• Journal of Digital Policy
• /
• v.3 no.3
• /
• pp.9-14
• /
• 2024

In this paper, proposes a method using a multi block structure composed of residual blocks with adaptive weights to improve the quality of results in single image super resolution. In the process of generating super resolution images using deep learning, the most critical factor for enhancing quality is feature extraction and application. While extracting various features is essential for restoring fine details that have been lost due to low resolution, issues such as increased network depth and complexity pose challenges in practical implementation. Therefore, the feature extraction process was structured efficiently, and the application process was improved to enhance quality. To achieve this, a multi block structure was designed after the initial feature extraction, with nested residual blocks inside each block, where adaptive weights were applied. Additionally, for final high resolution reconstruction, a multi kernel image reconstruction process was employed, further improving the quality of the results. The performance of the proposed method was evaluated by calculating PSNR and SSIM values compared to the original image, and its superiority was demonstrated through comparisons with existing algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.403-408
• /
• 2003

A general meaning of caricaturing is that a representation, especially pictorial or literary, in which the subject's distinctive features or peculiarities are deliberately exaggerated to produce a comic or grotesque effect. In other words, a caricature is defined as a rough sketch(dessin) which is made by detecting features from human face and exaggerating or warping those. There have been developed many methods which can make a caricature image from human face using computer. In this paper, we propose a new caricaturing system. The system uses a real-time image or supplied image as an input image and deals with it on four processing steps and then creates a caricatured image finally. The four Processing steps are like that. The first step is detecting a face from input image. The second step is extracting special coordinate values as facial geometric information. The third step is deforming the face image using local warping method and the coordinate values acquired in the second step. In fourth step, the system transforms the deformed image into the better improved edge image using a fuzzy Sobel method and then creates a caricatured image finally. In this paper , we can realize a caricaturing system which is simpler than any other exiting systems in ways that create a caricatured image and does not need complex algorithms using many image processing methods like image recognition, transformation and edge detection.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.7
• /
• pp.550-559
• /
• 2018

The effectiveness of deep neural networks (DNNs) for detection and classification of micro-Doppler signals generated by human walking and background noise sources is investigated. Previous research included a complex process for extracting meaningful features that directly affect classifier performance, and this feature extraction is based on experiences and statistical analysis. However, because a DNN gradually reconstructs and generates features through a process of passing layers in a network, the preprocess for feature extraction is not required. Therefore, binary classifiers and multiclass classifiers were designed and analyzed in which multilayer perceptrons (MLPs) and DNNs were applied, and the effectiveness of DNNs for recognizing micro-Doppler signals was demonstrated. Experimental results showed that, in the case of MLPs, the classification accuracies of the binary classifier and the multiclass classifier were 90.3% and 86.1%, respectively, for the test dataset. In the case of DNNs, the classification accuracies of the binary classifier and the multiclass classifier were 97.3% and 96.1%, respectively, for the test dataset.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.2
• /
• pp.32-46
• /
• 2017

Recent rapid urban expansion and crowding of various industrial facilities has affected the features of a significant part of downtown area, resulting in areas having buildings with a wide range of height and the foothills. To compute a velocity pressure exposure coefficient, namely the design wind speed factor, this study defines ground surface roughness by utilizing concentration analysis for the height of each building. After obtaining spatial data by extracting a building layer from digital maps, the study area was partitioned for the concentration analysis and to allow investigation of the frequency distribution of building heights. Concentration analysis by building height was determined with the Variation-to-Means Ratio (VMR) and Poisson distribution analysis using a buildings distribution chart, with statistical significance determined using Chi-square verification. Applying geographic information systems (GIS) with the architectural information made it possible to estimate a velocity pressure exposure coefficient factor more quantitatively and objectively, by including geographic features, as compared to current methods. Thus, this method is expected to eliminate inaccuracies that arise when building designers calculate the velocity pressure exposure coefficient in subjective way, and to help increase the wind resistance of buildings in a more logical and cost-effective way.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.28-34
• /
• 2012

Various feature extraction algorithms are widely applied to real-time image processing applications for extracting significant features from images. Feature extraction algorithms are mostly combined with image processing algorithms mostly for image tracking and recognition. Feature extraction function is used to supply feature information to the other image processing algorithms and it is mainly implemented in a preprocessing stage. Nowadays, image processing applications are faced with embedded system implementation for a real-time processing. In order to satisfy this requirement, it is necessary to reduce execution time so as to improve the performance. Reducing the time for executing a feature extraction function dose not only extend the execution time for the other image processing algorithms, but it also helps satisfy a real-time requirement. This paper explains FAST (Feature from Accelerated Segment Test algorithm) of E. Rosten and presents FPGA-based embedded hardware accelerator architecture. The proposed acceleration scheme can be implemented by using approximately 2,217 Flip Flops, 5,034 LUTs, 2,833 Slices, and 18 Block RAMs in the Xilinx Vertex IV FPGA. In the Modelsim - based simulation result, the proposed hardware accelerator takes 3.06 ms to extract 954 features from a image with $640{\times}480$ pixels and this result shows the cost effectiveness of the propose scheme.

• Journal of KIISE:Software and Applications
• /
• v.28 no.5
• /
• pp.389-401
• /
• 2001

This paper proposes an abstraction mechanism of the low-level digital video features for the automatic retrievals of the explosion scenes from the digital video library. In the proposed abstraction mechanism, the regional dominant colors of the key frame and the motion energy of the shot are defined as the primary abstractions of the shot for the explosion scene retrievals. It is because an explosion shot usually consists of the frames with a yellow-tone pixel and the objects in the shot are moved rapidly. The regional dominant colors of shot are selected by dividing its key frame image into several regions and extracting their regional dominant colors, and the motion energy of the shot is defined as the edge image differences between key frame and its neighboring frame. The edge image of the key frame makes the retrieval of the explosion scene more precisely, because the flames usually veils all other objects in the shot so that the edge image of the key frame comes to be simple enough in the explosion shot. The proposed automatic retrieval algorithm declares an explosion scene if it has a shot with a yellow regional dominant color and its motion energy is several times higher than the average motion energy of the shots in that scene. The edge image of the key frame is also used to filter out the false detection. Upon the extensive exporimental results, we could argue that the recall and precision of the proposed abstraction and detecting algorithm are about 0.8, and also found that they are not sensitive to the thresholds. This abstraction mechanism could be used to summarize the long action videos, and extract a high level semantic information from digital video archive.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.163-170
• /
• 2019

Over the past decade, the development of the Web explosively increased the data. Feature selection step is an important step in extracting valuable data from a large amount of data. This study proposes a novel opinion mining model based on combining feature selection (FS) methods with Word embedding to vector (Word2vec) and BOW (Bag-of-words). FS methods adopted for this study are CFS (Correlation based FS) and IG (Information Gain). To select an optimal FS method, a number of classifiers ranging from LR (logistic regression), NN (neural network), NBN (naive Bayesian network) to RF (random forest), RS (random subspace), ST (stacking). Empirical results with electronics and kitchen datasets showed that LR and ST classifiers combined with IG applied to BOW features yield best performance in opinion mining. Results with laptop and restaurant datasets revealed that the RF classifier using IG applied to Word2vec features represents best performance in opinion mining.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.553-566
• /
• 2021

River confluence is often characterized by shear layer and the associated strong mixing. In natural rivers, the main channel and its tributary can be separated by the shear layer using contrasting colors. The shear layer can be easily observed using aerial images from satellite or unmanned aerial vehicles. This study proposes a low-cost identification method extracting geographic features of the shear layer using RGB aerial image. The method consists of three stages. At first, in order to identify the shear layer, it performs image segmentation using a Gaussian mixture model and extracts the water bodies of the main channel and tributary. Next, the self-organizing map simplifies the flow line of the water bodies into the 1-dimensional curve grid. After that, the curvilinear coordinate transformation is performed using the water body pixels and the curve grid. As a result, the shear layer identification method was successfully applied to the confluence between Nakdong River and Nam River to extract geometric shear layer features (confluence angle, upstream- and downstream- channel widths, shear layer length, maximum shear layer thickness).

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.79-89
• /
• 2022

Images taken using drones have been applied to fields that require rapid decision-making as they can quickly construct high-quality 3D spatial information for small regions. To construct spatial information based on drone images, it is necessary to determine the relationship between images by extracting keypoints between adjacent drone images and performing image matching. Therefore, in this study, three study regions photographed using a drone were selected: a region where parking lots and a lake coexisted, a downtown region with buildings, and a field region of natural terrain, and the performance of AKAZE (Accelerated-KAZE), BRISK (Binary Robust Invariant Scalable Keypoints), KAZE, ORB (Oriented FAST and Rotated BRIEF), SIFT (Scale Invariant Feature Transform), and SURF (Speeded Up Robust Features) algorithms were analyzed. The performance of the keypoints extraction algorithms was compared with the distribution of extracted keypoints, distribution of matched points, processing time, and matching accuracy. In the region where the parking lot and lake coexist, the processing speed of the BRISK algorithm was fast, and the SURF algorithm showed excellent performance in the distribution of keypoints and matched points and matching accuracy. In the downtown region with buildings, the processing speed of the AKAZE algorithm was fast and the SURF algorithm showed excellent performance in the distribution of keypoints and matched points and matching accuracy. In the field region of natural terrain, the keypoints and matched points of the SURF algorithm were evenly distributed throughout the image taken by drone, but the AKAZE algorithm showed the highest matching accuracy and processing speed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.329-346
• /
• 2022

Recently, as the market for short form videos (Instagram, TikTok, YouTube) on social media has gradually increased, research using them is actively being conducted in the artificial intelligence field. A representative research field is Video to Shop, which detects fashion products in videos and searches for product images. In such a video-based artificial intelligence model, product features are extracted using convolution operations. However, due to the limitation of computational resources, extracting features using all the frames in the video is practically impossible. For this reason, existing studies have improved the model's performance by sampling only a part of the entire frame or developing a sampling method using the subject's characteristics. In the existing Video to Shop study, when sampling frames, some frames are randomly sampled or sampled at even intervals. However, this sampling method degrades the performance of the fashion product search model while sampling noise frames where the product does not exist. Therefore, this paper proposes a sampling method MF (Missing Fashion items on frame) sampler that removes noise frames and improves the performance of the search model. MF sampler has improved the problem of resource limitations by developing a keyframe mechanism. In addition, the performance of the search model is improved through noise frame removal using the noise detection model. As a result of the experiment, it was confirmed that the proposed method improves the model's performance and helps the model training to be effective.