A method to reduce errors of string recognition based on combination of several recognition results with per-character alternatives
    
    
  
  
  
      
      
      
        
Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematičeskoe modelirovanie i programmirovanie, Tome 12 (2019) no. 3, pp. 74-88
    
  
  
  
  
  
    
      
      
        
      
      
      
    Voir la notice de l'article provenant de la source Math-Net.Ru
            
              			We consider the problem on   recognition of a string object presented in several video stream frames.  In order to maximize the output accuracy, we combine  several  results of the recognition. To this end, we consider a model of result of a string object recognition. The model takes into account the estimations of alternative results of per-character classification. Also, we propose an algorithm to combine results of a string recognition   according to this model. The algorithm was evaluated on a MIDV-500 dataset of document images. The experimental results show that the proposed algorithm allows to achieve the high accuracy of recognition result  due to  an analysis of several images, and the use of the estimations of alternative results of per-character classification  gives the higher results then a combination of strings that contain only the final alternatives of each character.
			
            
            
            
          
        
      
                  
                    
                    
                    
                        
Keywords: 
recognition in video stream, recognition algorithms.
Mots-clés : mobile OCR
                    
                  
                
                
                Mots-clés : mobile OCR
@article{VYURU_2019_12_3_a6,
     author = {K. B. Bulatov},
     title = {A method to reduce errors of string recognition based on combination of several recognition results with per-character alternatives},
     journal = {Vestnik \^U\v{z}no-Uralʹskogo gosudarstvennogo universiteta. Seri\^a, Matemati\v{c}eskoe modelirovanie i programmirovanie},
     pages = {74--88},
     publisher = {mathdoc},
     volume = {12},
     number = {3},
     year = {2019},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/VYURU_2019_12_3_a6/}
}
                      
                      
                    TY - JOUR AU - K. B. Bulatov TI - A method to reduce errors of string recognition based on combination of several recognition results with per-character alternatives JO - Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematičeskoe modelirovanie i programmirovanie PY - 2019 SP - 74 EP - 88 VL - 12 IS - 3 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/VYURU_2019_12_3_a6/ LA - en ID - VYURU_2019_12_3_a6 ER -
%0 Journal Article %A K. B. Bulatov %T A method to reduce errors of string recognition based on combination of several recognition results with per-character alternatives %J Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematičeskoe modelirovanie i programmirovanie %D 2019 %P 74-88 %V 12 %N 3 %I mathdoc %U http://geodesic.mathdoc.fr/item/VYURU_2019_12_3_a6/ %G en %F VYURU_2019_12_3_a6
K. B. Bulatov. A method to reduce errors of string recognition based on combination of several recognition results with per-character alternatives. Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematičeskoe modelirovanie i programmirovanie, Tome 12 (2019) no. 3, pp. 74-88. http://geodesic.mathdoc.fr/item/VYURU_2019_12_3_a6/
