Click-Free, Video-Based Document Capture - Methodology and Evaluation

被引:2
|
作者
Tariq, Waqas [1 ]
Khan, Nazar [1 ]
机构
[1] Univ Punjab, Coll Informat Technol, Comp Vis & Machine Learning Grp, Lahore, Pakistan
来源
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2017), VOL 6 | 2017年
关键词
D O I
10.1109/ICDAR.2017.344
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a click-free method for video-based digitization of multi-page documents. The work is targeted at the non-commercial, low-volume, home user. The document is viewed through a mounted camera and the user is only required to turn pages manually while the system automatically extracts the video frames representing stationary document pages. This is in contrast to traditional document conversion approaches such as photocopying and scanning which can be time-consuming, repetitive, redundant and can lead to document deterioration. Main contributions of our work are i) a 3-step method for automatic extraction of unique, stable and clear document pages from video, ii) a manually annotated data set of 37 videos consisting of 763 page turn events covering a large variety of documents, and iii) a soft, quantitative evaluation criterion that is highly correlated with the hard F1-measure. The criterion is motivated by the need to counter the subjectivity in human marked ground truth for videos. On our data set, we report an F1-measure of 0.91 and a soft score of 0.94 for the page extraction task.
引用
收藏
页码:21 / 26
页数:6
相关论文
共 50 条
  • [1] Evaluating video-based motion capture
    Gleicher, M
    Ferrier, N
    CA 2002: PROCEEDINGS OF THE COMPUTER ANIMATION 2002, 2002, : 75 - 80
  • [2] Video motion capture in VBA—Video-based animation
    Pan Yun-he
    Zhuang Yue-ting
    Liu Xiao-ming
    Journal of Zhejiang University-SCIENCE A, 2000, 1 (1): : 1 - 7
  • [3] VIDEO MOTION CAPTURE IN VBA——VIDEO-BASED ANIMATION
    潘云鹤
    庄越挺
    刘小明
    Journal of Zhejiang University Science, 2000, (01) : 4 - 10
  • [4] Improved Video-Based Vehicle Detection Methodology
    Luo, Jinman
    Zhu, Juan
    PROCEEDINGS OF 2010 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY (ICCSIT 2010), VOL 6, 2010, : 602 - 606
  • [5] A structured document model for authoring video-based hypermedia
    Zhou, TT
    Jin, JS
    11TH INTERNATIONAL MULTIMEDIA MODELLING CONFERENCE, PROCEEDINGS, 2005, : 421 - 426
  • [6] Generic Video-Based Motion Capture Data Retrieval
    Jiang, Zifei
    Li, Zhen
    Li, Wei
    Li, Xueqing
    Peng, Jingliang
    2019 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2019, : 1950 - 1957
  • [7] Video-based observation in impact evaluation
    Borg, Simon
    EVALUATION AND PROGRAM PLANNING, 2021, 89
  • [8] AMMIL: A METHODOLOGY FOR DEVELOPING VIDEO-BASED LEARNING COURSES
    Quemada, J.
    Barra, E.
    Gordillo, A.
    Pavon, S.
    Salvachua, J.
    Vazquez, I.
    Lopez-Pernas, S.
    12TH INTERNATIONAL CONFERENCE OF EDUCATION, RESEARCH AND INNOVATION (ICERI 2019), 2019, : 4893 - 4901
  • [9] Video-Based Document Image Scanning Using a Mobile Device
    Jiang, Bo
    Liu, Sijiang
    Xia, Siyu
    Yu, Xiao
    Ding, Mengmeng
    Hou, Xuedong
    Gao, Yu
    2015 INTERNATIONAL CONFERENCE ON IMAGE AND VISION COMPUTING NEW ZEALAND (IVCNZ), 2015,
  • [10] Neurological Examination: An Evaluation of Video-Based Learning
    Guido, Giorgio
    Franceschini, Simone
    Oteri, Vittorio
    Pavan, Matilde
    Bernad, Peter G.
    CUREUS JOURNAL OF MEDICAL SCIENCE, 2024, 16 (01)