Handwritten Bangla Word Recognition using HOG Descriptor

被引：14
|
作者：
Bhowmik, Showmik [1 ]
Roushan, Md. Galib [1 ]
Sarkar, Ram [1 ]
Nasipuri, Mita [1 ]
Polley, Sanjib [2 ]
Malakar, Samir [3 ]
机构：
[1] Jadavpur Univ, Dept Comp Sc & Engg, Kolkata, India
[2] MCKV Inst Engn, Dept Comp Sc & Engg, Howrah, India
[3] MCKV Inst Engn, Dept Master Comp Applicat, Howrah, India
来源：
2014 FOURTH INTERNATIONAL CONFERENCE OF EMERGING APPLICATIONS OF INFORMATION TECHNOLOGY (EAIT) | 2014年
关键词：
Holistic word recognition; handwritten words; Histograms of oriented gradients; Bangla script;
D O I：
10.1109/EAIT.2014.43
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
The holistic approaches for handwritten word recognition treat the words as single, indivisible entity and attempt to recognize words from their overall shape. In the present work, a novel technique to recognize handwritten Bangla word is proposed. Histograms of Oriented Gradients (HOG) are used as the feature set to represent each word sample at the feature space and a neural network based classifier is applied to classify the word images. On the basis of the HOG feature set, the performance achieved by the technique on a small dataset is quite satisfactory.
引用
收藏
页码：193 / 197
页数：5
相关论文
共 50 条
  • [21] Cleaning of Online Bangla Free-form Handwritten Text
    Bhattacharya, Nilanjana
    Pal, Umapada
    Roy, Partha Pratim
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2017, 17 (01)
  • [22] Application of Structural and Topological Features to Recognize Online Handwritten Bangla Characters
    Sen, Shibaprasad
    Bhattacharyya, Ankan
    Singh, Pawan Kumar
    Sarkar, Ram
    Roy, Kaushik
    Doermann, David
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2018, 17 (03)
  • [23] BYANJON: A Ground Truth Preparation System for Online Handwritten Bangla Documents
    Sen, Shibaprasad
    Bhattacharyya, Ankan
    Sarkar, Ram
    Roy, Kaushik
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2021, 20 (06)
  • [24] Handwritten word recognition using lottery ticket hypothesis based pruned CNN model: a new benchmark on CMATERdb2.1.2
    Samir Malakar
    Sayantan Paul
    Soumyadeep Kundu
    Showmik Bhowmik
    Ram Sarkar
    Mita Nasipuri
    Neural Computing and Applications, 2020, 32 : 15209 - 15220
  • [25] Handwritten word recognition using lottery ticket hypothesis based pruned CNN model: a new benchmark on CMATERdb2.1.2
    Malakar, Samir
    Paul, Sayantan
    Kundu, Soumyadeep
    Bhowmik, Showmik
    Sarkar, Ram
    Nasipuri, Mita
    NEURAL COMPUTING & APPLICATIONS, 2020, 32 (18): : 15209 - 15220
  • [26] Word matching using single closed contours for indexing handwritten historical documents
    Tomasz Adamek
    Noel E. O’Connor
    Alan F. Smeaton
    International Journal of Document Analysis and Recognition (IJDAR), 2007, 9 : 153 - 165
  • [27] Word matching using single closed contours for indexing handwritten historical documents
    Adamek, Tornasz
    O'Connor, Noel E.
    Smeaton, Alan F.
    INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2007, 9 (2-4) : 153 - 165
  • [28] An image database of handwritten Bangla words with automatic benchmarking facilities for character segmentation algorithms
    Samir Malakar
    Ram Sarkar
    Subhadip Basu
    Mahantapas Kundu
    Mita Nasipuri
    Neural Computing and Applications, 2021, 33 : 449 - 468
  • [29] An image database of handwritten Bangla words with automatic benchmarking facilities for character segmentation algorithms
    Malakar, Samir
    Sarkar, Ram
    Basu, Subhadip
    Kundu, Mahantapas
    Nasipuri, Mita
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (01): : 449 - 468
  • [30] Understanding NFC-Net: a deep learning approach to word-level handwritten Indic script recognition
    Soumyadeep Kundu
    Sayantan Paul
    Pawan Kumar Singh
    Ram Sarkar
    Mita Nasipuri
    Neural Computing and Applications, 2020, 32 : 7879 - 7895
12345