can generate elemental images and sub-images for any lens array specifications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.4
• /
• pp.645-651
• /
• 2002

This paper presents a method to automatically synthesized human fare images from holistic descriptions. We compactly represent the face set by a small set of prototypes, which can be used in simple ways generated controlled morphings. This becomes possible because separation of 2D-shape and texture provides a faithful, closed and convex representation of images, and smooths the mapping between images and their properties. With this approach, the user watches an images being continuously morphed according to his indications, and the synthesized images always obey the natural physiognomic constraints.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.182-182
• /
• 2003

Generally, DEM (Digital Elevation Model) is generated by stereo-images acquired same conditions, sensor type, viewing angle, capturing elevation and etc. It is difficult to generate DEM with stereo images acquired different satellite. This study intends that it is DEM generation using pair-images with other sensor systems.

• Journal of Fashion Business
• /
• v.17 no.6
• /
• pp.111-124
• /
• 2013

The purpose of this research was to conduct a comparison analysis of color in the characteristics and image of Korea/China/Japan airline uniforms. Research subjects for this research included 19 Korean, Chinese and Japanese airlines servicing the Incheon International Airport in South Korea. The analysis methods are based on the Munsell Color Order System and PCCS (Practical Color Coordinate System) tone classification in order to examine the color characteristics. For the color image analysis, the present research performed a positioning on Shigenobu Kobayashi's color images scale with adjectives in order to compare the resulting differences. As a result of the analysis, this research discovered the following; First, achromatic colors were found to be used most frequently in flight attendant uniforms of Korea/China/Japan. In Korean flight attendant uniforms, YR/Y, GY and B/PB/P; in Chinese, R/PB, RP, YR/Y/GY and BG/P; in Japanese, RP, R/P/PB and Y/BG were found in order. As for the main uniform colors, Korean flight attendant uniforms were found to be in the colors YR, and R/GY/B/P; Chinese flight attendant uniforms, R, PB, and P/B; and Japanese flight attendant uniforms, R, BG, B, RP and N. Second, Korean flight attendant uniforms used W and It most frequently; China flight attendant uniforms, W; and Japanese flight attendant uniforms, W and v. Regarding the main colors, Korean flight atteddant uniforms used lt/g and v/p; Chinese flight attendant uniforms, v, dp and s/d/dkg; and Japanese flight attendant uniforms, v/dkg and Bk. Third, after positioning each country's uniform color combination bars on the Kobayashi image scale, Korean flight attendant uniforms showed classic images along with casual/pretty/elegant/chic images; Chinese flight attendant uniforms displayed, casual images as well as, dynamic/gorgeous/chic/cool casual/dandy images; and finally, Japanese flight attendant uniforms converyed dandy images along with casual/gorgeous images. This research findings indicate that Korea/China/Japan airlines' flight attendant uniforms seek for differentiated image establishment by reflecting their own CIs and unique national cultures in the uniform color marketing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.674-677
• /
• 2020

The cultural background of users utilizing image search engines has a significant impact on the satisfaction of the search results. Therefore, it is important to analyze and understand the cultural context of images for more accurate image search. In this paper, we investigate how the cultural context of images can affect the performance of image classification. To this end, we first collected various types of images (e.g,. food, temple, etc.) with various cultural contexts (e.g., Korea, Japan, etc.) from web search engines. Afterwards, a deep transfer learning approach using VGG19 and MobileNetV2 pre-trained with ImageNet was adopted to learn the cultural features of the collected images. Through various experiments we show the performance of image classification can be differently affected according to the cultural context of images.

• Investigative Magnetic Resonance Imaging
• /
• v.13 no.2
• /
• pp.183-189
• /
• 2009

Purpose : To evaluate the usefulness of three-dimensional (3D) maximal intensity projection (MIP) reconstruction method in breast MRI. Materials and Methods : Total 54 breasts of consecutive 27 patients were examined by breast MRI. Breast MRI was performed using GE Signa Excite Twin speed (GE medical system, Wisconsin, USA) 1.5T. We obtained routine breast MR images including axial T2WI, T1WI, sagittal T1FS, dynamic contrast-enhanced T1FS, and subtraction images. 3D MIP reconstruction images were obtained as follows; subtraction images were obtained using TIPS and early stage of contrast-enhanced TIPS images. And then 3D MIP images were obtained using the subtraction images through advantage workstation (GE Medical system). We detected and analyzed the lesions in the 3D MIP and routine MRI images according to ACR $BIRADS^{(R)}$ MRI lexicon. And then we compared the findings of 3D MIP and those of routine breast MR images and evaluated whether 3D MIP had additional information comparing to routine MR images. Results : 3D MIP images detect the 43 of 56 masses found on routine MR images (76.8%). In non-mass like enhancement, 3D MIP detected 17 of 20 lesions (85 %). And there were one hundred sixty nine foci at 3D MIP images and one hundred nine foci at routine MR images. 3D MIP images detected 14 of 23 category 3 lesions (60.9%), 11 of 16 category 4 lesions (68.87%), 28 of 28 Category 5 lesions (100%). In analyzing the enhancing lesions at 3D MIP images, assessment categories of the lesions were correlated as the results at routine MR images (p-value < 0.0001). 3D MIP detected additional two daughter nodules that were descriped foci at routine MR images and additional one nodule that was not detected at routine MR images. Conclusion : 3D MIP image has some limitations but is useful as additional image of routine breast MR Images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4763-4775
• /
• 2020

This research aims to develop a deep learning-based method that automatically detects and segments the defects on railroad surfaces to reduce the cost of visual inspection of the railroad. We developed our segmentation model by modifying a fully convolutional network model [1], a well-known segmentation model used for machine learning, to detect and segment railroad surface defects. The data used in this research are images of the railroad surface with one or more defect regions. Railroad images were cropped to a suitable size, considering the long height and relatively narrow width of the images. They were also normalized based on the variance and mean of the data images. Using these images, the suggested model was trained to segment the defect regions. The proposed method showed promising results in the segmentation of defects. We consider that the proposed method can facilitate decision-making about railroad maintenance, and potentially be applied for other analyses.