Exploiting State-of-the-Art Deep Learning Methods for Document Image Analysis

被引：7
|
作者：
Pondenkandath, Vinaychandran [1 ,2 ]
Seuret, Mathias [2 ]
Ingold, Rolf [2 ]
Afzal, Muhammad Zeshan [1 ]
Liwicki, Marcus [1 ,2 ]
机构：
[1] TU Kaiserslautern, MindGarage, Kaiserslautern, Germany
[2] Univ Fribourg, DIVA, Fribourg, Switzerland
来源：
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2017), VOL 5 | 2017年
基金：
瑞士国家科学基金会;
关键词：
RECOGNITION;
D O I：
10.1109/ICDAR.2017.325
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper provides details of our (partially awardwinning) methods submitted to four competitions of ICDAR 2017. In particular, they are designed to (i) classify scripts, (ii) perform pixel-based labeling for layout analysis, (iii) identify writers, and (iv) recognize font size and types. The methods build on the current state-of-the-art in Deep Learning and have been adapted to the specific needs of the individual tasks. All methods are variants of Convolutional Neural Network (CNN) with specialized architectures, initialization, and other tricks which have been introduced in the field of deep learning within the last few years.
引用
收藏
页码：30 / 35
页数：6
相关论文
共 50 条
  • [1] Deep Learning Methods for Microstructural Image Analysis: The State-of-the-Art and Future Perspectives
    Alrfou, Khaled
    Zhao, Tian
    Kordijazi, Amir
    INTEGRATING MATERIALS AND MANUFACTURING INNOVATION, 2024, 13 (03) : 703 - 731
  • [2] State-of-the-Art Deep Learning in Cardiovascular Image Analysis
    Litjens, Geert
    Ciompi, Francesco
    Wolterink, Jelmer M.
    de Vos, Bob D.
    Leiner, Tim
    Teuwen, Jonas
    Isgum, Ivana
    JACC-CARDIOVASCULAR IMAGING, 2019, 12 (08) : 1549 - 1565
  • [3] A state-of-the-art survey of object detection techniques in microorganism image analysis: from classical methods to deep learning approaches
    Ma, Pingli
    Li, Chen
    Rahaman, Md Mamunur
    Yao, Yudong
    Zhang, Jiawei
    Zou, Shuojia
    Zhao, Xin
    Grzegorzek, Marcin
    ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (02) : 1627 - 1698
  • [4] A state-of-the-art survey of object detection techniques in microorganism image analysis: from classical methods to deep learning approaches
    Pingli Ma
    Chen Li
    Md Mamunur Rahaman
    Yudong Yao
    Jiawei Zhang
    Shuojia Zou
    Xin Zhao
    Marcin Grzegorzek
    Artificial Intelligence Review, 2023, 56 : 1627 - 1698
  • [5] Music Deep Learning: Deep Learning Methods for Music Signal Processing-A Review of the State-of-the-Art
    Moysis, Lazaros
    Iliadis, Lazaros Alexios
    Sotiroudis, Sotirios P.
    Boursianis, Achilles D.
    Papadopoulou, Maria S.
    Kokkinidis, Konstantinos-Iraklis D.
    Volos, Christos
    Sarigiannidis, Panagiotis
    Nikolaidis, Spiridon
    Goudos, Sotirios K.
    IEEE ACCESS, 2023, 11 : 17031 - 17052
  • [6] State-of-the-Art Review of Deep Learning Methods in Fake Banknote Recognition Problem
    Sadyk, Ualikhan
    Baimukashev, Rashid
    Turan, Cemil
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (01) : 848 - 856
  • [7] Deep Reinforcement Learning: A State-of-the-Art Walkthrough
    Lazaridis, Aristotelis
    Fachantidis, Anestis
    Vlahavas, Ioannis
    JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2020, 69 : 1421 - 1471
  • [8] A systematic literature review on state-of-the-art deep learning methods for process prediction
    Dominic A. Neu
    Johannes Lahann
    Peter Fettke
    Artificial Intelligence Review, 2022, 55 : 801 - 827
  • [9] A systematic literature review on state-of-the-art deep learning methods for process prediction
    Neu, Dominic A.
    Lahann, Johannes
    Fettke, Peter
    ARTIFICIAL INTELLIGENCE REVIEW, 2022, 55 (02) : 801 - 827
  • [10] Deep reinforcement learning: A state-of-the-art walkthrough
    Lazaridis A.
    Fachantidis A.
    Vlahavas I.
    Journal of Artificial Intelligence Research, 2021, 69 : 1421 - 1471
12345