Base64.ai’s patent-pending Segmentation AI understands multiple documents in one photo, such as a few receipts in a single expense report.
— Ozan Bilgen, Base64.ai CEO
NEW YORK, NY, USA, October 27, 2023 /EINPresswire.com/ — Base64.ai announced a new technology named “Segmentation AI” to detect and understand multiple documents within a single image. The AI comprehends the physical boundaries of documents, allowing it to crop each document and process them individually. This ground-breaking new technology eliminates the need for users to manually split documents before processing, thereby reducing validation time and the chances of document type classification and data extraction errors. It’s beneficial for expense reporting and customer onboarding tasks, where a single image often contains multiple documents, such as multiple IDs. With Segmentation AI, there’s no requirement for additional setup to segment document information; Base64.ai automatically detects objects before classifying a document.
How does the Artificial Intelligence split documents?
Segmentation AI employs a specialized neural network for salient object detection. This process comprises two fundamental steps: first, it identifies the most essential elements on the page and then isolates them from the surrounding content. In this scenario, an image featuring a NY State ID and a Ukraine passport ID was processed and automatically split into two separate document files. Even though both files originate from the same image, they yield distinct results, each corresponding to a different section of the single document.
Once a multi-document image is split, Base64.ai detects the document type and uses the most relevant model for data extraction. Each file is labeled with the model name under “Name,” signifying its classification. After splitting, each document can be reviewed separately. In the cropped documents, data associated with other documents will not appear in the results, OCR, or API response. Signatures, tables, and face detection are extracted exclusively for the corresponding document.
While Base64.ai can automatically detect multiple documents, users can fine-tune their processing workflow by accessing the “Segmentation” feature under “AI Features” in flow settings. This allows the user to ensure that multi-document images are consistently split. Segmentation AI settings are available on the AI features page in Base64.ai Flow settings.
Base64.ai is a New York-based artificial intelligence platform that automates all document processes using Generative AI and Large Language Models. The startup is disrupting the $100 billion Intelligent Document Processing market with its unique capability to understand any document without training. It has four patent applications, supports over 2,800 document types, and has 400+ no-code integrations.
Segmentation AI Video