• Journal of Platform Technology
• /
• v.6 no.4
• /
• pp.26-33
• /
• 2018

In this paper, we propose an image retrieval algorithm for real-time processing and design it as hardware. The proposed method is based on the classification of BoWs(Bag of Words) algorithm and proposes an image search algorithm using bit stream. K-fold cross validation is used for the verification of the algorithm. Data is classified into seven classes, each class has seven images and a total of 49 images are tested. The test has two kinds of accuracy measurement and speed measurement. The accuracy of the image classification was 86.2% for the BoWs algorithm and 83.7% the proposed hardware-accelerated software implementation algorithm, and the BoWs algorithm was 2.5% higher. The image retrieval processing speed of BoWs is 7.89s and our algorithm is 1.55s. Our algorithm is 5.09 times faster than BoWs algorithm. The algorithm is largely divided into software and hardware parts. In the software structure, C-language is used. The Scale Invariant Feature Transform algorithm is used to extract feature points that are invariant to size and rotation from the image. Bit streams are generated from the extracted feature point. In the hardware architecture, the proposed image retrieval algorithm is written in Verilog HDL and designed and verified by FPGA and Design Compiler. The generated bit streams are stored, the clustering step is performed, and a searcher image databases or an input image databases are generated and matched. Using the proposed algorithm, we can improve convenience and satisfaction of the user in terms of speed if we search using database matching method which represents each object.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.3
• /
• pp.111-115
• /
• 2017

Terahertz waves are superior to conventional X-ray or Magnetic Resonance Tomography(MRI), and the amount of information that can be transmitted is as large as thousands of times that conventional X-ray or MRI. In addition, Terahertz waves have great performance in analyzing an object which have some layered structure. By using this advantage, we can extract the letters of a page by analyzing information such as absorption amount and reflection amount by irradiating a closed book with pulses of various frequencies within gap of a terahertz wave. However, in the image of each page using the Terahertz wave might be obtained various kinds of noise and the different character occlusion region. So, to extract letters from the terahertz image, we must take the noise and occlusion region away. We have been working to enhancement the image quality in various ways, and keep on studying de-noising processing for enhancement about the image quality and high resolution. Finally, we also keep on studying about OCR(Optical Character Recognition) technology, which based on pattern matching technique, to read letters.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.121-126
• /
• 2022

The number of vehicles has increased exponentially over the past 20 years due to technological advancements. It is becoming almost impossible to manually control and manage the traffic in a city like Karachi. Without license plate recognition, traffic management is impossible. The Framework for License Plate Detection & Recognition to overcome these issues is proposed. License Plate Detection & Recognition is primarily performed in two steps. The first step is to accurately detect the license plate in the given image, and the second step is to successfully read and recognize each character of that license plate. Some of the most common algorithms used in the past are based on colour, texture, edge-detection and template matching. Nowadays, many researchers are proposing methods based on deep learning. This research proposes a framework for License Plate Detection & Recognition using a custom YOLOv5 Object Detector, image segmentation techniques, and Tesseract's optical character recognition OCR. The accuracy of this framework is 0.89.

• Annual Conference of KIPS
• /
• 2009.04a
• /
• pp.216-219
• /
• 2009

3 차원 콘텐트를 이용한 물리기반 시뮬레이션은 최근 컴퓨터 그래픽스 분야에서 가장 활발히 연구되는 연구 중 하나이다. 이와 더불어 이러한 기술들과 사용자간의 몰입감을 증가시키는 상호작용 기술 역시 계속하여 증가하는 추세이다. 본 연구는 이러한 추세에 발맞추어 물리기반 형상변형 기술의 몰입감을 증가시키기 위한 상호작용 방법을 제안한다. 제안된 방법에서는 3 차원 객체와 사용자와의 효율적인 상호작용을 위해서 시스템을 증강현실 환경에서 구현하였다. 증강현실을 이용한 시스템의 제약조건은 실시간 계산이다. 때문에, 제안된 시스템은 RBF(Radial Basis Function) [1] 와 LSM (Lattice Shape Matching) [2, 3] 방법을 조합하여 물리기반 상호작용 기술을 완성 하였고 실험을 통해 실시간 계산을 확인하였다. 또한, 3 차원 객체가 충돌하여 변형이 일어날 때 감각형 객체 (Tangible object)에 진동을 주어 물리기반 형상변형의 사용자 상호작용에 관한 몰입감을 증가시켰다.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.210-215
• /
• 2023

As a public space providing night commercial services, night market represents the regional culture of a region or city to a certain extent. With the development of material economy and the continuous improvement of spiritual civilization, the modern night market has also begun to show some new changes. is an important strategy for the development and transformation of modern night market to build the brand image of night market and turn the traditional night market into a new "national tide" night market". Based on the regional cultural perspective, this paper takes many night markets in Changzhou, China as the object of study, and aims to summarize the effective ways to construct a new night market image. We are designed the following conclusions. The first is to deploy rational and unique features. The second is to enrich the business style and to perfect matching. The third is to regulate management and promote multiple effects. Therefore, it is expected that a new strategy will be proposed to create a night market brand image from a local cultural perspective.

• Journal of KIBIM
• /
• v.13 no.3
• /
• pp.30-38
• /
• 2023

Building Information Models(BIM) provides rich geometric and attribute information throughout the entire life cycle of a building and infrastructure object, while Geographic Information System(GIS) enables the detail analysis of urban issues based on the geo-spatial information in support of decision-making. The Integration of BIM and GIS data makes it possible to create a digital twin of the land in order to effectively manage smart cities. In the perspective of integrating BIM data into GIS systems, this study performs literature reviews on georeferencing techniques and identifies limitations in carrying out the georeferencing process using attribute information associated with absolute coordinates probided by Industry Foundation Classes(IFC) as a BIM standard. To address these limitations, an automated georeferencing process is proposed as a pilot study to position a IFC model with the Local Coordinate System(LCS) in GIS environments with the Reference Coordinate System(RCS). An evaluation of the proposed approach over a BIM model demonstrates that the proposed method is expected to be a great help for automatically georeferencing complex BIM models in a GIS environment, and thus provides benefits for efficient and reliable BIM and GIS integration in practice.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.577-584
• /
• 2024

The construction sector is known as a main source of increased CO2 emissions, and BIM-LCA integration is expected to reduce the environmental burden by helping to control emissions and energy during the basic design stage. However, numerous studies showed that LCA is complicated as it requires great efforts in creating BOQ and linking multiple databases together. In addition, a precise LCA requires LOD 300, a level of detail that often takes a lot of effort to establish at the basic design stage. To address this issue, this study proposes a BOM-based BIM-LCA integrated model that uses a combination of Uniclass, IDEA, and the Calculation Formula Library, which focuses on the development and exploitation of information, even if the 3D Object's Level of Detail is low. The model allows the decomposition of the building information in order to create BOM and BOQ at a high level of detail from the basic design stage onward. Furthermore, it allows the flexible connection of data sources to perform LCA in a systematic manner.

• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.877-895
• /
• 2014

It is common sense that providing specific odor can increase the video reality when video scene has an object having specific odor. However, people still do not know how to increase video reality and emotional immersion when there is no information on specific odor in the scene. So, present study explores how we improve video reality and immersion when the scene has no concrete odor information from some objects. Especially, this research focuses on diverse previous studies about matching between odor and color and then we expect providing odor can increase video reality if the odor is well-matched with the video's color. To do this, we collected 48 odors and investigated which color was well-matched with each odor. As a result, we get 5 odors which had clearly well-matched colors and decide ill-matched colors of those 5 odors as complementary colors of well-matched colors (Experiment 1). After that, we organize 3 conditions such as coloring image and video clip with well-matched color (color-odor match condition), coloring those with ill-matched color (color-odor mismatch condition), and coloring those with achromatic color by removing color saturation (color-odor neutral condition). Under each of these three conditions, image-odor matching, increment of reality with the odor, increment of immersion with the odor, and odor preference are asked (Experiment 2; 3). The results showed that the scores of all 4 questions in color-odor match condition were higher than color-odor mismatch condition and neutral condition. These results mean that providing matching odor with the scene's color in video is very effective to increase video reality and immersion. We expect experiencing better reality and immersion with olfactory information by adding various future research.

• Journal of Korean Society for Geospatial Information Science
• /
• v.7 no.1 s.13
• /
• pp.53-63
• /
• 1999

For the close range digital photogrammetry, multi-step procedures should be embodied in an integrated system. However, it is hard to construct an Integrated system through conventional procedural processing. Using Object Oriented Programming(OOP), photogrammetric processings can be classified with corresponding subjects and it is easy to construct an integrated system lot digital photogrammetry as well as to add the newly developed classes. In this study, the equation of 3-dimensional mathematic model is developed to make an immediate calibration of the CCD camera, the focus distance of which varies according to the distance of the object. Classes for the input and output of images are also generated to carry out the close range digital photogrammetric procedures by OOP. Image matching, coordinate transformation, dirct linear transformation and bundle adjustment are performed by producing classes corresponding to each part of data processing. The bundle adjustment, which adds the principle coordinate and focal length term to the non-photogrammetric CCD camera, is found to increase usability of the CCD camera and the accuracy of object positioning. In conclusion, classes and their hierarchies in the digital photogrammetry are designed to manage multi-step procedures using OOP and close range digital photogrammetric process is implemented using CCD camera in an integrated System.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.49-59
• /
• 2008

SIFT(Scale Invariant Feature Transform) is an algorithm to extract vectors at pixels around keypoints, in which the pixel colors are very different from neighbors, such as vortices and edges of an object. The SIFT algorithm is being actively researched for various image processing applications including 3-D image constructions, and its most computation-intensive stage is a keypoint localization. In this paper, we develope a fixed-point model of the keypoint localization and propose its efficient hardware architecture for embedded applications. The bit-length of key variables are determined based on two performance measures: localization accuracy and error rate. Comparing with the original algorithm (implemented in Matlab), the accuracy and error rate of the proposed fixed point model are 93.57% and 2.72% respectively. In addition, we found that most of missing keypoints appeared at the edges of an object which are not very important in the case of keypoints matching. We estimate that the hardware implementation will give processing speed of $10{\sim}15\;frame/sec$, while its fixed point implementation on Pentium Core2Duo (2.13 GHz) and ARM9 (400 MHz) takes 10 seconds and one hour each to process a frame.