Prices are prefixed with the ¤ symbol. This symbol is not in the english training set of Tesseract and is read as a random character. When this character is read as a digit, it inflates the prices read by an order of magnitude, i.e. ¤900 becomes 2900.
Tasks
Experiment with heuristics to mitigate the issue
Thousands are always separated by a comma , and groups of digit are only up to 3 long
Only 1 digit is present before the comma , when the price is listed in kilo units K
Situation
Prices are prefixed with the
¤symbol. This symbol is not in the english training set of Tesseract and is read as a random character. When this character is read as a digit, it inflates the prices read by an order of magnitude, i.e.¤900becomes2900.Tasks
,and groups of digit are only up to 3 long,when the price is listed in kilo unitsKResults
¤character doesn't inflate prices