Importing text into a draft email
Examples described herein include systems and methods for importing text into a draft email on a user device. In response to a user selecting the first selectable element, the user device can launch a camera interface on the display. The user can capture an image, such as a page of a book or newspaper, and then scale the captured image to the relevant desired portion. The example method can further include recognizing text within the scaled portion of the image and automatically importing the recognized text into the draft email. The user device can utilize a machine learning model to perform text recognition at the device and then insert the recognized text into the draft email automatically. The user device can also display an indication of the accuracy of the imported recognized text within the draft email.
1. A method for importing text into a draft email on a user device, comprising
displaying a draft email interface on a display of the user device;
displaying, within the draft email interface, a first selectable element;
in an instance where the first selectable element is selected, launching a camera interface on the display of the user device;
capturing an image with the camera interface;
recognizing text within the image;
importing the recognized text into the draft email; and
displaying a message, within the draft email interface, that provides an accuracy indication of one of at least three potential accuracy levels of the imported recognized text relative to the capture image.
2. The method of claim 1 , further comprising receiving user input scaling the captured image to a smaller portion of the captured image, wherein recognizing text is performed on the smaller portion of the captured image.
3. The method of claim 1 , further comprising, in an instance where the accuracy indication is the lowest accuracy of the at least three potential accuracy levels, prompting the user to decide whether to retain the imported text in the draft email.
4. The method of claim 1 , wherein recognizing text within the image is performed by a machine learning model.
5. The method of claim 1 , wherein recognizing text within the image is performed at the user device.
6. The method of claim 1 , further comprising:
displaying, within the draft email interface, a second selectable element;
in an instance where the second selectable element is selected, launching a file-storage interface;
receiving a selection of a file through the file-storage interface;
recognizing text within the file; and
importing the recognized text into the draft email interface.
7. The method of claim 6 , wherein the file is stored remotely from the user device.
8. A non-transitory, computer-readable medium containing instructions that, when executed by a hardware-based processor, performs stages for importing text into a draft email on a user device, the stages comprising:
displaying a draft email interface on a display of the user device;
displaying, within the draft email interface, a first selectable element;
in an instance where the first selectable element is selected, launching a camera interface on the display of the user device;
capturing an image with the camera interface;
recognizing text within the image;
importing the recognized text into the draft email; and
displaying a message, within the draft email interface, that provides an accuracy indication of one of at least three potential accuracy levels of the imported recognized text relative to the capture image.
9. The non-transitory, computer-readable medium of claim 8 , the stages further comprising receiving user input scaling the captured image to a smaller portion of the captured image, wherein recognizing text is performed on the smaller portion of the captured image.
10. The non-transitory, computer-readable medium of claim 8 , the stages further comprising, in an instance where the accuracy indication is the lowest accuracy of the at least three potential accuracy levels, prompting the user to decide whether to retain the imported text in the draft email.
11. The non-transitory, computer-readable medium of claim 8 , wherein recognizing text within the image is performed by a machine learning model.
12. The non-transitory, computer-readable medium of claim 8 , wherein recognizing text within the image is performed at the user device.
13. The non-transitory, computer-readable medium of claim 8 , the stages further comprising:
displaying, within the draft email interface, a second selectable element;
in an instance where the second selectable element is selected, launching a file-storage interface;
receiving a selection of a file through the file-storage interface;
recognizing text within the file; and
importing the recognized text into the draft email interface.
14. The non-transitory, computer-readable medium of claim 13 , wherein the file is stored remotely from the user device.
15. A system for importing text into a draft email, comprising:
a memory storage including a non-transitory, computer-readable medium comprising instructions; and
a user device including a hardware-based processor that executes the instructions to carry out stages comprising:
displaying a draft email interface on a display of the user device;
displaying, within the draft email interface, a first selectable element;
in an instance where the first selectable element is selected, launching a camera interface on the display of the user device;
capturing an image with the camera interface;
recognizing text within the image;
importing the recognized text into the draft email; and
displaying a message, within the draft email interface, that provides an accuracy indication of one of at least three potential accuracy levels of the imported recognized text relative to the capture image.
16. The system of claim 15 , the stages further comprising receiving user input scaling the captured image to a smaller portion of the captured image, wherein recognizing text is performed on the smaller portion of the captured image.
17. The system of claim 15 , the stages further comprising, in an instance where the accuracy indication is the lowest accuracy of the at least three potential accuracy levels, prompting the user to decide whether to retain the imported text in the draft email.
18. The system of claim 15 , wherein recognizing text within the image is performed by a machine learning model.
19. The system of claim 15 , wherein recognizing text within the image is performed at the user device.
20. The system of claim 15 , the stages further comprising:
displaying, within the draft email interface, a second selectable element;
in an instance where the second selectable element is selected, launching a file-storage interface;
receiving a selection of a file through the file-storage interface;
recognizing text within the file; and
importing the recognized text into the draft email interface.