公开(公告)号：EP4375955A1

公开(公告)日：2024-05-29

申请号：EP23161397.7

申请日：2023-03-13

申请人： L & T Technology Services Limited

发明人： DAS, TARUN KUMAR ,  MALLICK, TRIPTESH ,  SINGH, MADHUSUDAN ,  KUMAR, PRAGYESH ,  BALARAMAN, MRIDUL

IPC分类号： G06V30/12 ,  G06N20/20 ,  G06V30/40 ,  G06V30/148 ,  G06V30/413 ,  G06V30/414 ,  G06V30/18 ,  G06V30/19 ,  G06V30/24 ,  G06V10/80 ,  G06V10/774

CPC分类号： G06V30/133 ,  G06N20/20 ,  G06V30/43 ,  G06V10/82 ,  G06V30/148 ,  G06V30/413 ,  G06V30/414 ,  G06V30/18152 ,  G06V30/18086 ,  G06V30/19173 ,  G06V30/18057 ,  G06V30/1908 ,  G06V30/1918 ,  G06V30/2528 ,  G06V10/817 ,  G06V30/19147 ,  G06V10/7753 ,  G06V30/19093

摘要： A method and system of determining quality of a document image is disclosed that includes segmenting, by one or more processors, a document image into a plurality of regions each of which comprises text data. The plurality of regions is classified into one of a plurality of image quality classes based on a determination of a highest prediction value from one of a plurality of machine learning models. The plurality of machine learning models is trained corresponding to one of the plurality of image quality classes. A cumulative quality score for the image is computed based on a weighted average of a number of regions classified into each of the plurality of image quality classes. The quality of the image is determined based on the cumulative quality score.