• The KIPS Transactions:PartB
• /
• v.12B no.6 s.102
• /
• pp.671-678
• /
• 2005

In this paper, we suggest an algorithm that allows us to extract the important obbject from motion pictures and then replace the background with arbitrary images. The suggested technique can be used not only for protecting privacy and reducing the size of data to be transferred by removing the background of each frame, but also for replacing the background with user-selected image in video communication systems including mobile phones. Because of the relatively large size of image data, digital image processing usually takes much of the resources like memory and CPU. This can cause trouble especially for mobile video phones which typically have restricted resources. In our experiments, we could reduce the requirements of time and memory for processing the images by restricting the search area to the vicinity of major object's contour found in the previous frame based on the fact that the movement of major object is not wide or rapid in general. Specifically, we detected edges and used the edge image of the initial frame to locate candidate-object areas. Then, on the located areas, we computed the difference image between adjacent frames and used it to determine and trace the major object that might be moving. And then we computed the contour of the major object and used it to separate major object from the background. We could successfully separate major object from the background and replate the background with arbitrary images.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.362-371
• /
• 2014

Blur variation caused by camera de-focusing provides a proper cue for depth estimation. Depth from Defocus (DFD) technique calculates the blur amount present in an image considering that blur amount is directly related to scene depth. Conventional DFD methods use two defocused images that might yield the low quality of an estimated depth map as well as a reconstructed infocused image. To solve this, a new DFD methodology based on infocused and defocused images is proposed in this paper. In the proposed method, the outcome of Subbaro's DFD is combined with a novel edge blur estimation method so that improved blur estimation can be achieved. In addition, a saliency map mitigates the ill-posed problem of blur estimation in the region with low intensity variation. For validating the feasibility of the proposed method, twenty image sets of infocused and defocused images with 2K FHD resolution were acquired from a camera with a focus control in the experiments. 3D stereoscopic image generated by an estimated depth map and an input infocused image could deliver the satisfactory 3D perception in terms of spatial depth perception of scene objects.

• Ecology and Resilient Infrastructure
• /
• v.8 no.1
• /
• pp.1-8
• /
• 2021

A surface image velocimeter (SIV) measures the velocity of a particle group by calculating the intensity distribution of the particle group in two consecutive images of the water surface using a cross-correlation method. Therefore, to increase the accuracy of the flow velocity calculated by a SIV, it is important to accurately calculate the displacement of the particle group in the images. In other words, the change in the physical distance of the particle group in the two images to be analyzed must be accurately calculated. In the image of an actual river taken using a camera, camera lens distortion inevitably occurs, which affects the displacement calculation in the image. In this study, we analyzed the effect of camera lens distortion on the displacement calculation using a dense and uniformly spaced grid board. The results showed that the camera lens distortion gradually increased in the radial direction from the center of the image. The displacement calculation error reached 8.10% at the outer edge of the image and was within 5% at the center of the image. In the future, camera lens distortion correction can be applied to improve the accuracy of river surface flow rate measurements.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.35-43
• /
• 2022

Makeup is the most common way to improve a person's appearance. However, since makeup styles are very diverse, there are many time and cost problems for an individual to apply makeup directly to himself/herself.. Accordingly, the need for makeup automation is increasing. Makeup transfer is being studied for makeup automation. Makeup transfer is a field of applying makeup style to a face image without makeup. Makeup transfer can be divided into a traditional image processing-based method and a deep learning-based method. In particular, in deep learning-based methods, many studies based on Generative Adversarial Networks have been performed. However, both methods have disadvantages in that the resulting image is unnatural, the result of makeup conversion is not clear, and it is smeared or heavily influenced by the makeup style face image. In order to express the clear boundary of makeup and to alleviate the influence of makeup style facial images, this study divides the makeup area and calculates the loss function using HoG (Histogram of Gradient). HoG is a method of extracting image features through the size and directionality of edges present in the image. Through this, we propose a makeup transfer network that performs robust learning on edges.By comparing the image generated through the proposed model with the image generated through BeautyGAN used as the base model, it was confirmed that the performance of the model proposed in this study was superior, and the method of using facial information that can be additionally presented as a future study.

• Korean Journal of Radiology
• /
• v.21 no.10
• /
• pp.1165-1177
• /
• 2020

Objective: To assess the feasibility of applying a deep learning-based denoising technique to coronary CT angiography (CCTA) along with iterative reconstruction for additional noise reduction. Materials and Methods: We retrospectively enrolled 82 consecutive patients (male:female = 60:22; mean age, 67.0 ± 10.8 years) who had undergone both CCTA and invasive coronary artery angiography from March 2017 to June 2018. All included patients underwent CCTA with iterative reconstruction (ADMIRE level 3, Siemens Healthineers). We developed a deep learning based denoising technique (ClariCT.AI, ClariPI), which was based on a modified U-net type convolutional neural net model designed to predict the possible occurrence of low-dose noise in the originals. Denoised images were obtained by subtracting the predicted noise from the originals. Image noise, CT attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were objectively calculated. The edge rise distance (ERD) was measured as an indicator of image sharpness. Two blinded readers subjectively graded the image quality using a 5-point scale. Diagnostic performance of the CCTA was evaluated based on the presence or absence of significant stenosis (≥ 50% lumen reduction). Results: Objective image qualities (original vs. denoised: image noise, 67.22 ± 25.74 vs. 52.64 ± 27.40; SNR [left main], 21.91 ± 6.38 vs. 30.35 ± 10.46; CNR [left main], 23.24 ± 6.52 vs. 31.93 ± 10.72; all p < 0.001) and subjective image quality (2.45 ± 0.62 vs. 3.65 ± 0.60, p < 0.001) improved significantly in the denoised images. The average ERDs of the denoised images were significantly smaller than those of originals (0.98 ± 0.08 vs. 0.09 ± 0.08, p < 0.001). With regard to diagnostic accuracy, no significant differences were observed among paired comparisons. Conclusion: Application of the deep learning technique along with iterative reconstruction can enhance the noise reduction performance with a significant improvement in objective and subjective image qualities of CCTA images.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_1
• /
• pp.931-946
• /
• 2017

The purpose of this study is to observe and analyze soil moisture conditions with high resolution and to evaluate its application feasibility to agriculture. For this purpose, we used three Landsat-8 OLI (Operational Land Imager)/TIRS (Thermal Infrared Sensor) optical and thermal infrared satellite images taken from May to June 2015, 2016, and 2017, including the rural areas of Jeollabuk-do, where 46% of agricultural areas are located. The soil moisture conditions at each date in the study area can be effectively obtained through the SPI (Standardized Precipitation Index)3 drought index, and each image has near normal, moderately wet, and moderately dry soil moisture conditions. The temperature vegetation dryness index (TVDI) was calculated to observe the soil moisture status from the Landsat-8 OLI/TIRS images with different soil moisture conditions and to compare and analyze the soil moisture conditions obtained from the SPI3 drought index. TVDI is estimated from the relationship between LST (Land Surface Temperature) and NDVI (Normalized Difference Vegetation Index) calculated from Landsat-8 OLI/TIRS satellite images. The maximum/minimum values of LST according to NDVI are extracted from the distribution of pixels in the feature space of LST-NDVI, and the Dry/Wet edges of LST according to NDVI can be determined by linear regression analysis. The TVDI value is obtained by calculating the ratio of the LST value between the two edges. We classified the relative soil moisture conditions from the TVDI values into five stages: very wet, wet, normal, dry, and very dry and compared to the soil moisture conditions obtained from SPI3. Due to the rice-planing season from May to June, 62% of the whole images were classified as wet and very wet due to paddy field areas which are the largest proportions in the image. Also, the pixels classified as normal were analyzed because of the influence of the field area in the image. The TVDI classification results for the whole image roughly corresponded to the SPI3 soil moisture condition, but they did not correspond to the subdivision results which are very dry, wet, and very wet. In addition, after extracting and classifying agricultural areas of paddy field and field, the paddy field area did not correspond to the SPI3 drought index in the very dry, normal and very wet classification results, and the field area did not correspond to the SPI3 drought index in the normal classification. This is considered to be a problem in Dry/Wet edge estimation due to outlier such as extremely dry bare soil and very wet paddy field area, water, cloud and mountain topography effects (shadow). However, in the agricultural area, especially the field area, in May to June, it was possible to effectively observe the soil moisture conditions as a subdivision. It is expected that the application of this method will be possible by observing the temporal and spatial changes of the soil moisture status in the agricultural area using the optical satellite with high spatial resolution and forecasting the agricultural production.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.6
• /
• pp.623-629
• /
• 2002

In transmitting compressed video bit-stream over Internet, packet losses cause error propagations in both spatial and temporal domains, which in turn leads to severe degradation I image quality. In this paper, a new error concealment algorithm, called EBMA(Edge Detection based Boundary Matching Algorithm), is proposed to repair damaged portions of the video frames in the receiver. Conventional BMA(Boundary Matching Algorithm) assumes that the pixels on the boundary of the missing block and its neighboring blocks are very similar, but has no consideration of edges across the boundary. In our approach, the edges are detected across the boundary of the lost or erroneous block. Once the orientation of each edge is found, only the pixel difference along the expected edges across the boundary is measured instead of the calculation of difference along the expected edges across the boundary is measured instead of the calculation of differences between all adjacent pixels on the boundary Therefore, the proposed approach needs very few computations and the experiment shows and improvement of the performance over the conventional BMA in terms of both subjective and objective quality of video sequences.

• Journal of the Korean association of regional geographers
• /
• v.9 no.4
• /
• pp.425-436
• /
• 2003

Integrated approach is presented by developing the technology and the ways of the practical use of the integrated digital map of and Electronical Navigational Chart (ENC) and Digital Terrain Map (DTM) for the effective and scientific based conservation, development and management of coastal area in this study. At first as preliminary studies to make eventual integrated maps, the necessity of the integrated map is described with the concept of coastal areas. Then, the characteristics of digital maps developed by Korean Geography Institute and National Marine Investigation Institute are carefully analyzed and integrated to a digital map as a test for edge matching in coastal line. Developed test coastal map was overlayed with a high-resolution satellite image (KVR-1000). The ground survey using Global Positioning System was conducted for the analysis of edge matching along the coastal line. Results from the edge matching analysis of coastal lines showed about 14 meters mean difference in artificial terrain and 4 meters mean difference in natural terrain. The problems, causes and solutions for the edge-matched differences are described. Furthermore, the value of utilization, the future use and various fields of application produced by the integrated digital map database are suggested as a basis for ICZM implementation in South Korea.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.581-588
• /
• 2018

The aim of this study is to propose a fine co-registration approach for multi-temporal satellite images acquired from RapidEye, which has an advantage of availability for time-series analysis. To this end, we generate multitemporal ortho-rectified images using RPCs (Rational Polynomial Coefficients) provided with RapidEye images and then perform fine co-registration between the ortho-rectified images. A DEM (Digital Elevation Model) extracted from the digital map was used to generate the ortho-rectified images, and the RNCC (Registration Noise Cross Correlation) was applied to conduct the fine co-registration. Experiments were carried out using 4 RapidEye 1B images obtained from May 2015 to November 2016 over the Yeonggwang area. All 5 bands (blue, green, red, red edge, and near-infrared) that RapidEye provided were used to carry out the fine co-registration to show their possibility of being applicable for the co-registration. Experimental results showed that all the bands of RapidEye images could be co-registered with each other and the geometric alignment between images was qualitatively/quantitatively improved. Especially, it was confirmed that stable registration results were obtained by using the red and red edge bands, irrespective of the seasonal differences in the image acquisition.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.353-360
• /
• 2006

This paper presents a robust algorithm for segmenting a vehicle license plate area from a road image. We consider the features of license plates in three aspects : 1) edges due to the characters in the plate, 2) colors in the plate, and 3) geometric properties of the plate. In the preprocessing step, we compute the thresholds based on each feature to decide whether a pixel is inside a plate or not. A statistical approach is applied to the sample images to compute the thresholds. For a given road image, our algorithm binarizes it by using the thresholds. Then, we select three candidate regions to be a plate by searching the binary image with a moving window. The plate area is selected among the candidates with simple heuristics. This algorithm robustly detects the plate against the transformation or the difference of color intensity of the plate in the input image. Moreover, the preprocessing step requires only a small number of sample images for the statistical processing. The experimental results show that the algorithm has 97.8% of successful segmentation of the plate from 228 input images. Our prototype implementation shows average processing time of 0.676 seconds per image for a set of $1280{\times}960$ images, executed on a 3GHz Pentium4 PC with 512M byte memory.