PageNumber: Which page the field is found on.Confidence: How confident the model is in the detection of the field.BoundingBox: The coordinates of the field.Additional properties PropertyĪdditional information for each of the receipt properties You can also specify the language of the text with a language tag, such as 'en-US'. To manipulate them as dates or times, you can use the DateValue and TimeValue functions. To manipulate them as numbers, you can use the Value function. TotalPrice: Total price of the purchased item.Quantity: Quantity of the purchased item.For PDF documents, only the first 200 pages are processed.PDF dimensions must be at most 17 x 17 inches, which is the equivalent of the legal or A3 paper sizes or smaller.The image dimensions must be between 50 x 50 pixels and 10,000 x 10,000 pixels.The image format must be JPEG, PNG, or PDF.In order to get the best results, provide one clear photo or scan per receipt. Only English receipts from the United States are currently supported. Both print and handwritten text can be detected. The receipt processor component works best with sales receipts, those commonly used by restaurants, gas stations, and retailers, and others. These features are available before an official release so that customers can get early access and provide feedback. Preview features aren’t meant for production use and may have restricted functionality.