• Title/Summary/Keyword: 추출.변환소프트웨어

Search Result 146, Processing Time 0.03 seconds

Automatic 3D data extraction method of fashion image with mannequin using watershed and U-net (워터쉐드와 U-net을 이용한 마네킹 패션 이미지의 자동 3D 데이터 추출 방법)

  • Youngmin Park
    • The Journal of the Convergence on Culture Technology
    • /
    • v.9 no.3
    • /
    • pp.825-834
    • /
    • 2023
  • The demands of people who purchase fashion products on Internet shopping are gradually increasing, and attempts are being made to provide user-friendly images with 3D contents and web 3D software instead of pictures and videos of products provided. As a reason for this issue, which has emerged as the most important aspect in the fashion web shopping industry, complaints that the product is different when the product is received and the image at the time of purchase has been heightened. As a way to solve this problem, various image processing technologies have been introduced, but there is a limit to the quality of 2D images. In this study, we proposed an automatic conversion technology that converts 2D images into 3D and grafts them to web 3D technology that allows customers to identify products in various locations and reduces the cost and calculation time required for conversion. We developed a system that shoots a mannequin by placing it on a rotating turntable using only 8 cameras. In order to extract only the clothing part from the image taken by this system, markers are removed using U-net, and an algorithm that extracts only the clothing area by identifying the color feature information of the background area and mannequin area is proposed. Using this algorithm, the time taken to extract only the clothes area after taking an image is 2.25 seconds per image, and it takes a total of 144 seconds (2 minutes and 4 seconds) when taking 64 images of one piece of clothing. It can extract 3D objects with very good performance compared to the system.

Judgment about the Usefulness of Automatically Extracted Temporal Information from News Articles for Event Detection and Tracking (사건 탐지 및 추적을 위해 신문기사에서 자동 추출된 시간정보의 유용성 판단)

  • Kim Pyung;Myaeng Sung-Hyon
    • Journal of KIISE:Software and Applications
    • /
    • v.33 no.6
    • /
    • pp.564-573
    • /
    • 2006
  • Temporal information plays an important role in natural language processing (NLP) applications such as information extraction, discourse analysis, automatic summarization, and question-answering. In the topic detection and tracking (TDT) area, the temporal information often used is the publication date of a message, which is readily available but limited in its usefulness. We developed a relatively simple NLP method of extracting temporal information from Korean news articles, with the goal of improving performance of TDT tasks. To extract temporal information, we make use of finite state automata and a lexicon containing time-revealing vocabulary. Extracted information is converted into a canonicalized representation of a time point or a time duration. We first evaluated the extraction and canonicalization methods for their accuracy and investigated on the extent to which temporal information extracted as such can help TDT tasks. The experimental results show that time information extracted from text indeed helps improve both precision and recall significantly.

A Study on the Method and Tool Development for Extracting Objects from Procedure-oriented System (절차중심 시스템으로부터 객체추출 방법 및 도구개발에 관한 연구)

  • Kim, Jung-Jong;Son, Chang-Min
    • The Transactions of the Korea Information Processing Society
    • /
    • v.5 no.3
    • /
    • pp.649-661
    • /
    • 1998
  • If there is redeveloping into the system applying the object-oriented paradigm, productivity Improvement of software through reuse would be accomplished and maintenance cost be reduced. When a procedure-oriented system is transformed to a type applying the object-oriented paradigm, various techniques are studied to extract objects from source code automatically or semi-automatically. However, it is not easy to extract conceptuat objects when those techniques are applied, This problem entails another problem which drops the conceptual integrity of the extracted objects. In this paper, we suggest an object extraction method and tool development to resolve the problem occurring at the time when thc pr"~r"m, dcveloped through procedure-oriented is transformed to an object-oriented system. The suggested method allow to extract the desired objects using object modeling for various application domains of the real world given source code and design recovery information. During the extraction process, functionality and global variables of the source code as well as its intcrface arc rigorously analyzed. This process can enhance the conceptual integrity of the objects and make easy to construct class hierarchies.

  • PDF

A Research on Efficient Design and Creation of Ontology Using Software Engineering Method (소프트웨어 공학적 방법을 이용한 온톨로지의 효율적인 설계 및 생성에 관한 연구)

  • Lee Yun-Su;Kim Tae-Suk;Yang Jin-Hyuk;Chung In-Jeong
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2004.11a
    • /
    • pp.645-648
    • /
    • 2004
  • 현재 웹 데이터는 폭발적으로 증가하고 있지만 이를 통해 유용한 정보를 추출한 지식 표현 위주의 웹 데이터는 부족한 실정이다. 이러한 문제점을 해결하기 위해 제안된 시맨틱 웹은 온톨로지를 기반구조로 하고 있다. 그러나 현재 온톨로지의 생성에 관한 기존 연구들은 대부분 도메인 전문가들의 휴리스틱에 의존하는 수작업 형태를 띠고 있다. 이러한 방법은 많은 시간과 노력이 소요될 뿐만 아니라 뜻하지 않은 오류가 나타날 수 있다. 이와 같은 문제를 해결하기 위해 우리는 소프트웨어 공학적인 접근방법을 통하여 온톨로지를 효과적으로 설계 및 생성하는 방법을 제안한다. 우리는 기존의 UML과 OWL을 단순 매핑하는 방법에 MDA 접근법의 장점들을 취하여 통합, 확장하였다. 즉, MDA를 기반으로 UML을 이용하여 온톨로지를 설계한 후 설계된 온톨로지 모델을 XMI를 통해 온톨로지 기술 언어인 OWL로 변환하는 과정을 거쳐 온톨로지를 생성한다. 끝으로 구체적인 보기를 통해 본 논문에서 제안한 방법의 타당성을 보인다.

  • PDF

Anomaly detection performance improvement technique through weight matrix-based optical flow equalization (가중치 행렬 기반 광학 흐름 평활화를 통한 이상 행동 탐지 성능 향상 기법)

  • Lim, Hyun-seok;Kim, In-ki;Kang, Jaeyong;Gwak, Jeong-hwan
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2021.07a
    • /
    • pp.145-146
    • /
    • 2021
  • 본 연구에서는 카메라의 촬영 시점에 의해서 발생되는 원근감이 광학 흐름 생성에 어떠한 영향을 주는지 살펴보고 광학 흐름 기반 이상행동 탐지 솔루션의 성능을 고도화하기 위해 기존 광학 흐름 영상으로부터 소실점 기반 가중치 행렬을 계산하여 원근감에 따른 광학 흐름 정도를 평활하는 기법에 대해서 연구한다. 카메라의 뷰포인트에 따라 원근감의 발생 정도나 객체의 크기 및 움직임의 정도가 달라지게 되며, 이는 원본 영상 프레임을 광학 흐름의 크기와 방향성으로 표현하는 영상 변환 네트워크를 가진 생성적 적대 신경망을 학습할 때 정상적인 행동 패턴의 범위를 결정짓는 데 방해가 될 수 있다. 이러한 문제를 해결하기 위하여 데이터셋의 배경으로부터 소실점을 추출하고 원근감에 따라 결정되는 광학 흐름의 크기를 평활하는 기법을 개발하여 기존 모델의 성능과 비교하였으며, 프레임 단위의 정확도 성능이 5.75% 향상된 것으로 확인되었다.

  • PDF

Development of PSD Sensor Based Distance Measuring System Using Linearizing Function of Voltage-Distance Conversion (선형화 전압-거리 변환함수를 이용한 PSD 센서기반 거리계측시스템의 개발)

  • Kim Yu-Chan;Ryoo Young-Jae
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.15 no.6
    • /
    • pp.668-672
    • /
    • 2005
  • In this paper, a distance measuring system using a PSD sensor in proposed, which in suitable for low-cost localization sensor of a mobile robot. Because the distance-voltage output of PSD sensor has a non-linear property, the linearizing function is proposed through the experimental characteristics of the sensor. And the characteristics are tested and the distance-voltage data are measured in various colors and materials of object. The parameters of the proposed function are extracted by using the measured data. Finally, the performance and the accuracy of the developed system are verified according to the comparison of the distance by the proposed function with the real distance.

Detection of Direction Indicators on Road Surfaces Using Inverse Perspective Mapping and NN (원근투영법과 신경망을 이용한 도로노면 방향지시기호 검출 연구)

  • Kim, Jong Bae
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.4 no.4
    • /
    • pp.201-208
    • /
    • 2015
  • This paper proposes a method for detecting the direction indicator shown in the road surface efficiently from the black box system installed on the vehicle. In the proposed method, the direction indicators are detected by inverse perspective mapping(IPM) and bag of visual features(BOF)-based NN classifier. In order to apply the proposed method to real-time environments, the candidated regions of direction indicator in an image only performs IPM, and BOF-based NN is used for the classification of feature information from direction indicators. The results of applying the proposed method to the road surface direction indicators detection and recognition, the detection accuracy was presented at least about 89%, and the method presents a relatively high detection rate in the various road conditions. Thus it can be seen that the proposed method is applied to safe driving support systems available.

Three-Dimensional Image Registration using a Locally Weighted-3D Distance Map (지역적 가중치 거리맵을 이용한 3차원 영상 정합)

  • Lee, Ho;Hong, Helen;Shin, Yeong-Gil
    • Journal of KIISE:Software and Applications
    • /
    • v.31 no.7
    • /
    • pp.939-948
    • /
    • 2004
  • In this paper. we Propose a robust and fast image registration technique for motion correction in brain CT-CT angiography obtained from same patient to be taken at different time. First, the feature points of two images are respectively extracted by 3D edge detection technique, and they are converted to locally weighted 3D distance map in reference image. Second, we search the optimal location whore the cross-correlation of two edges is maximized while floating image is transformed rigidly to reference image. This optimal location is determined when the maximum value of cross-correlation does't change any more and iterates over constant number. Finally, two images are registered at optimal location by transforming floating image. In the experiment, we evaluate an accuracy and robustness using artificial image and give a visual inspection using clinical brain CT-CT angiography dataset. Our proposed method shows that two images can be registered at optimal location without converging at local maximum location robustly and rapidly by using locally weighted 3D distance map, even though we use a few number of feature points in those images.

Automatic Conversion of English Pronunciation Using Sequence-to-Sequence Model (Sequence-to-Sequence Model을 이용한 영어 발음 기호 자동 변환)

  • Lee, Kong Joo;Choi, Yong Seok
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.6 no.5
    • /
    • pp.267-278
    • /
    • 2017
  • As the same letter can be pronounced differently depending on word contexts, one should refer to a lexicon in order to pronounce a word correctly. Phonetic alphabets that lexicons adopt as well as pronunciations that lexicons describe for the same word can be different from lexicon to lexicon. In this paper, we use a sequence-to-sequence model that is widely used in deep learning research area in order to convert automatically from one pronunciation to another. The 12 seq2seq models are implemented based on pronunciation training data collected from 4 different lexicons. The exact accuracy of the models ranges from 74.5% to 89.6%. The aim of this study is the following two things. One is to comprehend a property of phonetic alphabets and pronunciations used in various lexicons. The other is to understand characteristics of seq2seq models by analyzing an error.

Aspect Mining Process Design Using Abstract Syntax Tree (추상구문트리를 이용한 어스팩트 마이닝 프로세스 설계)

  • Lee, Seung-Hyung;Song, Young-Jae
    • The Journal of the Korea Contents Association
    • /
    • v.11 no.5
    • /
    • pp.75-83
    • /
    • 2011
  • Aspect-oriented programming is the paradigm which extracts crosscutting concern from a system and solves scattering of a function and confusion of a code through software modularization. Existing aspect developing method has a difficult to extract a target area, so it is not easy to apply aspect mining. In an aspect minning, it is necessary a technique that convert existing program refactoring elements to crosscutting area. In the paper, it is suggested an aspect mining technique for extracting crosscutting concern in a system. Using abstract syntax structure specification, extract functional duplicated relation elements. Through Apriori algorithm, it is possible to create a duplicated syntax tree and automatic creation and optimization of a duplicated source module, target of crosscutting area. As a result of applying module of Berkeley Yacc(berbose.c) to mining process, it is confirmed that the length and volume of program has been decreased of 9.47% compared with original module, and it has been decreased of 4.92% in length and 5.11% in volume compared with CCFinder.