MHDID: A Multi-distortion Historical Document Image Database

被引：0
|
作者：
Shahkolaei, Atena [1 ]
Beghdadi, Azeddine [2 ]
Al-Maadeed, Somaya [3 ]
Cheriet, Mohamed [1 ]
机构：
[1] Ecole Technol Super, Montreal, PQ, Canada
[2] Paris 13 Univ, Paris, France
[3] Qatar Univ, Doha, Qatar
来源：
2018 IEEE 2ND INTERNATIONAL WORKSHOP ON ARABIC AND DERIVED SCRIPT ANALYSIS AND RECOGNITION (ASAR) | 2018年
关键词：
Historical document images; pair comparison rating; physical noises; human visual system; image quality assessment; QUALITY ASSESSMENT;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, a new dataset, called Multi-distortion Historical Document Image Database (MHDID), to be used for the research on quality assessment of degraded documents and degradation classification is proposed. The MHDID dataset contains 335 historical document images which are classified into four categories based on their distortion types, namely, paper translucency, stain, readers' annotations and worn holes. A total of 36 subjects participated to judge the quality of ancient document images. Pair comparison rating (PCR) is utilized as a subjective rating method for evaluating the visual quality of degraded document images. For each distortion image a mean opinion score (MOS) value is computed. This dataset could be used for evaluating the image quality assessment (IQA) measures as well as in the design of new metrics.
引用
收藏
页码：156 / 160
页数：5
相关论文
共 50 条
  • [31] Historical Document Image Binarization Based on Edge Contrast Information
    Li, Zhenjiang
    Wang, Weilan
    Cai, Zhengqi
    ADVANCES IN COMPUTER VISION, CVC, VOL 1, 2020, 943 : 614 - 628
  • [32] Texture feature benchmarking and evaluation for historical document image analysis
    Mehri, Maroua
    Heroux, Pierre
    Gomez-Kramer, Petra
    Mullot, Remy
    INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2017, 20 (01) : 1 - 35
  • [33] Restoration Based Contourlet Transform for Historical Document Image Binarization
    Zemouri, ET-Tahir
    Chibani, Youcef
    Brik, Youcef
    2014 INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS (ICMCS), 2014, : 309 - 313
  • [34] Multi-Document Summarization Using Distortion-Rate Ratio
    Attokurov, Ulukbek
    Bayazit, Ulug
    52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: STUDENT RESEARCH WORKSHOP (ACL 2014), 2014, : 64 - 70
  • [35] A simplified quantization rate-distortion model for fast document image segmentation
    Dong, Y
    Liu, LJ
    Song, XM
    Fan, GL
    2002 45TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL II, CONFERENCE PROCEEDINGS, 2002, : 557 - 560
  • [36] MULTI-RESOLUTION SEAMLESS IMAGE DATABASE
    WANG Mi GONG Jianya LI DerenWANG Mi
    Geo-Spatial Information Science , 2000, (03) : 52 - 56
  • [37] Statistical multi-resolution schemes for historical document binarization
    Obafemi-Ajayi, Tayo
    Agam, Gady
    DOCUMENT RECOGNITION AND RETRIEVAL XVIII, 2011, 7874
  • [38] Detection and Correction of Multi-Warping Document Image
    Wagdy, Marian
    Amin, Khaild
    Ibrahim, Mina
    INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS, 2022, 22 (04)
  • [39] A hybrid CNN-Transformer model for Historical Document Image Binarization
    Rezanezhad, Vahid
    Baierer, Konstantin
    Neudecker, Clemens
    PROCEEDINGS OF THE 2023 INTERNATIONAL WORKSHOP ON HISTORICAL DOCUMENT IMAGING AND PROCESSING, HIP 2023, 2023, : 79 - 84
  • [40] Histogram Peak Ratio-Based Binarization for Historical Document Image
    Mahastama, Aditya W.
    Krisnawati, Lucia D.
    PROCEEDINGS OF 2017 INTERNATIONAL CONFERENCE ON SMART CITIES, AUTOMATION & INTELLIGENT COMPUTING SYSTEMS (ICON-SONICS 2017), 2017, : 93 - 98
12345