01. Task Description
The challenge includes two tasks: Receipt Image Quality Evaluation and Key Information Extraction.
Task 1: Receipt Image Quality Assessment (IQA)
Receipt image quality is measured by the ratio of text lines associated with the “clear” label evaluated by human annotators. The quality ranges from 0 to 1 in which, score of 1 means the highest quality and score of 0 means the lowest quality.
Task 2: Key Information Extraction (KIE)
At maximum, a receipt image is associated with 4 text lines annotated by human annotators. With different receipt's formats, the number of text lines might be different as some receipts do not contain all fields. For instance, the SELLER_ADDRESS might not exist in the receipt or simply, because the line is not readable.
Note that detected fields (text lines) are ordered by SELLER, SELLER_ADDRESS, TIMESTAMP, TOTAL_COST. If a field is missing, it is set empty in the output text. For example, if SELLER_ADDRESS is missing, the output will be:
02. Technical System Papers