• 제목/요약/키워드: Image and Code Analysis

검색결과 131건 처리시간 0.027초

휴대전화의 2D 이미지코드 인식 기술동향 (Technological Tendency for 2D Image Code and Its Recognition on Mobile Phone)

  • 박종만;박종규
    • 한국통신학회논문지
    • /
    • 제36권6B호
    • /
    • pp.663-673
    • /
    • 2011
  • 휴대전화를 통한 2D(Two Dimensional) 이미지 인식기반의 QR(Quick Response)코드 및 칼라코드 활용이 급속히 확산되면서 디코딩 기술과 플랫폼의 개선이 요구되고 있으며, 범용 디지털카메라에 의한 소형 비주얼코드의 비 초점 이미지정보 인식기술인 새로운 보코드(Bokode)라는 기술이 발표되었다. 이에 스마트환경 기반의 2D 이미지코드와 인식기술에 대한 연구개발 및 산업 활성화를 위한 대응전략이 절실히 필요한 시점이다. 논문은 이 같은 전략수립을 지원하기 위해 기술 및 산업동향 조사 분석을 통한 정보지원 및 실천과제 제시에 중점을 두며 기술개요 기술동향, 기술 활성화 과제, 전망 및 제안 등으로 구성하였다.

트렌드 분석을 통한 남성 패션 이미지 연출에 관한 연구 (A Study on Men's Fashion Image Coordination through Trend Analysis)

  • 김윤경;이경희
    • 한국의류학회지
    • /
    • 제29권5호
    • /
    • pp.703-714
    • /
    • 2005
  • The purpose of this study is to acquire various methods for the fashion image coordination and to examine common features of variation of coordination methods according to the trend. It has attained by investigating Men's fashion image coordination through trend analysis in terms of its coordination features and its variety aspects. For this study, it has classified into twelve typical Men's fashion images in collecting 1,291 pieces of photographs on the subject of jackets and pants from Men's fashion collection$(1995\~2002)$. The study has examined methods and features of fashion image coordination by year according to design elements and the harmony between items. In addition, it has drawn common factors in the image coordination. The summary and conclusion are as follows. A year of 1995, it has presented as the essential code of the variation that morphologic aspects of a design in the fashion image coordination. Various designs have developed through the variation of shapes such as shoulder width, shoulder pad, jacket width and its length and so on. In the initial stage, the width of shoulder and jacket has fitted into large pattern and then adjusted elegantly to make fit the body that indicates a dissolution according to an avant-garde image. At the time that over-measurement of the shape has reduced and high quality and variation of materials has gradually become significant. Those are often used that high-quality glossy materials or other materials which are opposite to the basic code of the original fashion image materials and qualities regardless of images. On the pattern and color, in addition, have represented neat and elegant impression with moderate applications rather than quantitative abundance that have used opposite elements to the basic code f3r the change code like materials. Furthermore, before and after 1999, ' it shows that a concept of the total coordination has arisen that increased coordination methods to strengthen and affluent its images for the whole with wearing accessaries such as hats, gloves, sunglasses, mufflers, bags, belts and so on.

사각관 이상유동 분석을 위한 전기적 캐패시턴스 토모그라피 코드 개발 (Development of an Electrical Capacitance Tomography Code for Analysis of Two-Phase Flow in the Rectangular Pipe)

  • 이경황;이재영
    • 대한기계학회논문집B
    • /
    • 제29권1호
    • /
    • pp.87-94
    • /
    • 2005
  • A computer code for Electrical Capacitance Tomography (ECT) is developed to sense the cross sectional phase distribution of two-phase flow in the rectangular pipe in which the tomography sensor furnished by the insulated wall, electrodes, and electric field screen. The computer code had two steps for the image reconstruction. In the forward projection step, the sensitivity matrix was constructed based on the electric field calculated by the finite difference method. In the backward projection step, the sensitivity matrix and the measured capacitances were used to reconstruct the cross sectional image. Several algorithms including LBP, TR, ITR, and PLI were employed to find the proper one for the two-phase flow analysis. Since the dielectric constant of the water in two-phase flow is sensitive to the thermal parameter such as, temperature and pressure, the developed code was evaluated to find their accuracy, speed of calculation, and sensitivity to the variation of the dielectric constant. It was found that the iterative methods are superior to the direct methods for the image reconstruction, and the PLI method was the best in the variation of the dielectric constants.

중성자 토모그래피를 위한 영상처리 자체코드 개발 연구 (Research for development of our own image processing code for neutron tomography)

  • 김진만;김태주;유동인
    • 한국가시화정보학회지
    • /
    • 제18권1호
    • /
    • pp.44-49
    • /
    • 2020
  • Neutron radiography has been widely used in many research areas due to its different characteristics from X-rays. Neutron tomography is a powerful tool because it can clearly show the inside of an object that the eye cannot see. However, generally, commercial software is used for the reconstruction of neutron tomography. It means that maintenance costs are incurred and analysis is inefficient in some cases. In this respect, our own image processing code is required to reconstruct neutron images efficiently. In this study, an image processing code is developed for reconstruction of cross-sectional images from neutron radiography taken from the side of the object. Using the developed code, cross-sectional images of the sample are successfully reconstructed.

LLVM IR 대상 악성코드 탐지를 위한 이미지 기반 머신러닝 모델 (Image-Based Machine Learning Model for Malware Detection on LLVM IR)

  • 박경빈;윤요섭;또올가;임강빈
    • 정보보호학회논문지
    • /
    • 제34권1호
    • /
    • pp.31-40
    • /
    • 2024
  • 최근 정적분석 기반의 시그니처 및 패턴 탐지 기술은 고도화되는 IT 기술에 따라 한계점이 드러나고 있다. 이는 여러 아키텍처에 대한 호환 문제와 시그니처 및 패턴 탐지의 본질적인 문제이다. 악성코드는 자신의 정체를 숨기기 위하여 난독화, 패킹 기법 등을 사용하고 있으며 또한, 코드 재정렬, 레지스터 변경, 분기문 추가 등 기존 정적분석 기반의 시그니처 및 패턴 탐지 기법을 회피하고 있다. 이에 본 논문에서는 이러한 문제를 해결할 수 있는 머신러닝을 통한 LLVM IR 코드 이미지 기반 악성코드 정적분석 자동화 기술을 제안한다. 바이너리가 난독화되거나 패킹된 사실에 불구하고 정적 분석 및 최적화를 위한 중간언어인 LLVM IR로 디컴파일한다. 이후 LLVM IR 코드를 이미지로 변환하여 CNN을 이용한 알고리즘 중 전이 학습 및 Keras에서 지원하는 ResNet50v2으로 학습하여 악성코드를 탐지하는 모델을 제시한다.

변환부호화된 영상신호에 대한 채널 오류의 영향 (Effects of Channel Errors on Transform-Coded Image Signals)

  • 백종기;문상재
    • 한국통신학회논문지
    • /
    • 제12권3호
    • /
    • pp.216-223
    • /
    • 1987
  • 본 논문에서는 영상신호의 변환부호화 시스템에서 통계적으로 독립적인 채널 전송오류의 영향을 MSE로 계산하였다. 양자화가 입력신호의 확률밀도함수를 Laplacian, Gaussian, 그리고 uniform분포로 가정하였으며, 양자화된 신호의 부호화시 사용되는 코드로는 NBC, FBC, MDC 및 Gray code가 고려되었다. 본 연구의 결과들로부터, 양자화기입력신호의 확률밀도함수에 따라 어떠한 코드로 부호화하는 것이 채널 전송오류의 영향을 작게 받는가를 알 수 있다.

  • PDF

Joint-transform Correlator Multiple-image Encryption System Based on Quick-response Code Key

  • Chen, Qi;Shen, Xueju;Cheng, Yue;Huang, Fuyu;Lin, Chao;Liu, HeXiong
    • Current Optics and Photonics
    • /
    • 제3권4호
    • /
    • pp.320-328
    • /
    • 2019
  • A method for joint-transform correlator (JTC) multiple-image encryption based on a quick-response (QR) code key is proposed. The QR codes converted from different texts are used as key masks to encrypt and decrypt multiple images. Not only can Chinese text and English text be used as key text, but also symbols can be used. With this method, users have no need to transmit the whole key mask; they only need to transmit the text that is used to generate the key. The correlation coefficient is introduced to evaluate the decryption performance of our proposed cryptosystem, and we explore the sensitivity of the key mask and the capability for multiple-image encryption. Robustness analysis is also conducted in this paper. Computer simulations and experimental results verify the correctness of this method.

funcGNN과 Siamese Network의 코드 유사성 분석 성능비교 (Comparison of Code Similarity Analysis Performance of funcGNN and Siamese Network)

  • 최동빈;조인수;박용범
    • 반도체디스플레이기술학회지
    • /
    • 제20권3호
    • /
    • pp.113-116
    • /
    • 2021
  • As artificial intelligence technologies, including deep learning, develop, these technologies are being introduced to code similarity analysis. In the traditional analysis method of calculating the graph edit distance (GED) after converting the source code into a control flow graph (CFG), there are studies that calculate the GED through a trained graph neural network (GNN) with the converted CFG, Methods for analyzing code similarity through CNN by imaging CFG are also being studied. In this paper, to determine which approach will be effective and efficient in researching code similarity analysis methods using artificial intelligence in the future, code similarity is measured through funcGNN, which measures code similarity using GNN, and Siamese Network, which is an image similarity analysis model. The accuracy was compared and analyzed. As a result of the analysis, the error rate (0.0458) of the Siamese network was bigger than that of the funcGNN (0.0362).

한국 디지털 전통색채이미지를 이용한 배색유형 개발 (A Development of Color Prototypes Based on Digital Color Image Analysis)

  • 이현수;김준지
    • 한국실내디자인학회논문집
    • /
    • 제16권6호
    • /
    • pp.240-249
    • /
    • 2007
  • The purpose of this paper is to produce color harmony code based on color harmony prototype in terms of environmental color design. This paper proposes ways of categorizing more accurate color harmony prototype through digital image processing by the computer program called the Color Syntax. The method of analysis adopted in this paper is pixel based color image processing. The study suggests color harmony prototype which are categorized by a color harmony angles. These angles represented internal relations between colors. This study describes development processes of color harmony prototype which is a basis for creating color harmony codes. Development processes of color harmony schema consists of color analysis, color codes generation and color selection. Also, how to analyze color images and to chose suitable harmony color codes among various codes are main research issues. As a final result, 109 color harmony codes have been obtained. These code numbers are suggested through rotating 2 color pairs in a 360-degree arc in the same color harmony angles, the codes which is applicable to the color harmony schema previously developed. This color harmony codes will produce better color environment in a sense that it will help designers to maximally reduce their time consumption, and the results of their designs will also be related to the use of proper color for regional environments.

Numerical and experimental study on flexural behavior of reinforced concrete beams: Digital image correlation approach

  • Krishna, B. Murali;Reddy, V. Guru Prathap;Tadepalli, T.;Kumar, P. Rathish;Lahir, Yerra
    • Computers and Concrete
    • /
    • 제24권6호
    • /
    • pp.561-570
    • /
    • 2019
  • Understanding the realistic behavior of concrete up to failure under different loading conditions within the framework of damage mechanics and plasticity would lead to an enhanced design of concrete structures. In the present investigation, QR (Quick Response) code based random speckle pattern is used as a non-contact sensor, which is an innovative approach in the field of digital image correlation (DIC). A four-point bending test was performed on RC beams of size 1800 mm × 150 mm × 200 mm. Image processing was done using an open source Ncorr algorithm for the results obtained using random speckle pattern and QR code based random speckle pattern. Load-deflection curves of RC beams were plotted for the results obtained using both contact and non-contact (DIC) sensors, and further, Moment (M)-Curvature (κ) relationship of RC beams was developed. The loading curves obtained were used as input data for material model parameters in finite element analysis. In finite element method (FEM) based software, concrete damage plasticity (CDP) constitutive model is used to predict the realistic nonlinear quasi-static flexural behavior of RC beams for monotonic loading condition. The results obtained using QR code based DIC are observed to be on par with conventional results and FEM results.