• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.318-328
• /
• 2014

In this paper, as a way of performance improvement of business card recognition in the mobile environment, we suggested a hybrid OCR agent which combines data using a parallel processing sequence between various algorithms and different kinds of business card recognition engines which have learning data. We also suggested an Image Processing Method on mobile cameras which adapts to the changes of the lighting, exposing axis and the backgrounds of the cards which occur depending on the photographic conditions. In case a hybrid OCR agent is composed by the method suggested above, the average recognition rate of Korean business cards has improved from 90.69% to 95.5% compared to the cases where a single engine is used. By using the Image Processing Method, the image capacity has decreased to the average of 50%, and the recognition has improved from 83% to 92.48% showing 9.4% improvement.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.1
• /
• pp.37-45
• /
• 2008

This paper proposes a half-silvered mirror display system designed to demonstrate useful information about things on display into the air. It helps the spectators gain quick access to information near the area where the things are put on display. This paper deals with three matters: First, tracking based on camera images created in real time enables the provision of information about the things that are both still and moving. Second, as information is output based on the real-time coordinates of things on display, the parallel processing-based tracking algorithm is used to ensure smooth transfer. Third, a half-mirror is placed in front of the display area to establish an augmented reality system and visual distortion caused by mirror angle is adjusted by the reflection transformation matrix. The objectives of this system are to arouse the spectators' interest in things on display and offer easy and quick access to information about them.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.5_6
• /
• pp.360-370
• /
• 2004

Adaptive mesh refinement(AMR) is one of the popular computational simulation techniques used in various scientific and engineering fields. Although AMR data is organized in a hierarchical multi-resolution data structure, traditional volume visualization algorithms such as ray-casting and splatting cannot handle the form without converting it to a sophisticated data structure. In this paper, we present a hierarchical multi-resolution splatting technique using k-d trees and octrees for AMR data that is suitable for implementation on the latest consumer PC graphics hardware. We describe a graphical user interface to set transfer function and viewing / rendering parameters interactively. Experimental results obtained on a general purpose PC equipped with an nVIDIA GeForce3 card are presented to demonstrate that the proposed techniques can interactively render AMR data(over 20 frames per second). Our scheme can easily be applied to parallel rendering of time-varying AMR data.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.1-10
• /
• 2015

In this paper, we propose an efficient parallel implementation method of a widely used complex four-stage fire detection algorithm using a graphics processing unit (GPU) to improve the performance of the algorithm and analyze the performance of the parallel implementation method. In addition, we use seven different resolution videos (QVGA, VGA, SVGA, XGA, SXGA+, UXGA, QXGA) as inputs of the four-stage fire detection algorithm. Moreover, we compare the performance of the GPU-based approach with that of the CPU implementation for each different resolution video. Experimental results using five different fire videos with seven different resolutions indicate that the execution time of the proposed GPU implementation outperforms that of the CPU implementation in terms of execution time and takes a 25.11ms per frame for the UXGA resolution video, satisfying real-time processing (30 frames per second, 30fps) of the fire detection algorithm.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.2
• /
• pp.417-424
• /
• 2019

This paper presents the design of a JPEG-LS codec for lossless image compression from AR/VR device. The proposed JPEG-LS(: LosSless) codec is mainly composed of a context modeling block, a context update block, a pixel prediction block, a prediction error coding block, a data packetizer block, and a memory block. All operations are organized in a fully pipelined architecture for real time image processing and the LOCO-I compression algorithm using improved 2D approach to compliant with the SBT coding. Compared with a similar study in JPEG-LS, the Block-RAM size of proposed STB-FLC architecture is reduced to 1/3 compact and the parallel design of the predication block could improved the processing speed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.18 no.3
• /
• pp.23-32
• /
• 2008

The computing power of graphics processing units(GPU) has already surpassed that of CPU and the gap between their powers is getting wider. Thus, research on GPGPU which applies GPU to general purpose becomes popular and shows great success especially in the field of parallel data processing. Since the implementation of cryptographic algorithm using GPU was started by Cook et at. in 2005, improved results using graphic libraries such as OpenGL and DirectX have been published. In this paper, we present skills and results of implementing block ciphers using CUDA library announced by NVIDIA in 2007. Also, we discuss a general method converting source codes of block ciphers on CPU to those on GPU. On NVIDIA 8800GTX GPU, the resulting speeds of block cipher AES, ARIA, and DES are 4.5Gbps, 7.0Gbps, and 2.8Gbps, respectively which are faster than the those on CPU.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.63-69
• /
• 2022

In this paper, we propose a new GPU-based framework for quickly calculating adaptive and continuous SDF(Signed distance fields), and examine cases related to rendering/collision processing using them. The quadtree constructed from the triangle mesh is transferred to the GPU memory, and the Euclidean distance to the triangle is processed in parallel for each thread by using it to find the shortest continuous distance without discontinuity in the adaptive grid space. In this process, it is shown through experiments that the cut-off view of the adaptive distance field, the distance value inquiry at a specific location, real-time raytracing, and collision handling can be performed quickly and efficiently. Using the proposed method, the adaptive sign distance field can be calculated quickly in about 1 second even on a high polygon mesh, so it is a method that can be fully utilized not only for rigid bodies but also for deformable bodies. It shows the stability of the algorithm through various experimental results whether it can accurately sample and represent distance values in various models.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.176-188
• /
• 2022

In this paper, we propose a compact method for anthropomorphism that uses Deep Convolutional Neural Networks (DCNN) to detect the similarities between a human face and an animal face. We also apply texture feature-based morphing between them. We propose a basic texture feature-based morphing system for morphing between human faces only. The entire anthropomorphism process starts with the creation of an animal face classifier using a parallel DCNN that determines the most similar animal face to a given human face. The significance of our network is that it contains four sets of convolutional functions that run in parallel, allowing it to extract more features than a linear DCNN network. Our employed texture feature algorithm-based automatic morphing system recognizes the facial features of the human face and takes the Control Points automatically, rather than the traditional human aiding manual morphing system, once the similarity was established. The simulation results show that our suggested DCNN surpasses its competitors with a 92.0% accuracy rate. It also ensures that the most similar animal classes are found, and the texture-based morphing technology automatically completes the morphing process, ensuring a smooth transition from one image to another.