Algorithm for segmentation of documents based on texture features

被引：16
|
作者：
Vil'kin A.M. [1 ]
Safonov I.V. [1 ]
Egorova M.A. [1 ]
机构：
[1] National Research Nuclear University MEPhI, Kashirskoe sh. 31, Moscow
来源：
Pattern Recognition and Image Analysis | 2013年 / 23卷 / 1期
关键词：
feature extraction; segmentation; supervised learning;
D O I：
10.1134/S1054661813010136
中图分类号：
学科分类号：
摘要：
The ascending approach to segmentation of scanned documents in the area of background, text, and photographs is considered. In the first stage, the image is divided into blocks. For each block, a series of texture features is calculated. On the basis of these features, the type of the block is determined. Various positions and sizes of blocks, 26 texture features, and 4 algorithms of classification of blocks were considered. In the second stage, the type of block was corrected on the basis of the analysis of neighboring regions. For estimating the results, the error matrix and the ICDAR 2007 criterion are used. © 2013 Pleiades Publishing, Ltd.
引用
收藏
页码：153 / 159
页数：6
相关论文
共 50 条
  • [31] A robust texture, segmentation algorithm based on the Fourier spectrum analysis
    Pfeifer, T
    Sack, D
    Orth, A
    OPTOMECHATRONIC SYSTEMS III, 2002, 4902 : 322 - 333
  • [32] A color- and texture-based image segmentation algorithm
    Wang, Xiang-Yang
    Sun, Yi-Feng
    Machine Graphics and Vision, 2010, 19 (01): : 3 - 8
  • [33] Algorithm for segmentation of texture image based on image variogram function
    Wu, G.
    Yang, J.A.
    Wang, H.Y.
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2001, 29 (01): : 44 - 47
  • [34] Texture Features for Segmentation of Satellite Images
    Tsaneva, Mariana
    CYBERNETICS AND INFORMATION TECHNOLOGIES, 2008, 8 (03) : 73 - 85
  • [35] Weld features for unsupervised texture segmentation
    Lu, CS
    Chung, PC
    FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 1689 - 1693
  • [36] GPU Implementation of Haralick Texture Features Extraction Algorithm for a Neuro-morphological Texture Image Segmentation Approach
    Salhi, Khalid
    Jaara, El Miloud
    Talibi Alaoui, Mohammed
    Talibi Alaoui, Youssef
    2018 INTERNATIONAL CONFERENCE ON ELECTRONICS, CONTROL, OPTIMIZATION AND COMPUTER SCIENCE (ICECOCS), 2018,
  • [37] Texture Analysis: Algorithm for Texture Features Computation
    Lukashevich, Marina
    Sadykhov, Rauf
    2012 IV INTERNATIONAL CONFERENCE PROBLEMS OF CYBERNETICS AND INFORMATICS (PCI), 2012,
  • [38] SEGMENTATION OF NATURAL COLOUR IMAGE BASED ON COLOUR-TEXTURE FEATURES
    Shankar, T.
    Yamuna, G.
    Suman, Gaurav
    2013 INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND SIGNAL PROCESSING (ICCSP), 2013, : 455 - 459
  • [39] SEGMENTATION OF ANATOMICAL BRANCHING STRUCTURES BASED ON TEXTURE FEATURES AND GRAPH CUT
    Nuzhnaya, Tatyana
    Cheng, Erkang
    Ling, Haibin
    Kontos, Despina
    Bakic, Predrag R.
    Megalooikonomou, Vasileios
    2011 8TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, 2011, : 673 - 676
  • [40] An active contour model based on fused texture features for image segmentation
    Wu, Qinggang
    Gan, Yong
    Lin, Bin
    Zhang, Qiuwen
    Chang, Huawen
    NEUROCOMPUTING, 2015, 151 : 1133 - 1141
12345