Comment on page
How to get from Image to CSV in 3 easy steps.
Nanonets pre-trained or prebuilt models help you extract key information from documents without having to gather data and then build and train your own models.
- 1.Choose a pre-trained model based on your document type.
- 2.Click on the model card to add it to your account.
- 3.You will be redirected to the Extract data screen for your model.
- 4.Click on 'Add files' and upload document(s) to extract data from.
- 5.The documents may take 3-5 seconds to process, depending on their size.
- 6.Click on the processed document in the list to see the extracted and structured data.
Check if the data you needed is captured correctly. You can add missing information or delete extra fields. If you notice repeated errors, please refer to our accuracy troubleshooting page to find a solution.
- 1.Click on the box or field containing the wrongly extracted data.
- 2.You will see a popup on the image showing the extracted text and the label auto-assigned by the AI.
- 3.Drag the corners of the box to resize and re-capture the data, OR
- 4.Draw a new box where the correct data is present on the image.
- 5.Once you're happy with the extracted data, click Save.
- 1.From the image, locate the text you want to extract.
- 2.Click and drag your cursor over the text to draw a box around it.
- 3.You will see a popup with the extracted text and a dropdown to assign a label.
- 4.Click on the 'Label' dropdown.
- 5.Select the label you want to assign it.
- 6.Click Save.
- 7.Once you do this for other fields, click on Approve file. The model will learn and use this information to improve accuracy.
- 1.Open your model.
- 2.Navigate to the "Extract Data" section from the side navigation bar.
- 3.Select the files for which you want to download results.
- 4.Click on Download Extracted data at the bottom of the screen. You will see an Export results modal.
- 5.Select a format (CSV or XML).
- 6.Click on Download Results.
Click on the Advanced tab on the Export results modal to show/hide or reorder fields in the downloaded file.