• Title/Summary/Keyword: document image understanding

Search Result 10, Processing Time 0.022 seconds

Machine Learning Based Automatic Categorization Model for Text Lines in Invoice Documents

  • Shin, Hyun-Kyung
    • Journal of Korea Multimedia Society
    • /
    • v.13 no.12
    • /
    • pp.1786-1797
    • /
    • 2010
  • Automatic understanding of contents in document image is a very hard problem due to involvement with mathematically challenging problems originated mainly from the over-determined system induced by document segmentation process. In both academic and industrial areas, there have been incessant and various efforts to improve core parts of content retrieval technologies by the means of separating out segmentation related issues using semi-structured document, e.g., invoice,. In this paper we proposed classification models for text lines on invoice document in which text lines were clustered into the five categories in accordance with their contents: purchase order header, invoice header, summary header, surcharge header, purchase items. Our investigation was concentrated on the performance of machine learning based models in aspect of linear-discriminant-analysis (LDA) and non-LDA (logic based). In the group of LDA, na$\"{\i}$ve baysian, k-nearest neighbor, and SVM were used, in the group of non LDA, decision tree, random forest, and boost were used. We described the details of feature vector construction and the selection processes of the model and the parameter including training and validation. We also presented the experimental results of comparison on training/classification error levels for the models employed.

Document Structure Understanding on Subjects Registration Table

  • Ito, Yuichi;Ohno, Masanaga;Tsuruoka, Shinji;Yoshikawa, Tomohiro;Tsuyoshi, Shinogi
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 2003.09a
    • /
    • pp.571-574
    • /
    • 2003
  • This research is aimed to automate the generating process of the database from paper based table forms like this work. The registration table has so complicate table structures, ana in this research we used the registration tables as an example of general table structure understanding. We propose a table structure understanding system for some table types, and it has some steps. The first step is that the document images on paper are read from the image scanner. The second step is that a document image segments into some tables. In the third step, the character strings is extracted using image processing technology and the property of the character strings is determined. And the structured database is generated automatically. The proposed system consists of two systems. "Master document generation system" is used for the table form definition, and it doesn′t include the handwritten characters. "Structure analysis system for complete d table" is used for the written form, and it analyzes the table form filled in the handwritten character. We implemented the system using MS Visual C++ on Windows, and it can get the correct extraction rate 98% among 51 registration tables written by the different students.

  • PDF

A Novel Text to Image Conversion Method Using Word2Vec and Generative Adversarial Networks

  • LIU, XINRUI;Joe, Inwhee
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2019.05a
    • /
    • pp.401-403
    • /
    • 2019
  • In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.

The Type of Preference of Interior Design according to the Life Style (생활양식에 따른 실내디자인 선호유형)

  • 박혜숙;윤정숙
    • Korean Institute of Interior Design Journal
    • /
    • no.27
    • /
    • pp.64-75
    • /
    • 2001
  • As living condition has improved, agreeable living environmental plans that reflect residential traits are needed from. the first stage of house remodeling or interior construction. At the request of above, we need systematically study about the householder's preference according to the life style. The purpose of this study is to suggest the case of preferred interior by understanding preferred Interior image and interior design elements. Document and questionnaire research are used as the method of study. The subjects of research wear 702 persons from 20th to 40th. Contents are constituted with general traits, life style and preferred interior image and the analysis of the materials is quantifical analysis using statistics. In the base of the theory of interior image and interior design elements appeared In the documents, measuring apparatus is made up and suggested preferred examples of interior design depend on life style by combining preferences.

  • PDF

A Study on the Characteristics and Images of Rainbow Colors For Fashion Design (패션 디자인을 위한 무지개 색의 특성과 이미지 고찰)

  • 김지언;김영인
    • Journal of the Korean Society of Costume
    • /
    • v.54 no.5
    • /
    • pp.125-138
    • /
    • 2004
  • This study has the aim of defining the special characteristics and images of the rainbow colored fashion by understanding the theoretical bases of rainbow colors and analyzing rainbow colored fashion images in historical materials. western and folk costumes. modern fashion design. Giving careful consideration to the rainbow colored fashion makes it possible to develope the innovative way of fashion design to satisfy the needs of color usual for designers and colorists. To obtain the purposes, document study and survey study have been executed. The results of this study are as follows. In document studies, the beginning of rainbow colored fashion went back in ancient Egypt. Also saikdong of korea, poncho of indians are the examples of the rainbow colored fashion. The rainbow colored fashion were put on a man of position in principle ceremony for ornaments. In survey studies, the clothing perception characteristics in rainbow colored fashion were analyzed. Main factors of perception characteristics In the rainbow colored fashion are 'closed form', 'whole', 'indeterminate', 'rounded', 'planar separation' The factors that affect the perception of rainbow colored fashion are 'closed form' and 'indeterminate' characteristics. And rainbow colored fashion images and clothing perception characteristics can be classified into four main images : Vigorous, Colorful/fairy, Fresh, Mysterious/brilliant. Therefore. this study is to systematize the characteristics and images of rainbow colors. Based on the results makes it possible to adapt rainbow colors to fashion design efficiently, for the suggested design elements and color palettes include basic three fashion design elements color. texture. form.

Understanding Documents With Chemical Structures Using Image Segmentation (영상 분할을 활용한 화학 구조 문서 이해)

  • Yang, Haeyoon;Cho, Nam Ik
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2022.06a
    • /
    • pp.1297-1300
    • /
    • 2022
  • Document layout analysis는 문서 이미지의 구조와 구성요소를 파악하는 기술이다. 기존 딥러닝을 사용한 학습 기반 방법에는 각 구성 요소를 검출하는 detection 기반 방식이 많으나 이는 다양한 형식의 문서 이미지에 확장될 수 있는 가능성이 낮다는 한계가 존재한다. 특히, 다양한 모양과 크기의 화학 구조를 포함하는 화학 문서 이미지에 적용하기 어렵다. 본 논문에서는 영상분할을 활용하여 화학 구조 문서를 이해하는 연구를 진행하였다. 기존의 블록 단위로 레이블링된 벤치마크와 다르게 객체 단위로 레이블링한 학습 데이터를 가지고 DeepLabv3 구조의 네트워크를 학습하여 화학 문서 이미지를 효과적으로 분할하였다. 객체 단위 레이블링과 영상 분할을 사용한 방식이 문서 이해 및 화학 구조 검출에 준수한 성능을 보이는 것을 확인하였고 이 방식이 다양한 형식의 문서 이미지에 확장될 수 있음을 보였다.

  • PDF

Exploring Elementary Teachers' Difficulties on Teaching Science by Analyzing Questions in an Autonomous Online Teacher Community : Focusing on Physics Questions in Indischool (자생적 온라인 교사 공동체의 질문분석을 통한 초등교사의 과학 교수 관련 어려움 탐색 -인디스쿨의 물리 관련 질문 게시글을 중심으로-)

  • Kim, Yunhwa;Yoo, Junehee
    • Journal of The Korean Association For Science Education
    • /
    • v.39 no.1
    • /
    • pp.73-88
    • /
    • 2019
  • The purpose of this study is to explore elementary teachers' difficulties on teaching science by analyzing questions that have been posted for a long time in an autonomous online teacher community named Indischool. For this purpose, 409 question postings(the 2007 and 2009 revised curriculum, third to sixth grade) were analyzed using the framework for analyzing questions about elementary teachers' science teaching(modified from Alake-Tuenter et al., 2013). The study revealed that there were more science-SMK questions than science-PCK questions, and most of the questions were 'about lenses' and 'in 2014 and 2015, when the curriculum was changing from the 2007 to the 2009 revised curriculum'. The long-standing difficulties in science-SMK were 'an application of facts and concepts in lenses' and 'an unexpected experimental error in electricity'. In particular, there are the principle of transparent cup-shaped objects acting as lenses, the process of image formation by convex lenses, experimental errors of 'compass movement due to current flow change' and experimental errors 'serial connection of bulbs'. The long-standing difficulties in science-PCK were 'understanding and response to context' and 'understanding and response to aims mentioned in standard document' and these are not related to physical units but to others. In particular, there are request class materials, activity ideas at the end of the semester and understanding the national curriculum guidelines. These teachers' difficulties should be reflected in the science teaching support system like a teacher's guide compilation, teacher's training curriculum development, etc.

A study on the Application of XML based Annotation for National Base Digital Map (XML기반 국가공간데이터의 주석 활용에 관한 연구)

  • Kwon, Gu-Ho;Seok, Hyun-Jeong;Kim, Young-Sup
    • Journal of Korea Spatial Information System Society
    • /
    • v.4 no.1 s.7
    • /
    • pp.15-25
    • /
    • 2002
  • The OGC(OpenGIS Consortium), which is standardization organization of geographic data, have been studied standard for geographic data such as GML and GML based annotation for image and map. Annotation for map is applicable in various ways, understanding about geographic data, decision making and exchange of communication. For instance, Map annotation can be used for highlighting tour-course as symbols or explaining it as text on a map in tourism. This study suggests some annotation methodology for national digital map and presents a simple implementation of it. Firstly, this study suggests a way of updating OGC annotation schema which corresponds with DXF format and creating a GML application schema using the updated OGC annotation schema. Also it suggest a way of converting instance documents of annotated map to VML document with XSLT and VML for display. Later, it is needed to study for supporting another formats as well as DXF format. In addition, it is needed to study for managing the history of updated map entity with annotation in Local governments UIS(Urban Information System) in practical aspects.

  • PDF

A Study on the Necessity and Applicability of Interactive Electronic Technical Manual(IETM) for Construction Projects (건설분야 전자매뉴얼의 필요성 및 특성분석을 통한 실무적용성 연구)

  • Kang, Leen-Seok;Jung, Won-Myung;Kwak, Joong-Min
    • Korean Journal of Construction Engineering and Management
    • /
    • v.6 no.1 s.23
    • /
    • pp.99-108
    • /
    • 2005
  • Interactive electronic technical manual(IETM) for construction projects means an electronic tool that regulations and specifications related to construction method or maintenance process ale described by electronic book type. It has a meaning of integrated information system that includes virtual reality(VR), 3D animation and image contents for representing real construction information so that user can easily understand the construction situation and maintenance process. The basic information and technical manuals of construction facilities are being written as paper documents in our construction industry. As the result, the information management in the maintenance phase of construction projects is inefficient, and maintenance cost is being increased. This study attempts to improve the lack of understanding about construction IETM through the analysis of necessity and unique function of construction IETM comparing with the IETMS in other industry, Finally, this study shows a scenario of construction IErM for mitigating natural disaster of construction facilities to verify applicability of IETM.

A Research on Service and Awareness of Dental Coordinators by Manpower at Dental Care Service Institutions - Centering on Manpower Other than Dentists (치과코디네이터 업무 및 인식에 관한 조사연구 - 치과의사를 제외한 기타 인력을 중심으로)

  • Choi, Boo-Keun;Han, Su-Jin;Kwon, Soon-Bok;Jung, Jae-Yeon;Cho, Myung-Sook;Hwang, Yoon-Sook
    • Journal of Korean society of Dental Hygiene
    • /
    • v.6 no.4
    • /
    • pp.437-453
    • /
    • 2006
  • To analyze dental hygienists and other manpower at dental care service institutions where a dental coordinator was working among about 200 dental care service institutions in Seoul, Gyeonggi Province, and Incheon as of June 2005 for contents of training for dental coordinators, opinions of qualification of dental coordinators, present and future services provided by dental coordinators, and awareness of dental coordinators and to provide basic data about future services, roles, and cultivation of dental coordinators, a survey was conducted and 216 copies returned were analyzed, obtaining the following results. 1. 83.8 percent needed an educational program for dental coordinators as an educational content; 41.7% had awareness of the educational content; and 83.8 percent insisted that over the intermediate level of curricula should be taken. Dental coordinator cultivation institutions identified included the institution under the control of the Korean Dental Hygienists Association and the education center for the department of dental hygiene; 76.9% insisted that an appropriate qualifying examination should be necessary. They suggested the central government department and the local government as a certification institution; 39.4% insisted that financial support for the education should be provided by financing education alone. Only 28.7% experienced dental coordinator education and 73.1% hoped to serve as a dental coordinator. They were found to expect a rise in payment(64.4%) and in the title(46.8%) after completion of the educational program. 2. 66.2% saw a dental hygienist as the most appropriate for a dental coordinator; clinical career (39.4%) and practical capacity(29.2%) were suggested as requirements for a dental coordinator; and a period of over three years(47.2%) was suggested for appropriate dental career. 3. Dental coordinators' present services included 'reservation management' for customer management, 'staff service training' for organization management, 'understanding of customer reception attitudes and actions' for self-management, 'hospital information management' for hospital marketing, 'acceptance' for hospital affairs management, and 'hospital environment management' for hospital facilities management; their future services included 'acquisition of ability to use a foreign language' for self-management, followed by 'staff service training' for organization management, 'training and counseling' for customer management, 'acquisition of counseling capacity' for self-management, 'complaining customer reception' for customer management, and 'marketing strategy implementation' for hospital marketing. 4. After comparing dental hygienists and other manpower in terms of dental coordinators' future services, dental hygienists showed interest in 'acquisition of ability to use a foreign language,' 'staff service training,' 'complaining customer reception,' and 'acquisition of counseling capacity' while other manpower showed interest in 'acquisition of ability to use a foreign language,' 'document data management,' 'acquisition of basic service manner,' 'acquisition of counseling capacity,' 'manpower management,' 'establishment and evaluation of a marketing strategy,' and 'education and counseling.' 5. As for awareness of dental coordinators, they were thought of as helpful in improving image of a dental clinic; it was found that continuous training should be necessary to develop dental coordinators' capacity; dental coordinators' services should be important and contribute to patients' qualitative satisfaction.

  • PDF