A python implementation to extract data in structured form from an image of an invoice

this is being done to accurately detect text contours

after getting contours and merging them on the basis of their size and nearness *the red boxes are the identified keyfields the keyfields can be changes according to keywords given in labels.csv and label_synonnyms.csv *green boxes are the values *relation between the keyfields and it's possible values is shown by using straight lines