• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1242-1250
• /
• 2019

Super resolution technique aims to convert a low-resolution image with coarse details to a corresponding high-resolution image with refined details. In the past decades, the performance is greatly improved due to progress of deep learning models. However, universal solution for various objects is a still challenging issue. We observe that learning super resolution with a general dataset has poor performance on faces. In this paper, we propose a super resolution fusion scheme that works well for both general- and face datasets to achieve more universal solution. In addition, object-specific feature extractor is employed for better reconstruction performance. In our experiments, we compare our fusion image and super-resolved images from one- of the state-of-the-art deep learning models trained with DIV2K and FFHQ datasets. Quantitative and qualitative evaluates show that our fusion scheme successfully works well for both datasets. We expect our fusion scheme to be effective on other objects with poor performance and this will lead to universal solutions.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.88-91
• /
• 1997

One of the most significant feature of diagnostic ultrasonic instrument is to display information on the soft tissues in the body in real time. In this paper we carried out basic study on the digital moving image processing for tracing the movement of heart valves in echocardiograms. Digital moving image file was made from analog echocardiograms and it was remade as 256 gray-level images on each frame. The ROI(Region of interest) was placed on a heart valve region to process images efficiently. Images were processed by the use of image enhancement filters and morphology filters. The result shows that the processed images were more enhanced than original images. When a moving image is reconstructed by using these enhanced images, we can trace the movement of heart valves more easily. In this study we proposed the availability of the moving image reconstruction using enhancement images.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.2
• /
• pp.89-89
• /
• 2014

While the current consensus view holds that galaxy mergers are commonplace, it is sometimes speculated that Globular Clusters (GCs) may also have undergone merging events, possibly resulting in massive objects with a strong metallicity spread such as Omega Centauri. Galaxies are mostly far, unresolved systems whose mergers are most likely wet, resulting in observational as well as modeling difficulties, but GCs are resolved into stars that can be used as discrete dynamical tracers, and their mergers might have been dry, therefore easily simulated with an N-body code. It is however difficult to determine the observational parameters best suited to reveal a history of merging based on the positions and kinematics of GC stars, if evidence of merging is at all observable. To overcome this difficulty, we investigate the applicability of supervised and unsupervised machine learning to the automatic reconstruction of the dynamical history of a stellar system. In particular we test whether statistical clustering methods can classify simulated systems into monolithic versus merger products. We run direct N-body simulations of two identical King-model clusters undergoing a head-on collision resulting in a merged system, and other simulations of isolated King models with the same total number of particles as the merged system. After several relaxation times elapse, we extract a sample of snapshots of the sky-projected positions of particles from each simulation at different dynamical times, and we run a variety of clustering and classification algorithms to classify the snapshots into two subsets in a relevant feature space.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1262-1272
• /
• 1996

Pure functional languages have the referential transparency feature sothat all objects cannot be updated destuctively. Once an aggregated data structure such as array is updated, both the original and newly updated array must be preserved to maintain reverential transparency. Thus, it is required to develop an efficient mechanism with which can reduce the maintenance cost while maintaining referential transparency for whole data. This study is to suggest a functional array to solve the problem, and them test it. For that, the proposed mechanism was implemented on a combinator graph reduction machine. The result shows that proposed mechanism reduces traversal time for array operations. Also, updating all versions and accessing the recent version are achieved in constant time without reconstruction of updated data in execution time.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.262-268
• /
• 2017

Intelligent video surveillance systems have been developed to monitor global areas and find specific target objects using a large-scale database. However, person re-identification presents some challenges, such as pose change and occlusions. To solve the problems, this paper presents an improved person re-identification method using sparse representation and saliency-based dictionary construction. The proposed method consists of three parts: i) feature description based on salient colors and textures for dictionary elements, ii) orthogonal atom selection using cosine similarity to deal with pose and viewpoint change, and iii) measurement of reconstruction error to rank the gallery corresponding a probe object. The proposed method provides good performance, since robust descriptors used as a dictionary atom are generated by weighting some salient features, and dictionary atoms are selected by reducing excessive redundancy causing low accuracy. Therefore, the proposed method can be applied in a large scale-database surveillance system to search for a specific object.

• Journal of Information Display
• /
• v.8 no.4
• /
• pp.27-31
• /
• 2007

In this paper, we present an efficient tiled stereo display system for tangible meeting. For tangible meeting, it is important to provide immersive display with high resolution image to cover up the field of view and provide to the local user the same environment as that of remote site. To achieve these, a high resolution image needs to be transmitted for reconstruction of remote world, and it should be displayed using a tiled display. However, it is hard to transmit high resolution image in real time due to the limit of network bandwidth, and so we receive multiple images and reconstruct a remote world with received images in advance. Then, we update only a specific area where remote user exists by receiving low resolution image in realtime. We synthesize the transmitted image to the existing environmental map of remote world and display it as a stereo image. For this, we developed a new system which supports GPU based real time warping and blending, automatic feature extraction using machine vision technique.

• Cartoon and Animation Studies
• /
• s.32
• /
• pp.363-381
• /
• 2013

In this paper, on the web, offline mobile learning content to reinforce the learning of the video frame-by-frame necessary for re-learning area to capture only the important areas. The frame of the captured image and the image in the form of advanced training time saved and also a description of the notes feature to store. The area needed for the capture area re-learning the learner to learner-centered custom systems can be applied. In order to capture the learning program, regardless of the configuration of the selected frame by frame in order to capture the user-centric storytelling-based learning can be applied. Capture the full effect of the system compared to learning and learner-centered learning time-saving reconstruction of the frame according to the customized learning to play a positive role in improving effectiveness.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.1
• /
• pp.8-16
• /
• 2016

In the field of computer vision and robotics, bin picking is an important application area in which object pose estimation is necessary. Different approaches, such as 2D feature tracking and 3D surface reconstruction, have been introduced to estimate the object pose accurately. We propose a new approach where we can use both 2D image features and 3D surface information to identify the target object and estimate its pose accurately. First, we introduce a label detection technique using Maximally Stable Extremal Regions (MSERs) where the label detection results are used to identify the target objects separately. Then, the 2D image features on the detected label areas are utilized to generate 3D surface information. Finally, we calculate the 3D position and the orientation of the target objects using the information of the 3D surface.

• International journal of advanced smart convergence
• /
• v.7 no.3
• /
• pp.130-139
• /
• 2018

This study is to analyze the relationship between character and human semantic production through research on character visualization artworks and to develop a creative platform that visually expresses the formative and semantic dynamics of characters using the results will be. The 3D spatial interaction system using the character visualization proposed generates the transformation of the character in real time using the interaction with user and the deconstruction of the character structure. Transformations of characters including the intentions of the viewers provide a dynamic visual representation to the viewer and maximize the efficiency of meaning transfer by producing various related meanings. The method of dynamic deconstruction and reconstruction of the characters provided by this system creates special shapes that viewers cannot imagine until now and further extends the interpretation range of the meaning of the characters. Therefore, the proposed system not only induces an active viewing attitude from viewers, but also gives them an opportunity to enjoy watching the artwork and demonstrate creativity as a creator. This system induces new gestures of the viewer in real time through the transformation of characters in accordance with the viewer''s gesture, and has the feature of exchanging emotions with viewers.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.487-495
• /
• 2007

When error occurs during the network transmission of the image, the quality of the restored image is very serious. Therefore to maintain the received image quality, the error concealment technique is necessary. This paper presents an efficient spatial error concealment method using adaptive edge-oriented interpolation. It deals with errors on slice level. The proposed method uses boundary matching method having 2-step processes. We divide error block into external and internal region, adaptively restore each region. Because this method use overall as well as local edge characteristics, it preserves edge continuity and texture feature. The proposed technique reduces the complexity and provide better reconstruction quality for damaged images than the previous methods.