• Title/Summary/Keyword: Document Image

Search Result 300, Processing Time 0.024 seconds

Adaptive Binarization using Integral Image (적분영상을 이용한 적응적 이진화)

  • Lee, Yeon-Kyung;Yoo, Hoon
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2012.10a
    • /
    • pp.109-110
    • /
    • 2012
  • In this paper, we propose an adaptive thresholding method to binarize two-dimensional barcode images. Adaptive thresholding methods are applied to document image binarization. Thus, they inappropriate to use in recognition of two-dimensional barcode images. To overcome the problem, we propose a new adaptive threshold method using the integral image. To show the effectiveness of our method, we compared our method with the well-known existing method in terms of visual quality and processing time. The experimental result indicates that the proposed method is superior to the existing method.

  • PDF

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

Character Matching Using a Hausdorff Distance (Hausdorff 거리를 이용한 문자 매칭)

  • Kim, Kyeongtaek;Kyung, Ji Hun
    • Journal of Korean Society of Industrial and Systems Engineering
    • /
    • v.38 no.2
    • /
    • pp.56-62
    • /
    • 2015
  • The Hausdorff distance is commonly used as a similarity measure between two-dimensional binary images. Since the document images may be contaminated by a variety of noise sources during transmission, scanning or conversion to digital form, the measure should be robust to the noise. Original Hausdorff distance has been known to be sensitive to outliers. Transforming the given image to grayscale image is one of methods to deal with the noises. In this paper, we propose a Hausdorff distance applied to grayscale images. The proposed method is tested with synthetic images with various levels of noises and compared with other methods to show its robustness.

Character Segmentation on Printed Korean Document Images Using a Simplification of Projection Profiles (투영 프로파일의 간략화 방법을 이용한 인쇄체 한글 문서 영상에서의 문자 분할)

  • Park Sang-Cheol;Kim Soo-Hyung
    • The KIPS Transactions:PartB
    • /
    • v.13B no.2 s.105
    • /
    • pp.89-96
    • /
    • 2006
  • In this paper, we propose two approaches for the character segmentation on Korean document images. One is an improved version of a projection profile-based algorithm. It involves estimating the number of characters, obtaining the split points and then searching for each character's boundary, and selecting the best segmentation result. The other is developed for low quality document images where adjacent characters are connected. In this case, parts of the projection profile are cut to resolve the connection between the characters. This is called ${\alpha}$-cut. Afterwards, the revised former segmentation procedure is conducted. The two approaches have been tested with 43,572 low-quality Korean word images punted in various font styles. The segmentation accuracies of the former and the latter are 91.81% and 99.57%, respectively. This result shows that the proposed algorithm using a ${\alpha}$-cut is effective for low-quality Korean document images.

Jointly Image Topic and Emotion Detection using Multi-Modal Hierarchical Latent Dirichlet Allocation

  • Ding, Wanying;Zhu, Junhuan;Guo, Lifan;Hu, Xiaohua;Luo, Jiebo;Wang, Haohong
    • Journal of Multimedia Information System
    • /
    • v.1 no.1
    • /
    • pp.55-67
    • /
    • 2014
  • Image topic and emotion analysis is an important component of online image retrieval, which nowadays has become very popular in the widely growing social media community. However, due to the gaps between images and texts, there is very limited work in literature to detect one image's Topics and Emotions in a unified framework, although topics and emotions are two levels of semantics that often work together to comprehensively describe one image. In this work, a unified model, Joint Topic/Emotion Multi-Modal Hierarchical Latent Dirichlet Allocation (JTE-MMHLDA) model, which extends previous LDA, mmLDA, and JST model to capture topic and emotion information at the same time from heterogeneous data, is proposed. Specifically, a two level graphical structured model is built to realize sharing topics and emotions among the whole document collection. The experimental results on a Flickr dataset indicate that the proposed model efficiently discovers images' topics and emotions, and significantly outperform the text-only system by 4.4%, vision-only system by 18.1% in topic detection, and outperforms the text-only system by 7.1%, vision-only system by 39.7% in emotion detection.

  • PDF

Gathering and Retrieval of the graphic images on a Web document (웹 문서내의 그래픽 영상 수집 및 검색)

  • 최진영;이은애;하석운
    • Proceedings of the Korea Multimedia Society Conference
    • /
    • 2000.11a
    • /
    • pp.607-610
    • /
    • 2000
  • 특정, 컴퓨터 사용자들이 자기가 관심을 가지고 있는 문서에서 어느 한 영상을 일괄 수집(Gathering)하고자 하는 욕구가 생길 수 있다. 그런데, 그래픽 영상(Graphic Image)이 여러 개로 세분화되어 있고, 한 문서 내에 다량으로 존재하기 때문에 선택하는 데 한계가 있다. 따라서, 웹(Web) 문서내의 모든 영상을 일괄 수집할 필요가 있으며 이 수집한 영상 중에서 사용자가 관심을 가지는 영상을 검색(Retrieval)하면 그와 유사한 다른 영상들도 같이 검색할 수 있는 시스템(System)이 필요하다는 생각에서 본 시스템을 구현하였는데, 그래픽영상의 일괄 수집이 가능하였고, 사용자의 관심영상에 대한 유사영상 검색이 가능하였다.

  • PDF

Restoration of Distorted Document Image Due to Depth Variation by Using Structured Light (Structured light를 이용한 깊이 차이에 문자 왜곡 교정)

  • Heo, Hoon;Chae, Ok-Sam
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2001.04b
    • /
    • pp.487-489
    • /
    • 2001
  • 제본된 책이나 고문서를 디자타이즈할 때 책을 바르게 펴지 못하거나 지정된 위치나 방위로 위치시키지 못해서 문제가 발생한다. 특히 힘을 가할 수 없는 고문서의 경우에는 바르게 펼수가 없기 때문에 깊이 차이에 의한 문서의 왜곡이 발생한다. 본 연구에서는 Structured Light을 이용하여 깊이 차에 의한 문자의 왜곡을 복원하는 방안을 제안한다. 또한 입력시 책의 위치와 방위에 대한 제한을 완화시킬 수 있도록 책의 위치와 방위 변화에 적을 알 수 있는 방안을 제안한다,

  • PDF

Component Analysis and Classification for Rotated Document Image (회전된 문서영상에서의 구성요소 분석 및 분류)

  • 모문정;김욱현
    • Proceedings of the Korea Institute of Convergence Signal Processing
    • /
    • 2001.06a
    • /
    • pp.169-172
    • /
    • 2001
  • 본 논문에서는 회전된 문서에서의 회전각 검출과 문서에 포함된 그림, 글자, 표, 직선과 같은 구성요소를 자동으로 분석하고 분류하는 방법을 제안한다. 본 연구는 입력영상을 획득하는 과정에서 발생되는 회전각에 의해 발생되는 오류를 최소화하기 위한 회전각 검출단계, 각 구성요소 검출에 불필요한 배경제거 단계, 각 구성요소의 특성을 통한 구성요소 분류단계로 이루어진다. 제안한 문서 인식 시스템의 성능 평가를 위해서 다양 한 문서에 제안한 방법을 적용하고, 성공적인 결과를 보인다.

  • PDF