mask

mask.py

destination_t = '\content\drive\MyDrive\cs2_table'
destination_c = '\content\drive\MyDrive\cs2_col'


for i in df_org['filename'].unique():

    # for each unique file, we take the height,width,depth from dataframe
    file_width = int(df_org[df_org['filename']==i]['width'].unique())
    file_height = int(df_org[df_org['filename']==i]['height'].unique())
    # Creating an image array of dtype int32
    col_mask = np.zeros((file_height,file_width), dtype=np.int32)
    table_mask = np.zeros((file_height,file_width), dtype = np.int32) 
    
    #All the tabular coordinates assiciated with each unique file get added to lists
    xmin_ = df_org[df_org['filename']==i]['xmin'].tolist()
    ymin_ = df_org[df_org['filename']==i]['ymin'].tolist()
    xmax_ = df_org[df_org['filename']==i]['xmax'].tolist()
    ymax_ = df_org[df_org['filename']==i]['ymax'].tolist()
    
    # Corresponding min/max is performed to finalize the coordinates for each unique file
    xmin_resultant = int(min(df_org[df_org['filename']==i]['xmin'].tolist()))
    ymin_resultant = int(min(df_org[df_org['filename']==i]['ymin'].tolist()))
    xmax_resultant = int(max(df_org[df_org['filename']==i]['xmax'].tolist()))
    ymax_resultant = int(max(df_org[df_org['filename']==i]['ymax'].tolist()))
    
    # Here we leverage the min/max bndbox coordinates and the masked portion of image(table),
    # is given the value 255 as compared to the rest of the part having value 0   
    # For column detection within tables, we take into account all the bndbox coordinates in the lists we formed
    # Just like table masks, here we too give value 255 for the masked portion 
          
    for k in range(len(ymin_)):
        col_mask[ymin_[k]:ymax_[k],xmin_[k]:xmax_[k]]=255
        
    table_mask[ymin_resultant:ymax_resultant,xmin_resultant:xmax_resultant]=255
    
    #Using imageio to save the resultant table masks and column masks
    imageio.imsave(destination_t + '\\' + i[:-4] + '.jpeg',table_mask)  
    imageio.imsave(destination_c + '\\' + i[:-4] + '.jpeg',column_mask)